CN108960049A - Recognition methods, device and the storage medium in the high consequence area of long-distance oil & gas pipeline - Google Patents

Recognition methods, device and the storage medium in the high consequence area of long-distance oil & gas pipeline Download PDF

Info

Publication number
CN108960049A
CN108960049A CN201810513064.XA CN201810513064A CN108960049A CN 108960049 A CN108960049 A CN 108960049A CN 201810513064 A CN201810513064 A CN 201810513064A CN 108960049 A CN108960049 A CN 108960049A
Authority
CN
China
Prior art keywords
region
image
area
conduit
remote sensing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201810513064.XA
Other languages
Chinese (zh)
Other versions
CN108960049B (en
Inventor
韩文超
刘亮
高海康
周利剑
贾韶辉
郭磊
欧新伟
徐杰
吴官生
杨宝龙
任武
张新建
吴志强
朱峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Petroleum and Natural Gas Co Ltd
Original Assignee
China Petroleum and Natural Gas Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Petroleum and Natural Gas Co Ltd filed Critical China Petroleum and Natural Gas Co Ltd
Priority to CN201810513064.XA priority Critical patent/CN108960049B/en
Publication of CN108960049A publication Critical patent/CN108960049A/en
Application granted granted Critical
Publication of CN108960049B publication Critical patent/CN108960049B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • G06V20/13Satellite images

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses recognition methods, device and the storage mediums in a kind of high consequence area of long-distance oil & gas pipeline, belong to the risk assessment technical field of long-distance oil & gas pipeline.The described method includes: obtaining the Object in Remote Sensing that the conduit region using the center line of Target pipe as symmetry axis, first distance threshold value for symmetrical radius forms, pass through the first Classification and Identification model, multiple atural object classifications in Object in Remote Sensing are identified, with the region where the multiple atural object classifications of determination, according to the geography information of the conduit region in Object in Remote Sensing, it determines the terrain object attribute information in the region in multiple atural object classifications where each atural object classification, and then identifies the high consequence area of Target pipe from the conduit region in multiple images region.The present invention can carry out automatic identification by the Object in Remote Sensing to coverage goal pipeline and improve the recognition efficiency and accuracy in the high consequence area of long-distance oil & gas pipeline to determine the high consequence area of Target pipe.

