CN108805864A - The acquisition methods and device of architecture against regulations object based on view data - Google Patents
The acquisition methods and device of architecture against regulations object based on view data Download PDFInfo
- Publication number
- CN108805864A CN108805864A CN201810426677.XA CN201810426677A CN108805864A CN 108805864 A CN108805864 A CN 108805864A CN 201810426677 A CN201810426677 A CN 201810426677A CN 108805864 A CN108805864 A CN 108805864A
- Authority
- CN
- China
- Prior art keywords
- architectural drawing
- information
- against regulations
- architecture against
- architectural
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/37—Determination of transform parameters for the alignment of images, i.e. image registration using transform domain methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
This application involves a kind of acquisition methods, system, computer equipment and the storage mediums of architecture against regulations object based on view data.The method includes:Obtain the first Architectural drawing and with matched second Architectural drawing of the first Architectural drawing, wherein the Architectural drawing includes multiple building sides;Image alignment processing is carried out according to first the second Architectural drawing of Architectural drawing pair, obtains third Architectural drawing, wherein the building sides building sides corresponding with the first Architectural drawing in third Architectural drawing is aligned one by one;The profile information of building sides in the first Architectural drawing and third Architectural drawing is obtained respectively and is compared, and profile difference information is obtained;Architecture against regulations object is determined according to profile difference information.The recognition efficiency of architecture against regulations object and the timeliness of architecture against regulations object processing can be improved using this method.
Description
Technical field
This application involves information monitoring technical fields, more particularly to a kind of obtaining for architecture against regulations object based on view data
Take method, apparatus, computer equipment and storage medium.
Background technology
With the rapid economic development in our country, the demand sustainable growth in soil, illegal building occupies cultivated land, occupies high speed public affairs
The architectures against regulations methods such as road building control area gradually increase, and especially occupy highway construction control zone, in highway both sides
Dysopia can be caused by building illegal building object, influence driver drives vehicle judgement, traffic accident rate is caused to improve.At present
What the modes such as the identification of architecture against regulations object is mainly gone on patrol by administration of highways personnel or the masses independently report were realized, these sides
Formula be often difficult to realize it is real-time, accurately know architecture against regulations object, the acquisition inefficiency of architecture against regulations object, while also reducing pair
The timeliness of architecture against regulations object processing.
Invention content
Based on this, it is necessary to for the timeliness that the acquisition efficiency of above-mentioned architecture against regulations object is low and handles architecture against regulations object
Property difference technical problem, provides a kind of acquisition methods, device, computer equipment and the storage of architecture against regulations object based on view data
Medium.
A kind of acquisition methods of architecture against regulations object based on view data, include the following steps:
Obtain the first Architectural drawing and with matched second Architectural drawing of first Architectural drawing, wherein it is described to build
It includes multiple building sides to build image;
Image alignment processing is carried out to second Architectural drawing according to first Architectural drawing, obtains third architectural drawing
Picture, wherein the building sides in the third Architectural drawing is aligned one by one with corresponding building sides in first Architectural drawing;
The profile information of building sides and progress in first Architectural drawing and the third Architectural drawing are obtained respectively
Comparison obtains profile difference information;
Architecture against regulations object is determined according to the profile difference information.
In one of the embodiments, after described the step of determining architecture against regulations object according to the profile difference information,
It is further comprising the steps of:
The latitude and longitude information of the architecture against regulations object is obtained, the identification report of architecture against regulations object is generated.
In one of the embodiments, described the step of architecture against regulations object is determined according to the profile difference information, also wrap
Include following steps:
According to the profile difference acquisition of information profile difference degree;
If the profile difference degree is more than predetermined threshold value, the profile difference information is marked on the third Architectural drawing
Corresponding building sides obtains architecture against regulations object.
The step of the acquisition and matched second Architectural drawing of first Architectural drawing in one of the embodiments,
Suddenly, include the following steps:
The latitude and longitude information for obtaining first Architectural drawing screens second architectural drawing according to the latitude and longitude information
Picture.
It is described in one of the embodiments, that image is carried out to second Architectural drawing according to first Architectural drawing
The step of registration process, acquisition third Architectural drawing, include the following steps:
Image transformation is carried out to second Architectural drawing using first Architectural drawing as references object, obtains described the
Three Architectural drawings, wherein described image transformation includes that rotation transformation and/or translation transformation and/or scale transformation and/or shear become
It changes.
Described in one of the embodiments, using first Architectural drawing is references object to second Architectural drawing
The step of carrying out image transformation, includes the following steps:
By first Architectural drawing and second Architectural drawing be respectively converted into the first gray level image information and
Second gray level image information, and obtain predetermined movement model matrix and default error coefficient threshold value;
According to first gray level image information and second gray level image information, and using gradient algorithm to described
The parameter of predetermined movement model matrix optimizes, and obtains intermediate distortion matrix;
The intermediate matrix that distorts is multiplied with second gray level image information, changing image information is obtained, calculates institute
State the error coefficient between the first gray level image information and the changing image information;
If the error coefficient reaches the default error coefficient threshold value, the intermediate matrix that distorts is distorted as target
Matrix application is in second Architectural drawing.
