CN113345019B - Method, equipment and medium for measuring potential hazards of transmission line channel target - Google Patents

Method, equipment and medium for measuring potential hazards of transmission line channel target Download PDF

Info

Publication number
CN113345019B
CN113345019B CN202110643955.9A CN202110643955A CN113345019B CN 113345019 B CN113345019 B CN 113345019B CN 202110643955 A CN202110643955 A CN 202110643955A CN 113345019 B CN113345019 B CN 113345019B
Authority
CN
China
Prior art keywords
hidden danger
dimensional
data
position information
wire
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.)
Active
Application number
CN202110643955.9A
Other languages
Chinese (zh)
Other versions
CN113345019A (en
Inventor
刘伟
蔡富东
吕昌峰
刘焕云
郭国信
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.)
Shandong Senter Electronic Co Ltd
Original Assignee
Shandong Senter Electronic 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 Shandong Senter Electronic Co Ltd filed Critical Shandong Senter Electronic Co Ltd
Priority to CN202110643955.9A priority Critical patent/CN113345019B/en
Publication of CN113345019A publication Critical patent/CN113345019A/en
Application granted granted Critical
Publication of CN113345019B publication Critical patent/CN113345019B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/08—Systems determining position data of a target for measuring distance only
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
    • G01S17/894—3D imaging with simultaneous measurement of time-of-flight at a 2D array of receiver pixels, e.g. time-of-flight cameras or flash lidar
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/30181—Earth observation
    • G06T2207/30184—Infrastructure
    • 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
    • G06T2207/30244—Camera pose
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Electromagnetism (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Image Processing (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the specification discloses a method for measuring potential hazards of a transmission line channel target, which comprises the following steps: acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel, and acquiring two-dimensional position information of a hidden danger target according to a target segmentation network model; if the two-dimensional position information of the hidden danger target is in the preset channel three-dimensional protection area, mapping the two-dimensional position information of the hidden danger target into three-dimensional point cloud data through a preset ground data mapping model to obtain three-dimensional coordinate position information of the hidden danger target; and obtaining the distance information between the hidden danger target and the lead according to the three-dimensional coordinate position information of the hidden danger target and a preset lead data mapping model. The method comprehensively utilizes the dense information advantage of the two-dimensional image data and the precision advantage of the three-dimensional point cloud data, and provides more effective early warning information for the safety of the transmission line channel.