Description

Recognition methods, device and the storage medium in the high consequence area of long-distance oil & gas pipeline
Technical field
The present invention relates to the risk assessment technical field of long-distance oil & gas pipeline, in particular to a kind of height of long-distance oil & gas pipeline Recognition methods, device and the storage medium in consequence area.
Background technique
Long-distance oil & gas pipeline refers to that length is greater than the long distance oil-gas conveyance conduit of 50 kms, after the height of long-distance oil & gas pipeline Fruit area refers to that the pipe leakage existing for the periphery of long-distance oil & gas pipeline can seriously jeopardize public security or cause broken compared with overall situation Bad region.With the continuous social and economic development, the population and environmental resource on built long-distance oil & gas pipeline periphery can be with When change, lead to its periphery new crowded place easy to form or environment sensitive place Deng Gao consequence area, it is practical In, if taking risk management and control measure to these places not in time, once the oil and gas leakage thing of long-distance oil & gas pipeline occurs Part will result in adverse effect or even casualties.Therefore, it is necessary to carry out in time, accurately to the high consequence area of long-distance oil & gas pipeline Identification, to reduce the adverse effect that the operation of long-distance oil & gas pipeline generates the public and living environment.
Currently, artificial on-the-spot make an inspection tour is the main means for identifying the high consequence area of long-distance oil & gas pipeline.Specifically, technical staff Manual patrol can be carried out to long-distance oil & gas pipeline periphery along duct orientation, with 2000 meters of length be standard to long oil transportation in tour Feed channel is segmented, and is manually visualized respectively to every section of a certain range of ambient condition in oil-gas pipeline periphery, with right Existing personnel in every section of oil-gas pipeline periphery a certain range, building, water system, vegetation, soil, wetland and road distribution feelings Condition is counted.Then according to the statistical result of every section of oil-gas pipeline, the personnel of every section of oil-gas pipeline neighboring area is estimated and are built It builds the quantity of object, and according to the quantity of the personnel of every section of oil-gas pipeline neighboring area and building, determines every segment length's oil/gas pipe Whether the neighboring area in road is high consequence area, and then identifies the high consequence area of entire long-distance oil & gas pipeline.
In the implementation of the present invention, the inventor finds that the existing technology has at least the following problems:
Since long-distance oil & gas pipeline route is long, tube circumference environment is complicated, and artificial on-the-spot make an inspection tour is often by geographical environment, gas The limitation for waiting environment and traffic, causes the heavy workload for identifying high consequence area, working efficiency is low, and identification process is by subjectivity It influences, it is as a result not accurate enough.
Summary of the invention
The embodiment of the invention provides a kind of recognition methods in the high consequence area of long-distance oil & gas pipeline, device and storages to be situated between Matter can be used for solving the problems, such as that the result in the high consequence area of manual identified is not accurate enough and efficiency is lower.The technical solution is such as Under:
In a first aspect, providing a kind of recognition methods in the high consequence area of long-distance oil & gas pipeline, which comprises
Object in Remote Sensing is obtained, the Object in Remote Sensing includes using the center line of Target pipe as symmetry axis, first Distance threshold is the conduit region of symmetrical radius, and the first distance threshold value is greater than the outer diameter of the Target pipe, the target Pipeline is long-distance oil & gas pipeline to be studied;
By the first Classification and Identification model, multiple atural object classifications in the Object in Remote Sensing are identified, with true Region where fixed the multiple atural object classification, the first Classification and Identification model is the sample according to the multiple atural object classification Image training obtains;
According to the geography information of the conduit region in the Object in Remote Sensing, determine each in the multiple atural object classification The terrain object attribute information in the region where atural object classification;
The terrain object attribute information in the region where the multiple atural object classification, the pipe line area out of multiple images region Identify the high consequence area of the Target pipe in domain, described multiple images region be along the Target pipe duct orientation, Using second distance threshold value as interval, the Object in Remote Sensing is divided to obtain.
Optionally, the terrain object attribute information according to the region where the multiple atural object classification, from multiple images area The high consequence area of the Target pipe is identified in conduit region in domain, comprising:
The terrain object attribute information in the region where the multiple atural object classification determines every in described multiple images region The Location class of conduit region in a image-region, the Location class are used to indicate the conduit region in each image-region Population concentration degree;
It is each in the terrain object attribute information in the region where the multiple atural object classification and described multiple images region The Location class of conduit region in image-region identifies the target tube from the conduit region in described multiple images region The high consequence area in road.
Optionally, the terrain object attribute information according to the region where the multiple atural object classification, determines the multiple The Location class of conduit region in image-region in each image-region, comprising:
The initial position for the pipeline for including according to (i-1)-th image-region that the Object in Remote Sensing includes, described Two distance thresholds and third distance threshold determine i-th of image-region that the Object in Remote Sensing includes;
Wherein, the length for the pipeline that i-th of image-region includes is equal to the second distance threshold value, and described i-th The initial position for the pipeline that the initial position for the pipeline that a image-region includes and (i-1)-th image-region include is at a distance of institute Third distance threshold is stated, the third distance threshold is less than the second distance threshold value, and the i is the integer more than or equal to 1, When the i is 1, the initial position for the pipeline that (i-1)-th image-region includes and i-th of image-region include The initial position of pipeline is overlapped, and is initial position of the Target pipe in the Object in Remote Sensing;
From the terrain object attribute information in the region where the multiple atural object classification, determines and be located at i-th of image district The terrain object attribute information of the multiple atural object classification in domain;
According to be located at i-th of image-region in the multiple atural object classification terrain object attribute information, determine described in The initial Location class of conduit region in i-th of image-region;
From the multiple images region that the Object in Remote Sensing includes determine be overlapped with i-th of image-region to A few image-region, and the initial Location class of maximum in the initial Location class of at least one image-region is determined For the Location class of i-th of image-region.
Optionally, the basis is located at the terrain object attribute letter of the multiple atural object classification in i-th of image-region Breath, determines the initial Location class of the conduit region in i-th of image-region, comprising:
According to be located at i-th of image-region in the multiple atural object classification terrain object attribute information, determine described in The one-storey house area and lower building area that i-th of image-region includes, the lower building refer to that floor is greater than 1 and is less than or waits In the building constructions of floor threshold value;
When the one-storey house area that i-th of image-region includes is less than the first area threshold, the lower building area for including Believe less than second area threshold value and according to the terrain object attribute for the multiple atural object classification being located in i-th of image-region When breath determines that i-th of image-region does not include that suburban population concentrates place, urban district and transport hub, determine described i-th The initial Location class of image-region is level-one;
When the one-storey house area that i-th of image-region includes is greater than or equal to first area threshold and is less than third Area threshold, the lower building area for including are greater than or equal to the second area threshold value and are less than fourth face product threshold value and root I-th of image district is determined according to the terrain object attribute information for the multiple atural object classification being located in i-th of image-region When domain does not include that suburban population concentrates place, urban district and transport hub, the initial Location class of i-th of image-region is determined For second level, the third area threshold is greater than first area threshold, and the fourth face product threshold value is greater than the second area Threshold value;
When the one-storey house area that i-th of image-region includes be greater than or equal to the third area threshold, or including Lower building area be greater than or equal to the fourth face product threshold value, or according to be located at i-th of image-region in institute State multiple atural object classifications terrain object attribute information determine i-th of image-region include suburban population concentrate place when, determine The initial Location class of i-th of image-region is three-level;
When according to the determination of the terrain object attribute information for the multiple atural object classification being located in i-th of image-region When i-th of image-region includes urban district or transport hub, determine that the initial Location class of i-th of image-region is level Four.
Optionally, the terrain object attribute information and described multiple images according to the region where the multiple atural object classification The Location class of conduit region in region in each image-region is identified from the conduit region in described multiple images region The high consequence area of the Target pipe, comprising:
When the Target pipe is long oil pipeline road, for any image region A in described multiple images region, such as Fruit described image region A meets the first identification condition, it is determined that the conduit region in the A of described image region is the Target pipe High consequence area, the first identification condition refer to the conduit region in the A of described image region Location class be three-level or four Perhaps there are the roads or described image region A packet in environment sensitive place or non-transport hub in the A of described image region for grade The one-storey house area included is greater than the 6th area threshold and described image region greater than the 5th area threshold, the lower building area for including Conduit region in A belongs to rural area or small towns, and the environment sensitive place includes nature reserve area and water source;
When the Target pipe is long gas pipeline, for any image region A in described multiple images region, such as Fruit described image region A meets the second identification condition, it is determined that the conduit region in the A of described image region is the Target pipe High consequence area, the second identification condition refer to the conduit region in the A of described image region Location class be three-level or four There are population concentration place or combustible and explosive areas in grade or described image region A.
Optionally, if the described image region A meets the first identification condition, it is determined that in the A of described image region Conduit region is the high consequence area of the Target pipe, comprising:
If in the A of described image region, there are the roads of non-transport hub, it is determined that the pipe line area in the A of described image region Domain is the high consequence area of level-one of the Target pipe;
If the Location class of the conduit region in the A of described image region is to exist in three-level or described image region A The lower building that the one-storey house area that nature reserve area or described image region A include is greater than the 5th area threshold, includes The conduit region that area is greater than in the 6th area threshold and described image region A belongs to rural area or small towns, it is determined that described Conduit region in image-region A is the high consequence area of second level of the Target pipe;
If the Location class of the conduit region in the A of described image region is to exist in level Four or described image region A Water source, it is determined that the conduit region in the A of described image region is the high consequence area of three-level of the Target pipe.
Optionally, if the described image region A meets the second identification condition, it is determined that in the A of described image region Conduit region is the high consequence area of the Target pipe, comprising:
If there are population concentration place and the potential shadow of pipeline that described image region A includes in the A of described image region It rings radius and is less than or equal to the 4th distance threshold, it is determined that the conduit region in the A of described image region is the Target pipe The high consequence area of level-one, the potential impact radius are the outer diameter and maximum allowable behaviour according to the described image region A pipeline for including Make pressure determination to obtain;
If there are population concentration place and the potential shadow of pipeline that described image region A includes in the A of described image region Ringing radius greater than the Location class of the conduit region in the 4th distance threshold perhaps described image region A is three-level or described There are combustible and explosive areas in image-region A, it is determined that the conduit region in the A of described image region is the two of the Target pipe Ji Gao consequence area;
If the Location class of the conduit region in the A of described image region is level Four, it is determined that in the A of described image region Conduit region is the high consequence area of three-level of the Target pipe.
Optionally, the acquisition Object in Remote Sensing, comprising:
Obtain the boundary bit confidence of the position of center line information of the Target pipe and the conduit region of the Target pipe Breath, the boundary position information is used to indicate is by symmetry axis, the first distance threshold value of the center line of the Target pipe The conduit region of symmetrical radius;
According to the position of center line information, multiple initial remote sensing images are obtained, described in every initial remote sensing images covering The section of tubing region of Target pipe;
According to the position of center line information, splicing is carried out to multiple described initial remote sensing images, obtains splicing distant Feel image, the splicing remote sensing images cover whole conduit regions of the Target pipe;
According to the boundary position information, cutting processing is carried out to the splicing remote sensing images, obtains the target remote sensing Image.
Optionally, described to pass through the first Classification and Identification model, to multiple atural object classifications in the Object in Remote Sensing into Before row identification, further includes:
Obtain the sample image of the multiple atural object classification;
Feature extraction is carried out to the sample image of the multiple atural object classification, obtains the sample graph of the multiple atural object classification The geometric error modeling feature and spectral signature of picture;
According to the sample image of the multiple atural object classification and the geometry line of the sample image of the multiple atural object classification Feature and spectral signature are managed, the second Classification and Identification model is trained, obtains the first Classification and Identification model, described second Classification and Identification model refers to be trained, atural object classification for identification Classification and Identification model.
Second aspect, provides a kind of identification device in the high consequence area of long-distance oil & gas pipeline, and described device includes:
First obtains module, and for obtaining Object in Remote Sensing, the Object in Remote Sensing includes in Target pipe Heart line is symmetry axis, the conduit region that first distance threshold value is symmetrical radius, and the first distance threshold value is greater than the target tube The outer diameter in road, the Target pipe are long-distance oil & gas pipeline to be studied;
First determining module, for passing through the first Classification and Identification model, to multiple atural objects in the Object in Remote Sensing Classification is identified that, with the region where the multiple atural object classification of determination, the first Classification and Identification model is according to The sample image training of multiple atural object classifications obtains;
Second determining module, for the geography information according to the conduit region in the Object in Remote Sensing, determine described in The terrain object attribute information in the region in multiple atural object classifications where each atural object classification;
Identification module, for the terrain object attribute information according to the region where the multiple atural object classification, from multiple images Identify that the high consequence area of the Target pipe, described multiple images region are along the target tube in conduit region in region The duct orientation in road, using second distance threshold value as interval, the Object in Remote Sensing is divided to obtain.
Optionally, the identification module includes:
First determination unit determines institute for the terrain object attribute information according to the region where the multiple atural object classification The Location class of the conduit region in multiple images region in each image-region is stated, the Location class is used to indicate each figure As the population concentration degree of the conduit region in region;
First recognition unit, for according to the terrain object attribute information in the region where the multiple atural object classification and described more The Location class of conduit region in a image-region in each image-region, the conduit region out of described multiple images region The high consequence area of the middle identification Target pipe.
Optionally, first determination unit includes:
First determines subelement, the pipe that (i-1)-th image-region for including according to the Object in Remote Sensing includes The initial position in road, the second distance threshold value and third distance threshold determine i-th of figure that the Object in Remote Sensing includes As region;
Wherein, the length for the pipeline that i-th of image-region includes is equal to the second distance threshold value, and described i-th The initial position for the pipeline that the initial position for the pipeline that a image-region includes and (i-1)-th image-region include is at a distance of institute Third distance threshold is stated, the third distance threshold is less than the second distance threshold value, and the i is the integer more than or equal to 1, When the i is 1, the initial position for the pipeline that (i-1)-th image-region includes and i-th of image-region include The initial position of pipeline is overlapped, and is initial position of the Target pipe in the Object in Remote Sensing;
Second determines subelement, for determining from the terrain object attribute information in the region where the multiple atural object classification The terrain object attribute information of the multiple atural object classification in i-th of image-region;
Third determines subelement, for the ground according to the multiple atural object classification being located in i-th of image-region Object attribute information determines the initial Location class of the conduit region in i-th of image-region;
4th determines subelement, for determining with described the from the multiple images region that the Object in Remote Sensing includes At least one image-region that i image-region is overlapped, and will be in the initial Location class of at least one image-region Maximum initial Location class is determined as the Location class of i-th of image-region.
Optionally, the third determines that subelement is specifically used for:
According to be located at i-th of image-region in the multiple atural object classification terrain object attribute information, determine described in The one-storey house area and lower building area that i-th of image-region includes, the lower building refer to that floor is greater than 1 and is less than or waits In the building constructions of floor threshold value;
When the one-storey house area that i-th of image-region includes is less than the first area threshold, the lower building area for including Believe less than second area threshold value and according to the terrain object attribute for the multiple atural object classification being located in i-th of image-region When breath determines that i-th of image-region does not include that suburban population concentrates place, urban district and transport hub, determine described i-th The initial Location class of image-region is level-one;
When the one-storey house area that i-th of image-region includes is greater than or equal to first area threshold and is less than third Area threshold, the lower building area for including are greater than or equal to the second area threshold value and are less than fourth face product threshold value and root I-th of image district is determined according to the terrain object attribute information for the multiple atural object classification being located in i-th of image-region When domain does not include that suburban population concentrates place, urban district and transport hub, the initial Location class of i-th of image-region is determined For second level, the third area threshold is greater than first area threshold, and the fourth face product threshold value is greater than the second area Threshold value;
When the one-storey house area that i-th of image-region includes be greater than or equal to the third area threshold, or including Lower building area be greater than or equal to the fourth face product threshold value, or according to be located at i-th of image-region in institute State multiple atural object classifications terrain object attribute information determine i-th of image-region include suburban population concentrate place when, determine The initial Location class of i-th of image-region is three-level;
When according to the determination of the terrain object attribute information for the multiple atural object classification being located in i-th of image-region When i-th of image-region includes urban district or transport hub, determine that the initial Location class of i-th of image-region is level Four.
Optionally, first recognition unit includes:
First identification subelement, apparatus is when the Target pipe is long oil pipeline road, for described multiple images region In any image region A, if described image region A meet first identification condition, it is determined that the pipe in the A of described image region Road region is the high consequence area of the Target pipe, and the first identification condition refers to the conduit region in the A of described image region Location class be in three-level or level Four or described image region A there are the road in environment sensitive place or non-transport hub, Or the one-storey house area that described image region A includes is greater than the 6th face greater than the 5th area threshold, the lower building area for including It accumulates the conduit region in threshold value and described image region A and belongs to rural area or small towns, the environment sensitive place includes conservation of nature Area and water source;
Second identification subelement, is used for when the Target pipe is long gas pipeline, for described multiple images region In any image region A, if described image region A meet second identification condition, it is determined that the pipe in the A of described image region Road region is the high consequence area of the Target pipe, and the second identification condition refers to the conduit region in the A of described image region Location class be that there are population concentration place or combustible and explosive areas in three-level or level Four or described image region A.
Optionally, the first identification subelement is specifically used for:
If in the A of described image region, there are the roads of non-transport hub, it is determined that the pipe line area in the A of described image region Domain is the high consequence area of level-one of the Target pipe;
If the Location class of the conduit region in the A of described image region is to exist in three-level or described image region A The lower building that the one-storey house area that nature reserve area or described image region A include is greater than the 5th area threshold, includes The conduit region that area is greater than in the 6th area threshold and described image region A belongs to rural area or small towns, it is determined that described Conduit region in image-region A is the high consequence area of second level of the Target pipe;