In one of the embodiments, between calculating first gray level image information and the changing image information
Error coefficient the step of after, it is further comprising the steps of:
If the error coefficient is not up to the default error coefficient threshold value, jump to using gradient algorithm to described pre-
If the step of parameter of motion model matrix optimizes.
A kind of acquisition device of architecture against regulations object based on view data, including:
Architectural drawing acquisition module, for obtain the first Architectural drawing and with first Architectural drawing matched second
Architectural drawing, wherein the Architectural drawing includes multiple building sides;
Building sides alignment module, for carrying out image alignment to second Architectural drawing according to first Architectural drawing
Processing obtains third Architectural drawing, wherein the building sides in the third Architectural drawing is corresponding to first Architectural drawing
Building sides be aligned one by one;
Difference profile acquisition module is built for obtaining respectively in first Architectural drawing and the third Architectural drawing
It builds the profile information in face and is compared, obtain profile difference information;
Architecture against regulations acquisition module, for determining architecture against regulations object according to the profile difference information.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes following steps when executing the computer program:
Obtain the first Architectural drawing and with matched second Architectural drawing of first Architectural drawing, wherein it is described to build
It includes multiple building sides to build image;
Image alignment processing is carried out to second Architectural drawing according to first Architectural drawing, obtains third architectural drawing
Picture, wherein the building sides in the third Architectural drawing is aligned one by one with corresponding building sides in first Architectural drawing;
The profile information of building sides and progress in first Architectural drawing and the third Architectural drawing are obtained respectively
Comparison obtains profile difference information;
Architecture against regulations object is determined according to the profile difference information.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Following steps are realized when row:
Obtain the first Architectural drawing and with matched second Architectural drawing of first Architectural drawing, wherein it is described to build
It includes multiple building sides to build image;
Image alignment processing is carried out to second Architectural drawing according to first Architectural drawing, obtains third architectural drawing
Picture, wherein the building sides in the third Architectural drawing is aligned one by one with corresponding building sides in first Architectural drawing;
The profile information of building sides and progress in first Architectural drawing and the third Architectural drawing are obtained respectively
Comparison obtains profile difference information;
Architecture against regulations object is determined according to the profile difference information.
Acquisition methods, device, computer equipment and the storage medium of above-mentioned architecture against regulations object based on view data, pass through
Image alignment processing is carried out to two Architectural drawings being mutually matched, the profile of the building sides in the Architectural drawing after alignment is believed
Breath is compared, and is obtained the place of profile difference between building sides in two Architectural drawings, is therefrom determined architecture against regulations object, improves and disobey
The timeliness of recognition efficiency and the architecture against regulations object processing of chapter building.
Description of the drawings
Fig. 1 is the application environment of the acquisition methods of architecture against regulations object based on view data in one embodiment of the invention
Figure;
Fig. 2 is the flow signal of the acquisition methods of architecture against regulations object based on view data in one embodiment of the invention
Figure;
Fig. 3 is the flow diagram of profile difference information Step in one embodiment of the invention;
Fig. 4 is to carry out image in one embodiment of the invention by the second Architectural drawing of references object pair of the first Architectural drawing
The flow chart of transformation;
Fig. 5 is the structure diagram of the acquisition device of architecture against regulations object based on view data in one embodiment of the invention;
Fig. 6 is the internal structure chart of one embodiment of the invention Computer equipment.
Specific implementation mode
It is with reference to the accompanying drawings and embodiments, right in order to make the object, technical solution and advantage of the application be more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
The acquisition methods of architecture against regulations object based on view data provided by the present application, can be applied to as shown in Figure 1
In application environment.Wherein, terminal 102 is communicated with server 104 by network by network.Terminal 102 obtains first and builds
Image and the second Architectural drawing are built, and the first Architectural drawing and the second Architectural drawing are sent in server 104, is serviced
Device 104 therefrom identifies architecture against regulations object according to the first Architectural drawing and the second Architectural drawing.Wherein, terminal 102 can with but
It is not limited to various aerial photography devices and photography unmanned plane, server 104 can use independent server either multiple servers
The server cluster of composition is realized.
Referring to Fig. 2, Fig. 2 is the stream of the acquisition methods of architecture against regulations object based on view data in one embodiment of the invention
Cheng Tu.In the present embodiment, the acquisition methods of architecture against regulations object based on view data include the following steps:
Step S210:Obtain the first Architectural drawing and with matched second Architectural drawing of the first Architectural drawing, wherein build
It includes multiple building sides to build image.
In this step, the first Architectural drawing and the second Architectural drawing can vertically shoot ground in high-altitude by unmanned plane
The image of face building, wherein architectural drawing includes multiple building sides, the shooting of the first Architectural drawing and the second Architectural drawing
Time is different;Can be the shooting area similarity with the first Architectural drawing with matched second Architectural drawing of the first Architectural drawing
Or registration is compared with hi-vision.
Specifically, after obtaining the first Architectural drawing, according to the feature of image information in the first Architectural drawing, obtain and first
Image information feature registration reaches the second Architectural drawing of certain threshold value in Architectural drawing.
Step S220:Image alignment processing is carried out according to first the second Architectural drawing of Architectural drawing pair, obtains third building
Image, wherein the building sides building sides corresponding with the first Architectural drawing in third Architectural drawing is aligned one by one.