Description

Method, equipment and medium for measuring potential hazards of transmission line channel target
Technical Field
The specification relates to the technical field of transmission lines, in particular to a method, equipment and medium for measuring potential hazards of a transmission line channel.
Background
The transmission line channels are hundreds of times long, the environment is complicated, the transmission line channels are possibly influenced by external environment factors at all times, and potential safety hazards appear. Therefore, in the operation and maintenance of the power transmission line, monitoring the surrounding environment of the power transmission line is an important task, such as monitoring whether the power transmission line has ultrahigh trees, and environmental hidden troubles affecting the safety of the power transmission line, such as illegal construction, illegal construction and the like. Meanwhile, along with the acceleration of the urban process, the construction of the machinery is more and more, and when the shortest distance of the machinery during construction is smaller than the safety distance of a power transmission line, the discharge is likely to occur, so that the safety problem of casualties or tripping is caused. In addition, large construction machines, particularly cranes, cement pump trucks in the raised or extended state, easily hang up wires during operation, creating a significant threat to the wires. Therefore, in order to ensure the transmission safety of the transmission line channel, it is necessary to identify these hidden dangers and to quantitatively and qualitatively determine the threat level of the wires.
In the prior art, an unmanned aerial vehicle shooting mode and a fixed-point monitoring mode are mainly adopted to detect hidden danger and judge the dangerous degree of a power transmission line channel. However, the manner in which unmanned aerial vehicle patrols and photographs is susceptible to flight factors such as: the influence of radio environment, meteorological environment, geographical environment, and unmanned aerial vehicle patrol and shoot single collection quantity is limited, and operation cost is high, gathers the inefficiency, is not fit for the transmission line passageway monitoring scene of the faster scene of hidden danger target update. In the current distance measurement technology, a monitoring camera is installed on a power transmission line, regular photographing is carried out for inspection, and hidden danger detection is carried out by using an image analysis service on an edge equipment end or a server, so that a monitoring center person can detect a picture of a hidden danger target and observe state information of hidden danger. However, to obtain the information of hidden trouble and wire distance, it is necessary to combine with ranging algorithm to perform post calculation to obtain the information, and the calculation process is very complex.
Therefore, there is a need for a distance measurement method for potential transmission line targets that is less costly and more convenient and efficient.
Disclosure of Invention
One or more embodiments of the present disclosure provide a method for ranging potential hazards of a transmission line channel, which is used to solve the following technical problems: how to provide a distance measuring method for hidden danger targets of a power transmission line, which is lower in cost and more convenient and effective.
One or more embodiments of the present disclosure adopt the following technical solutions:
one or more embodiments of the present disclosure provide a method for ranging potential hazards of a transmission line channel, where the method includes:
acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image is obtained by shooting with a monocular camera;
detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target at least includes: the position information of the hidden danger target and the segmentation contour of the hidden danger target;
if the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets;
Mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation;
acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data.
Optionally, in one or more embodiments of the present disclosure, before the detecting the hidden danger target by the two-dimensional image data through the preset target recognition segmentation network model, the method further includes:
collecting the potential risk samples of the transmission line channel to construct a sample set of potential risk of the transmission line channel;
constructing an initial target recognition segmentation network model, and training the initial target recognition segmentation network model according to a sample set of hidden danger of the transmission line channel to train a target recognition segmentation network model meeting the conditions;
The potential risk sample of the transmission line channel at least comprises any one or more of the following: large construction machinery, towers, tower cranes, trees, and buildings.
Optionally, in one or more embodiments of the present disclosure, before determining that the hidden danger target is in the pre-established channel stereoscopic protection zone according to the location information of the hidden danger target, the method further includes:
fitting discrete points of the wires in the three-dimensional point cloud data into a three-dimensional curve, and establishing a corresponding wire data mapping model according to the three-dimensional curve; wherein the wire is an edge wire of the transmission line channel;
acquiring three-dimensional coordinate position information of the wire according to the wire data mapping model;
and generating a channel three-dimensional protection area of the transmission line channel according to the three-dimensional coordinate position information of the wire and the voltage class safety distance of the transmission line channel.
Optionally, in one or more embodiments of the present disclosure, after determining the location information of the segmented hidden danger target, the method further includes:
acquiring historical two-dimensional image data shot by the monocular camera;
acquiring historical segmentation image data consistent with the position information in the historical two-dimensional image data;
Comparing and analyzing the history segmentation image data with the data information of the hidden danger targets;
and if the difference between the data information of the hidden danger target and the historical segmentation image data exceeds a preset rule, updating the three-dimensional point cloud data.
Optionally, in one or more embodiments of the present disclosure, before the mapping, by using a pre-established ground data mapping model, the method further includes:
calibrating a monocular camera to obtain internal parameters of the monocular camera;
adjusting the view angle of the three-dimensional point cloud data so as to enable the three-dimensional point cloud data to coincide with the two-dimensional image data acquired by the monocular camera;
taking the coordinates of the three-dimensional point cloud data as preset reference coordinates, and combining the three-dimensional point cloud data with the pixel coordinates of the monocular camera through a camera pose estimation algorithm to obtain the three-dimensional point cloud data and external parameters of the monocular camera;
and obtaining a second space mapping conversion relation between each data in the two-dimensional image data and the three-dimensional point cloud data through joint calculation of the internal parameters and the external parameters so as to establish a ground data mapping model according to the second space mapping conversion relation.
Optionally, in one or more embodiments of the present disclosure, the obtaining the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model specifically includes:
acquiring three-dimensional coordinate position information of a wire in three-dimensional point cloud data according to a wire data mapping model;
calculating the distance between the three-dimensional coordinate position information of the highest point of the hidden danger target and the coordinate position information of the lead in the three-dimensional point cloud data to obtain the actual distance between the hidden danger target and the lead
Optionally, in one or more embodiments of the present disclosure, after the obtaining the distance between the hidden danger target and the wire based on the coordinate position information in the three-dimensional point cloud data and the pre-established wire model, the method further includes:
determining the shortest distance between the hidden danger targets and each point in the lead according to the actual distance between the hidden danger targets and each point in the lead;
outputting threat levels of the hidden danger targets according to the shortest distance and the clearance distances preset by different voltage levels of the power transmission line; wherein the threat level is set with a plurality of levels from high to low.
Optionally, in one or more embodiments of the present disclosure, after determining the shortest distance from the actual distances between the hidden danger target and each point in the wire, the method further includes:
mapping wires in the three-dimensional point cloud data through a wire mapping conversion relation to obtain a third space mapping conversion relation between the three-dimensional coordinate position information of the wires and the two-dimensional image data;
and mapping the lead points corresponding to the shortest distance into two-dimensional image data according to the third space mapping conversion relation, and marking the lead points in the two-dimensional image.
One or more embodiments of the present specification provide a power transmission line channel hidden danger target ranging apparatus, including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image is obtained by shooting with a monocular camera;
Detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target includes: the position information of the hidden danger target and the segmentation contour of the hidden danger target;
if the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets;
mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation;
acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data.
One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to:
acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image is obtained by shooting with a monocular camera;
detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target at least includes: the position information of the hidden danger target and the segmentation contour of the hidden danger target;
if the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets;
mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation;
Acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data.
The above-mentioned at least one technical scheme that this description embodiment adopted can reach following beneficial effect: the method for distance measurement between the hidden danger targets and the wires is optimized by utilizing the dense information advantage of the two-dimensional image data shot by the monocular camera and the precision advantage of the three-dimensional point cloud data. The conversion between the two-dimensional image data and the three-dimensional laser point cloud data is realized through the constructed second space mapping conversion relation, so that the distance information between the hidden danger target and the lead can be effectively judged, and the distance measurement function of the hidden danger target is realized. The cost of potential hazard target monitoring of the power transmission line is reduced, and the effectiveness of potential hazard data is improved. And by judging the dangerous grade of the hidden danger target, more effective early warning information is provided for the safety of the transmission line channel, and the probability of false alarm is greatly reduced.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some of the embodiments described in the present description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
Fig. 1 is a schematic flow chart of a method for measuring potential hazards of a transmission line channel in a target ranging method according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of a hidden danger target in an application scenario provided in an embodiment of the present disclosure;
fig. 3 is a schematic flow chart of a monocular camera and laser point cloud combined calibration provided in an embodiment of the present disclosure;
fig. 4 (a) is a schematic diagram of a two-dimensional image data perspective in an application scenario according to an embodiment of the present disclosure;
fig. 4 (b) is a schematic diagram of a three-dimensional point cloud data perspective in an application scenario according to an embodiment of the present disclosure;
fig. 5 is a schematic conversion diagram of a second spatial mapping conversion relationship according to an embodiment of the present disclosure;
fig. 6 is a schematic diagram of an implementation flow of potential energy source target ranging for a transmission line channel according to an embodiment of the present disclosure;
fig. 7 is a schematic diagram of an internal structure of a power transmission line channel hidden danger target ranging device according to an embodiment of the present disclosure;
fig. 8 is a schematic diagram of an internal structure of a nonvolatile storage medium according to an embodiment of the present disclosure.
Detailed Description
The embodiment of the specification provides a method, equipment and medium for measuring potential hazards of a transmission line channel.
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
In the operation and maintenance of a power transmission line, it is an important task to monitor the environment around the power transmission line. The traditional environment monitoring is generally carried out by adopting a manual inspection mode, and the potential hazard distance identification and the dangerous degree judgment of the transmission line channel are realized by adopting unmanned aerial vehicle shooting and fixed-point monitoring modes.
Aiming at the existing inspection mode, the problems of large workload, wide range, high difficulty and the like of manual inspection are easy to cause the phenomenon that inspection is not in place or does not reach the standard. And the period of manual inspection is long, so that the problem of supervision blank exists. While the way unmanned aerial vehicle patrols and examines the shooting receives for example: the influence of flight environment factors such as radio environment, meteorological environment, geographical environment and the like is excessive in uncontrollable factors. And secondly, the unmanned aerial vehicle inspection mode has the advantages of limited data volume, low collection effectiveness and high cost. And the quality of the photo needs to be checked after acquisition, when the condition of overexposure or underexposure exists, the supplementary shooting needs to be carried out, the data measurement is carried out by utilizing 3D software through the later three-dimensional reconstruction, and the ranging process and the steps are quite complex.
The current method for acquiring distance information in a power transmission line scene is mainly divided into two types, namely passive distance measurement sensing and active distance measurement sensing. The passive ranging sensing is mainly based on a visual mode, and one is a monocular ranging algorithm which relies on a specific scale to calculate target depth information, has poor precision, is easy to be interfered by the outside and has poor robustness; the other is a multi-visual distance algorithm, which is represented by a binocular distance algorithm, and the algorithm is not dependent on a specific scale, but is limited by hardware, the distance measurement range is generally within 20m, the accuracy is influenced by hardware equipment, and the parallax map obtained by the stereo matching algorithm can obtain the approximate three-dimensional information of a scene, but the parallax of part of pixel points has larger error.
The specification provides a method for measuring the distance of potential hazards of a transmission line channel target in order to solve the problems. Aiming at the camera equipment arranged on the monitoring terminal, the method reduces the data error in the hidden danger target ranging process and improves the effectiveness of hidden danger target data through the dense information advantage of the two-dimensional image data and the laser point cloud precision advantage. And obtaining a second space mapping conversion relation between the three-dimensional point cloud data and the two-dimensional image data by jointly calibrating the two-dimensional point cloud data and the two-dimensional image data. And a three-dimensional protection area of the transmission line channel is established through the second space mapping conversion relation, and the three-dimensional point cloud data is updated according to the type of the hidden danger target and the distribution of the hidden danger target, so that the effectiveness of the three-dimensional point cloud data is ensured. In addition, the hidden danger targets are positioned in the two-dimensional image data, so that the dependence on the three-dimensional point cloud can be greatly reduced, the measurement accuracy is ensured, and meanwhile, the cost in the measurement process is effectively reduced. And judging the distance information between the hidden danger target and the lead in the three-dimensional space, and omitting the process of post calculation processing. The method improves the efficiency and effectiveness of potential targets detection and ranging of the transmission line channel, provides safe and effective early warning information for the transmission line channel, and reduces the detection cost and human resources.
One or more embodiments of the present disclosure may perform the following steps by a server built into a transmission line channel hidden danger target ranging system.
The technical scheme provided in the specification is described below with reference to the accompanying drawings.
As shown in fig. 1, fig. 1 is a schematic flow chart of a method for measuring distance of a hidden danger target of a transmission line channel according to one or more embodiments of the present disclosure, where steps in the method may be executed by a corresponding distance measuring server.
The flow in fig. 1 may include the steps of:
s101: acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image data is obtained by photographing with a monocular camera.
The server acquires two-dimensional image data of the transmission line channel shot by the monocular camera based on wired transmission and/or wireless transmission, and acquires three-dimensional point cloud data acquired by the three-dimensional laser scanner. And carrying out subsequent potential hazard target ranging of the transmission line channel according to the two-dimensional image data and the data of the potential hazard targets contained in the three-dimensional point cloud data.