If the Location class of the conduit region in the A of described image region is to exist in level Four or described image region A Water source, it is determined that the conduit region in the A of described image region is the high consequence area of three-level of the Target pipe.
Optionally, the second identification subelement is specifically used for:
If there are population concentration place and the potential shadow of pipeline that described image region A includes in the A of described image region It rings radius and is less than or equal to the 4th distance threshold, it is determined that the conduit region in the A of described image region is the Target pipe The high consequence area of level-one, the potential impact radius are the outer diameter and maximum allowable behaviour according to the described image region A pipeline for including Make pressure determination to obtain;
If there are population concentration place and the potential shadow of pipeline that described image region A includes in the A of described image region Ringing radius greater than the Location class of the conduit region in the 4th distance threshold perhaps described image region A is three-level or described There are combustible and explosive areas in image-region A, it is determined that the conduit region in the A of described image region is the two of the Target pipe Ji Gao consequence area;
If the Location class of the conduit region in the A of described image region is level Four, it is determined that in the A of described image region Conduit region is the high consequence area of three-level of the Target pipe.
Optionally, the first acquisition module includes:
First acquisition unit, for obtaining the position of center line information of the Target pipe and the pipeline of the Target pipe The boundary position information in region, the boundary position information are used to indicate using the center line of the Target pipe as symmetry axis, institute State the conduit region that first distance threshold value is symmetrical radius;
Second acquisition unit, for according to the position of center line information, obtaining multiple initial remote sensing images, every initial Remote sensing images cover the section of tubing region of the Target pipe;
First processing units, for being spelled to multiple described initial remote sensing images according to the position of center line information Processing is connect, splicing remote sensing images are obtained, the splicing remote sensing images cover whole conduit regions of the Target pipe;
The second processing unit, for carrying out cutting processing to the splicing remote sensing images according to the boundary position information, Obtain the Object in Remote Sensing.
Optionally, described device further include:
Second obtains module, for obtaining the sample image of the multiple atural object classification;
Extraction module carries out feature extraction for the sample image to the multiple atural object classification, obtains the multiplely The geometric error modeling feature and spectral signature of the other sample image of species;
Training module, for according to the sample image of the multiple atural object classification and the sample of the multiple atural object classification The geometric error modeling feature and spectral signature of image are trained the second Classification and Identification model, obtain first Classification and Identification Model, the second Classification and Identification model refer to be trained, atural object classification for identification Classification and Identification model.
The third aspect, provides a kind of identification device in the high consequence area of long-distance oil & gas pipeline, and described device includes:
Processor and memory for storage processor executable instruction;
Wherein, the processor is configured to the high consequence area for any long-distance oil & gas pipeline that above-mentioned first aspect provides Recognition methods.
Fourth aspect provides a kind of computer readable storage medium, is stored with computer program in the storage medium, The computer program realizes the high consequence for any long-distance oil & gas pipeline that above-mentioned first aspect provides when being executed by processor The recognition methods in area.
Technical solution provided in an embodiment of the present invention at least bring it is following the utility model has the advantages that in the embodiment of the present invention, for Long-distance oil & gas pipeline, that is, Target pipe of research, it is available using the center line of Target pipe as symmetry axis, first distance threshold value For symmetrical radius conduit region form Object in Remote Sensing, by the first Classification and Identification model, in Object in Remote Sensing Multiple atural object classifications identified, with the region where the multiple atural object classifications of determination, and according to the pipe in Object in Remote Sensing The geography information in road region determines the terrain object attribute information in the region in multiple atural object classification where each atural object classification, most Afterwards according to the terrain object attribute information in the region where multiple atural object classification, identified from the conduit region in multiple images region The high consequence area of Target pipe.It that is to say, in embodiments of the present invention, the mesh of the conduit region of available coverage goal pipeline Remote sensing images are marked, and using image recognition algorithm to Object in Remote Sensing progress automatic identification, after the height to determine Target pipe Fruit area improves recognition efficiency and accuracy compared to the method in the high consequence area of manual identified in the related technology.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other Attached drawing.
Fig. 1 is a kind of schematic diagram of the identifying system in high consequence area provided in an embodiment of the present invention;
Fig. 2 is a kind of process signal of the recognition methods in the high consequence area of long-distance oil & gas pipeline provided in an embodiment of the present invention Figure;
Fig. 3 is that the process of the recognition methods in the high consequence area of another long-distance oil & gas pipeline provided in an embodiment of the present invention is shown It is intended to;
Fig. 4 is a kind of structural representation of the identification device in the high consequence area of long-distance oil & gas pipeline provided in an embodiment of the present invention Figure;
Fig. 5 is a kind of structural schematic diagram of terminal 500 provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention Formula is described in further detail.
Before carrying out detailed explanation to the embodiment of the present invention, first to the name being related in the embodiment of the present invention Word, application scenarios and system architecture are explained respectively.
Firstly, the noun being related in the embodiment of the present invention is introduced.
Atural object classification
Atural object refers on ground various corporeal things (such as mountains and rivers, forest, building) and intangibles (Ru Sheng, circle of county etc.) General name refers to relatively-stationary object on earth surface.Atural object classification is to be classified to obtain to atural object, for example atural object classification can To include building, water system, vegetation, soil and road etc..
Terrain object attribute information
Terrain object attribute information is used to indicate the specific object of atural object, for example can be the information of instruction its function and purposes, It can be used for carrying out exhaustive division to every kind of atural object.For example, the attribute information of building can be residential block, hospital, school, quotient Industry area, industrial area, kindergarten, home for destitute or market etc..
Classification and Identification model
Classification and Identification model refers to the model that can be identified to multiple atural object classifications in remote sensing images, specifically can be with For CNN (Convolutional Neural Networks, convolutional neural networks) model, or RNN (Recurrent Neural Network, Recognition with Recurrent Neural Network) model.
Potential impact radius
When the potential impact radius of gas pipeline refers to that gas pipeline fails, periphery public security and property may It is significantly affected the radius in region, is determined by the outer diameter and maximum allowable operating pressure of gas pipeline.
Secondly, to the present embodiments relate to application scenarios be introduced.
The safe operation of long-distance oil & gas pipeline is not only related to the feedback on performance of pipeline operator, is also related to tube circumference The life of the people and the safety of property, and with the rapid development of social economy, the expansion of urban central zone can make The Fei Gao consequence area of script long-distance oil & gas pipeline becomes high consequence area, it is therefore desirable to periodically to the high consequence area of long-distance oil & gas pipeline It is identified, to reduce the adverse effect that the operation of long-distance oil & gas pipeline generates the public and living environment.
Finally, to the present embodiments relate to system architecture be introduced.
The recognition methods in the high consequence area of long-distance oil & gas pipeline provided in an embodiment of the present invention can be applied to high consequence area Identifying system in, Fig. 1 is a kind of schematic diagram of the identifying system in high consequence area provided in an embodiment of the present invention, as shown in Figure 1, The identifying system may include database server 10, location information is shown and analysis module 20, preprocessing of remote sensing images module 30, remote sensing image classification module 40, geography information module 50, high consequence area identification module 60 and data capture management module 70. Wherein, modules and database server 10 can carry out data interaction, and can be carried out by network between modules Connection.
Database server 10, the contents such as data result, data directory, document for storing other each modules, such as Can store location information show and the pre-processed results of the location information of analysis module 20, preprocessing of remote sensing images module 30, The recognition result etc. of the classification results of remote sensing image classification module 40 or high consequence area identification module 60.
Location information is shown and analysis module 20, for storing, showing or analyzing the position of center line of Target pipe, and can The position of center line of Target pipe as the foundation for obtaining remote sensing images, to be sweared in addition it can define and manage tube circumference Measure bounds.
Preprocessing of remote sensing images module 30 carries out geometry for pre-processing to remote sensing images, including to remote sensing images It corrects, be registrated, merge, inlay and cut.
Remote sensing image classification module 40, multiple atural object classifications in remote sensing images for identification, to realize to remote sensing figure The classification of atural object as in.
Geography information module 50, for improving the classification results and identification each ground species of remote sensing image classification module 40 Other terrain object attribute information can specifically be configured with GIS (Geographic Information System, geography information system System), electronic map, thematic maps, political affairs layout data, the auxiliary informations such as environmental ecology data or demographic data.
High consequence area identification module 60 is identified, shown and is managed for the high consequence area to Target pipe.
Data capture management module 70 is acquired for the position of center line information to Target pipe, and to target The periphery vector bounds of pipeline are acquired.
It should be noted that above-mentioned identifying system is only the exemplary system that the embodiment of the present invention provides, in practical application In, above-mentioned identifying system can also include more or fewer modules or some of them module can also by other modules Lai Instead of as long as can be realized the recognition methods in the high consequence area of long-distance oil & gas pipeline provided in an embodiment of the present invention.Into one Step ground, the module that above-mentioned identifying system is included can concentrate in a terminal, can also concentrate in multiple terminals, connect down By in following Fig. 3 embodiments by taking all modules that the identifying system is included are concentrated in a terminal as an example, to this hair The recognition methods in the high consequence area for the long-distance oil & gas pipeline that bright embodiment provides is described in detail.
Fig. 2 is a kind of process signal of the recognition methods in the high consequence area of long-distance oil & gas pipeline provided in an embodiment of the present invention Figure, this method can be applied in terminal, which can be mobile phone, tablet computer or computer etc..Referring to fig. 2, this method Include the following steps:
Step 201: obtaining Object in Remote Sensing, it is symmetrical which, which includes with the center line of Target pipe, Axis, the conduit region that first distance threshold value is symmetrical radius, first distance threshold value are greater than the outer diameter of Target pipe, and Target pipe is Long-distance oil & gas pipeline to be studied.
Step 202: by the first Classification and Identification model, multiple atural object classifications in Object in Remote Sensing are identified, With the region where the multiple atural object classifications of determination, the first Classification and Identification model is according to the training of the sample image of multiple atural object classifications It obtains.
Step 203: according to the geography information of the conduit region in Object in Remote Sensing, determining each in multiple atural object classifications The terrain object attribute information in the region where atural object classification.
Step 204: the terrain object attribute information in the region where multiple atural object classifications, the pipe out of multiple images region In road region identify Target pipe high consequence area, multiple images region be along Target pipe duct orientation, with second away from It is interval from threshold value, Object in Remote Sensing is divided to obtain.
It is available with Target pipe for long-distance oil & gas pipeline, that is, Target pipe to be studied in the embodiment of the present invention Center line be symmetry axis, the Object in Remote Sensing of conduit region that first distance threshold value is symmetrical radius composition, pass through first Classification and Identification model identifies multiple atural object classifications in Object in Remote Sensing, where the multiple atural object classifications of determination Region, and according to the geography information of the conduit region in Object in Remote Sensing, determine each ground species in multiple atural object classification The terrain object attribute information in the region where not, finally according to the terrain object attribute information in the region where multiple atural object classification, from The high consequence area of Target pipe is identified in conduit region in multiple images region.It that is to say, it in embodiments of the present invention, can be with The Object in Remote Sensing of the conduit region of coverage goal pipeline is obtained, and Object in Remote Sensing is carried out using image recognition algorithm Automatic identification, compared to the method in the high consequence area of manual identified in the related technology, improves to determine the high consequence area of Target pipe Recognition efficiency and accuracy.
Optionally, the pipe according to the terrain object attribute information in the region where multiple atural object classifications, out of multiple images region The high consequence area of Target pipe is identified in road region, comprising:
The terrain object attribute information in the region where multiple atural object classifications determines each image district in multiple images region The Location class of conduit region in domain, Location class are used to indicate the population concentration journey of the conduit region in each image-region Degree;
Each image-region in the terrain object attribute information in the region where multiple atural object classifications and multiple images region The Location class of interior conduit region identifies the high consequence area of Target pipe from the conduit region in multiple images region.
Optionally, it according to the terrain object attribute information in the region where multiple atural object classifications, determines every in multiple images region The Location class of conduit region in a image-region, comprising:
The initial position for the pipeline for including according to (i-1)-th image-region that Object in Remote Sensing includes, second distance threshold Value and third distance threshold, determine i-th of image-region that Object in Remote Sensing includes;
Wherein, the length for the pipeline that i-th of image-region includes is equal to second distance threshold value, and i-th of image-region packet The initial position for the pipeline that the initial position of the pipeline included and (i-1)-th image-region include is at a distance of third distance threshold, third Distance threshold is less than second distance threshold value, and i is the integer more than or equal to 1, and when i is 1, (i-1)-th image-region includes The initial position of pipeline is overlapped with the initial position for the pipeline that i-th of image-region includes, and is that Target pipe is distant in target Feel the initial position in image;
From the terrain object attribute information in the region where multiple atural object classifications, determine more in i-th of image-region The terrain object attribute information of a atural object classification;
According to the terrain object attribute information for the multiple atural object classifications being located in i-th of image-region, i-th of image-region is determined The initial Location class of interior conduit region;
At least one figure being overlapped with i-th of image-region is determined from the multiple images region that Object in Remote Sensing includes It is determined as i-th of image as region, and by the initial Location class of maximum in the initial Location class of at least one image-region The Location class in region.
Optionally, it according to the terrain object attribute information for the multiple atural object classifications being located in i-th of image-region, determines i-th The initial Location class of conduit region in image-region, comprising:
According to the terrain object attribute information for the multiple atural object classifications being located in i-th of image-region, i-th of image-region is determined Including one-storey house area and lower building area, lower building refer to floor be greater than 1 and be less than or equal to floor threshold value building Building;
When the one-storey house area that i-th of image-region includes is less than less than the first area threshold, the lower building area for including Second area threshold value and i-th of figure is determined according to the terrain object attribute information for the multiple atural object classifications being located in i-th image-region As region does not include that suburban population concentrates place, urban district and when transport hub, determines the initial Location class of i-th of image-region For level-one;
When the one-storey house area that i-th of image-region includes is greater than or equal to the first area threshold and is less than third area threshold It is worth, the lower building area that includes is greater than or equal to second area threshold value and is less than fourth face product threshold value and according to being located at i-th It includes that suburban population collects midfield that the terrain object attribute information of multiple atural object classifications in image-region, which determines i-th of image-region not, When institute, urban district and transport hub, determine that the initial Location class of i-th of image-region is second level, third area threshold is greater than the One area threshold, fourth face product threshold value are greater than second area threshold value;
When the one-storey house area that i-th of image-region includes be greater than or equal to third area threshold, or including low layer building Room area is greater than or equal to fourth face product threshold value, or the atural object according to the multiple atural object classifications being located in i-th of image-region When attribute information determines that i-th of image-region includes that suburban population concentrates place, initial area of i-th of image-region etc. is determined Grade is three-level;
When the terrain object attribute information that basis is located at multiple atural object classifications in i-th of image-region determines i-th of image district When domain includes urban district or transport hub, determine that the initial Location class of i-th of image-region is level Four.
Optionally, according to each figure in the terrain object attribute information in the region where multiple atural object classifications and multiple images region As the Location class of the conduit region in region, the high consequence of Target pipe is identified from the conduit region in multiple images region Area, comprising:
When Target pipe is long oil pipeline road, for any image region A in multiple images region, if image district Domain A meets the first identification condition, it is determined that the conduit region in image-region A is the high consequence area of Target pipe, the first identification Condition refers to that the Location class of the conduit region in image-region A is quick for there are environment in three-level or level Four or image-region A Sense place or non-transport hub road or image-region A include one-storey house area be greater than the 5th area threshold, include it is low The conduit region that floor room area is greater than in the 6th area threshold and image-region A belongs to rural area or small towns, environment sensitive place Including nature reserve area and water source;
When Target pipe is long gas pipeline, for any image region A in multiple images region, if image district Domain A meets the second identification condition, it is determined that the conduit region in image-region A is the high consequence area of Target pipe, the second identification Condition refers to that the Location class of the conduit region in image-region A is that there are population collection in three-level or level Four or image-region A Middle place or combustible and explosive area.
Optionally, if image-region A meets the first identification condition, it is determined that the conduit region in image-region A is mesh Mark the high consequence area of pipeline, comprising:
If there are the roads of non-transport hub in image-region A, it is determined that the conduit region in image-region A is target The high consequence area of the level-one of pipeline;
If the Location class of the conduit region in image-region A is that there are conservations of nature in three-level or image-region A The one-storey house area that area or image-region A include is greater than the 6th area greater than the 5th area threshold, the lower building area for including Conduit region in threshold value and image-region A belongs to rural area or small towns, it is determined that the conduit region in image-region A is target tube The high consequence area of the second level in road;
If the Location class of the conduit region in image-region A is in level Four or image-region A there are water source, Determine that the conduit region in image-region A is the high consequence area of three-level of Target pipe.
Optionally, if image-region A meets the second identification condition, it is determined that the conduit region in image-region A is mesh Mark the high consequence area of pipeline, comprising:
If there are population concentration place and the potential impact radius of pipeline that image-region A includes is small in image-region A In or equal to the 4th distance threshold, it is determined that the conduit region in image-region A is the high consequence area of level-one of Target pipe, potential The radius of influence is obtained according to the determination of the outer diameter and maximum allowable operating pressure of the image-region A pipeline for including;
If there are population concentration place and the potential impact radius of pipeline that image-region A includes is big in image-region A It is to exist in three-level or image-region A in the Location class of the conduit region in the 4th distance threshold perhaps image-region A Combustible and explosive area, it is determined that the conduit region in image-region A is the high consequence area of second level of Target pipe;
If the Location class of the conduit region in image-region A is level Four, it is determined that the conduit region in image-region A For the high consequence area of three-level of Target pipe.
Optionally, Object in Remote Sensing is obtained, comprising:
Obtain the boundary position information of the position of center line information of Target pipe and the conduit region of Target pipe, boundary bit Confidence breath is used to indicate the conduit region using the center line of Target pipe as symmetry axis, first distance threshold value for symmetrical radius;
According to position of center line information, multiple initial remote sensing images, every initial remote sensing images coverage goal pipeline are obtained Section of tubing region;