In this step, building sides can refer to the cross section of building, can also be when vertically shooting building from high-altitude
The contoured surface of building, the first Architectural drawing and the second Architectural drawing include multiple building sides.
Using the first Architectural drawing as reference template, the second Architectural drawing is carried out according to the first Architectural drawing at image alignment
Reason obtains the third Architectural drawing that building sides building sides corresponding to the first Architectural drawing is aligned.
Step S230:The profile information of building sides and progress in the first Architectural drawing and third Architectural drawing are obtained respectively
Comparison obtains profile difference information.
In this step, obtain building sides profile information can by gray processing, binaryzation, Fuzzy Processing, edge detection,
The image processing techniques such as corrosion expansion obtain the profile information in Architectural drawing.It illustrates, is being schemed by taking binaryzation as an example
As after, gray level image is converted the image into, then selectes suitable threshold value and binaryzation is carried out to image, from the gray scale after binaryzation
Image obtains profile information.
Since the common region of the first Architectural drawing and third Architectural drawing is aligned one by one, the first architectural drawing is obtained
After profile information in picture and third Architectural drawing, by comparing the profile information of two width Architectural drawings, obtaining
Profile difference information between the two.
It is the schematic diagram of profile difference information in one embodiment of the invention for example, with reference to Fig. 3, Fig. 3;In figure, first builds
Image 310 is built to be aligned one by one with building sides common in third Architectural drawing 320, obtain the first Architectural drawing 310 and
It the profile information of building sides and is compared in 320a in third Architectural drawing, profile difference information is obtained, in image 320b
The difference profile 321 and difference profile 322 of the lines of overstriking.
Step S240:Architecture against regulations object is determined according to profile difference information.
The acquisition methods of above-mentioned architecture against regulations object based on view data are carried out by two architectural drawings to being mutually matched
Image alignment processing, compares the profile information of the building sides in the Architectural drawing after alignment, obtains two Architectural drawings
The place of profile difference between middle building sides therefrom determines architecture against regulations object, improves the recognition efficiency of architecture against regulations object and breaks rules and regulations
The timeliness of building processing;Simultaneously as handled by image alignment, can reduce between Architectural drawing because of different shooting conditions
Lead to the acquisition difficulty of difference object, improves the accuracy rate of architecture against regulations object identification.
The step of obtaining the second Architectural drawing matched with the first Architectural drawing in one of the embodiments, including with
Lower step:The latitude and longitude information for obtaining the first Architectural drawing screens the second Architectural drawing according to latitude and longitude information.
In the present embodiment, the image data information of image includes latitude and longitude information, according to the longitude and latitude of the first Architectural drawing
Information is spent, the image for reaching certain threshold value with the latitude and longitude information registration of the first Architectural drawing is filtered out, as matched the
Two Architectural drawings.The first Architectural drawing and the second matching architectural drawing are screened by the latitude and longitude information in image information
Picture, can ensure to the full extent the first Architectural drawing and the second Architectural drawing shooting area have higher similarity or
Registration.
After the step of determining architecture against regulations object according to profile difference information in one of the embodiments, further include with
Lower step:The latitude and longitude information of architecture against regulations object is obtained, the identification report of architecture against regulations object is generated.
Specifically, after identifying architecture against regulations object, the latitude and longitude information of building is obtained, it includes architecture against regulations object to generate
The architecture against regulations object identification report of detailed location information.
For example, after the latitude and longitude information of acquisition building, the position of architecture against regulations object can be carried out according to latitude and longitude information
Point list generates the report of architecture against regulations object;Display architecture against regulations object position can also be marked on two-dimensional map, generated and disobeyed
The image of chapter building is reported.In the present embodiment, by obtaining latitude and longitude information, its accurately position can be accurately obtained
Point facilitates administrative staff to search architecture against regulations object.
In view of difference object has certain volume size, and some the area very little noises occurred on such as Architectural drawing
Profile is not difference object, therefore, determines the step of architecture against regulations object according to profile difference information in one of the embodiments,
Suddenly, further comprising the steps of:According to profile difference acquisition of information profile difference degree;If profile difference degree is more than predetermined threshold value,
The corresponding building sides of profile difference information is marked on third Architectural drawing, obtains architecture against regulations object.
In the present embodiment, profile difference degree can be the perimeter of difference profile, can also be the enclosed region of difference profile
Face amount;Correspondingly, predetermined threshold value could be provided as the perimeter threshold of profile, the area threshold in the enclosed region of profile may be set to be
Value.
After obtaining profile difference information, the perimeter value for obtaining difference profile is calculated as profile according to profile difference information
Diversity factor, or calculated according to profile difference information and to obtain the area value in the enclosed region of difference profile as profile difference degree, when
Profile difference degree is more than predetermined threshold value, then the enclosed region of difference profile on the second image is target difference object so that mesh
The acquisition accuracy of mark difference object greatly improves.
By taking predetermined threshold value could be provided as the area threshold in the enclosed region of profile as an example, in figure three, the first figure is being compared
After the profile information in 310 and third image 320a, difference profile 321 and difference profile 322 can be obtained, if differentiated wheels
The area (i.e. dash area in Fig. 3 in difference profile 321) that exterior feature 321 is surrounded is more than preset area threshold value, then difference profile
321 corresponding dash areas are labeled as target difference object, similarly, if the area that difference profile 322 is surrounded is (i.e. in Fig. 3
Dash area in difference profile 322) be more than preset area threshold value, then 322 corresponding dash area of difference profile is also marked
For target difference object.
