Image-based power transmission hidden danger spatial position acquisition method and device, and computer readable storage medium

By applying object detection and depth estimation calculation methods on visual monitoring equipment, combined with camera parameters, the three-dimensional spatial information acquisition of the transmission potential hazard frame is achieved, and the qualitative analysis of mechanical external damage potential hazards in the existing technology is solved, and the positioning of potential hazards is improved. Accuracy and operation and maintenance efficiency reduce the accident rate.

CN119048743APending Publication Date: 2024-11-29SHANDONG ZHIYANG ELECTRIC

Patent Information

Application Number
CN202411201332.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The existing technology can only realize the qualitative analysis of mechanical external damage hazards, and cannot specifically and reliably determine the risk situation of mechanical hidden dangers in high frequency and high precision transmission scenarios, resulting in high cost of positioning hidden dangers in transmission scenarios and low operation and maintenance efficiency.

Method used

By obtaining images taken by the visual monitoring device, using object detection algorithms and depth estimation algorithms, combined with camera parameters, the three-dimensional spatial information of the transmission potential hazard frame is obtained to achieve accurate potential hazard positioning.

Benefits of technology

It reduces the cost of hidden danger positioning, improves the operation and maintenance efficiency of transmission line scenarios, enhances the intelligence and robustness of dealing with mechanical external hazards, and ensures the stable operation of the transmission system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048743A_ABST
    Figure CN119048743A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of image analysis, and more specifically relates to an image-based power transmission hidden danger spatial position acquisition method and device, and a computer readable storage medium. The method comprises the steps of obtaining a hidden danger area through a target detection algorithm in combination with an area expansion method, obtaining a power transmission line hidden danger area, then performing target segmentation and depth estimation on the area, obtaining power transmission line hidden danger depth information, and then achieving power transmission hidden danger space point cloud obtaining in combination with camera parameters of a shot image. And finally, through power transmission hidden danger height acquisition, power transmission line hidden danger space position information acquisition is realized in combination with a hidden danger positioning module. According to the invention, the problem that most detection means can only realize qualitative analysis of mechanical external damage hidden dangers and cannot specifically and reliably realize high-frequency and high-precision judgment of mechanical hidden dangers and dangerous conditions in a power transmission scene is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of image analysis, and more specifically, relates to a method and device for acquiring the spatial position of power transmission hidden dangers based on an image, and a computer-readable storage medium. Background Art

[0002] In recent years, with the rapid development of my country's economy, there are more and more power facilities, especially power towers and power transmission lines. At the same time, the safety of power transmission lines has also received more and more attention. Hidden dangers such as wildfires, floating objects, wind deviation, dancing, mechanical damage, etc. may cause the collapse of transmission towers, wire breakage or insulation material damage, directly interrupting power supply and affecting power services in a large area. Among them, mechanical damage (excavators, cranes, etc.) is one of the most common and most destructive safety hazards of power transmission lines.

[0003] Chinese invention patent CN107657260A discloses a method for detecting ground hidden dangers in the surrounding environment of a power transmission line, including step 1: performing image preprocessing on the current image to be detected, and performing edge detection to obtain its edge image; step 2: using the edge image to segment the ground area range, and setting the pixel value of the non-ground area to 0; step 3: selecting the previous image of the current image to be detected as the comparison image, performing the same operation on the comparison image according to step 1, performing differential processing using the edge image of the current image to be detected and the comparison image, and determining the changed area in the current image to be detected according to the differential result; step 4: counting the changed area information of N images before and after the current image to be detected, selecting the changed areas with high frequency and concentrated positions as areas with hidden dangers, and issuing an alarm.

[0004] In summary, most of the current detection methods can only achieve qualitative analysis of mechanical external damage hazards, that is, whether there are mechanical hazards around the transmission channel, and cannot achieve high-frequency and high-precision mechanical hazard judgment in transmission scenarios in a more specific and reliable manner. Summary of the invention

[0005] The present invention aims to overcome at least one defect of the above-mentioned prior art and provide an image-based method for acquiring the spatial position of power transmission hidden dangers, so as to solve the problem that the prior art can only realize qualitative analysis of mechanical external failure hidden dangers, but cannot realize specific and reliable high-frequency and high-precision judgment of dangerous situations of mechanical hidden dangers in power transmission scenes, reduce the cost of locating hidden dangers in power transmission scenes, and improve the operation and maintenance efficiency of power transmission line scenes based on visual monitoring equipment.