According to position of center line information, splicing is carried out to multiple initial remote sensing images, splicing remote sensing images is obtained, spells Connect whole conduit regions of remote sensing images coverage goal pipeline;
According to boundary position information, cutting processing is carried out to splicing remote sensing images, obtains Object in Remote Sensing.
Optionally, by the first Classification and Identification model, multiple atural object classifications in Object in Remote Sensing are carried out identifying it Before, further includes:
Obtain the sample image of multiple atural object classifications;
Feature extraction is carried out to the sample image of multiple atural object classifications, obtains the geometry of the sample image of multiple atural object classifications Textural characteristics and spectral signature;
According to the geometric error modeling feature of the sample image of multiple atural object classifications and the sample image of multiple atural object classifications and Spectral signature is trained the second Classification and Identification model, obtains the first Classification and Identification model, and the second Classification and Identification model refers to To be trained, atural object classification for identification Classification and Identification model.
All the above alternatives, can form alternative embodiment of the invention according to any combination, and the present invention is real It applies example and this is no longer repeated one by one.
Fig. 3 is that the process of the recognition methods in the high consequence area of another long-distance oil & gas pipeline provided in an embodiment of the present invention is shown It is intended to, this method can be applied in terminal, which can be smart phone, tablet computer, computer or server etc..Ginseng See Fig. 3, this method comprises the following steps:
Step 301: obtain Object in Remote Sensing, Object in Remote Sensing include using the center line of Target pipe as symmetry axis, First distance threshold value is the conduit region of symmetrical radius, and Target pipe is long-distance oil & gas pipeline to be studied.
Wherein, remote sensing images refer to the film or photo for recording various atural object electromagnetic wave sizes, are broadly divided into airphoto And satellite photograph.Object in Remote Sensing refer to include the conduit region of Target pipe remote sensing images.
In the embodiment of the present invention, Object in Remote Sensing can be directly transmitted to obtain by other equipment, can be from image data It is acquired in library, multiple the initial remote sensing images that can also be sent to remote sensing satellite are spliced to obtain.For example, image data The Object in Remote Sensing that one includes the conduit region of Target pipe is stored in library, terminal can be directly from the picture number According to obtaining Object in Remote Sensing in library.
Wherein, first distance threshold value is greater than the outer diameter of Target pipe, that is to say, the conduit region of Target pipe includes target Pipeline, and regional scope is greater than the range of Target pipe.First distance threshold value is used to indicate the conduit region boundary of Target pipe The vertical range of center line away from Target pipe, specifically, first distance threshold value can be pipeline after Target pipe generation accident Two sides generate biggest impact range when coverage boundary to Target pipe center line vertical range, or target The potential impact radius of pipeline.
In the embodiment of the present invention, first distance threshold value can be preset, specifically can be with terminal default configuration, can also be by Technical staff is configured according to actual needs, for example, can be set by technical staff according to the potential impact radius of Target pipe It sets.It is exemplary, when Target pipe is long-distance oil & gas pipeline, can will be permitted according to the maximum of Target pipe outer diameter and Target pipe Perhaps the potential impact radius that operating pressure is calculated is determined as first distance threshold value.In one example, the first distance threshold Value can be 200 meters, that is to say, the conduit region of the Target pipe refers to that the center line two sides of distance objective pipeline are each wide by 200 The conduit region of rice.
In a possible embodiment, Object in Remote Sensing can be obtained by following steps 3011-3014.
Step 3011:Obtain the boundary bit confidence of the position of center line information of Target pipe and the conduit region of Target pipe Breath, boundary position information are used to indicate the pipe using the center line of Target pipe as symmetry axis, first distance threshold value for symmetrical radius Road region.
Wherein, position of center line information is used to indicate the position of center line of Target pipe, can be the center of Target pipe The coordinate information of line, the coordinate information can be GPS (Global Positioning System, global positioning system) coordinate Information, the coordinate information of dipper system or Gray receive the coordinate information etc. of this system.In the embodiment of the present invention, the center line position Confidence breath can be manually entered as needed by terminal default configuration by user, can be by position indicator in Target pipe Mobile obtain in portion is simultaneously sent to terminal, location instrument can also be held by technical staff outside Target pipe along Target pipe Heart line direction is mobile to be obtained and is sent to terminal by location instrument.For example, technical staff can hold location instrument along target tube Road direction is moved outside Target pipe, and line position information centered on positioning result is sent to end by location instrument End.
Wherein, boundary position information is used to indicate the boundary position of conduit region, can be the seat on the boundary of conduit region Mark information.Specifically, which can determine according to the center line and first distance threshold value of Target pipe, can also be with It is determined according to multiple key point location informations of the conduit region of Target pipe, for example, multiple key point location information can be with For the location information of the corner of Target pipe.In the embodiment of the present invention, the boundary position information can by terminal default configuration, It can also be manually entered by user, terminal can also be sent to by other equipment.For example, target tube can be obtained by location instrument After the position of center line information in road, which is determined according to the position of center line information and first distance threshold value, so The boundary position information is sent to terminal afterwards.
In a possible embodiment, in the borderline region for determining Target pipe, in available Target pipe Then the GPS coordinate of each point on heart line determines Target pipe according to the GPS coordinate of each point and first distance threshold value Conduit region boundary position GPS coordinate.For example, it is assumed that first distance threshold value is 200 meters, positioned using pocket GPS Instrument positions the center line of Target pipe, and the GPS coordinate in the center position certain point of the straightway of Target pipe is (109.88836,35.23849), then can be by Target pipe two sides perpendicular to tube wall direction and apart from 200 meters of this GPS coordinate Two points at place, are determined as two boundary points of the conduit region of Target pipe.
It should be noted that above-mentioned numerical value is only the exemplary value that the embodiment of the present invention provides, in practical applications, on Stating numerical value can also be to take other values, and the embodiment of the present invention is not specifically limited in this embodiment.
Step 3012:According to position of center line information, multiple initial remote sensing images, every initial remote sensing images covering are obtained The section of tubing region of Target pipe.
It cannot include complete target tube with the remote sensing images that high-resolution obtains since the distance of Target pipe is longer Road, and if the resolution ratio of the remote sensing images compares when one remote sensing images of acquisition be can wrap containing complete Target pipe again It is low, the high consequence area of Target pipe cannot precisely be identified, it is therefore desirable to obtain multiple with high-resolution initial distant Feel image.
Specifically, which can be sent to more scape remote sensing satellites by terminal, by more scape remote sensing satellite roots Shoot the initial remote sensing images in the section of tubing region of multiple coverage goal pipelines respectively according to the position of center line information, and should Multiple initial remote sensing images are sent to terminal.Specifically, more scape remote sensing satellites, can be by target when shooting initial remote sensing images The position of center line of pipeline is shot as the middle position of to be captured every initial remote sensing images, in this way, every initial Remote sensing images not only may include the segmented conduit of Target pipe, can be with the conduit region of overlay segments pipeline, i.e. target tube The section of tubing region in road.Moreover, every initial remote sensing images can also be Hi-spatial resolution remote sensing image.
Further, the position of center line information and first distance threshold value can also be sent to more Jing Yaoganwei by terminal Star shoots multiple initial remote sensing figures according to the position of center line information and the first distance threshold value by more scape remote sensing satellites respectively Picture, and multiple initial remote sensing images of shooting are sent to terminal.In addition, this multiple initial remote sensing images can also be set by other Preparation is sent to obtain, or acquires from image data base, and it is not limited in the embodiment of the present invention.
Step 3013:According to position of center line information, to this, multiple initial remote sensing images carry out splicing, are spliced Remote sensing images, whole conduit regions of the splicing remote sensing images coverage goal pipeline.
Specifically, when multiple initial remote sensing images carry out splicing to this, first multiple initial remote sensing images by this are needed The partial target pipeline for being included by every initial remote sensing images is ranked up the location of in target complete pipeline, is ensured The physical location that the target complete pipeline obtained after splicing is Target pipe is carried out, is then with the center line of Target pipe Multiple initial remote sensing images after sequence are carried out splicing, obtain the splicing remote sensing images by tie point.
It further, can also first to this, multiple be initial distant before to this, multiple initial remote sensing images carry out splicings The pretreatments such as sense image carries out geometric correction, image registration, image remove cloud or remove shade, make the geometry of every initial remote sensing images Size or image display degree are completely the same, after completing pretreatment, further according to position of center line information, by pretreated at the beginning of multiple Beginning remote sensing images carry out splicing, obtain the splicing remote sensing images.
Step 3014:According to boundary position information, cutting processing is carried out to splicing remote sensing images, obtains target remote sensing figure Picture.
It may be deposited since the position of center line information of according to target pipeline carries out the splicing remote sensing images that splicing obtains In image range phenomenon not of uniform size, or the phenomenon excessive in the presence of the range for the conduit region for including, and image range Inconsistent or regional scope, which crosses conference, reduces the recognition efficiency in high consequence area, therefore, can be with after obtaining splicing remote sensing images First according to boundary position information, cutting processing is carried out to splicing remote sensing images, is only included boundary position information instruction Conduit region Object in Remote Sensing.
Step 302: by the first Classification and Identification model, multiple atural object classifications in Object in Remote Sensing are identified, With the region where the multiple atural object classifications of determination.
Wherein, the first Classification and Identification model, which refers to, can be identified and be classified to multiple atural object classifications in remote sensing images Model, can according to the sample image of multiple atural object classifications training obtain.It that is to say, it can by the first Classification and Identification model To carry out automatic identification and classification to multiple atural object classifications in Object in Remote Sensing.In a particular embodiment, this first point Class identification model can be CNN model or RNN model, or using the model of other algorithms, the embodiment of the present invention is to this Without limitation.
Wherein, atural object refers to relatively-stationary object on earth surface, and atural object classification is to be classified to obtain to atural object.Than Such as, multiple atural object classification may include building, water system, vegetation, soil and road etc., which is can To identify the Classification and Identification model of the building in remote sensing images, water system, vegetation, soil and road etc..
In a possible embodiment, following steps 3021- can be passed through according to the sample image of multiple atural object classifications It is by model that 3023 training, which obtain first classification,.
Step 3021:Obtain the sample image of multiple atural object classifications.
Wherein, the sample image of multiple atural object classifications refers to the sample of multiple atural object classification of selection in target remote sensing figure The image presented as in.In the embodiment of the present invention, the sample image of multiple atural object classification can be sent by other equipment and , it can be acquired from image data base, can also extract and obtain from Object in Remote Sensing, the embodiment of the present invention is to this The acquisition source of the sample image of multiple atural object classifications is without limitation.
For example, difference can be extracted out of Object in Remote Sensing an image-region in an Object in Remote Sensing It include the image of building, water system, vegetation, soil and road etc., and using the image of extraction as multiple atural object classification Sample image.
Step 3022:Feature extraction is carried out to the sample image of multiple atural object classifications, obtains the sample of multiple atural object classifications The geometric error modeling feature and spectral signature of image.
Wherein, what geometric error modeling was characterized in that the sample image of atural object classification in remote sensing images is presented rough has The rill feature of space scale.Spectral signature is the presented Electromagnetic radiation laws of sample image of atural object classification in remote sensing images.
Step 3023:According to the sample image of multiple atural object classifications and the geometry line of the sample image of multiple atural object classifications Feature and spectral signature are managed, the second Classification and Identification model is trained, the first Classification and Identification model is obtained.
Wherein, the second Classification and Identification model refers to be trained, atural object classification for identification Classification and Identification model, utilizes The geometric error modeling feature and spectral signature of the sample image of multiple atural object classification and the sample image of multiple atural object classification, The second Classification and Identification model is trained, the first Classification and Identification model can be obtained.In a particular embodiment, this second Classification and Identification model can be CNN model or RNN model, or using the model of other algorithms, the embodiment of the present invention pair This is without limitation.
During being trained to the second Classification and Identification model, which can be constantly more to this The geometric error modeling feature and spectral signature of the sample image of a atural object classification are learnt, and can model parameter to itself into Row adjustment, in this way, the second Classification and Identification model can be exchanged into and can recognize that by the training of enough sample images First Classification and Identification model of multiple atural object classification.
It, can be using Object in Remote Sensing as first Classification and Identification after training obtains the first Classification and Identification model The input of model identifies multiple atural object classifications in Object in Remote Sensing by the first Classification and Identification model, and marks Know the range of each atural object classification in multiple atural object classification out, and then determines the region where multiple atural object classification.
For example, according to the first Classification and Identification model, can to building all in Object in Remote Sensing, water system, vegetation, Soil and road are identified, and identify building, water system, vegetation, soil and road respectively in Object in Remote Sensing Range, and then determine the region where building, water system, vegetation, soil and road difference.
Step 303: according to the geography information of the conduit region in Object in Remote Sensing, determining each in multiple atural object classifications The terrain object attribute information in the region where atural object classification.
Wherein, geography information is used to indicate the location information of the atural object in the conduit region, can specifically include GIS, electricity The auxiliary informations such as sub- map, thematic maps, political affairs layout data or environmental ecology data.
Further, it can also be determined according to the geography information and population information of the conduit region in Object in Remote Sensing The terrain object attribute information in the region in multiple atural object classifications where each atural object classification.Wherein, population information can indicate the pipe Population distribution situation in road region, is specifically as follows the demographic data of each region counted in advance.
Wherein, terrain object attribute information is used to indicate the specific object of atural object, for example can be to indicate its function and purposes Information can be used for carrying out exhaustive division to every kind of atural object.For example, the attribute information of building may include residential block (including One-storey house, lower building and skyscraper), hospital, school, shopping centre, industrial area, kindergarten, home for destitute or market etc., it is water-based Attribute information may include river, lake or reservoir etc., and the attribute information of vegetation may include meadow or forest land etc., the category in soil Property information may include arable land, wetland or wasteland etc., and the attribute information of road may include highway, national highway, provincial highway, railway Or backroad etc..
Specifically, can be believed according to the geography information and population of the geography information of the conduit region or the conduit region Breath carries out assignment to the attribute of each atural object classification in multiple atural object classification, obtains to identify every in multiple atural object classifications The attribute information of a atural object classification.In practical applications, terrain object attribute information can be by user according to geography information or geographical letter Breath and population information carry out matching assignment manually to atural object classification each in multiple atural object classifications, can also directly be read by terminal The various geography information stored in database or geography information and population information are taken, to each ground species in multiple atural object classifications It carry out not Auto-matching assignment.
In a possible embodiment, in the geography information according to the conduit region in Object in Remote Sensing, determination is more It, can be by the building in Object in Remote Sensing when the terrain object attribute information in the region in a atural object classification where each atural object classification Object is identified as residential block, hospital, school, shopping centre, industrial area, kindergarten, home for destitute, market, country fair, temple, movement Field, square, amusement and leisure, theater or spot camping etc., water system is identified as river, lake or reservoir etc., is by road Identification Soil is identified as arable land, wetland or wasteland etc., vegetation is identified by highway, national highway, provincial highway, railway or backroad etc. For meadow or forest land etc..
Further, multiple ground species are determined according to the geography information of the conduit region in Object in Remote Sensing in terminal After the terrain object attribute information in the region in not where each atural object classification, terminal can also be determined by the method for artificial visual Multiple atural object classifications in the terrain object attribute information in region where each atural object classification checked and corrected, it is multiple to improve The accuracy of the terrain object attribute information identification in the region in atural object classification where each atural object classification.
In the geography information according to the conduit region in Object in Remote Sensing, each ground species in multiple atural object classifications are determined It, can be according to the region where atural object classification each in multiple atural object classifications after the terrain object attribute information in the region where not Terrain object attribute information identifies the high consequence area of Target pipe from the conduit region in multiple images region.
Wherein, multiple image-region be along the duct orientation of Target pipe, using second distance threshold value as interval, to mesh Mark remote sensing images are divided to obtain, and that is to say, the length for the pipeline that each image-region includes is second distance threshold value.This Two distance thresholds can be preset, and can also specifically be set as needed by technical staff by terminal default configuration It sets, for example, second pre-determined distance can be 2000 meters.
Specifically, according to the terrain object attribute information in the region where atural object classification each in multiple atural object classifications, from multiple Identify that the high consequence area of Target pipe can be realized by following steps 304-305 in conduit region in image-region.
Step 304: the terrain object attribute information in the region where multiple atural object classifications determines every in multiple images region The Location class of conduit region in a image-region.
Wherein, Location class is used to indicate the population concentration degree of the conduit region in each image-region, and area etc. Grade is higher, indicates that population is more concentrated.
Specifically, following steps 3041- can be passed through according to the terrain object attribute information in the region where multiple atural object classifications 3044 determine the Location class of the conduit region in multiple image-region in each image-region.
Step 3041:The initial position for the pipeline for including according to (i-1)-th image-region that Object in Remote Sensing includes, Two distance thresholds and third distance threshold determine i-th of image-region that Object in Remote Sensing includes.
Wherein, second distance threshold value is the length for the pipeline for including in i-th of image.Third distance threshold is i-th of figure As the pipeline initial position for including and the distance between the pipeline initial position for including in (i-1)-th image, and third is apart from threshold Value is less than second distance threshold value.In a particular embodiment, third distance threshold can be by terminal default setting, can also be by technology Personnel are configured as needed, such as can directly input third distance threshold at the terminal by technical staff.
Wherein, i is the integer more than or equal to 1.When i is 1, the start bit for the pipeline that (i-1)-th image-region includes The initial position for setting the pipeline for including with i-th of image-region is overlapped, and is Target pipe rising in Object in Remote Sensing Beginning position.It that is to say, the initial position for the pipeline that the 1st image-region includes is Target pipe rising in Object in Remote Sensing Beginning position.
Specifically, as i=1, the 1st image-region, and the 1st image-region can be determined according to the second pre-determined distance Including the initial position of pipeline be initial position of the Target pipe in Object in Remote Sensing, including the length of pipeline be the Two distance thresholds.It, can be by the initial position for the pipeline for including with the 1st image-region after determining the 1st image-region It is determined as the initial position for the pipeline that the 2nd image-region includes at a distance of the pipeline location of third distance threshold, and according to second Distance threshold determines the 2nd image-region, so that the length for the pipeline that the 2nd image-region includes is the second pre-determined distance, weight Multiple above-mentioned steps, until determining the last one image-region that Object in Remote Sensing includes.