Image alignment processing is carried out according to first the second Architectural drawing of Architectural drawing pair in one of the embodiments, is obtained
The step of taking third Architectural drawing, includes the following steps:It is carried out by the second Architectural drawing of references object pair of the first Architectural drawing
Image converts, and obtains third Architectural drawing, wherein image transformation includes rotation transformation and/or translation transformation and/or scale transformation
And/or shear transformation.
In the present embodiment, due to the shooting conditions such as the first Architectural drawing and the second Architectural drawing camera site, shooting angle
It is not quite identical, it is reference with the first Architectural drawing, by executing the figures such as rotation, translation, scaling, shear to the second Architectural drawing
As map function so that the second Architectural drawing corresponds to identical region with the first Architectural drawing and is aligned one by one, and rejects alignment
Fringe region extra in second Architectural drawing afterwards obtains third Architectural drawing.By the map function to the second Architectural drawing,
It is aligned one by one so that the second Architectural drawing corresponds to identical region with the first Architectural drawing so that can subsequently realize profile pair
Than improving efficiency, while rejecting to extra fringe region, the False Rate of difference object can be reduced.
It is in one embodiment of the invention using the first Architectural drawing as the second Architectural drawing of references object pair referring to Fig. 4, Fig. 4
Carry out the flow chart of image transformation.In the present embodiment, it is carried out by the second Architectural drawing of references object pair of the first Architectural drawing
The step of image converts, includes the following steps:
Step S410:By the first Architectural drawing and the second Architectural drawing be respectively converted into the first gray level image information and
Second gray level image information, and obtain predetermined movement model matrix and default error coefficient threshold value.
In this step, motion model matrix refers to the mapping matrix for referring to geometric transformation, and default error coefficient threshold value refers to
Optimize the termination criteria of kinematic matrix parameter.
Step S420:According to the first gray level image information and the second gray level image information, and using gradient algorithm to pre-
If the parameter of motion model matrix optimizes, intermediate distortion matrix is obtained.
Step S430:Centre distortion matrix is multiplied with the second gray level image information, acquisition changing image information, calculating the
Error coefficient between one gray level image information and changing image information.
Step S440:If error coefficient reaches default error coefficient threshold value, square is distorted using centre distortion matrix as target
Battle array is applied to the second Architectural drawing.
In the present embodiment, using the first gray level image information as standard form, using gradient algorithm to motion model matrix
Parameter optimizes calculating, and the geometric transformation searched between the first gray level image information and the second gray level image information is corresponding
Motion model matrix.In motion model matrix parameter optimizes calculating process, when current motion model matrix application in
The changing image that second gray level image information obtains, reaches default error coefficient threshold with the error coefficient of the first gray level image information
When value, you can think that current motion model matrix is several between the first gray level image information and the second gray level image information
What corresponding motion model matrix of transformation, that is, obtain distortion matrix, and by distortion matrix application in the second image, realization is built to second
It builds image and carries out image transformation.
Optionally, predetermined movement model matrix can be radiation transformation model, can also be selected as homography matrix transformation square
Battle array.
Further, when the error coefficient of changing image and the first gray level image information reaches default error coefficient not yet
When threshold value, then needs to continue with gradient calculation and the parameter of predetermined movement model matrix is continued to optimize, therefore, wherein one
In a embodiment, after the step of calculating the error coefficient between the first gray level image information and changing image information, further include
Following steps:If the not up to default error coefficient threshold value of error coefficient, jumps to using gradient algorithm to predetermined movement model
The step of parameter of matrix optimizes.
The above-mentioned process that image transformation is carried out to the second Architectural drawing is found by the way that original building image is converted to gray-scale map
Distort matrix so that image transformation in terms of contrast and brightness is constant for photometric distortion, makes picture contrast and bright
Degree variation adaptability enhancing, and simple alternative manner is used in the distortion matrix for calculating target, the complexity of calculating is low,
Processing speed is fast, greatly improves the efficiency of the acquisition methods of difference object between image based on view data.
It should be understood that although each step in the flow chart of Fig. 2 and Fig. 4 is shown successively according to the instruction of arrow
Show, but these steps are not the inevitable sequence indicated according to arrow to be executed successively.Unless expressly state otherwise herein, this
There is no stringent sequences to limit for the execution of a little steps, these steps can execute in other order.Moreover, Fig. 2 and Fig. 4
In at least part step may include that either these sub-steps of multiple stages or stage are not necessarily multiple sub-steps
Completion is executed in synchronization, but can be executed at different times, the execution in these sub-steps or stage sequence is not yet
Necessarily carry out successively, but can either the sub-step of other steps or at least part in stage be in turn with other steps
Or it alternately executes.