[0006] The detailed technical scheme of the present invention is as follows:

[0007] A method for obtaining the spatial position of power transmission hidden dangers based on an image, the method comprising:

[0008] S1. Obtain the image to be inspected taken by the visual monitoring device of the power transmission scene, and at the same time obtain the camera internal parameter matrix of the monitoring device;

[0009] S2. Detect the image to be inspected by using a target detection algorithm to obtain an identified power transmission hidden danger frame;

[0010] S3, based on the transmission potential hazard frame, the area is expanded to obtain the transmission line potential hazard area;

[0011] S4. Segment the hidden dangers in the image using the target segmentation algorithm for the hidden danger area of ​​the transmission line, and obtain the hidden danger segmentation result seg_idx; then perform depth estimation on the hidden danger area of ​​the transmission line using the depth estimation algorithm, and obtain the hidden danger depth information dep in combination with the hidden danger segmentation result seg_idx;

[0012] S5. Realize the power transmission hidden danger spatial point cloud pc according to the hidden danger depth information, and obtain the height DH and width DW of the hidden danger frame in three-dimensional space;

[0013] S6. The camera parameters are combined with the height DH and width DW of the hidden danger frame in three-dimensional space to obtain the hidden danger location information d_l.

[0014] Furthermore, the power transmission potential hazard frame is identified as potential hazard equipment, which includes but is not limited to cranes, excavators, cement tankers, bulldozers, and tower cranes.

[0015] Furthermore, the area is expanded to expand N pixels upward, downward, leftward, and rightward of the hidden danger frame based on the hidden danger frame to prevent errors caused by edge detection deviation, making the calculation more accurate:

[0016] d_exp_bbox=

[0017] [danger_bbox[0]-50,danger_bbox[1]-50,danger_bbox[2]+50,danger_bbox[3]+50] (1);

[0019] In formula (1), d_exp_bbox is the potential danger area of ​​the transmission line, danger_bbox[0] is the horizontal coordinate of the upper left corner of the potential danger box, danger_bbox[1] is the vertical coordinate of the upper left corner of the potential danger box, danger_bbox[2] is the horizontal coordinate of the lower right corner of the potential danger box, and danger_bbox[3] is the vertical coordinate of the lower right corner of the potential danger box.

[0020] Furthermore, the spatial point cloud of power transmission hidden dangers is realized by combining the camera parameters of the captured image, including:

[0021] pc=M*[seg_idx[0],seg_idx[1],dep[seg_idx]] (2);

[0022] In formula (2), seg_idx[0] refers to the horizontal coordinate of each pixel of the hidden danger segmentation result, seg_idx[1] refers to the vertical coordinate of each pixel of the hidden danger segmentation result, and dep[seg_idx] refers to the depth value of the scene corresponding to each pixel of the hidden danger segmentation result.

[0023] Based on the generated transmission potential hazard spatial point cloud pc, measure the height information from the lowest point to the highest point to obtain the height DH and width DW of the three-dimensional space of the potential hazard frame:

[0024] DH=max(pc[0,:])-min(pc[0,:]) (3);

[0025] DW=max(pc[1,:])-min(pc[1,:]) (4);

[0026] In formulas (3) to (4), max and min are operations to obtain the maximum and minimum values ​​of the array in the brackets, pc[0,:] refers to the horizontal coordinates of all points in the hidden danger space point cloud, and pc[1,:] refers to the vertical coordinates of all points in the hidden danger space point cloud.

[0027] Furthermore, the acquisition of the hidden danger location information d_1 includes:

[0028] h=danger_bbox[2]-danger_bbox[0] (5);

[0029] w=danger_bbox[3]-danger_bbox[1] (6);

[0030] u=(danger_bbox[2]+danger_bbox[0]) / 2 (7);

[0031] v=(danger_bbox[3]-danger_bbox[1]) / 2 (8);

[0032] z=max([DH / h*M[0,0],DW / w*M[1,1]]) (9);

[0033] x=(uM[0,2])*z / M[0,0] (10);

[0034] y = (vM[1,2])*z / M[1,1] (11);

[0035] d_l=[x,y,z] (12).