For example, it is assumed that second distance threshold value is 2000 meters, third distance threshold is 200 meters, then the 1st image-region includes Pipeline initial position be initial position of the Target pipe in Object in Remote Sensing, and including pipeline length be 2000 Rice.It, can be by the initial position for the pipeline for including with the 1st image-region at a distance of 200 meters after determining the 1st image-region Pipeline location be determined as the initial position of the pipeline that the 2nd image-region includes, and according to 2000 meters of determining 2nd image districts Domain so repeats the above steps so that the length for the pipeline that the 2nd image-region includes is 2000 meters, until determining target Until the last one image-region that remote sensing images include.
It should be noted that above-mentioned numerical value is only the exemplary value that the embodiment of the present invention provides, in practical applications, on Stating numerical value can also be other numerical value, and the embodiment of the present invention is not specifically limited in this embodiment.
Step 3042:From the terrain object attribute information in the region where multiple atural object classifications, determines and be located at i-th of image district The terrain object attribute information of multiple atural object classifications in domain.
Specifically, after determining i-th of image-region, can according in fixed Object in Remote Sensing multiplely The terrain object attribute information in the species not region at place, determines the atural object for the multiple atural object classifications being located in i-th of image-region Attribute information.
Step 3043:According to the terrain object attribute information for the multiple atural object classifications being located in i-th of image-region, i-th is determined The initial Location class of conduit region in a image-region.
Wherein, initial Location class is the region rank divided according to population concentration degree.It specifically, can be according to being located at The terrain object attribute information and Location class division rule of multiple atural object classifications in i-th of image-region, determine i-th of image district The initial Location class of conduit region in domain.
Wherein, grade classification rule in this area's can be preset, and can be by terminal default configuration, can also be by technology Personnel are configured according to actual needs.It next will be only with a kind of Location class of exemplary stroke provided in an embodiment of the present invention Divider then for be illustrated, in practical application, this area's grade classification rule may be other rule, the embodiment of the present invention It does not limit this.
Specifically, it can be determined first according to the terrain object attribute information for the multiple atural object classifications being located in i-th of image-region The one-storey house area and lower building area that i-th of image-region includes, then according to be located in i-th image-region multiplely The one-storey house area and lower building area that the other terrain object attribute information of species and i-th of image-region include, determine i-th The initial Location class of conduit region in image-region.
Wherein, one-storey house refers to that floor is 1 layer of building constructions, and lower building refers to that floor is greater than 1 and is less than or equal to building Wherein, floor threshold value is the positive integer greater than 1 to the building constructions of layer threshold value.Wherein, floor threshold value is the The Highest Tower of lower building Number of plies value.In practical applications, floor threshold value can also be set as needed by terminal default configuration by technical staff It sets.For example, floor threshold value can be 6, lower building refers to that floor is greater than 1 and is less than or equal to 6 building constructions.
Specifically, according to the terrain object attribute information for the multiple atural object classifications being located in i-th of image-region and i-th The one-storey house area and lower building area that image-region includes, determine the initial area of the conduit region in i-th of image-region Grade may include following several situations:
1) the one-storey house area for including when i-th of image-region is small less than the first area threshold, the lower building area for including It is determined i-th in second area threshold value and according to the terrain object attribute information for the multiple atural object classifications being located in i-th of image-region When image-region does not include that suburban population concentrates place, urban district and transport hub, initial area of i-th of image-region etc. is determined Grade is level-one.
Wherein, the first area threshold and second area threshold value can be preset, specifically can by terminal default configuration, It can be configured as needed by technical staff.For example, the first area threshold can be 1500 square meters, second area threshold value can Think 450 square meters.Wherein, it may include suburb hospital, suburb school, suburb shopping centre or suburb work that suburban population, which concentrates place, Industry area etc..
For example, it is assumed that the first area threshold is 1500 square meters, second area threshold value is 450 square meters, then when i-th of image district The one-storey house area that domain includes less than 450 square meters and does not include suburban population's collection less than 1500 square meters, the lower building area for including When middle place, urban district and transport hub, that is, it can determine that the initial Location class of i-th of image-region is level-one.
It further, can also be in the terrain object attribute information according to the multiple atural object classifications being located in i-th of image-region When determining that i-th of image-region includes that people or depopulated zone are lacked in wasteland, arable land, wetland, meadow and forest land etc., i-th of image is determined The initial Location class in region is level-one.
2) when the one-storey house area that i-th of image-region includes is greater than or equal to the first area threshold and is less than third area threshold It is worth, the lower building area that includes is greater than or equal to second area threshold value and is less than fourth face product threshold value and according to being located at i-th It includes that suburban population collects midfield that the terrain object attribute information of multiple atural object classifications in image-region, which determines i-th of image-region not, When institute, urban district and transport hub, determine that the initial Location class of i-th of image-region is second level.
Wherein, third area threshold is greater than the first area threshold, and fourth face product threshold value is greater than second area threshold value.Moreover, Third area threshold and fourth face product threshold value can be preset, specifically can be by terminal default configuration, can also be by technology people Member is configured as needed.For example, third area threshold can be 1000 square meters, fourth face product threshold value can be flat for 3000 Rice.
For example, it is assumed that the first area threshold is 1500 square meters, second area threshold value is 450 square meters, third area threshold is 10000 square meters, fourth face product threshold value are 3000, then the one-storey house area for including when i-th of image-region be greater than or equal to 1500 and Less than 10000, the lower building area that includes be greater than or equal to 450 and less than 3000 and do not include suburban population concentrate place, When urban district and transport hub, that is, it can determine that the initial Location class of i-th of image-region is second level.
3) the one-storey house area for including when i-th of image-region is greater than or equal to third area threshold, or including low layer Building area is greater than or equal to fourth face product threshold value, or the ground according to the multiple atural object classifications being located in i-th of image-region When object attribute information determines that i-th of image-region includes that suburban population concentrates place, the initial area of i-th of image-region is determined Grade is three-level.
For example, it is assumed that third area threshold is 10000 square meters, fourth face product threshold value is 3000, and suburban population concentrates place For suburb hospital, suburb school, suburb shopping centre or suburb industrial area etc., then when the one-storey house area that i-th of image-region includes More than or equal to 10000, perhaps including lower building area be greater than or equal to 3000 or include suburb hospital, suburb learning Whens school, suburb shopping centre, suburb industrial area etc., that is, it can determine that the initial Location class of i-th of image-region is three-level.
4) when the terrain object attribute information that basis is located at multiple atural object classifications in i-th of image-region determines i-th of image When region includes urban district or transport hub, determine that the initial Location class of i-th of image-region is level Four.
Wherein, urban district can also include skyscraper, that is to say, can also be according in i-th of image-region When the terrain object attribute information of multiple atural object classifications determines that i-th of image-region includes urban district, skyscraper or transport hub, determine The initial Location class of i-th of image-region is level Four.
It should be noted that above-mentioned numerical value and place are only the exemplary value and place that the embodiment of the present invention provides, In practical application, above-mentioned numerical value and place can also be other numerical value and place, and the embodiment of the present invention is not specifically limited in this embodiment.
Step 3044:Determination is overlapped with i-th of image-region from the multiple images region that Object in Remote Sensing includes At least one image-region, and the initial Location class of maximum in the initial Location class of at least one image-region is determined as The Location class of i-th of image-region.
Specifically, since third distance threshold is less than second distance threshold value, can exist at least in i-th of image-region One image-region being overlapped with other image-regions, at least one image-region being overlapped with i-th of image-region, originally In inventive embodiments, can the initial Location class of maximum in the initial Location class of at least one image-region, be determined as The accuracy of determining Location class so can be improved in the Location class of i-th of image-region.
For example, it is assumed that second distance threshold value is 2000 meters, third distance threshold is 200 meters, then to the 2nd image-region When carrying out initial Location class and determining, exist in the multiple images region that includes due to Object in Remote Sensing and the 2nd image district 10 image-regions that domain is overlapped, and the initial regional ranking score of this 10 image-regions be not level-one, level-one, second level, level-one, Three-level, level-one, second level, level-one, firsts and seconds, i.e. the initial Location class of the maximum of this 10 image-regions is three-level, therefore The Location class of 2nd image-region can be determined as to three-level, i.e. conduit region in the 2nd image-region belongs to three-level Area.
Further, after the Location class that terminal determines i-th of image-region, the method for artificial visual can also be passed through Artificial verification and amendment are carried out to the Location class of i-th of image-region, further increase the Location class of i-th of image-region Definitive result accuracy.
It should be noted that the division of above-mentioned numerical value and Location class is only the exemplary value that the embodiment of the present invention provides With the division of Location class, in practical applications, the division of above-mentioned numerical value and Location class can also be other numerical value and area The division of grade, the embodiment of the present invention are not specifically limited in this embodiment.
Step 305: each in the terrain object attribute information in the region where multiple atural object classifications and multiple images region The Location class of conduit region in image-region, after the height for identifying Target pipe in the conduit region in multiple images region Fruit area.
Wherein, according to the difference of the pumped (conveying) medium of Target pipe, Target pipe can be divided into long oil pipeline road and long gas transmission Pipeline, and the difference of the pumped (conveying) medium according to Target pipe identify high consequence area from the conduit region in multiple images region Identification method it is accordingly different, can specifically include following two identification method.
The first identification method:When Target pipe is long oil pipeline road, for any image in multiple images region Region A, if image-region A meets the first identification condition, it is determined that the conduit region in image-region A is the height of Target pipe Consequence area.
Wherein, the first identification condition can also be carried out according to actual needs by terminal default configuration by technical staff Setting.In the embodiment of the present invention, the first identification condition refer to the conduit region in image-region A Location class be three-level or Level Four perhaps in image-region A there are the road or image-region A of environment sensitive place or non-transport hub include it is flat The lower building area that room area is greater than the 5th area threshold, includes be greater than the 6th area threshold and conduit region belong to rural area or Small towns.
Wherein, environment sensitive place includes nature reserve area and water source, and nature reserve area includes river mouth, forest or wetland Deng water source includes river, lake and reservoir etc..The road of non-transport hub includes highway, national highway, provincial highway and railway etc.. 5th area threshold and the 6th area threshold can be preset, and in the embodiment of the present invention, and the 5th area threshold is greater than upper It states the first area threshold and is less than above-mentioned third area threshold, the 6th area threshold is greater than above-mentioned second area threshold value and is less than upper State fourth face product threshold value.For example, the 5th area threshold can be 5000 square meters, the 6th area threshold can be 1500 square meters.
Further, after determining the high consequence area that the conduit region in image-region A is target long oil pipeline road, may be used also With being classified for the high consequence area to image-region A.Specifically, to the side be classified in the high consequence area of image-region A Formula may include following several:
1) if there are the roads of non-transport hub in image-region A, it is determined that the conduit region in image-region A is mesh Mark the high consequence area of level-one of pipeline.
For example, can there are the non-traffic pivots such as highway, national highway, provincial highway, country road and railway in image-region A When the road of knob, determine that the conduit region in image-region A is the high consequence area of level-one of Target pipe.
Further, the vertical range of the center line of distance objective pipeline can also be less than or equal in image-region A In the regional scope of 5th distance threshold there are the conduit region when road of non-transport hub, determined in image-region A be mesh Mark the high consequence area of level-one of pipeline.
Wherein, the 5th distance threshold is greater than the outer diameter of Target pipe and is less than first distance threshold value, for example, the 5th apart from threshold Value can be 50 meters.When the 5th distance threshold is 50 meters, indicating can center line two in image-region A away from Target pipe There are the level-ones that the conduit region when road of non-transport hub, determined in image-region A is Target pipe within the scope of 50 meters of side High consequence area.
2) if the Location class of the conduit region in image-region A is that there are nature guarantors in three-level or image-region A The one-storey house area that shield area or image-region A include is greater than the 6th face greater than the 5th area threshold, the lower building area for including It accumulates the conduit region in threshold value and image-region A and belongs to rural area or small towns, it is determined that the conduit region in image-region A is target The high consequence area of the second level of pipeline.
For example, can in image-region A there are Location class be three-level area location or image-region A in One-storey house area is greater than the 5th area threshold, lower building area is greater than the 6th area threshold and conduit region belongs to rural area or township When there are the nature reserve areas such as river mouth, forest or wetland in town or image-region A, determine that the conduit region in image-region A is The high consequence area of the second level of Target pipe.
If 3) Location class of the conduit region in image-region A is in level Four or image-region A there are water source, Then determine that the conduit region in image-region A is the high consequence area of three-level of Target pipe.
For example, can be the location in level Four area there are Location class in image-region A, or there are rivers, lake And when the water sources such as reservoir, determine that the conduit region in image-region A is the high consequence area of three-level of Target pipe.
Second of identification method:When Target pipe is long gas pipeline, for any image in multiple images region Region A, if image-region A meets the second identification condition, it is determined that the conduit region in image-region A is the height of Target pipe Consequence area.
Wherein, the second identification condition can also be carried out according to actual needs by terminal default configuration by technical staff Setting.In the embodiment of the present invention, the second identification condition refers to that the Location class of the conduit region in image-region A is three-level or four There are population concentration place or combustible and explosive areas in grade or image-region A.
Wherein, population concentration place includes that the first concentration place and second concentrate place.First concentration place refer to hospital, The construction area of the crowd evacuations such as institute, nursery, home for destitute, prison or store difficulty.Second concentration place refers to frequent remittance The open-air area of at least 50 days 30 people of aggregation or more, exemplary within the open-air area of collection crowd, such as 1 year, and second Concentrate place can for country fair, temple or sports ground, amusement and leisure, theater or spot camping etc..Combustible and explosive area is Refer to the place for being easy to happen burning or explosion, such as gas station, oil depot.
In a particular embodiment, population concentration place and combustible and explosive area can be identified by the first Classification and Identification model It arrives, can also be identified by user's population and manual configuration obtains, it is not limited in the embodiment of the present invention.
Further, after determining the high consequence area that the conduit region in image-region A is the long gas pipeline of target, may be used also With being classified for the high consequence area to image-region A.Specifically, to the side be classified in the high consequence area of image-region A Formula may include following several:
If 1) in image-region A there are population concentration place and the potential shadow of long gas pipeline that image-region A includes It rings radius and is less than or equal to the 4th distance threshold, it is determined that the conduit region in image-region A is after the level-one of Target pipe is high Fruit area.
Wherein, when potential impact radius refers to that gas pipeline fails, periphery public security and property may be by The radius in region is significantly affected, is specifically permitted by the maximum of the corresponding pipeline section of outer diameter of the outer diameter and long gas pipeline of long gas pipeline Perhaps operating pressure determines.For example, the potential impact radius for the long gas pipeline that image-region A includes can be by by lower formula (1) determination obtains:
Wherein, r is potential impact radius, and d is the outer diameter of pipeline, and p is the maximum allowable operating pressure of corresponding pipeline section.
Wherein, after the 4th distance threshold refers to long gas pipeline generation accident, when pipeline two sides generate biggest impact range Vertical range of the coverage boundary at long-distance oil & gas pipeline position of center line.In the specific implementation process, the 4th distance Threshold value can also be configured according to actual needs by terminal default configuration by technical staff.Exemplary, the 4th apart from threshold Value can be 200 meters.
For example, it is assumed that the 4th distance threshold is 200 meters, then can there are such as hospital, institute, capper in image-region A The population concentrations such as institute, home for destitute, prison, store, country fair, temple or sports ground place, and the potential impact of pipeline half When diameter is less than or equal to 200 meters, determine that the conduit region in image-region A is the high consequence area of level-one of Target pipe.
If 2) in image-region A there are population concentration place and the potential impact radius of pipeline that image-region A includes Location class greater than the conduit region in the 4th distance threshold perhaps image-region A is three-level or image-region A memory In combustible and explosive area, it is determined that the conduit region in image-region A is the high consequence area of second level of Target pipe.
For example, it is assumed that the 4th distance threshold is 200 meters, then can there are such as hospital, institute, capper in image-region A The population concentrations such as institute, home for destitute, prison, store, country fair, temple or sports ground place, and the potential impact of pipeline half When diameter is greater than 200 meters, determine that the conduit region in image-region A is the high consequence area of second level of Target pipe.
3) if the Location class of the conduit region in image-region A is level Four, it is determined that the pipe line area in image-region A Domain is the high consequence area of three-level of Target pipe.
Further, after the Location class that terminal determines the conduit region in image-region A, artificial mesh can also be passed through Depending on method image-region A that terminal is determined in conduit region Location class carry out it is artificial verify and amendment, further Improve the accuracy of the definitive result of the Location class of the conduit region in image-region A.
It is available with Target pipe for long-distance oil & gas pipeline, that is, Target pipe to be studied in the embodiment of the present invention Center line be symmetry axis, the Object in Remote Sensing of conduit region that first distance threshold value is symmetrical radius composition, pass through first Classification and Identification model identifies multiple atural object classifications in Object in Remote Sensing, where the multiple atural object classifications of determination Region, and according to the geography information of the conduit region in Object in Remote Sensing, determine each ground species in multiple atural object classification The terrain object attribute information in the region where not, finally according to the terrain object attribute information in the region where multiple atural object classification, from The high consequence area of Target pipe is identified in conduit region in multiple images region.It that is to say, it in embodiments of the present invention, can be with The Object in Remote Sensing of the conduit region of coverage goal pipeline is obtained, and Object in Remote Sensing is carried out using image recognition algorithm Automatic identification, compared to the method in the high consequence area of manual identified in the related technology, improves to determine the high consequence area of Target pipe Recognition efficiency and accuracy.
Fig. 4 is a kind of structural representation of the identification device in the high consequence area of long-distance oil & gas pipeline provided in an embodiment of the present invention Figure.Referring to fig. 4, the apparatus may include:
First obtains module 401, and for obtaining Object in Remote Sensing, Object in Remote Sensing includes the center with Target pipe Line is symmetry axis, the conduit region that first distance threshold value is symmetrical radius, and first distance threshold value is greater than the outer diameter of Target pipe, mesh Mark pipeline is long-distance oil & gas pipeline to be studied.
First determining module 402, for passing through the first Classification and Identification model, to multiple ground species in Object in Remote Sensing It is not identified, with the region where the multiple atural object classifications of determination, the first Classification and Identification model is according to multiple atural object classifications Sample image training obtains.
Second determining module 403 determines multiplely for the geography information according to the conduit region in Object in Remote Sensing Species not in region where each atural object classification terrain object attribute information.
Identification module 404, for the terrain object attribute information according to the region where multiple atural object classifications, from multiple images area In conduit region in domain identify Target pipe high consequence area, multiple images region be along Target pipe duct orientation, Using second distance threshold value as interval, Object in Remote Sensing is divided to obtain.
Optionally, identification module includes:
First determination unit determines multiple figures for the terrain object attribute information according to the region where multiple atural object classifications As the Location class of the conduit region in image-region each in region, Location class is used to indicate the pipe in each image-region The population concentration degree in road region;