Referring to Fig. 5, Fig. 5 is the knot of the acquisition device of architecture against regulations object based on view data in one embodiment of the invention
Structure schematic diagram.In the present embodiment, the acquisition device of architecture against regulations object based on view data, including:
Architectural drawing acquisition module 510, for obtain the first Architectural drawing and with the first Architectural drawing matched second
Architectural drawing, wherein the Architectural drawing includes multiple building sides;
Building sides alignment module 520, for carrying out image alignment processing according to first the second Architectural drawing of Architectural drawing pair,
Obtain third Architectural drawing, wherein the building sides building sides corresponding with the first Architectural drawing in third Architectural drawing is one by one
Alignment;
Difference profile acquisition module 530, the wheel for obtaining building sides in the first Architectural drawing and third building respectively
Wide information is simultaneously compared, and profile difference information is obtained;
Architecture against regulations acquisition module 540, for determining architecture against regulations object according to profile difference information.
Architecture against regulations acquisition module 540 is additionally operable to obtain the longitude and latitude letter of architecture against regulations object in one of the embodiments,
Breath generates the identification report of architecture against regulations object.
Architecture against regulations acquisition module 540 is used for according to profile difference acquisition of information profile differences in one of the embodiments,
Different degree;If profile difference degree is more than predetermined threshold value, the corresponding building sides of profile difference information is marked on third Architectural drawing, is obtained
Obtain architecture against regulations object.
Architectural drawing acquisition module 510 is used to obtain the longitude and latitude letter of the first Architectural drawing in one of the embodiments,
Breath screens the second Architectural drawing according to latitude and longitude information.
Building sides alignment module 520 is used for using the first Architectural drawing as references object pair the in one of the embodiments,
Two Architectural drawings carry out image transformation, obtain third Architectural drawing, wherein image transformation includes that rotation transformation and/or translation become
Change and/or scale transformation and/or shear transformation.
Building sides alignment module 520 is used for the first Architectural drawing and the second architectural drawing in one of the embodiments,
As being respectively converted into the first gray level image information and the second gray level image information, and obtain predetermined movement model matrix and pre-
If error coefficient threshold value;According to the first gray level image information and the second gray level image information, and using gradient algorithm to default
The parameter of motion model matrix optimizes, and obtains intermediate distortion matrix;By centre distortion matrix and the second gray level image information
It is multiplied, obtains changing image information, calculate the error coefficient between the first gray level image information and changing image information;If error
Coefficient reaches default error coefficient threshold value, and matrix application is distorted in the second Architectural drawing using centre distortion matrix as target.
Building sides alignment module 520 is additionally operable in the not up to default error system of error coefficient in one of the embodiments,
When number threshold value, then the parameter of predetermined movement model matrix is optimized using using gradient algorithm.
The specific restriction of acquisition device about architecture against regulations object based on view data may refer to above for base
In the restriction of the acquisition methods of the architecture against regulations object of image data, details are not described herein.It is above-mentioned based on view data violating the regulations to build
Building the modules in the acquisition device of object can realize fully or partially through software, hardware and combinations thereof.Above-mentioned each module
It can be embedded in the form of hardware or independently of in the processor in computer equipment, computer can also be stored in a software form
In memory in equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include the processor connected by system bus, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing Architectural drawing data information.The network interface of the computer equipment is used for and external terminal
It is communicated by network connection.To realize a kind of architecture against regulations object based on view data when the computer program is executed by processor
Acquisition methods.
It will be understood by those skilled in the art that structure shown in Fig. 6, is only tied with the relevant part of application scheme
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
May include either combining certain components than more or fewer components as shown in the figure or being arranged with different components.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor realize following steps when executing computer program:
Obtain the first Architectural drawing and with matched second Architectural drawing of the first Architectural drawing, wherein the architectural drawing
As including multiple building sides;
Image alignment processing is carried out according to first the second Architectural drawing of Architectural drawing pair, obtains third Architectural drawing, wherein
Building sides building sides corresponding with the first Architectural drawing in third Architectural drawing is aligned one by one;
The profile information of building sides in the first Architectural drawing and third Architectural drawing is obtained respectively and is compared, and is obtained
Profile difference information;
Architecture against regulations object is determined according to profile difference information.
Following steps are also realized when processor executes computer program in one of the embodiments,:Obtain the architecture against regulations
The latitude and longitude information of object generates the identification report of architecture against regulations object.
Following steps are also realized when processor executes computer program in one of the embodiments,:If profile difference degree
More than predetermined threshold value, the corresponding building sides of profile difference information is marked on third Architectural drawing, obtains architecture against regulations object.
Following steps are also realized when processor executes computer program in one of the embodiments,:Obtain the first building
The latitude and longitude information of image screens the second Architectural drawing according to latitude and longitude information.
Following steps are also realized when processor executes computer program in one of the embodiments,:With the first architectural drawing
As being that the second Architectural drawing of references object pair carries out image transformation, third Architectural drawing is obtained, wherein image transformation includes rotation
Transformation and/or translation transformation and/or scale transformation and/or shear transformation.
Following steps are also realized when processor executes computer program in one of the embodiments,:By the first architectural drawing
Picture and the second Architectural drawing are respectively converted into the first gray level image information and the second gray level image information, and obtain default fortune
Movable model matrix and default error coefficient threshold value;According to the first gray level image information and the second gray level image information, and profit
The parameter of predetermined movement model matrix is optimized with gradient algorithm, obtains intermediate distortion matrix;By centre distortion matrix with
Second gray level image information is multiplied, and obtains changing image information, calculates between the first gray level image information and changing image information
Error coefficient;If error coefficient reaches default error coefficient threshold value, matrix application is distorted using centre distortion matrix as target
In the second Architectural drawing.