[0036] In formulas (5) to (12), M[0,0] is fx, M[1,1] is fy, M[0,2] is cx, and M[1,2] is cy.

[0037] x, y, z are the calculated coordinates of the hidden danger in three dimensions in three-dimensional space, w, h are the two-dimensional width and height of the hidden danger box, and u, v are the horizontal and vertical coordinates of the center point of the hidden danger box.

[0038] In another aspect of the present invention, a device for implementing a method for acquiring a spatial position of a power transmission hazard based on an image is provided, the device comprising:

[0039] at least one processor; and

[0040] A memory storing instructions, which, when executed by the at least one processor, enable the at least one processor to execute the above-mentioned method for acquiring the spatial position of power transmission hidden dangers based on an image.

[0041] In another aspect of the present invention, a machine-readable storage medium is provided, which stores executable instructions, and when the instructions are executed, the machine executes the above-mentioned method for acquiring the spatial position of power transmission hidden dangers based on an image.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] (2) The present invention provides an image-based method, device and computer-readable storage medium for obtaining the spatial position of a power transmission hazard. The method can directly obtain the hazard location point through a single image obtained by the existing installed and deployed visual monitoring equipment. Compared with equipment such as millimeter wave radar, the method has the advantages of low cost, convenience and high efficiency. The process of obtaining the spatial position of the hazard will not be troubled by problems such as hazard obstruction, and the method has high robustness.

[0044] (3) The present invention provides a method, device and computer-readable storage medium for acquiring the spatial position of power transmission hidden dangers based on an image, and a method for acquiring power transmission scene hidden dangers based on a single image. The method is used to acquire the spatial position of power transmission scene hidden dangers based on the existing installed visual monitoring equipment combined with deep learning technology, so that the power transmission field can be more proactive and intelligent in dealing with mechanical external damage hidden dangers, reduce the accident rate, and ensure the stable operation of the power transmission system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of the method for acquiring the spatial position of power transmission hidden dangers based on images described in the present invention.

[0046] Figure 2It is a schematic diagram of the visualization effect of the target detection algorithm in Example 1 of the present invention.

[0047] Figure 3 It is a schematic diagram of the target segmentation algorithm result in Example 1 of the present invention. DETAILED DESCRIPTION

[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0049] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0050] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0051] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0052] Example 1

[0053] Ginseng Figure 1 This embodiment provides a method for obtaining the spatial position of power transmission hidden dangers based on an image, the method comprising:

[0054] S1. Obtain the image to be inspected taken by the visual monitoring device of the power transmission scene, and at the same time obtain the camera internal parameter matrix M of the monitoring device;

[0055] Preferably, the camera intrinsic parameter matrix M of the visualization monitoring device is simultaneously obtained based on the visible light image taken by the transmission line visualization monitoring device installed at a certain point on a certain line.

[0056]

[0057] The camera parameters of the captured image are a 3*3 matrix. It represents the mapping relationship between the point cloud and the depth map. It is obtained by camera parameter calibration or by calculating the visible light image size, camera focal length f and camera CCD or COMS sensor size. The specific form is as follows:

[0058]

[0059] In formula (14), M is the camera intrinsic parameter matrix, fx is the horizontal focal length of the camera, fy is the vertical focal length of the camera, cx is the horizontal center point of the image coordinate system, and cy is the vertical center point of the image coordinate system.

[0060] S2. Detect the image to be inspected through the target detection algorithm, and obtain the identified power transmission hidden danger box danger_bbox, that is, the two-dimensional power transmission hidden danger box;

[0061] The target detection algorithm is a neural network algorithm capable of realizing the ability to identify power transmission hazards in images taken by visual monitoring equipment of power transmission scenes with different resolutions;

[0062] The power transmission hidden danger frame is identified as hidden danger equipment, which includes but is not limited to cranes, excavators, cement tankers, bulldozers, and tower cranes.

[0063] Specifically, the coordinates of the transmission potential hazard frame are obtained through the target detection algorithm.