First recognition unit, for according to the region where multiple atural object classifications terrain object attribute information and multiple images area The Location class of conduit region in domain in each image-region identifies target tube from the conduit region in multiple images region The high consequence area in road.
Optionally, the first determination unit includes:
First determines subelement, the pipeline that (i-1)-th image-region for including according to Object in Remote Sensing includes Initial position, second distance threshold value and third distance threshold determine i-th of image-region that Object in Remote Sensing includes;
Wherein, the length for the pipeline that i-th of image-region includes is equal to second distance threshold value, and i-th of image-region packet The initial position for the pipeline that the initial position of the pipeline included and (i-1)-th image-region include is at a distance of third distance threshold, third Distance threshold is less than second distance threshold value, and i is the integer more than or equal to 1, and when i is 1, (i-1)-th image-region includes The initial position of pipeline is overlapped with the initial position for the pipeline that i-th of image-region includes, and is that Target pipe is distant in target Feel the initial position in image;
Second determines subelement, for from the terrain object attribute information in the region where multiple atural object classifications, determination to be located at The terrain object attribute information of multiple atural object classifications in i-th of image-region;
Third determines subelement, for the terrain object attribute letter according to the multiple atural object classifications being located in i-th of image-region Breath, determines the initial Location class of the conduit region in i-th of image-region;
4th determines subelement, for determining and i-th of image from the multiple images region that Object in Remote Sensing includes At least one image-region of area coincidence, and the maximum in the initial Location class of at least one image-region is initial regional Grade is determined as the Location class of i-th of image-region.
Optionally, third determines that subelement is specifically used for:
According to the terrain object attribute information for the multiple atural object classifications being located in i-th of image-region, i-th of image-region is determined Including one-storey house area and lower building area, lower building refer to floor be greater than 1 and be less than or equal to floor threshold value building Building;
When the one-storey house area that i-th of image-region includes is less than less than the first area threshold, the lower building area for including Second area threshold value and i-th of figure is determined according to the terrain object attribute information for the multiple atural object classifications being located in i-th image-region As region does not include that suburban population concentrates place, urban district and when transport hub, determines the initial Location class of i-th of image-region For level-one;
When the one-storey house area that i-th of image-region includes is greater than or equal to the first area threshold and is less than third area threshold It is worth, the lower building area that includes is greater than or equal to second area threshold value and is less than fourth face product threshold value and according to being located at i-th It includes that suburban population collects midfield that the terrain object attribute information of multiple atural object classifications in image-region, which determines i-th of image-region not, When institute, urban district and transport hub, determine that the initial Location class of i-th of image-region is second level, third area threshold is greater than the One area threshold, fourth face product threshold value are greater than second area threshold value;
When the one-storey house area that i-th of image-region includes be greater than or equal to third area threshold, or including low layer building Room area is greater than or equal to fourth face product threshold value, or the atural object according to the multiple atural object classifications being located in i-th of image-region When attribute information determines that i-th of image-region includes that suburban population concentrates place, initial area of i-th of image-region etc. is determined Grade is three-level;
When the terrain object attribute information that basis is located at multiple atural object classifications in i-th of image-region determines i-th of image district When domain includes urban district or transport hub, determine that the initial Location class of i-th of image-region is level Four.
Optionally, the first recognition unit includes:
First identification subelement, apparatus is when Target pipe is long oil pipeline road, for any in multiple images region Image-region A, if image-region A meets the first identification condition, it is determined that the conduit region in image-region A is Target pipe High consequence area, the first identification condition refer to the conduit region in image-region A Location class be three-level or level Four, Huo Zhetu The one-storey house area for including as the road or image-region A in the A of region there are environment sensitive place or non-transport hub is greater than the The conduit region that five area thresholds, the lower building area for including are greater than in the 6th area threshold and image-region A belongs to rural area Or small towns, environment sensitive place include nature reserve area and water source;
Second identification subelement, is used for when Target pipe is long gas pipeline, for any in multiple images region Image-region A, if image-region A meets the second identification condition, it is determined that the conduit region in image-region A is Target pipe High consequence area, the second identification condition refer to the conduit region in image-region A Location class be three-level or level Four, Huo Zhetu As there are population concentration place or combustible and explosive areas in the A of region.
Optionally, the first identification subelement is specifically used for:
If there are the roads of non-transport hub in image-region A, it is determined that the conduit region in image-region A is target The high consequence area of the level-one of pipeline;
If the Location class of the conduit region in image-region A is that there are conservations of nature in three-level or image-region A The one-storey house area that area or image-region A include is greater than the 6th area greater than the 5th area threshold, the lower building area for including Conduit region in threshold value and image-region A belongs to rural area or small towns, it is determined that the conduit region in image-region A is target tube The high consequence area of the second level in road;
If the Location class of the conduit region in image-region A is in level Four or image-region A there are water source, Determine that the conduit region in image-region A is the high consequence area of three-level of Target pipe.
Optionally, the second identification subelement is specifically used for:
If there are population concentration place and the potential impact radius of pipeline that image-region A includes is small in image-region A In or equal to the 4th distance threshold, it is determined that the conduit region in image-region A is the high consequence area of level-one of Target pipe, potential The radius of influence is obtained according to the determination of the outer diameter and maximum allowable operating pressure of the image-region A pipeline for including;
If there are population concentration place and the potential impact radius of pipeline that image-region A includes is big in image-region A It is to exist in three-level or image-region A in the Location class of the conduit region in the 4th distance threshold perhaps image-region A Combustible and explosive area, it is determined that the conduit region in image-region A is the high consequence area of second level of Target pipe;
If the Location class of the conduit region in image-region A is level Four, it is determined that the conduit region in image-region A For the high consequence area of three-level of Target pipe.
Optionally, the first acquisition module includes:
First acquisition unit, for obtaining the side of the position of center line information of Target pipe and the conduit region of Target pipe Boundary's location information, it is symmetrical that boundary position information, which is used to indicate by symmetry axis, first distance threshold value of the center line of Target pipe, The conduit region of radius;
Second acquisition unit, for obtaining multiple initial remote sensing images, every initial remote sensing according to position of center line information The section of tubing region of image coverage goal pipeline;
First processing units, for carrying out splicing to multiple initial remote sensing images, obtaining according to position of center line information To splicing remote sensing images, splice whole conduit regions of remote sensing images coverage goal pipeline;
The second processing unit, for carrying out cutting processing to splicing remote sensing images, obtaining target according to boundary position information Remote sensing images.
Optionally, device further include:
Second obtains module, for obtaining the sample image of multiple atural object classifications;
Extraction module carries out feature extraction for the sample image to multiple atural object classifications, obtains multiple atural object classifications The geometric error modeling feature and spectral signature of sample image;
Training module, for according to the several of the sample image of the sample images and multiple atural object classifications of multiple atural object classifications What textural characteristics and spectral signature, is trained the second Classification and Identification model, obtains the first Classification and Identification model, the second classification Identification model refers to be trained, atural object classification for identification Classification and Identification model.
It is available with Target pipe for long-distance oil & gas pipeline, that is, Target pipe to be studied in the embodiment of the present invention Center line be symmetry axis, the Object in Remote Sensing of conduit region that first distance threshold value is symmetrical radius composition, pass through first Classification and Identification model identifies multiple atural object classifications in Object in Remote Sensing, where the multiple atural object classifications of determination Region, and according to the geography information of the conduit region in Object in Remote Sensing, determine each ground species in multiple atural object classification The terrain object attribute information in the region where not, finally according to the terrain object attribute information in the region where multiple atural object classification, from The high consequence area of Target pipe is identified in conduit region in multiple images region.It that is to say, it in embodiments of the present invention, can be with The Object in Remote Sensing of the conduit region of coverage goal pipeline is obtained, and Object in Remote Sensing is carried out using image recognition algorithm Automatic identification, compared to the method in the high consequence area of manual identified in the related technology, improves to determine the high consequence area of Target pipe Recognition efficiency and accuracy.
It should be understood that the identification device in the high consequence area of long-distance oil & gas pipeline provided by the above embodiment is grown in identification When the high consequence area of oil and gas pipeline, only the example of the division of the above functional modules, in practical application, Ke Yigen Above-mentioned function distribution is completed by different functional modules according to needs, i.e., the internal structure of device is divided into different functions Module, to complete all or part of the functions described above.In addition, after the height of long-distance oil & gas pipeline provided by the above embodiment The recognition methods embodiment in the high consequence area of the identification device in fruit area and above-mentioned long-distance oil & gas pipeline belongs to same design, specific Realization process is detailed in embodiment of the method, and which is not described herein again.
Fig. 5 is a kind of structural schematic diagram of terminal 500 provided in an embodiment of the present invention.The terminal 500 may is that intelligent hand (Moving Picture Experts Group Audio Layer III, dynamic image are special for machine, tablet computer, MP3 player Family's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image Expert's compression standard audio level 4) player, laptop or desktop computer.Terminal 500 is also possible to referred to as user and sets Other titles such as standby, portable terminal, laptop terminal, terminal console.
In general, terminal 500 includes: processor 501 and memory 502.
Processor 501 may include one or more processing cores, such as 4 core processors, 8 core processors etc..Place Reason device 501 can use DSP (Digital Signal Processing, Digital Signal Processing), FPGA (Field- Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, may be programmed Logic array) at least one of example, in hardware realize.Processor 501 also may include primary processor and coprocessor, master Processor is the processor for being handled data in the awake state, also referred to as CPU (Central Processing Unit, central processing unit);Coprocessor is the low power processor for being handled data in the standby state.? In some embodiments, processor 501 can be integrated with GPU (Graphics Processing Unit, image processor), GPU is used to be responsible for the rendering and drafting of content to be shown needed for display screen.In some embodiments, processor 501 can also be wrapped AI (Artificial Intelligence, artificial intelligence) processor is included, the AI processor is for handling related machine learning Calculating operation.
Memory 502 may include one or more computer readable storage mediums, which can To be non-transient.Memory 502 may also include high-speed random access memory and nonvolatile memory, such as one Or multiple disk storage equipments, flash memory device.In some embodiments, the non-transient computer in memory 502 can Storage medium is read for storing at least one instruction, at least one instruction performed by processor 501 for realizing this Shen Please in embodiment of the method provide long-distance oil & gas pipeline high consequence area recognition methods.
In some embodiments, terminal 500 is also optional includes: peripheral device interface 503 and at least one peripheral equipment. It can be connected by bus or signal wire between processor 501, memory 502 and peripheral device interface 503.Each peripheral equipment It can be connected by bus, signal wire or circuit board with peripheral device interface 503.Specifically, peripheral equipment includes: radio circuit 504, at least one of touch display screen 505, camera 506, voicefrequency circuit 507, positioning component 508 and power supply 509.
Peripheral device interface 503 can be used for I/O (Input/Output, input/output) is relevant outside at least one Peripheral equipment is connected to processor 501 and memory 502.In some embodiments, processor 501, memory 502 and peripheral equipment Interface 503 is integrated on same chip or circuit board;In some other embodiments, processor 501, memory 502 and outer Any one or two in peripheral equipment interface 503 can realize on individual chip or circuit board, the present embodiment to this not It is limited.
Radio circuit 504 is for receiving and emitting RF (Radio Frequency, radio frequency) signal, also referred to as electromagnetic signal.It penetrates Frequency circuit 504 is communicated by electromagnetic signal with communication network and other communication equipments.Radio circuit 504 turns electric signal It is changed to electromagnetic signal to be sent, alternatively, the electromagnetic signal received is converted to electric signal.Optionally, radio circuit 504 wraps It includes: antenna system, RF transceiver, one or more amplifiers, tuner, oscillator, digital signal processor, codec chip Group, user identity module card etc..Radio circuit 504 can be carried out by least one wireless communication protocol with other terminals Communication.The wireless communication protocol includes but is not limited to: Metropolitan Area Network (MAN), each third generation mobile communication network (2G, 3G, 4G and 5G), wireless office Domain net and/or WiFi (Wireless Fidelity, Wireless Fidelity) network.In some embodiments, radio circuit 504 may be used also To include the related circuit of NFC (Near Field Communication, wireless near field communication), the application is not subject to this It limits.
Display screen 505 is for showing UI (User Interface, user interface).The UI may include figure, text, figure Mark, video and its their any combination.When display screen 505 is touch display screen, display screen 505 also there is acquisition to show The ability of the touch signal on the surface or surface of screen 505.The touch signal can be used as control signal and be input to processor 501 are handled.At this point, display screen 505 can be also used for providing virtual push button and/or dummy keyboard, also referred to as soft button and/or Soft keyboard.In some embodiments, display screen 505 can be one, and the front panel of terminal 500 is arranged;In other embodiments In, display screen 505 can be at least two, be separately positioned on the different surfaces of terminal 500 or in foldover design;In still other reality It applies in example, display screen 505 can be flexible display screen, be arranged on the curved surface of terminal 500 or on fold plane.Even, it shows Display screen 505 can also be arranged to non-rectangle irregular figure, namely abnormity screen.Display screen 505 can use LCD (Liquid Crystal Display, liquid crystal display), OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) Etc. materials preparation.
CCD camera assembly 506 is for acquiring image or video.Optionally, CCD camera assembly 506 include front camera and Rear camera.In general, the front panel of terminal is arranged in front camera, the back side of terminal is arranged in rear camera.One In a little embodiments, rear camera at least two is main camera, depth of field camera, wide-angle camera, focal length camera shooting respectively Any one in head, to realize that main camera and the fusion of depth of field camera realize background blurring function, main camera and wide-angle Camera fusion realizes that pan-shot and VR (Virtual Reality, virtual reality) shooting function or other fusions are clapped Camera shooting function.In some embodiments, CCD camera assembly 506 can also include flash lamp.Flash lamp can be monochromatic warm flash lamp, It is also possible to double-colored temperature flash lamp.Double-colored temperature flash lamp refers to the combination of warm light flash lamp and cold light flash lamp, can be used for not With the light compensation under colour temperature.
Voicefrequency circuit 507 may include microphone and loudspeaker.Microphone is used to acquire the sound wave of user and environment, and will Sound wave, which is converted to electric signal and is input to processor 501, to be handled, or is input to radio circuit 504 to realize voice communication. For stereo acquisition or the purpose of noise reduction, microphone can be separately positioned on the different parts of terminal 500 to be multiple.Mike Wind can also be array microphone or omnidirectional's acquisition type microphone.Loudspeaker is then used to that processor 501 or radio circuit will to be come from 504 electric signal is converted to sound wave.Loudspeaker can be traditional wafer speaker, be also possible to piezoelectric ceramic loudspeaker.When When loudspeaker is piezoelectric ceramic loudspeaker, the audible sound wave of the mankind can be not only converted electrical signals to, it can also be by telecommunications Number the sound wave that the mankind do not hear is converted to carry out the purposes such as ranging.In some embodiments, voicefrequency circuit 507 can also include Earphone jack.
Positioning component 508 is used for the current geographic position of positioning terminal 500, to realize navigation or LBS (Location Based Service, location based service).Positioning component 508 can be the GPS (Global based on the U.S. Positioning System, global positioning system), the dipper system of China, Russia Gray receive this system or European Union The positioning component of Galileo system.
Power supply 509 is used to be powered for the various components in terminal 500.Power supply 509 can be alternating current, direct current, Disposable battery or rechargeable battery.When power supply 509 includes rechargeable battery, which can support wired charging Or wireless charging.The rechargeable battery can be also used for supporting fast charge technology.
In some embodiments, terminal 500 further includes having one or more sensors 510.The one or more sensors 510 include but is not limited to: acceleration transducer 511, gyro sensor 512, pressure sensor 513, fingerprint sensor 514, Optical sensor 515 and proximity sensor 516.
The acceleration that acceleration transducer 511 can detecte in three reference axis of the coordinate system established with terminal 500 is big It is small.For example, acceleration transducer 511 can be used for detecting component of the acceleration of gravity in three reference axis.Processor 501 can With the acceleration of gravity signal acquired according to acceleration transducer 511, touch display screen 505 is controlled with transverse views or longitudinal view Figure carries out the display of user interface.Acceleration transducer 511 can be also used for the acquisition of game or the exercise data of user.
Gyro sensor 512 can detecte body direction and the rotational angle of terminal 500, and gyro sensor 512 can To cooperate with acquisition user to act the 3D of terminal 500 with acceleration transducer 511.Processor 501 is according to gyro sensor 512 Following function may be implemented in the data of acquisition: when action induction (for example changing UI according to the tilt operation of user), shooting Image stabilization, game control and inertial navigation.
The lower layer of side frame and/or touch display screen 505 in terminal 500 can be set in pressure sensor 513.Work as pressure When the side frame of terminal 500 is arranged in sensor 513, user can detecte to the gripping signal of terminal 500, by processor 501 Right-hand man's identification or prompt operation are carried out according to the gripping signal that pressure sensor 513 acquires.When the setting of pressure sensor 513 exists When the lower layer of touch display screen 505, the pressure operation of touch display screen 505 is realized to UI circle according to user by processor 501 Operability control on face is controlled.Operability control includes button control, scroll bar control, icon control, menu At least one of control.
Fingerprint sensor 514 is used to acquire the fingerprint of user, collected according to fingerprint sensor 514 by processor 501 The identity of fingerprint recognition user, alternatively, by fingerprint sensor 514 according to the identity of collected fingerprint recognition user.It is identifying When the identity of user is trusted identity out, the user is authorized to execute relevant sensitive operation, the sensitive operation packet by processor 501 Include solution lock screen, check encryption information, downloading software, payment and change setting etc..Terminal can be set in fingerprint sensor 514 500 front, the back side or side.When being provided with physical button or manufacturer Logo in terminal 500, fingerprint sensor 514 can be with It is integrated with physical button or manufacturer Logo.
Optical sensor 515 is for acquiring ambient light intensity.In one embodiment, processor 501 can be according to optics The ambient light intensity that sensor 515 acquires controls the display brightness of touch display screen 505.Specifically, when ambient light intensity is higher When, the display brightness of touch display screen 505 is turned up;When ambient light intensity is lower, the display for turning down touch display screen 505 is bright Degree.In another embodiment, the ambient light intensity that processor 501 can also be acquired according to optical sensor 515, dynamic adjust The acquisition parameters of CCD camera assembly 506.
Proximity sensor 516, also referred to as range sensor are generally arranged at the front panel of terminal 500.Proximity sensor 516 For acquiring the distance between the front of user Yu terminal 500.In one embodiment, when proximity sensor 516 detects use When family and the distance between the front of terminal 500 gradually become smaller, touch display screen 505 is controlled from bright screen state by processor 501 It is switched to breath screen state;When proximity sensor 516 detects user and the distance between the front of terminal 500 becomes larger, Touch display screen 505 is controlled by processor 501 and is switched to bright screen state from breath screen state.
It that is to say, the embodiment of the present invention provides not only a kind of terminal, including processor and can hold for storage processor The memory of row instruction, wherein processor is configured as executing the method in Fig. 2 or embodiment shown in Fig. 3, moreover, this hair Bright embodiment additionally provides a kind of computer readable storage medium, is stored with computer program in the storage medium, the computer The knowledge in the high consequence area of Fig. 2 or the long-distance oil & gas pipeline in embodiment shown in Fig. 3 may be implemented when program is executed by processor Other method.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal 500 of structure shown in Fig. 5, can wrap It includes than illustrating more or fewer components, perhaps combine certain components or is arranged using different components.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.