Following steps are also realized when processor executes computer program in one of the embodiments,:If error coefficient is not
Reach default error coefficient threshold value, then jumps to the step optimized to the parameter of predetermined movement model matrix using gradient algorithm
Suddenly.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor:
Obtain the first Architectural drawing and with matched second Architectural drawing of the first Architectural drawing, wherein the architectural drawing
As including multiple building sides;
Image alignment processing is carried out according to first the second Architectural drawing of Architectural drawing pair, obtains third Architectural drawing, wherein
Building sides building sides corresponding with the first Architectural drawing in third Architectural drawing is aligned one by one;
The profile information of building sides in the first Architectural drawing and third Architectural drawing is obtained respectively and is compared, and is obtained
Profile difference information;
Architecture against regulations object is determined according to profile difference information.
Following steps are also realized when computer program is executed by processor in one of the embodiments,:Obtain violating the regulations build
The latitude and longitude information of object is built, the identification report of architecture against regulations object is generated.
Following steps are also realized when computer program is executed by processor in one of the embodiments,:If profile difference
Degree is more than predetermined threshold value, and the corresponding building sides of profile difference information is marked on third Architectural drawing, obtains architecture against regulations object.
Following steps are also realized when computer program is executed by processor in one of the embodiments,:First is obtained to build
The latitude and longitude information for building image screens the second Architectural drawing according to latitude and longitude information.
Following steps are also realized when computer program is executed by processor in one of the embodiments,:With the first building
Image is that the second Architectural drawing of references object pair carries out image transformation, obtains third Architectural drawing, wherein image transformation includes rotation
Transformation is changed and/or translation transformation and/or scale transformation and/or shear transformation.
Following steps are also realized when computer program is executed by processor in one of the embodiments,:By the first building
Image and the second Architectural drawing are respectively converted into the first gray level image information and the second gray level image information, and obtain default
Motion model matrix and default error coefficient threshold value;According to the first gray level image information and the second gray level image information, and
The parameter of predetermined movement model matrix is optimized using gradient algorithm, obtains intermediate distortion matrix;Centre is distorted into matrix
It is multiplied with the second gray level image information, obtains changing image information, calculate the first gray level image information and changing image information
Between error coefficient;If error coefficient reaches default error coefficient threshold value, answered centre distortion matrix as target distortion matrix
For the second Architectural drawing.
Following steps are also realized when computer program is executed by processor in one of the embodiments,:If error coefficient
Not up to default error coefficient threshold value is then jumped to and is optimized to the parameter of predetermined movement model matrix using gradient algorithm
Step.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein,
Any reference to memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above example can be combined arbitrarily, to keep description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield is all considered to be the range of this specification record.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the protection domain of the application patent should be determined by the appended claims.
Claims (10)
1. a kind of acquisition methods of architecture against regulations object based on view data, which is characterized in that include the following steps:
Obtain the first Architectural drawing and with matched second Architectural drawing of first Architectural drawing, wherein the architectural drawing
As including multiple building sides;
Image alignment processing is carried out to second Architectural drawing according to first Architectural drawing, obtains third Architectural drawing,
Wherein, the building sides in the third Architectural drawing is aligned one by one with corresponding building sides in first Architectural drawing;
The profile information of building sides in first Architectural drawing and the third Architectural drawing is obtained respectively and is compared,
Obtain profile difference information;
Architecture against regulations object is determined according to the profile difference information.
2. the acquisition methods of architecture against regulations object based on view data according to claim 1, which is characterized in that described
It is further comprising the steps of after the step of determining architecture against regulations object according to the profile difference information:
The latitude and longitude information of the architecture against regulations object is obtained, the identification report of architecture against regulations object is generated.
3. the acquisition methods of architecture against regulations object based on view data according to claim 1, which is characterized in that described
The step of architecture against regulations object being determined according to the profile difference information, it is further comprising the steps of:
According to the profile difference acquisition of information profile difference degree;
If the profile difference degree is more than predetermined threshold value, the profile difference information is marked on the third Architectural drawing and is corresponded to
Building sides, obtain architecture against regulations object.
4. the acquisition methods of architecture against regulations object based on view data according to claim 1, which is characterized in that described to obtain
The step of taking the second Architectural drawing matched with first Architectural drawing, includes the following steps:
The latitude and longitude information for obtaining first Architectural drawing screens second Architectural drawing according to the latitude and longitude information.
5. the acquisition methods of architecture against regulations object based on view data according to claim 1, which is characterized in that described
The step of is carried out by image alignment processing, obtains third Architectural drawing for second Architectural drawing according to first Architectural drawing,
Include the following steps:
Image transformation is carried out to second Architectural drawing using first Architectural drawing as references object, the third is obtained and builds
Build image, wherein described image transformation includes rotation transformation and/or translation transformation and/or scale transformation and/or shear transformation.