The following description is needed: point cloud data (point cloud data) refers to a set of vectors in a three-dimensional coordinate system. The scan data is recorded in the form of dots, each dot containing three-dimensional coordinates, some possibly containing color information or reflected intensity information. And the point cloud data set is a three-dimensional data and may be referred to as three-dimensional point cloud data. And the three-dimensional point cloud data has good environmental robustness, and the acquired data has high precision. However, the three-dimensional point cloud data acquired by the laser scanner is often excessively discretized to the environment, and the acquired data has large granularity and limited information quantity. The acquisition cost of the three-dimensional point cloud data is higher, and the acquisition cost of the information density contained in the two-dimensional image data is relatively reduced, so that the dependence on the three-dimensional point cloud data can be reduced by carrying out joint analysis on the two-dimensional image data and the three-dimensional point cloud data, and the cost in the monitoring process can be reduced while the effectiveness and the accuracy of the data in the monitoring process of the power transmission line are improved.
S102: detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target at least includes: and the position information of the hidden danger target and the segmentation contour of the hidden danger target.
In one or more embodiments of the present disclosure, before the detecting the hidden danger target by the two-dimensional image data through the preset target recognition segmentation network model, the method further includes:
collecting the potential risk samples of the transmission line channel to construct a sample set of potential risk of the transmission line channel;
constructing an initial target recognition segmentation network model, and training the initial target recognition segmentation network model according to a sample set of hidden danger of the transmission line channel to train a target recognition segmentation network model meeting the conditions;
the potential risk sample of the transmission line channel at least comprises any one or more of the following: large construction machinery, towers, tower cranes, trees, and buildings.
And collecting hidden danger samples of the transmission line channel through historical data stored in the Internet or a memory thereof. After a sufficient number of samples capable of guaranteeing the accuracy of the model training result are collected, a Mask-RCNN or other example segmentation algorithm model can be adopted to construct a target recognition network model. Training the target recognition network model according to the collected samples to obtain the target recognition segmentation network model meeting the conditions.
The following description is needed: because of the development of modern industrial parks and the acceleration of urban processes, large-scale machines such as cranes, cement pump trucks, excavators and the like may have the phenomenon of hanging up wires in the arm lifting process or the digging process, thereby damaging electric power facilities such as power transmission lines and the like. Secondly, because of the discharge property of the power transmission line, the power transmission line and personal safety can be influenced by the excessively high trees in the illegally built building smaller than the safety range of the power transmission line. Therefore, the potential risk sample of the transmission line channel should at least include one or more of the following: large construction machinery, towers, tower cranes, trees, and buildings.
It should also be noted that Mask-RCNN obtained by the Faster R-CNN extension extends the classification and regression tasks. And each segmentation task aiming at the region of interest (region of interest, abbreviated as ROI) is added in the learning model so as to decouple the segmentation task and the classification task and output the position information of the hidden danger target, the segmentation contour of the hidden danger target and the target type of the hidden danger target. Compared with other example segmentation algorithms which carry out segmentation and then classification, the method can simply and efficiently obtain the segmentation result and the classification result. The type of the hidden danger target is shown in fig. 2. The type of hidden danger target in the power transmission line scene in one or more embodiments of the present disclosure may be the type of suspension in hidden danger target 1 in fig. 2: crane, etc., can also be the ground type in hidden danger target 2, hidden danger target 3: forklift trucks, excavators, and the like.
S103: if the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets.
In one or more embodiments of the present disclosure, before the determining that the hidden danger target is in the pre-established channel stereoscopic protection zone according to the position information of the hidden danger target, the method further includes:
fitting discrete points of the wires in the three-dimensional point cloud data into a three-dimensional curve, and establishing a corresponding wire data mapping model according to the three-dimensional curve; wherein the wire is an edge wire of the transmission line channel;
acquiring three-dimensional coordinate position information of the wire according to the wire data mapping model;
and generating a channel three-dimensional protection area of the transmission line channel according to the three-dimensional coordinate position information of the wire and the voltage class safety distance of the transmission line channel.
In one or more embodiments of the present disclosure, after determining the location information of the segmented hidden danger target, the method further includes:
acquiring historical two-dimensional image data shot by the monocular camera;
Acquiring historical segmentation image data consistent with the position information in the historical two-dimensional image data;
comparing and analyzing the history segmentation image data with the data information of the hidden danger targets;
and if the difference between the data information of the hidden danger target and the historical segmentation image data exceeds a preset rule, updating the three-dimensional point cloud data.
In one or more embodiments of the present disclosure, a moving least square method may be used to fit discrete points of an edge wire to a three-dimensional curve, and a corresponding wire data mapping model may be established according to the three-dimensional curve of the edge wire. And obtaining the three-dimensional coordinate position information of the edge wire after fitting according to the wire data mapping model. Because of the high voltage characteristics in overhead transmission lines, the conductors should be kept a safe distance from other objects in the building to ensure proper operation of the transmission lines and safety of the transmission lines. For example: when the 220kV overhead transmission line spans a building, the minimum vertical distance between the wire and the building is not less than 6 meters; when the 220kV overhead transmission line is adjacent to a building, the minimum clearance distance between the wire and any point of the building is not less than 5 meters. Therefore, a channel three-dimensional protection area of the power transmission line is generated according to the three-dimensional coordinate position information of the edge wire and combining safety distances specified by different voltage levels so as to define the safety range of the power transmission line channel.
The process of fitting the discrete points of the edge wire into a three-dimensional curve can be performed by adopting interpolation methods such as RBF (Radial Basis Function) -based curve fitting and cubic spline curve fitting.
If the hidden danger target is located in the pre-established channel three-dimensional protection area according to the position information of the hidden danger target obtained by the two-dimensional image data, the hidden danger target is safe to the wires in the power transmission line. At this time, the hidden danger target needs to be segmented based on the segmentation contour of the hidden danger target obtained by the target segmentation network model in S102, so as to determine the two-dimensional position information of the segmented hidden danger target and the target type of the hidden danger target.
Because of various movable unstable target hidden troubles such as forklift in the scene of the transmission line channel, the three-dimensional laser point cloud data needs to be updated with a fixed period. The cost of three-dimensional point cloud acquisition is relatively high relative to two-dimensional image data. Therefore, in the specification, hidden danger target positioning and segmentation is placed in two-dimensional image data, so that dependence on three-dimensional point cloud can be greatly reduced, and detection cost can be effectively reduced while accuracy is ensured. The specific implementation manner of the three-dimensional point cloud data updating can be as follows:
And extracting historical two-dimensional image data corresponding to the two-dimensional image data through the monocular camera, and if the historical two-dimensional image data are compared with the data information of the hidden danger targets after being analyzed, updating the current three-dimensional point cloud data to ensure the accuracy and the effectiveness of the detection result. Wherein the preset rules comprise: (1) And if the difference between the distribution ratio of the hidden danger targets in the historical two-dimensional data and the distribution ratio of the hidden danger targets contained in the current hidden danger target data exceeds 5%, the three-dimensional point cloud data needs to be updated. (2) Because the large construction machinery has mobility, aiming at a hidden danger target 1 with a ground shielding target as shown in fig. 2, the hidden danger that the shielding of a house possibly changes from the hidden danger on the ground to the hidden danger of a hanging type exists. The lifting arm process is likely to hang off the edge wire, so that the damage is strong, and after the type of the hidden danger target is changed into a hanging type as shown by the hidden danger target 1, the data information of the current hidden danger target and the type of the target hidden danger in the history segmentation image data are changed, and the three-dimensional point cloud data need to be updated again so as to ensure the safety of the power transmission line. (3) The height and the volume of a building are changed in the illegal building construction process, and when the distribution of hidden danger targets and the occupation ratio of the hidden danger targets in an image are detected to be changed greatly, the point cloud data are required to be updated. If the difference between the data of the hidden danger target and the historical two-dimensional image data information does not exceed the preset rule, namely the difference is negligible, the effectiveness of subsequent analysis is not affected. The three-dimensional point cloud data does not need to be updated so as to save the cost in the process of acquiring the point cloud data.
S104: mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; and converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation.
In one or more embodiments of the present disclosure, before the mapping, by using a pre-established ground data mapping model, the method further includes:
calibrating a monocular camera to obtain internal parameters of the monocular camera;
adjusting the view angle of the three-dimensional point cloud data so as to enable the three-dimensional point cloud data to coincide with the two-dimensional image data acquired by the monocular camera;
taking the coordinates of the three-dimensional point cloud data as preset reference coordinates, and combining the three-dimensional point cloud data with the pixel coordinates of the monocular camera through a camera pose estimation algorithm to obtain the three-dimensional point cloud data and external parameters of the monocular camera;
and obtaining a second space mapping conversion relation between each data in the two-dimensional image data and the three-dimensional point cloud data through joint calculation of the internal parameters and the external parameters so as to establish a ground data mapping model according to the second space mapping conversion relation.
The data acquired by the three-dimensional point cloud has larger discreteness and large granularity. According to the method, the internal parameters of the camera are obtained through monocular camera calibration, and the relation between the two-dimensional plane pixel coordinates and the three-dimensional world coordinates is obtained, so that the three-dimensional reconstruction is performed by utilizing the information consistency of the two-dimensional image data. On the basis of the advantage of guaranteeing the precision of the three-dimensional point cloud data, the characteristic of large discreteness of the three-dimensional point cloud data is made up, so that the data for carrying out hidden danger target ranging is complete, effective and high in precision. The joint calibration process of the two-dimensional image data and the three-dimensional point cloud data is shown in fig. 3. As can be seen from fig. 3, the monocular camera needs to perform calibration to obtain two-dimensional image data of the power transmission channel, and performs joint calibration on the two-dimensional image data and three-dimensional point cloud data of the power transmission channel obtained by the three-dimensional point cloud, so as to implement modeling of a ground data mapping model and modeling of a wire data mapping model on the basis of joint calibration. After the ground data mapping model is constructed, the mapping conversion relation from the two-dimensional image data of the ground data to the three-dimensional point cloud data can be obtained. Meanwhile, a channel three-dimensional protection area can be constructed according to the wire data mapping model.
First, in the case of calibrating a monocular camera, there are various calibration methods, for example: zhang Zhengyou, using opencv and other modes can realize monocular calibration. In one or more embodiments of the present application, a Zhang Zhengyou calibration method is selected to calibrate the camera, and the Zhang Zhengyou calibration algorithm is used to obtain internal parameters of the camera: f (f) x 、f y C is the focal length parameter of the camera x 、c y Is a camera optical center parameter. And then reading the three-dimensional point cloud data, and adjusting the view angle of the three-dimensional point cloud data by taking the view angle in the two-dimensional image data as a reference. And selecting points with clear and obvious characteristics in the two-dimensional image data as characteristic points, and finding out the positions of the corresponding characteristic points in the three-dimensional point cloud data. Fig. 4 (a) is two-dimensional image data under an embodiment application scene, and fig. 4 (b) is a three-dimensional point cloud data image under an embodiment application scene, which are the same transmission line scene under a unified viewing angle. As can be seen from fig. 4 (a) and fig. 4 (b), the feature points selected in the scene are point 1, point 2, point 3, and point 4, and the feature points in the two-dimensional image data are the same points in one-to-one correspondence with the points in the three-dimensional point cloud data.
The following description is needed: as long as it is determined that the points in the two-dimensional image data and the points in the three-dimensional point cloud data are the same points, the points may be used as the feature points, and the position with the large turning degree may be preferentially selected as the feature points. In order to ensure the accuracy of the hidden danger target ranging, the point correspondence of the selected characteristic points is greater than or equal to 4 groups. After the visual angle is adjusted, the coordinates of the three-dimensional point cloud are used as preset reference coordinates to be input. In one or more embodiments of the present disclosure, world coordinates are selected as preset reference coordinates. After the coordinates of the three-dimensional point cloud are input as world coordinates, the three-dimensional point cloud coordinates and the pixel coordinates of the monocular camera can be combined through a camera pose estimation algorithm, so that external parameters of the three-dimensional point cloud and the monocular camera are obtained: the rotation matrix R and the translation matrix t. And performing joint calculation on the internal parameters and the external parameters obtained after calibration according to the Zhang Zhengyou algorithm to obtain a second space mapping conversion relation between the three-dimensional point cloud data and the two-dimensional image data, so as to obtain a ground data mapping model and a wire data mapping model according to the second space mapping conversion relation, and a first space mapping conversion relation and a third space mapping conversion relation which correspond to the two models respectively.
As shown in fig. 4 (a) and fig. 4 (b), four pairs of non-coplanar 3D and 2D feature point pairs are provided, and based on the 4 pairs of feature point pairs, the world coordinate system and the camera coordinate system can be converted to obtain a second spatial mapping conversion relationship between the three-dimensional point cloud data and the two-dimensional image data through Zhang Zhengyou joint calibration and camera pose estimation described in fig. 5. The conversion process of the second spatial mapping conversion relationship described in fig. 5 is as follows:
the origin coordinate system of the three-dimensional point cloud is taken as a unified world coordinate system and is defined as X w ，Y w ，Z w The unit is a length unit. The camera coordinate system takes the optical center as the origin of the camera coordinate system and takes the X direction and the y direction parallel to the two-dimensional image data as the X C Axes and Y C A shaft. And Z is C The axis being parallel to the optical axis, X C 、Y C 、Z C Perpendicular to each other, the units are units of length. The physical coordinate system of the image takes the intersection point of the main optical axis and the image plane as the origin of coordinates, and the x direction and the y direction are shown as the figure, and the unit is the length unit. The image pixel coordinate system takes the vertex of the image as the origin of coordinates, the u direction and the v direction are parallel to the x direction and the y direction, and the units are calculated in pixels.
World coordinate system (X) w ，Y w ，Z w ) Through the external parameters determined in the above process: the rotation matrix R and the translation matrix t are subjected to affine transformation Conversion to camera coordinate system (X C 、Y C 、Z C ). After conversion from the world coordinate system to the camera coordinate system, the three-dimensional image is converted to a two-dimensional image to an image coordinate system (x, y) from the camera coordinate system via the 3D-2D perspective projection relationship determined by the camera pose algorithm. The image coordinate system (x, y) is converted into the pixel coordinate system (u, v) by performing proper translation transformation on the part with the non-coincident coordinates through the adjustment of the internal parameters until the coordinates are consistent. The conversion from the world coordinate system to the image coordinate system is completed. Because the three-dimensional point cloud data is used as a preset world coordinate system, the joint calibration between the two-dimensional image data and the three-dimensional point cloud data is realized, and the three-dimensional image data (X w ，Y w ，Z w ) And two-dimensional image data (u, v).
Specifically, the second spatial mapping conversion relationship is obtained by calculating the external parameter and the internal parameter as follows:
wherein R is a rotation matrix, t is a translation matrix, and the two matrices form a 3×4 matrix, namely an external parameter matrix of the camera. f (f) x ，f y ，c x ，c y Is an internal parameter of the camera.
In the same manner as in the generation of the wire data map model described in S103, discrete points on the ground in the three-dimensional point cloud data are fitted into a three-dimensional curved surface in advance. Because the second space mapping conversion relation can obtain the conversion relation between each data in the two-dimensional image data and the three-dimensional point cloud data. Therefore, according to the three-dimensional curved surface, a corresponding ground data mapping model can be established so as to map the ground data in the three-dimensional point cloud data according to the ground data mapping model, and a first space mapping conversion relation between the ground data and the two-dimensional image data is obtained. And converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to a first space mapping conversion relation, and laying a foundation for determining the distance between the hidden danger targets and the wires in a three-dimensional space. By performing space mapping conversion on the three-dimensional point cloud data and the two-dimensional image data, coordinate position information of each data in the three-dimensional point cloud data can be simply obtained. The complex steps of carrying out data analysis and measurement by utilizing software after carrying out the post three-dimensional reconstruction on the underexposed photo in the traditional unmanned aerial vehicle ranging process are avoided.
S105: acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data.
In one or more embodiments of the present disclosure, the obtaining the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model specifically includes:
acquiring three-dimensional coordinate position information of a wire in three-dimensional point cloud data according to a wire data mapping model;
calculating the distance between the three-dimensional coordinate position information of the highest point of the hidden danger target and the coordinate position information of the lead in the three-dimensional point cloud data to obtain the actual distance between the hidden danger target and the lead
In one or more embodiments of the present disclosure, after the obtaining the distance between the hidden danger target and the wire based on the coordinate position information in the three-dimensional point cloud data and the pre-established wire model, the method further includes:
obtaining the shortest distance between the hidden danger target and each point in the lead according to the actual distance between the hidden danger target and each point in the lead;
Outputting threat levels of the hidden danger targets according to the shortest distance and the clearance distances preset by different voltage levels of the power transmission line; wherein the threat level is set with a plurality of levels from high to low.
In one or more embodiments of the present disclosure, if it is determined that the hidden danger target is outside the pre-established channel stereoscopic protection area according to the location information of the hidden danger target, the method further includes: and outputting the threat level of the lowest level according to the hidden danger target.
In one or more embodiments of the present disclosure, after the obtaining the shortest distance from the actual distances between the hidden danger target and each point in the wire, the method further includes:
mapping wires in the three-dimensional point cloud data through a wire data mapping model to obtain a third space mapping conversion relation between the three-dimensional coordinate position information of the wires and the two-dimensional image data;
and mapping the lead points corresponding to the shortest distance into two-dimensional image data according to the third space mapping conversion relation, and marking the lead points in the two-dimensional image.
And (3) acquiring three-dimensional coordinate position information of the wire according to the pre-established wire data mapping model recorded in the step (S103), and calculating the distance between the three-dimensional position information of the highest point of the hidden danger target and the wire to obtain the distance between the hidden danger target and the wire in the power transmission line. And judging the shortest distance and the clearance distance preset by different voltage levels in a combined way to output the threat level of the hidden danger target. The voltage class of different transmission lines is different, so threat classes can be divided into: emergency, severe, general. Taking a 110KV power transmission line as an example, if the shortest distance between a hidden danger target and a wire is more than 10 meters, the hidden danger target and the wire are of a general level; if the shortest distance between the hidden danger target and the lead is between 6 and 10 meters, the threat level is a severity level; if the shortest distance between the hidden danger target and the lead is less than 6 meters, the threat level output is urgent. And secondly, if the hidden danger target is determined to be outside the pre-established channel three-dimensional protection area according to the position information of the hidden danger target, the threat level of the hidden danger target can be directly output to be general.
And simultaneously, mapping the fitted three-dimensional wire in the three-dimensional point cloud data by a preset wire data mapping model to acquire a third space mapping conversion relation between the three-dimensional coordinate position information of the wire and the two-dimensional image data. According to the third space mapping conversion relation, the wire point corresponding to the shortest distance between the hidden danger target and the wire can be mapped into the two-dimensional image coordinates so as to mark and warn the wire point in the two-dimensional image. According to one or more embodiments of the present disclosure, by further judging the risk level of the hidden danger target, effective early warning information is provided for the safety of the transmission line channel, and the effectiveness of the monitoring result is improved by combining the three-dimensional point cloud data and the two-dimensional image data, so that the probability of false alarm is greatly reduced.
Fig. 6 is a flowchart of a method for measuring distance of hidden danger targets in a transmission line channel according to one or more embodiments of the present disclosure. As can be seen from fig. 6, in one or more embodiments, the present disclosure needs to acquire two-dimensional image data in a power transmission line channel scene when detecting a hidden danger target. Detecting the position information of the hidden danger target according to the two-dimensional image data, and if the hidden danger target is determined to be in the preset three-dimensional channel protection area, segmenting the hidden danger target to obtain contour segmentation data of the hidden danger target. And judging whether the three-dimensional point cloud data need to be updated according to the contour segmentation data of the hidden danger targets and the distribution positions of hidden danger points. And if the three-dimensional point cloud data is required to be updated, starting to acquire the updated three-dimensional point cloud data, and updating the ground data mapping model to obtain a second space mapping conversion relation from the two-dimensional image data to the three-dimensional point cloud data. And calculating the distance between the hidden danger target and the wire in the three-dimensional space, and obtaining the threat level of the hidden danger target according to the distance. If the position information of the hidden danger target is detected according to the two-dimensional image data, and the hidden danger target is determined not to be in the preset three-dimensional channel protection area, the threat level of the hidden danger target is directly output to be general.
Fig. 7 is a schematic internal structure diagram of a power transmission line channel hidden danger target ranging method device according to one or more embodiments of the present disclosure.
As can be seen from fig. 7, the apparatus comprises:
at least one processor 701; the method comprises the steps of,
a memory 702 communicatively coupled to the at least one processor 701; wherein,,
the memory 702 stores instructions executable by the at least one processor 701 to enable the at least one processor 701 to:
acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image is obtained by shooting with a monocular camera;
detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target at least includes: the position information of the hidden danger target and the segmentation contour of the hidden danger target;
if the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets;
Mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation;
acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data.
As shown in fig. 8, is a non-volatile storage medium provided in one or more embodiments of the present description.
As shown in fig. 8, a nonvolatile storage medium stores computer executable instructions 801, the executable instructions 801 comprising:
acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image is obtained by shooting with a monocular camera;
detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target at least includes: the position information of the hidden danger target and the segmentation contour of the hidden danger target;
If the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets;
mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation;
acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.

Claims (8)

1. The method for measuring the potential hazards of the transmission line channel targets is characterized by comprising the following steps:
acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image is obtained by shooting with a monocular camera;
Detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target at least includes: the position information of the hidden danger target and the segmentation contour of the hidden danger target;
if the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets;
mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation;
acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data; the wire data mapping model is obtained by fitting discrete points of wires in the three-dimensional point cloud data into a three-dimensional curve so as to establish according to the three-dimensional curve; the wire is an edge wire of the transmission line channel;
After the position information of the segmented hidden danger target is determined, the method further comprises the following steps:
acquiring historical two-dimensional image data shot by the monocular camera;
acquiring historical segmentation image data consistent with the position information in the historical two-dimensional image data;
comparing and analyzing the history segmentation image data with the data information of the hidden danger targets;
if the difference between the data information of the hidden danger targets and the historical segmentation image data exceeds a preset rule, updating the three-dimensional point cloud data;
before the hidden danger target is determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger target, the method further comprises:
acquiring three-dimensional coordinate position information of the wire according to the wire data mapping model;
and generating a channel three-dimensional protection area of the transmission line channel according to the safety distance corresponding to the corresponding voltage level of the transmission line channel and the three-dimensional coordinate position information of the wire.
2. The method for measuring potential targets of transmission line channels according to claim 1, wherein before the potential targets are detected on the two-dimensional image data by using a preset target recognition and segmentation network model, the method further comprises:
Collecting the potential risk samples of the transmission line channel to construct a sample set of potential risk of the transmission line channel;
constructing an initial target recognition segmentation network model, and training the initial target recognition segmentation network model according to a sample set of hidden danger of the transmission line channel to train a target recognition segmentation network model meeting the conditions;
the transmission line channel hidden trouble sample comprises one or more of the following: large construction machinery, towers, tower cranes, trees, and buildings.
3. The method for ranging hidden danger targets of a transmission line channel according to claim 1, wherein before mapping the ground discrete points in the three-dimensional point cloud data by using a pre-established ground data mapping model, the method further comprises:
calibrating a monocular camera to obtain internal parameters of the monocular camera;
adjusting the view angle of the three-dimensional point cloud data so as to enable the three-dimensional point cloud data to coincide with the two-dimensional image data acquired by the monocular camera;
taking the coordinates of the three-dimensional point cloud data as preset reference coordinates, and combining the three-dimensional point cloud data with the pixel coordinates of the monocular camera through a camera pose estimation algorithm to obtain the three-dimensional point cloud data and external parameters of the monocular camera;
And obtaining a second space mapping conversion relation between each data in the two-dimensional image data and the three-dimensional point cloud data through joint calculation of the internal parameters and the external parameters so as to establish a ground data mapping model according to the second space mapping conversion relation.
4. The method for measuring the distance between the hidden danger target and the wire according to claim 1, wherein the obtaining the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model specifically comprises:
acquiring three-dimensional coordinate position information of a wire in three-dimensional point cloud data according to a wire data mapping model;
and calculating the distance between the three-dimensional coordinate position information of the highest point of the hidden danger target and the coordinate position information of the lead in the three-dimensional point cloud data to obtain the actual distance between the hidden danger target and the lead.
5. The method for ranging hidden danger targets of a power transmission line channel according to claim 4, wherein after the actual distance between the hidden danger targets and the wires is obtained based on the three-dimensional coordinate position information of the hidden danger targets and a pre-established wire data mapping model, the method further comprises:
Determining the shortest distance between the hidden danger targets and each point in the lead according to the actual distance between the hidden danger targets and each point in the lead;
and outputting threat levels of the hidden danger targets according to the shortest distance and the clearance distances preset by different voltage levels of the power transmission line.
6. The method for measuring the distance of potential targets in a power transmission line channel according to claim 5, wherein after determining the shortest distance from the actual distances between the potential targets and each point in the wire, the method further comprises:
mapping the fitted three-dimensional wire in the three-dimensional point cloud data through the wire data mapping model to obtain a third space mapping conversion relation between the three-dimensional coordinate position information of the wire and the two-dimensional image data;
and mapping the lead points corresponding to the shortest distance into two-dimensional image data according to the third space mapping conversion relation, and marking the lead points in the two-dimensional image.
7. A transmission line channel hidden danger target ranging apparatus, the apparatus comprising: at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
The memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image is obtained by shooting with a monocular camera;
detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target at least includes: the position information of the hidden danger target and the segmentation contour of the hidden danger target;
if the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets;
mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation;
Acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data; the wire data mapping model is obtained by fitting discrete points of wires in the three-dimensional point cloud data into a three-dimensional curve so as to establish according to the three-dimensional curve; the wire is an edge wire of the transmission line channel; after the position information of the segmented hidden danger target is determined, the method further comprises the following steps:
acquiring historical two-dimensional image data shot by the monocular camera;
acquiring historical segmentation image data consistent with the position information in the historical two-dimensional image data;
comparing and analyzing the history segmentation image data with the data information of the hidden danger targets;
if the difference between the data information of the hidden danger targets and the historical segmentation image data exceeds a preset rule, updating the three-dimensional point cloud data;
before determining that the hidden danger target is in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger target, the method further comprises the following steps:
Acquiring three-dimensional coordinate position information of the wire according to the wire data mapping model;
and generating a channel three-dimensional protection area of the transmission line channel according to the safety distance corresponding to the corresponding voltage level of the transmission line channel and the three-dimensional coordinate position information of the wire.
8. A non-volatile storage medium storing computer-executable instructions, the executable instructions comprising:
acquiring two-dimensional image data and three-dimensional point cloud data of a transmission line channel; wherein the two-dimensional image is obtained by shooting with a monocular camera;
detecting hidden danger targets on the two-dimensional image data through a preset target identification segmentation network model so as to acquire data information of the hidden danger targets; wherein, the data information of hidden danger target at least includes: the position information of the hidden danger target and the segmentation contour of the hidden danger target;
if the hidden danger targets are determined to be in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger targets, dividing the hidden danger targets according to the dividing outline of the hidden danger targets, and determining the position information of the divided hidden danger targets;
mapping the ground data in the three-dimensional point cloud data through a pre-established ground data mapping model to acquire a first space mapping conversion relation between the ground data and the two-dimensional image data; converting the position information of the segmented hidden danger targets into three-dimensional coordinate position information according to the first space mapping conversion relation;
Acquiring the actual distance between the hidden danger target and the wire based on the three-dimensional coordinate position information of the hidden danger target and a pre-established wire data mapping model; the wire data mapping model comprises three-dimensional coordinate position information of the wire in three-dimensional point cloud data; the wire data mapping model is obtained by fitting discrete points of wires in the three-dimensional point cloud data into a three-dimensional curve so as to establish according to the three-dimensional curve; the wire is an edge wire of the transmission line channel; after the position information of the segmented hidden danger target is determined, the method further comprises the following steps:
acquiring historical two-dimensional image data shot by the monocular camera;
acquiring historical segmentation image data consistent with the position information in the historical two-dimensional image data;
comparing and analyzing the history segmentation image data with the data information of the hidden danger targets;
if the difference between the data information of the hidden danger targets and the historical segmentation image data exceeds a preset rule, updating the three-dimensional point cloud data;
before determining that the hidden danger target is in the pre-established channel three-dimensional protection zone according to the position information of the hidden danger target, the method further comprises the following steps:
Acquiring three-dimensional coordinate position information of the wire according to the wire data mapping model;
and generating a channel three-dimensional protection area of the transmission line channel according to the safety distance corresponding to the corresponding voltage level of the transmission line channel and the three-dimensional coordinate position information of the wire.
CN202110643955.9A 2021-06-09 2021-06-09 Method, equipment and medium for measuring potential hazards of transmission line channel target Active CN113345019B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110643955.9A CN113345019B (en) 2021-06-09 2021-06-09 Method, equipment and medium for measuring potential hazards of transmission line channel target

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110643955.9A CN113345019B (en) 2021-06-09 2021-06-09 Method, equipment and medium for measuring potential hazards of transmission line channel target

Publications (2)

Publication Number Publication Date
CN113345019A CN113345019A (en) 2021-09-03
CN113345019B true CN113345019B (en) 2023-07-18

Family

ID=77475818

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110643955.9A Active CN113345019B (en) 2021-06-09 2021-06-09 Method, equipment and medium for measuring potential hazards of transmission line channel target

Country Status (1)

Country Link
CN (1) CN113345019B (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113808096B (en) * 2021-09-14 2024-01-30 成都主导软件技术有限公司 Non-contact bolt loosening detection method and system
CN113822249B (en) * 2021-11-23 2022-05-17 山东信通电子股份有限公司 Method and equipment for monitoring position of hidden danger of overhead line
CN114066985B (en) * 2022-01-11 2023-01-20 深圳金三立视频科技股份有限公司 Method for calculating hidden danger distance of power transmission line and terminal
CN116027321B (en) * 2022-01-14 2024-01-30 北京中创恒益科技有限公司 High-precision real-time protection system and method for power transmission line
CN114543680B (en) * 2022-02-18 2022-12-02 国网湖北省电力有限公司电力科学研究院 On-site monitoring and distance measuring method for overhead transmission line channel construction vehicle
CN115014216A (en) * 2022-06-27 2022-09-06 山东信通电子股份有限公司 Method and device for detecting icing of power transmission line
CN118037849A (en) * 2022-11-11 2024-05-14 华为技术有限公司 Calibration method and related device based on point cloud data and image
CN116091494B (en) * 2023-04-07 2023-06-27 智洋创新科技股份有限公司 Method for measuring distance of hidden danger of external damage of power transmission machinery
CN116245932B (en) * 2023-05-10 2023-08-22 智洋创新科技股份有限公司 Hidden danger ranging method for power transmission line based on grid idea
CN117092641B (en) * 2023-10-20 2023-12-15 江苏翰林正川工程技术有限公司 Information fusion method based on radar ranging and image recognition

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111353726A (en) * 2020-04-07 2020-06-30 国网福建省电力有限公司漳州供电公司 Power transmission and distribution line passageway defect hidden danger analysis and processing system
CN112396650A (en) * 2020-03-30 2021-02-23 青岛慧拓智能机器有限公司 Target ranging system and method based on fusion of image and laser radar

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107391631A (en) * 2017-07-10 2017-11-24 国家电网公司 A kind of electric transmission line channel solid space monitoring and fast ranging method
CN110264416B (en) * 2019-05-28 2020-09-29 深圳大学 Sparse point cloud segmentation method and device
CN110232418B (en) * 2019-06-19 2021-12-17 达闼机器人有限公司 Semantic recognition method, terminal and computer readable storage medium
CN112581629B (en) * 2020-12-09 2024-05-28 中国科学院深圳先进技术研究院 Augmented reality display method, device, electronic equipment and storage medium
CN112489130B (en) * 2021-01-11 2024-03-08 国网江苏省电力有限公司泰州供电分公司 Distance measurement method and device for power transmission line and target object and electronic equipment

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112396650A (en) * 2020-03-30 2021-02-23 青岛慧拓智能机器有限公司 Target ranging system and method based on fusion of image and laser radar
CN111353726A (en) * 2020-04-07 2020-06-30 国网福建省电力有限公司漳州供电公司 Power transmission and distribution line passageway defect hidden danger analysis and processing system

Also Published As

Publication number Publication date
CN113345019A (en) 2021-09-03

Similar Documents

Publication Publication Date Title
CN113345019B (en) Method, equipment and medium for measuring potential hazards of transmission line channel target
CN107392247B (en) Real-time detection method for ground object safety distance below power line
CN112686938B (en) Power transmission line clear distance calculation and safety alarm method based on binocular image ranging
CN113887641A (en) Hidden danger target determination method, device and medium based on power transmission channel
JP2014217052A (en) Traffic camera calibration update utilizing scene analysis
CN114241298A (en) Tower crane environment target detection method and system based on laser radar and image fusion
CN113240887A (en) Slope rockfall collapse monitoring method, device and equipment
CN113971768A (en) Unmanned aerial vehicle-based three-dimensional dynamic detection method for power transmission line illegal building
CN114255405A (en) Hidden danger target identification method and device
CN116363585A (en) On-line monitoring method and system for power transmission line
CN114066985B (en) Method for calculating hidden danger distance of power transmission line and terminal
CN109360269B (en) Ground three-dimensional plane reconstruction method based on computer vision
CN114821497A (en) Method, device and equipment for determining position of target object and storage medium
CN113965733A (en) Binocular video monitoring method, system, computer equipment and storage medium
CN114531700B (en) Non-artificial base station antenna work parameter acquisition system and method
CN112816053A (en) Non-contact vibration information detection method and system for ship equipment
JP6546898B2 (en) Three-dimensional space identification apparatus, method, and program
CN116973939B (en) Safety monitoring method and device
US20230243976A1 (en) Systems and methods for utility pole loading and/or clearance analyses
CN115861439B (en) Depth information measurement method and device, computer equipment and storage medium
CN117809297B (en) Three-dimensional reconstruction-based intelligent identification method for dangerous source of power transmission line
CN116168283A (en) Method, equipment and storage medium for judging hidden danger degree of transmission line channel
CN116704138B (en) Method and device for establishing oblique photography three-dimensional model
CN113936207B (en) Portable power inspection method, equipment and medium
CN114114291A (en) Distance detection method, device, server 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