Claims (12)

1. a kind of recognition methods in the high consequence area of long-distance oil & gas pipeline, which is characterized in that the described method includes:
Object in Remote Sensing is obtained, the Object in Remote Sensing includes using the center line of Target pipe as symmetry axis, first distance Threshold value is the conduit region of symmetrical radius, and the first distance threshold value is greater than the outer diameter of the Target pipe, the Target pipe For long-distance oil & gas pipeline to be studied;
By the first Classification and Identification model, multiple atural object classifications in the Object in Remote Sensing are identified, to determine The region where multiple atural object classifications is stated, the first Classification and Identification model is the sample image according to the multiple atural object classification Training obtains;
According to the geography information of the conduit region in the Object in Remote Sensing, each atural object in the multiple atural object classification is determined The terrain object attribute information in the region where classification;
The terrain object attribute information in the region where the multiple atural object classification, from the conduit region in multiple images region Identify that the high consequence area of the Target pipe, described multiple images region are along the duct orientation of the Target pipe, with Two distance thresholds are interval, are divided to obtain to the Object in Remote Sensing.
2. the method as described in claim 1, which is characterized in that the ground according to the region where the multiple atural object classification Object attribute information identifies the high consequence area of the Target pipe from the conduit region in multiple images region, comprising:
The terrain object attribute information in the region where the multiple atural object classification determines each figure in described multiple images region As the Location class of the conduit region in region, the Location class is used to indicate the people of the conduit region in each image-region Mouth intensity;
Each image in the terrain object attribute information in the region where the multiple atural object classification and described multiple images region The Location class of conduit region in region identifies the Target pipe from the conduit region in described multiple images region High consequence area.
3. method according to claim 2, which is characterized in that the ground according to the region where the multiple atural object classification Object attribute information determines the Location class of the conduit region in described multiple images region in each image-region, comprising:
The initial position for the pipeline for including according to (i-1)-th image-region that the Object in Remote Sensing includes, described second away from From threshold value and third distance threshold, i-th of image-region that the Object in Remote Sensing includes is determined;
Wherein, the length for the pipeline that i-th of image-region includes is equal to the second distance threshold value, and i-th of figure The initial position for the pipeline that the initial position for the pipeline for including as region and (i-1)-th image-region include is at a distance of described the Three distance thresholds, the third distance threshold are less than the second distance threshold value, and the i is the integer more than or equal to 1, work as institute When to state i be 1, pipeline that the initial position of the pipeline that (i-1)-th image-region includes and i-th of image-region include Initial position be overlapped, and be initial position of the Target pipe in the Object in Remote Sensing;
From the terrain object attribute information in the region where the multiple atural object classification, determines and be located in i-th of image-region The multiple atural object classification terrain object attribute information;
According to the terrain object attribute information for the multiple atural object classification being located in i-th of image-region, determine described i-th The initial Location class of conduit region in image-region;
At least one be overlapped with i-th of image-region is determined from the multiple images region that the Object in Remote Sensing includes A image-region, and the initial Location class of maximum in the initial Location class of at least one image-region is determined as institute State the Location class of i-th of image-region.
4. method as claimed in claim 3, which is characterized in that the basis is located at described in i-th of image-region The terrain object attribute information of multiple atural object classifications determines the initial Location class of the conduit region in i-th of image-region, packet It includes:
According to the terrain object attribute information for the multiple atural object classification being located in i-th of image-region, determine described i-th The one-storey house area and lower building area that image-region includes, the lower building refer to that floor is greater than 1 and is less than or equal to building The building constructions of layer threshold value;
When the one-storey house area that i-th of image-region includes is less than less than the first area threshold, the lower building area for including Second area threshold value and according to be located at i-th of image-region in the multiple atural object classification terrain object attribute information it is true When fixed i-th of image-region does not include that suburban population concentrates place, urban district and transport hub, i-th of image is determined The initial Location class in region is level-one;
When the one-storey house area that i-th of image-region includes is greater than or equal to first area threshold and is less than third area Threshold value, the lower building area for including are greater than or equal to the second area threshold value and less than fourth face product threshold values and according to position The terrain object attribute information of the multiple atural object classification in i-th of image-region determines i-th of image-region not When concentrating place, urban district and transport hub including suburban population, determine that the initial Location class of i-th of image-region is two Grade, the third area threshold are greater than first area threshold, and the fourth face product threshold value is greater than the second area threshold value;
When the one-storey house area that i-th of image-region includes be greater than or equal to the third area threshold, or including it is low Floor room area is greater than or equal to fourth face product threshold value, or described more in i-th of image-region according to being located at When the terrain object attribute information of a atural object classification determines that i-th of image-region includes that suburban population concentrates place, described in determination The initial Location class of i-th of image-region is three-level;
When the terrain object attribute information that basis is located at the multiple atural object classification in i-th of image-region determines described i-th When a image-region includes urban district or transport hub, determine that the initial Location class of i-th of image-region is level Four.
5. method according to claim 2, which is characterized in that the ground according to the region where the multiple atural object classification The Location class of conduit region in object attribute information and described multiple images region in each image-region, from the multiple figure High consequence area as identifying the Target pipe in the conduit region in region, comprising:
When the Target pipe is long oil pipeline road, for any image region A in described multiple images region, if institute It states image-region A and meets the first identification condition, it is determined that the conduit region in the A of described image region is the height of the Target pipe Consequence area, the first identification condition refer to the conduit region in the A of described image region Location class be three-level or level Four, or Road or described image region A in person's described image region A there are environment sensitive place or non-transport hub include flat Room area is greater than in the 6th area threshold and described image region A greater than the 5th area threshold, the lower building area for including Conduit region belongs to rural area or small towns, and the environment sensitive place includes nature reserve area and water source;
When the Target pipe is long gas pipeline, for any image region A in described multiple images region, if institute It states image-region A and meets the second identification condition, it is determined that the conduit region in the A of described image region is the height of the Target pipe Consequence area, the second identification condition refer to the conduit region in the A of described image region Location class be three-level or level Four, or There are population concentration place or combustible and explosive areas in person's described image region A.
6. method as claimed in claim 5, which is characterized in that if the described image region A meets the first identification condition, Then determine that the conduit region in the A of described image region is the high consequence area of the Target pipe, comprising:
If in the A of described image region, there are the roads of non-transport hub, it is determined that the conduit region in the A of described image region is The high consequence area of the level-one of the Target pipe;
If the Location class of the conduit region in the A of described image region is that there are natures in three-level or described image region A The lower building area that the one-storey house area that protection zone or described image region A include is greater than the 5th area threshold, includes Belong to rural area or small towns greater than the conduit region in the 6th area threshold and described image region A, it is determined that described image Conduit region in the A of region is the high consequence area of second level of the Target pipe;
If the Location class of the conduit region in the A of described image region is that there are water in level Four or described image region A Source, it is determined that the conduit region in the A of described image region is the high consequence area of three-level of the Target pipe.
7. method as claimed in claim 5, which is characterized in that if the described image region A meets the second identification condition, Then determine that the conduit region in the A of described image region is the high consequence area of the Target pipe, comprising:
If there are population concentration place and the potential impact of pipeline that described image region A includes half in the A of described image region Diameter is less than or equal to the 4th distance threshold, it is determined that the conduit region in the A of described image region is the level-one of the Target pipe High consequence area, the potential impact radius are pressed according to the outer diameter of the described image region A pipeline for including and maximum allowable operation Power determination obtains;
If there are population concentration place and the potential impact of pipeline that described image region A includes half in the A of described image region Diameter is three-level or described image greater than the Location class of the conduit region in the 4th distance threshold perhaps described image region A There are combustible and explosive areas in the A of region, it is determined that the conduit region in the A of described image region is that the second level of the Target pipe is high Consequence area;
If the Location class of the conduit region in the A of described image region is level Four, it is determined that the pipeline in the A of described image region Region is the high consequence area of three-level of the Target pipe.
8. method as claimed in claim 1, which is characterized in that the acquisition Object in Remote Sensing, comprising:
Obtain the boundary position information of the position of center line information of the Target pipe and the conduit region of the Target pipe, institute Stating boundary position information and being used to indicate by symmetry axis, the first distance threshold value of the center line of the Target pipe is symmetrical half The conduit region of diameter;
According to the position of center line information, multiple initial remote sensing images are obtained, every initial remote sensing images cover the target The section of tubing region of pipeline;
According to the position of center line information, splicing is carried out to multiple described initial remote sensing images, obtains splicing remote sensing figure Picture, the splicing remote sensing images cover whole conduit regions of the Target pipe;
According to the boundary position information, cutting processing is carried out to the splicing remote sensing images, obtains the Object in Remote Sensing.
9. method as claimed in claim 1, which is characterized in that it is described to pass through the first Classification and Identification model, to described Before multiple atural object classifications in Object in Remote Sensing are identified, further includes:
Obtain the sample image of the multiple atural object classification;
Feature extraction is carried out to the sample image of the multiple atural object classification, obtains the sample image of the multiple atural object classification Geometric error modeling feature and spectral signature;
According to the geometric error modeling of the sample image of the multiple atural object classification and the sample image of the multiple atural object classification spy It seeks peace spectral signature, the second Classification and Identification model is trained, obtain the first Classification and Identification model, second classification Identification model refers to be trained, atural object classification for identification Classification and Identification model.
10. a kind of identification device in the high consequence area of long-distance oil & gas pipeline, which is characterized in that described device includes:
Module is obtained, for obtaining Object in Remote Sensing, it is pair that the Object in Remote Sensing, which includes with the center line of Target pipe, Axis, first distance threshold value are referred to as the conduit region of symmetrical radius, and the first distance threshold value is greater than the outer diameter of the Target pipe, The Target pipe is long-distance oil & gas pipeline to be studied;
First determining module, for passing through the first Classification and Identification model, to multiple atural object classifications in the Object in Remote Sensing It is identified, with the region where the multiple atural object classification of determination, the first Classification and Identification model is according to the multiple The sample image training of atural object classification obtains;
Second determining module determines the multiple for the geography information according to the conduit region in the Object in Remote Sensing The terrain object attribute information in the region in atural object classification where each atural object classification;
Identification module, for the terrain object attribute information according to the region where the multiple atural object classification, from multiple images region Identify that the high consequence area of the Target pipe, described multiple images region are along the Target pipe in interior conduit region Duct orientation, using second distance threshold value as interval, the Object in Remote Sensing is divided to obtain.
11. a kind of identification device in the high consequence area of long-distance oil & gas pipeline, which is characterized in that described device includes:
Processor and memory for storage processor executable instruction;
Wherein, the processor is configured to executing such as the described in any item methods of claim 1-9.
12. a kind of computer readable storage medium, which is characterized in that computer program is stored in the storage medium, it is described Claim 1-9 any method is realized when computer program is executed by processor.
CN201810513064.XA 2018-05-25 2018-05-25 Method and device for identifying high back fruit zone of long oil and gas pipeline and storage medium Active CN108960049B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810513064.XA CN108960049B (en) 2018-05-25 2018-05-25 Method and device for identifying high back fruit zone of long oil and gas pipeline and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810513064.XA CN108960049B (en) 2018-05-25 2018-05-25 Method and device for identifying high back fruit zone of long oil and gas pipeline and storage medium