6. the acquisition methods of architecture against regulations object based on view data according to claim 5, which is characterized in that it is described with
First Architectural drawing is the step of references object carries out image transformation to second Architectural drawing, is included the following steps:
First Architectural drawing and second Architectural drawing are respectively converted into the first gray level image information and second
Gray level image information, and obtain predetermined movement model matrix and default error coefficient threshold value;
According to first gray level image information and second gray level image information, and using gradient algorithm to described default
The parameter of motion model matrix optimizes, and obtains intermediate distortion matrix;
The intermediate matrix that distorts is multiplied with second gray level image information, acquisition changing image information, calculating described the
Error coefficient between one gray level image information and the changing image information;
If the error coefficient reaches the default error coefficient threshold value, the intermediate matrix that distorts is distorted into matrix as target
Applied to second Architectural drawing.
7. the acquisition methods of architecture against regulations object based on view data according to claim 5, which is characterized in that the meter
Further include following step after the step of calculating the error coefficient between first gray level image information and the changing image information
Suddenly:
If the error coefficient is not up to the default error coefficient threshold value, jump to using gradient algorithm to the default fortune
The step of parameter of movable model matrix optimizes.
8. a kind of acquisition device of architecture against regulations object based on view data, which is characterized in that including:
Architectural drawing acquisition module, for obtaining the first Architectural drawing and being built with first Architectural drawing matched second
Image, wherein the Architectural drawing includes multiple building sides;
Building sides alignment module, for being carried out at image alignment to second Architectural drawing according to first Architectural drawing
Reason obtains third Architectural drawing, wherein the building sides in the third Architectural drawing is corresponding with first Architectural drawing
Building sides is aligned one by one;
Difference profile acquisition module, for obtaining building sides in first Architectural drawing and the third Architectural drawing respectively
Profile information and compared, obtain profile difference information;
Architecture against regulations acquisition module, for determining architecture against regulations object according to the profile difference information.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the processor realizes that any one of claim 1 to 7 is described based on view data separated when executing the computer program
The step of acquisition methods of chapter building.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The acquisition methods of any one of claim 1 to 7 architecture against regulations object based on view data are realized when being executed by processor
The step of.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810426677.XA CN108805864A (en) | 2018-05-07 | 2018-05-07 | The acquisition methods and device of architecture against regulations object based on view data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810426677.XA CN108805864A (en) | 2018-05-07 | 2018-05-07 | The acquisition methods and device of architecture against regulations object based on view data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108805864A true CN108805864A (en) | 2018-11-13 |
Family
ID=64091099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810426677.XA Pending CN108805864A (en) | 2018-05-07 | 2018-05-07 | The acquisition methods and device of architecture against regulations object based on view data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108805864A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109753928A (en) * | 2019-01-03 | 2019-05-14 | 北京百度网讯科技有限公司 | The recognition methods of architecture against regulations object and device |
CN110503108A (en) * | 2019-07-11 | 2019-11-26 | 平安科技(深圳)有限公司 | Architecture against regulations recognition methods and device, storage medium, computer equipment |
CN110928976A (en) * | 2019-12-05 | 2020-03-27 | 重庆商勤科技有限公司 | Water source illegal activity recognition early warning method, server and storage medium |
CN111368615A (en) * | 2019-06-26 | 2020-07-03 | 杭州海康威视***技术有限公司 | Violation building early warning method and device and electronic equipment |
CN111563448A (en) * | 2020-04-30 | 2020-08-21 | 北京百度网讯科技有限公司 | Method and device for detecting illegal building, electronic equipment and storage medium |
CN111882660A (en) * | 2020-07-23 | 2020-11-03 | 广联达科技股份有限公司 | Three-dimensional display method and three-dimensional display device based on CAD drawing |
CN112954226A (en) * | 2021-05-11 | 2021-06-11 | 江苏瞭望神州大数据科技有限公司 | Monitoring method and system for identifying construction site |
WO2021189870A1 (en) * | 2020-03-27 | 2021-09-30 | 北京百度网讯科技有限公司 | Method, apparatus and device for identifying illegal building, and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103546726A (en) * | 2013-10-28 | 2014-01-29 | 东南大学 | Method for automatically discovering illegal land use |
CN105872479A (en) * | 2016-05-27 | 2016-08-17 | 广东亿迅科技有限公司 | Community grid managing, monitoring and early warning system based on unmanned aerial vehicle |
CN105893972A (en) * | 2016-04-08 | 2016-08-24 | 深圳市智绘科技有限公司 | Automatic illegal building monitoring method based on image and realization system thereof |
CN107564084A (en) * | 2017-08-24 | 2018-01-09 | 腾讯科技(深圳)有限公司 | A kind of cardon synthetic method, device and storage device |
-
2018
- 2018-05-07 CN CN201810426677.XA patent/CN108805864A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103546726A (en) * | 2013-10-28 | 2014-01-29 | 东南大学 | Method for automatically discovering illegal land use |
CN105893972A (en) * | 2016-04-08 | 2016-08-24 | 深圳市智绘科技有限公司 | Automatic illegal building monitoring method based on image and realization system thereof |
CN105872479A (en) * | 2016-05-27 | 2016-08-17 | 广东亿迅科技有限公司 | Community grid managing, monitoring and early warning system based on unmanned aerial vehicle |
CN107564084A (en) * | 2017-08-24 | 2018-01-09 | 腾讯科技(深圳)有限公司 | A kind of cardon synthetic method, device and storage device |
Non-Patent Citations (2)
Title |
---|
丁明跃: "《物联网识别技术》", 31 July 2012 * |
杨磊: "《数字媒体技术概论》", 31 July 2017 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109753928B (en) * | 2019-01-03 | 2022-03-29 | 北京百度网讯科技有限公司 | Method and device for identifying illegal buildings |
CN109753928A (en) * | 2019-01-03 | 2019-05-14 | 北京百度网讯科技有限公司 | The recognition methods of architecture against regulations object and device |
CN111368615A (en) * | 2019-06-26 | 2020-07-03 | 杭州海康威视***技术有限公司 | Violation building early warning method and device and electronic equipment |
CN111368615B (en) * | 2019-06-26 | 2024-04-05 | 杭州海康威视***技术有限公司 | Illegal building early warning method and device and electronic equipment |
CN110503108A (en) * | 2019-07-11 | 2019-11-26 | 平安科技(深圳)有限公司 | Architecture against regulations recognition methods and device, storage medium, computer equipment |
CN110503108B (en) * | 2019-07-11 | 2024-05-28 | 平安科技(深圳)有限公司 | Method and device for identifying illegal buildings, storage medium and computer equipment |
WO2021003824A1 (en) * | 2019-07-11 | 2021-01-14 | 平安科技(深圳)有限公司 | Image recognition-based illegal building identification method and device |
CN110928976A (en) * | 2019-12-05 | 2020-03-27 | 重庆商勤科技有限公司 | Water source illegal activity recognition early warning method, server and storage medium |
CN110928976B (en) * | 2019-12-05 | 2022-12-23 | 重庆商勤科技有限公司 | Water source illegal activity recognition early warning method, server and storage medium |
US20230005257A1 (en) * | 2020-03-27 | 2023-01-05 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Illegal building identification method and apparatus, device, and storage medium |
EP3916629A4 (en) * | 2020-03-27 | 2022-05-11 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus and device for identifying illegal building, and storage medium |
WO2021189870A1 (en) * | 2020-03-27 | 2021-09-30 | 北京百度网讯科技有限公司 | Method, apparatus and device for identifying illegal building, and storage medium |
CN111563448B (en) * | 2020-04-30 | 2023-10-31 | 北京百度网讯科技有限公司 | Method and device for detecting illegal building, electronic equipment and storage medium |
CN111563448A (en) * | 2020-04-30 | 2020-08-21 | 北京百度网讯科技有限公司 | Method and device for detecting illegal building, electronic equipment and storage medium |
CN111882660A (en) * | 2020-07-23 | 2020-11-03 | 广联达科技股份有限公司 | Three-dimensional display method and three-dimensional display device based on CAD drawing |
CN112954226A (en) * | 2021-05-11 | 2021-06-11 | 江苏瞭望神州大数据科技有限公司 | Monitoring method and system for identifying construction site |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108805864A (en) | The acquisition methods and device of architecture against regulations object based on view data | |
US10509987B1 (en) | Learning method and learning device for object detector based on reconfigurable network for optimizing customers' requirements such as key performance index using target object estimating network and target object merging network, and testing method and testing device using the same | |
CN113362329B (en) | Method for training focus detection model and method for recognizing focus in image | |
CN113468967B (en) | Attention mechanism-based lane line detection method, attention mechanism-based lane line detection device, attention mechanism-based lane line detection equipment and attention mechanism-based lane line detection medium | |
CN114863368B (en) | Multi-scale target detection model and method for road damage detection | |
CN104700099A (en) | Method and device for recognizing traffic signs | |
US10402692B1 (en) | Learning method and learning device for fluctuation-robust object detector based on CNN using target object estimating network adaptable to customers' requirements such as key performance index, and testing device using the same | |
CN111767962B (en) | One-stage target detection method, system and device based on generation countermeasure network | |
CN112613375B (en) | Tire damage detection and identification method and equipment | |
CN109858547A (en) | A kind of object detection method and device based on BSSD | |
He et al. | A robust method for wheatear detection using UAV in natural scenes | |
CN108875780A (en) | The acquisition methods and device of difference object between image based on view data | |
CN115063454B (en) | Multi-target tracking matching method, device, terminal and storage medium | |
CN111340877A (en) | Vehicle positioning method and device | |
CN112686274A (en) | Target object detection method and device | |
CN115546705A (en) | Target identification method, terminal device and storage medium | |
CN115205855A (en) | Vehicle target identification method, device and equipment fusing multi-scale semantic information | |
Guan et al. | EARL: an elliptical distribution aided adaptive rotation label assignment for oriented object detection in remote sensing images | |
CN113505769A (en) | Target detection method and vehicle throwing and dripping identification method applying same | |
CN116895036A (en) | Deep learning-based farmland protection early warning method and device | |
CN116363532A (en) | Unmanned aerial vehicle image traffic target detection method based on attention mechanism and re-parameterization | |
CN112818837B (en) | Aerial photography vehicle weight recognition method based on attitude correction and difficult sample perception | |
CN115171079A (en) | Vehicle detection method based on night scene | |
CN114782983A (en) | Road scene pedestrian detection method based on improved feature pyramid and boundary loss | |
CN109376653B (en) | Method, apparatus, device and medium for locating vehicle |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |
|
RJ01 | Rejection of invention patent application after publication |