[0064] danger_bbox=[1459,892,1654,1004], the visualization effect is as follows Figure 2 Shown in the green box.

[0065] S3. Expand the area based on the transmission potential hazard frame to obtain the transmission line potential hazard area d_exp_bbox.

[0066] The area expansion method is: based on the power transmission hidden danger frame obtained by the mark detection algorithm, N pixels are expanded outward to the top, bottom, left and right of the hidden danger frame respectively, preferably, N=50.

[0067] Specifically, the transmission line hidden danger area d_exp_bbox is:

[0068] d_exp_bbox=

[0069] [danger_bbox[0]-50,danger_bbox[1]-50,danger_bbox[2]+50,danger_bbox[3]+50] (1);

[0071] In formula (1), danger_bbox[0] is the horizontal coordinate of the upper left corner of the danger box, danger_bbox[1] is the vertical coordinate of the upper left corner of the danger box, danger_bbox[2] is the horizontal coordinate of the lower right corner of the danger box, and danger_bbox[3] is the vertical coordinate of the lower right corner of the danger box. Figure 2 As shown in the yellow box.

[0072] S4. Segment the hidden dangers in the image using the target segmentation algorithm for the hidden danger area of ​​the transmission line, and obtain the hidden danger segmentation result seg_idx; then perform depth estimation on the hidden danger area of ​​the transmission line using the depth estimation algorithm (monocular depth estimation algorithm), and obtain the hidden danger depth information dep of the transmission line combined with the hidden danger segmentation result seg_idx;

[0073] The target segmentation algorithm can realize the power transmission potential hazard area segmentation function in the input image. Preferably, the target segmentation algorithm is a YOLO series or a pointrend algorithm.

[0074] Specifically, the hidden danger segmentation result seg_idx=[[9,165],...,[120,23]], such as Figure 3 The position of the pixels in the green part shown in the image is used to segment the hidden dangers of the excavator in the image through the target segmentation algorithm.

[0075] Perform depth estimation on each pixel of the image to obtain the real space represented by the pixel to the camera position and the depth information of the hidden dangers of the transmission line

[0076] S5. Acquisition of the spatial point cloud of power transmission hidden dangers and the height and width of the three-dimensional space of the hidden danger frame;

[0077] The acquisition of the spatial point cloud of power transmission hidden dangers and the height and width of the three-dimensional space of the hidden danger box can be achieved through the recognition model, but there are inaccuracies in recognition and edge errors.

[0078] Preferably, this article combines the camera parameters of the captured image to realize the spatial point cloud pc of the power transmission hidden danger, and then calculates the height DH and width DW of the hidden danger frame in the three-dimensional space in combination with the spatial point cloud data. The hidden danger location point can be realized through a single image obtained by the existing installed and deployed visual monitoring equipment, which is low-cost, convenient, efficient and more accurate.

[0079] The transmission potential hazard spatial point cloud acquisition is based on the camera imaging principle to achieve the acquisition of potential hazard point cloud from potential hazard depth map:

[0080] pc=M*[seg_idx[0],seg_idx[1],dep[seg_idx]] (2);

[0081] In formula (2), seg_idx[0] refers to the horizontal coordinate of each pixel of the hidden danger segmentation result, seg_idx[1] refers to the vertical coordinate of each pixel of the hidden danger segmentation result, and dep[seg_idx] refers to the depth information and depth value of the scene corresponding to each pixel of the hidden danger segmentation result;

[0082] Specifically,

[0083] Preferably, the method for obtaining the height DH and width DW of the three-dimensional space of the hidden danger frame is as follows: based on the generated power transmission hidden danger space point cloud pc, the height information and width information from the lowest point to the highest point are measured:

[0084] DH=max(pc[0,:])-min(pc[0,:])=4.78m (3);

[0085] DW=max(pc[1,:])-min(pc[1,:])=8.32m (4);

[0086] In formulas (3) to (4), max and min are operations for taking the maximum and minimum values ​​of the array in the brackets, pc[0,:] refers to the horizontal coordinates of all points in the hidden danger space point cloud, and pc[1,:] refers to the vertical coordinates of all points in the hidden danger space point cloud. Each element of the power transmission hidden danger space point cloud pc is composed of three values, which respectively represent the horizontal coordinate, vertical coordinate and height information of a point in space. These points together constitute a hidden danger point cloud.

[0087] S6. The camera parameters are combined with the height DH and width DW of the hidden danger frame in three-dimensional space to obtain the hidden danger location information d_l:

[0088] h=danger_bbox[2]-danger_bbox[0] (5);

[0089] w=danger_bbox[3]-danger_bbox[1] (6);

[0090] u=(danger_bbox[2]+danger_bbox[0]) / 2 (7);

[0091] v=(danger_bbox[3]-danger_bbox[1]) / 2 (8);

[0092] z=max([DH / h*M[0,0],DW / w*M[1,1]]) (9);

[0093] x=(uM[0,2])*z / M[0,0] (10);

[0094] y = (vM[1,2])*z / M[1,1] (11);

[0095] d_l=[x,y,z]=[12.94,0.93,146.95] (12);

[0096] In formulas (5) to (12), M[0,0] is fx, M[1,1] is fy, M[0,2] is cx, and M[1,2] is cy.

[0097] After obtaining the spatial location of the hidden danger, it can be combined with the location of the transmission channel or the position of the wire in space to determine whether the hidden danger will cause damage to the transmission scene. If the hidden danger is close to the transmission line, it can be determined that it may cause damage, and the transmission line operation and maintenance personnel will need to remove the hidden danger.

[0098] Example 2

[0099] This embodiment provides a device for acquiring the spatial position of a power transmission hazard based on an image, the device comprising:

[0100] at least one processor; and

[0101] A memory storing instructions, which, when executed by the at least one processor, enable the at least one processor to execute the above-mentioned method for acquiring the spatial position of power transmission hidden dangers based on an image.

[0102] In this embodiment, the device includes but is not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile computing devices, smart phones, tablet computers, cellular phones, personal digital assistants (PDAs), handheld devices, messaging devices, wearable computing devices, consumer electronic devices, etc.

[0103] Example 3

[0104] This embodiment also provides a computer-readable storage medium storing executable instructions, which, when executed, enable the machine to execute the above-mentioned method for acquiring the spatial position of power transmission hidden dangers based on an image.

[0105] Specifically, a system or device equipped with a readable storage medium can be provided, on which software program codes that implement the functions of any of the above-mentioned embodiments are stored, and a computer or processor of the system or device can read and execute instructions stored in the readable storage medium.

[0106] In this case, the program code itself read from the machine-readable medium can realize the function of any one of the above embodiments, and thus the machine-readable code and the machine-readable storage medium storing the machine-readable code constitute part of this specification.

[0107] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or a cloud via a communication network.

[0108] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0112] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the technical solution of the present invention, and are not intended to limit the specific implementation methods of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the claims of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A method for obtaining the spatial position of power transmission hidden dangers based on an image, characterized in that: The method comprises: S1. Obtain the image to be inspected taken by the visual monitoring device of the power transmission scene, and at the same time obtain the camera internal parameter matrix of the monitoring device; S2. Detect the image to be inspected by using a target detection algorithm to obtain an identified power transmission hidden danger frame; S3, based on the transmission potential hazard frame, the area is expanded to obtain the transmission line potential hazard area; S4. Segment the hidden dangers in the image using the target segmentation algorithm for the hidden danger area of ​​the transmission line, and obtain the hidden danger segmentation result seg_idx; then perform depth estimation on the hidden danger area of ​​the transmission line using the depth estimation algorithm, and obtain the hidden danger depth information dep in combination with the hidden danger segmentation result seg_idx; S5. Realize the power transmission hidden danger spatial point cloud pc according to the hidden danger depth information, and obtain the height DH and width DW of the hidden danger frame in three-dimensional space in combination with the power transmission hidden danger spatial point cloud; S6. The camera parameters are combined with the height DH and width DW of the hidden danger frame in three-dimensional space to obtain the hidden danger location information d_l.

2. The method for obtaining the spatial position of power transmission hidden dangers based on an image according to claim 1, characterized in that: The area is expanded by N pixels upward, downward, leftward, and rightward based on the power transmission potential hazard frame: d_exp_bbox= [danger_bbox[0]-50,danger_bbox[1]-50,danger_bbox[2]+50,danger_bbox[3]+50] (1); In formula (1), d_exp_bbox is the potential danger area of ​​the transmission line, danger_bbox[0] is the horizontal coordinate of the upper left corner of the potential danger box, danger_bbox[1] is the vertical coordinate of the upper left corner of the potential danger box, danger_bbox[2] is the horizontal coordinate of the lower right corner of the potential danger box, and danger_bbox[3] is the vertical coordinate of the lower right corner of the potential danger box.

3. The method for acquiring the spatial position of power transmission hidden dangers based on an image according to claim 1 or 2, characterized in that: Combine the camera parameters of the captured image to realize the spatial point cloud pc of power transmission hidden dangers: pc=M*[seg_idx[0],seg_idx[1],dep[seg_idx]] (3); In formula (3), M is the camera internal parameter matrix, seg_idx[0] refers to the horizontal coordinate of each pixel of the hidden danger segmentation result, seg_idx[1] refers to the vertical coordinate of each pixel of the hidden danger segmentation result, and dep[seg_idx] refers to the depth value of the scene corresponding to each pixel of the hidden danger segmentation result; Based on the generated transmission potential hazard spatial point cloud pc, the height DH and width DW of the potential hazard box in three-dimensional space are obtained: DH=max(pc[0,:])-min(pc[0,:]) (4); DW=max(pc[1,:])-min(pc[1,:]) (5); In formulas (4) to (5), max and min are operations to obtain the maximum and minimum values ​​of the array in the brackets, pc[0,:] refers to the horizontal coordinates of all points in the hidden danger space point cloud, and pc[1,:] refers to the vertical coordinates of all points in the hidden danger space point cloud.

4. The method for obtaining the spatial position of power transmission hidden dangers based on an image according to claim 3, characterized in that: The acquisition of the hidden danger location information d_1 includes: h=danger_bbox[2]-danger_bbox[0] (5); w=danger_bbox[3]-danger_bbox[1] (6); u=(danger_bbox[2]+danger_bbox[0]) / 2 (7); v=(danger_bbox[3]-danger_bbox[1]) / 2 (8); z=max([DH / h*M[0,0],DW / w*M[1,1]]) (9); x=(uM[0,2])*z / M[0,0] (10); y=(vM[1,2])*z / M[1,1] (11); d_l=[x,y,z] (12); In formulas (5) to (12), M[0,0] is fx, i.e., the horizontal focal length of the camera; M[1,1] is fy, i.e., the vertical focal length of the camera; M[0,2] is cx, i.e., the horizontal center point of the image coordinate system; M[1,2] is cy, i.e., the vertical center point of the image coordinate system; x, y, z are the coordinates of the hidden danger in three dimensions in three-dimensional space; w, h are the width and height of the hidden danger frame in two dimensions; u, v are the horizontal and vertical coordinates of the center point of the hidden danger frame in two dimensions.

5. The method for obtaining the spatial position of power transmission hidden dangers based on an image according to claim 1, characterized in that: The power transmission hidden danger frame is identified as hidden danger equipment, which includes but is not limited to cranes, excavators, cement tankers, bulldozers, and tower cranes.

6. An image-based device for acquiring the spatial position of power transmission hazards, characterized in that: The device comprises: processor; a memory having stored thereon a computer program executable on the processor; Wherein, when the computer program is executed by the processor, the steps of the method for acquiring the spatial position of power transmission hazards based on an image as described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Citation Information

Patent Citations

  • Point cloud-based hidden danger distance measurement method in power transmission channel

    CN113465522A

  • Early warning method and system

    CN113609921A

  • License plate position identification method and system, and computer storage medium

    CN114821135A

  • Power transmission machinery external damage hidden danger distance measurement method

    CN116091494A

  • Three-dimensional road line extraction method and related equipment

    CN116385994A

Cited By

  • Method and system for quickly positioning vertex of suspension arm based on laser radar point cloud calibration monocular depth estimation

    CN121685631A

  • A method and system for fast positioning of the top point of a boom based on laser radar point cloud calibration monocular depth estimation

    CN121685631B