Publications (2)

Publication Number Publication Date
CN108960049A true CN108960049A (en) 2018-12-07
CN108960049B CN108960049B (en) 2021-01-29

Family

ID=64492199

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810513064.XA Active CN108960049B (en) 2018-05-25 2018-05-25 Method and device for identifying high back fruit zone of long oil and gas pipeline and storage medium

Country Status (1)

Country Link
CN (1) CN108960049B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109978374A (en) * 2019-03-27 2019-07-05 中国环境科学研究院 Oil-gas pipeline system risk appraisal procedure
CN111310978A (en) * 2020-01-20 2020-06-19 中国石油天然气股份有限公司 Method and device for determining key monitoring pipe section of oil and gas pipeline
CN112257633A (en) * 2020-10-29 2021-01-22 中国安全生产科学研究院 Pipeline high-consequence area dynamic identification method based on image identification
CN112527928A (en) * 2019-09-19 2021-03-19 中国石油天然气股份有限公司 Pipeline protection area dividing method and device and readable storage medium
CN112765389A (en) * 2021-02-04 2021-05-07 中国石油天然气集团有限公司 Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium
CN113256647A (en) * 2021-04-14 2021-08-13 广西扬翔股份有限公司 Image processing method, image processing apparatus, electronic apparatus, and storage medium
CN113344198A (en) * 2021-06-09 2021-09-03 北京三快在线科技有限公司 Model training method and device
CN113688758A (en) * 2021-08-31 2021-11-23 重庆科技学院 Gas transmission pipeline high consequence district intelligent recognition system based on edge calculation
CN115170980A (en) * 2022-07-06 2022-10-11 广东大鹏液化天然气有限公司 Gas pipeline high consequence area intelligent identification method based on satellite image identification
CN116958907A (en) * 2023-09-18 2023-10-27 四川泓宝润业工程技术有限公司 Method and system for inspecting surrounding hidden danger targets of gas pipeline

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060129338A1 (en) * 2003-12-11 2006-06-15 Turley Richard D Pipeline integrity management process
CN103559500A (en) * 2013-10-15 2014-02-05 北京航空航天大学 Multispectral remote sensing image land feature classification method based on spectrum and textural features
CN103699543A (en) * 2012-09-28 2014-04-02 南京理工大学 Information visualization method based on ground object classification of remote sensing image
CN103778514A (en) * 2014-02-12 2014-05-07 西南石油大学 Oil-gas pipeline high-consequence area identification system and identification method
CN108052966A (en) * 2017-12-08 2018-05-18 重庆邮电大学 Remote sensing images scene based on convolutional neural networks automatically extracts and sorting technique

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060129338A1 (en) * 2003-12-11 2006-06-15 Turley Richard D Pipeline integrity management process
CN103699543A (en) * 2012-09-28 2014-04-02 南京理工大学 Information visualization method based on ground object classification of remote sensing image
CN103559500A (en) * 2013-10-15 2014-02-05 北京航空航天大学 Multispectral remote sensing image land feature classification method based on spectrum and textural features
CN103778514A (en) * 2014-02-12 2014-05-07 西南石油大学 Oil-gas pipeline high-consequence area identification system and identification method
CN108052966A (en) * 2017-12-08 2018-05-18 重庆邮电大学 Remote sensing images scene based on convolutional neural networks automatically extracts and sorting technique

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
中国人民共和国住房和城乡***: "输气管道工程设计规范", 《HTTP://WWW.DOC88.COM/P-1426124813032.HTML》 *
中国国家标准化管理委员会: "油气输送管道完整性管理规范", 《HTTP://WWW.JIANBIAOKU.COM/WEBARBS/BOOK/78011/1972845.SHTML》 *
卢琳琳等: "基于UAV技术的长输管道高后果区识别方法研究", 《石油和化工设备》 *
张辉: "基于BP神经网络的遥感影像分类研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109978374A (en) * 2019-03-27 2019-07-05 中国环境科学研究院 Oil-gas pipeline system risk appraisal procedure
CN112527928A (en) * 2019-09-19 2021-03-19 中国石油天然气股份有限公司 Pipeline protection area dividing method and device and readable storage medium
CN112527928B (en) * 2019-09-19 2024-05-31 中国石油天然气股份有限公司 Pipeline protection area division method and device and readable storage medium
CN111310978A (en) * 2020-01-20 2020-06-19 中国石油天然气股份有限公司 Method and device for determining key monitoring pipe section of oil and gas pipeline
CN112257633B (en) * 2020-10-29 2023-06-02 中国安全生产科学研究院 Pipeline high-consequence area dynamic identification method based on image identification
CN112257633A (en) * 2020-10-29 2021-01-22 中国安全生产科学研究院 Pipeline high-consequence area dynamic identification method based on image identification
CN112765389A (en) * 2021-02-04 2021-05-07 中国石油天然气集团有限公司 Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium
CN113256647A (en) * 2021-04-14 2021-08-13 广西扬翔股份有限公司 Image processing method, image processing apparatus, electronic apparatus, and storage medium
CN113344198A (en) * 2021-06-09 2021-09-03 北京三快在线科技有限公司 Model training method and device
CN113344198B (en) * 2021-06-09 2022-08-26 北京三快在线科技有限公司 Model training method and device
CN113688758B (en) * 2021-08-31 2023-05-30 重庆科技学院 Intelligent recognition system for high-consequence region of gas transmission pipeline based on edge calculation
CN113688758A (en) * 2021-08-31 2021-11-23 重庆科技学院 Gas transmission pipeline high consequence district intelligent recognition system based on edge calculation
CN115170980A (en) * 2022-07-06 2022-10-11 广东大鹏液化天然气有限公司 Gas pipeline high consequence area intelligent identification method based on satellite image identification
CN116958907A (en) * 2023-09-18 2023-10-27 四川泓宝润业工程技术有限公司 Method and system for inspecting surrounding hidden danger targets of gas pipeline
CN116958907B (en) * 2023-09-18 2023-12-26 四川泓宝润业工程技术有限公司 Method and system for inspecting surrounding hidden danger targets of gas pipeline

Also Published As

Publication number Publication date
CN108960049B (en) 2021-01-29

Similar Documents

Publication Publication Date Title
CN108960049A (en) Recognition methods, device and the storage medium in the high consequence area of long-distance oil & gas pipeline
KR102344012B1 (en) Method and apparatus for displaying point of interest
CN109962939B (en) Position recommendation method, device, server, terminal and storage medium
US8812990B2 (en) Method and apparatus for presenting a first person world view of content
CN107133325A (en) A kind of internet photo geographical space localization method based on streetscape map
TW201107713A (en) Apparatus and method for position determination
KR102308960B1 (en) Methods of specifying global locations including indoor locations and database using the same
CN112732858B (en) Path planning method and device, computer equipment and storage medium
US11486711B2 (en) Methods of specifying global locations including indoor locations and database using the same
CN110490179A (en) Licence plate recognition method, device and storage medium
CN110457571B (en) Method, device and equipment for acquiring interest point information and storage medium
CN112966124B (en) Training method, alignment method, device and equipment of knowledge graph alignment model
US10444954B2 (en) Distinguishable geographic area presentation
CN110096525A (en) Calibrate method, apparatus, equipment and the storage medium of interest point information
CN106912003A (en) A kind of short distance hunting system and object method for searching
CN109992685A (en) A kind of method and device of retrieving image
US11442997B2 (en) System and method associated with an insular digital content distribution platform that generates discrete epochs of content based on determination of a germane zip-span polygon region
CN110175653A (en) Method, apparatus, equipment and the storage medium of image recognition
Li et al. Are you lying: Validating the time-location of outdoor images
KR20150077607A (en) Dinosaur Heritage Experience Service System Using Augmented Reality and Method therefor
CN113822263A (en) Image annotation method and device, computer equipment and storage medium
CN110147796A (en) Image matching method and device
CN110471614A (en) A kind of method of storing data, the method and device for detecting terminal
CN110245206B (en) Map style acquisition method and device, server, terminal and storage medium
CN113569822B (en) Image segmentation method and device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant