Real-time detection method for safe distance of power line

Abstract

The invention relates to the technical field of power line measurement, in particular to a power line safety distance real-time detection method, which comprises the following steps: when a suspension arm of a power inspection crane moves, a binocular camera acquires image data in real time, and a laser radar acquires point cloud data in real time; the image data comprises a first image and a second image, matching and splicing the first image and the second image, and preprocessing the spliced image to obtain a target image; processing the point cloud data and performing target identification to obtain power line information, and extracting a minimum bounding box of a power line based on an OBB algorithm; jointly calibrating the binocular camera and the laser radar, mapping eight angular points of the minimum bounding box to a target image, and forming eight points on the target image; connecting the eight points according to the distribution of the cubic edges to obtain a surrounding frame of the power line; the distance between the power line and the suspension arm is judged, the distance is displayed at the surrounding frame of the power line, if the distance is smaller than the safety distance, alarm information is output, and the safety distance detection accuracy of the power line is high.

Description

Technical Field

[0001] The present invention relates to the technical field of power line measurement, and in particular to a real-time detection method for a power line safety distance. Background Art

[0002] During the inspection of high-voltage substations, it involves the construction of cranes in the environment of high-voltage power lines. The crane driver cannot clearly observe the distance between the crane arm and the high-voltage wires during the construction process, so necessary protection measures must be taken during construction. The general protection measures are mostly to set up safety observers next to the crane to observe the environment around the crane arm at all times and quickly convey the message to the crane driver when danger is detected. This method will cause a waste of manpower, and manual communication may be inaccurate. It cannot adapt to the development and safe operation needs of modern power grids. Ultra-high voltage and UHV power grids urgently need efficient, advanced and scientific power line safety detection methods.

[0003] In the existing monocular camera-based UAV wire inspection, in order to restore the three-dimensional information of the wire and the objects below it with absolute scale, it is necessary to know the position and attitude information of the camera at each exposure moment, and perform same-name point matching and wire extraction between sequence images. The position and attitude information of the camera can be obtained by the high-precision GPS and inertial navigation carried on the UAV; the acquisition of spatial information of the wire and the crossing objects below it depends on the acquisition of the same-name features on the image, which is solved by the image matching method. However, image matching is a pathological problem. Especially for characteristic targets such as wires, it is difficult to achieve stable and reliable image matching, and the field of view detection range of the monocular camera is very limited; and the UAV needs to detect the distance between the boom and the high-voltage power line during inspection. Since the crane is in motion during construction in the high-voltage power line environment, it is more difficult to perform image matching, and due to the limitations of field of view detection, it is even more impossible to accurately detect the safe distance of the power line. Summary of the invention

[0004] The technical problem to be solved by the present invention is: in order to solve the technical problem that the prior art cannot accurately detect the safe distance of power lines, the present invention provides a real-time detection method for the safe distance of power lines, which increases the field of view and can accurately detect the safe distance of power lines.

[0005] The technical solution adopted by the present invention to solve the technical problem is: a real-time detection method for the safety distance of power lines, the method comprising the following steps:

[0006] S1, installing a monitoring device on the boom of a power inspection crane, wherein the monitoring device includes a binocular camera and a laser radar;

[0007] S2, when the boom of the electric power inspection crane is moving, the binocular camera collects image data in front of the boom in real time, and the laser radar collects point cloud data in front of the boom in real time;

[0008] S3, acquiring the image data, the image data including a first image and a second image, matching and splicing the first image and the second image, and preprocessing the spliced ​​image to obtain a target image;

[0009] S4, acquiring the point cloud data, processing the point cloud data and performing target recognition to obtain power line information, and extracting the minimum bounding box of the power line by using an OBB algorithm according to the power line information;

[0010] S5, jointly calibrating the binocular camera and the laser radar so that eight corner points of the minimum bounding box of the power lines are mapped to the target image, that is, eight points are formed on the target image;

[0011] S6, connecting the eight points on the target image according to the distribution of the cube edges to obtain a bounding box of the electric lines;

[0012] S7, determining the distance between the power line and the boom of the power inspection crane, and displaying the distance in the enclosing frame of the power line; if the distance is less than the safe distance, the monitoring device outputs an alarm message.

[0013] Further, specifically, the step S3 specifically includes the following steps:

[0014] Create a stitching Stitcher object, and use the ORB feature point detection algorithm to perform optimal feature point matching, projective transformation, seam selection, and image stitching fusion on the first image and the second image;

[0015] The initUndistortRectifyMap() function in OpenCV is used to calculate the mapping relationship from the distorted image to the corrected image, that is, to calculate the parameters required for dedistortion, and then combined with the dedistortion function remap() to dedistort the spliced ​​image to obtain the target image.

[0016] Further, specifically, the step S4 specifically includes:

[0017] Performing filtering processing on the acquired point cloud data;

[0018] The target point cloud is segmented based on the KD-tree Euclidean clustering method to obtain the clustering results;

[0019] Extracting the power line information according to the clustering result;

[0020] The x value, y value, and z value of each point in the power line information are judged to obtain six groups of values, namely: minimum x value minx, maximum x value maxx, minimum y value miny, maximum y value maxy, minimum z value minz, and maximum z value maxz;

[0021] The six groups of values ​​are combined to form the eight corner points of the minimum bounding box of the power lines, and the coordinates of the eight corner points are: (minx, miny, minz), (minx, miny, maxz), (minx, maxy, minz), (minx, maxy, maxz), (maxx, miny, minz), (maxx, miny, maxz), (maxx, maxy, minz), (maxx, maxy, minz), (maxx, maxy, maxz).

[0022] Further, specifically, the calculation formula for the joint calibration of the binocular camera and the laser radar in step S5 is:

[0023]

[0024] Among them, P w (x w ,y w ,z w ) represents the coordinates of point P in the world coordinate system, that is, the coordinates of a point cloud P in the laser radar coordinate system, R cw and t cw represents the rotation and translation between the world coordinate system and the camera world coordinate system, T represents the external parameter matrix of the laser radar, z c Indicates the depth value of point P in the camera coordinate system, u p and v p represents the pixel coordinates corresponding to the observed point P, that is, the coordinates of the two-dimensional point to be converted from the three-dimensional point, K represents the intrinsic parameter matrix of the camera, and f x and f y They represent the focal lengths in the x-axis and y-axis directions, respectively, and c x and c y Indicates the actual position of the principal point in pixels;

[0025] Substitute the coordinates of the eight corner points of the minimum bounding box of the electric line into formula (1) to obtain the two-dimensional coordinates of the eight points on the target image.

[0026] Furthermore, specifically, in the step S6, a rectangular frame will also be drawn according to the enclosing frame of the power lines, specifically including: obtaining the minimum and maximum values ​​of the horizontal and vertical axis pixel coordinates in the enclosing frame of the power lines, using the minimum value of the horizontal coordinate and the minimum value of the vertical coordinate to synthesize the minimum pixel point, subtracting the minimum value of the horizontal coordinate from the maximum value of the horizontal coordinate to obtain the pixel width, subtracting the minimum value of the vertical coordinate from the maximum value of the vertical coordinate to obtain the pixel height, obtaining a rectangular frame according to the minimum pixel point, pixel height and pixel width, and drawing the enclosing frame of the power lines.

[0027] Further, specifically, the step S7 specifically includes the following steps:

[0028] Traverse each point cloud in the power line information, calculate the distance between each point cloud and the monitoring device, sort all the point clouds, and the minimum distance is the distance between the power line and the boom of the power inspection crane;

[0029] Set two safety distances and output two levels of alarm information.

[0030] Further, specifically, in step S3, the embedded CUDA software and hardware platform parallel computing technology is used to perform real-time image processing on the collected image data.

[0031] Further, specifically, the binocular camera includes a first camera and a second camera, and a center line of the first camera and a center line of the second camera are arranged at an angle, and the angle of the angle is 120 degrees.

[0032] Further, specifically, both the first camera and the second camera are 5-megapixel high-definition camera modules with a horizontal field of view of 120 degrees and a vertical field of view of 90 degrees.

[0033] Further, specifically, before the binocular camera collects the image data in front of the boom in real time, the parameters of the binocular camera are set so that the current camera resolution is the same as the camera calibrated resolution.

[0034] The beneficial effects of the present invention are that the real-time detection method for the safety distance of power lines of the present invention increases the field of view angle and expands the visual detection range by setting up a binocular camera. The transition at the splicing point of the matched and spliced ​​target image is natural and the splicing effect is good. The power line information and the power line safety distance calculation are obtained by acquiring point cloud data, and the data is aligned with the image data. The power line frame and distance display are performed on the target image. The whole process is fully automated, does not require human participation, and has a high detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0036] Figure 1It is a structural diagram of embodiment 1 of the present invention.

[0037] Figure 2 It is a schematic diagram of the target detection part of the first embodiment of the present invention.

[0038] Figure 3 It is a schematic diagram of the structure of a computer device according to the second embodiment of the present invention.

[0039] In the figure, 10 is a computer device; 1002 is a processor; 1004 is a memory; and 1006 is a transmission device. DETAILED DESCRIPTION

[0040] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0041] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0042] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0043] Example 1

[0044] The present application embodiment provides a method for real-time detection of power line safety distance, such as Figure 1-2 As shown, the method comprises the following steps:

[0045] S1, installing the monitoring equipment on the boom of the power inspection crane, the monitoring equipment includes a binocular camera and a laser radar;

[0046] S2, when the boom of the power inspection crane is moving, the binocular camera collects the image data in front of the boom in real time, and the laser radar collects the point cloud data in front of the boom in real time;

[0047] S3, acquiring image data, the image data including a first image and a second image, matching and splicing the first image and the second image, and preprocessing the spliced ​​image to obtain a target image;

[0048] S4, acquiring point cloud data, processing the point cloud data and performing target recognition, obtaining power line information, and extracting the minimum bounding box of the power line through the OBB algorithm according to the power line information;

[0049] S5, jointly calibrating the binocular camera and the laser radar so that the eight corner points of the minimum bounding box of the power line are mapped to the target image, that is, eight points are formed on the target image;

[0050] S6, connecting the eight points on the target image according to the distribution of the cube edges to obtain a bounding box of the electric lines;

[0051] S7, determine the distance between the power line and the boom of the power inspection crane, and display the distance in the enclosing frame of the power line. If the distance is less than the safe distance, the monitoring device outputs an alarm message.

[0052] In this embodiment, step S3 specifically includes the following steps:

[0053] Create a stitching Stitcher object, and use but not limited to the ORB feature point detection algorithm to perform optimal feature point matching, projective transformation, seam selection and image stitching fusion on the first image and the second image;

[0054] The initUndistortRectifyMap() function in OpenCV is used to calculate the mapping relationship from the distorted image to the corrected image, that is, to calculate the parameters required for dedistortion, and then combined with the dedistortion function remap() to dedistort the spliced ​​image to obtain the target image. The video stream formed by the target image has a natural transition at the splicing point without obvious lag.

[0055] It should be noted that by creating a stitching Stitcher object to stitch images, the image stitching effect is good. When using it, you only need to provide the images to be stitched. The object created by the stitching Stitcher supports different stitching modes, and will automatically detect the overlapping area between the first image and the second image, perform the best matching of feature points, projective transformation, and stitching selection, and finally generate a stitched image. At the same time, because the powerful computer vision library OpenCV is used when using the stitching Stitcher object, some functions in OpenCV can also be used when framing and dedistorting the image, which is convenient for unified processing of images.

[0056] In addition, when stitching images, although a relatively fast algorithm is selected, the entire stitching process takes a long time, and the frame rate of the video is only 1 to 2 frames. Image remapping involves mapping and transforming each pixel of the image, which requires a large number of repeated calculations, which takes three to four hundred milliseconds, affecting the detection efficiency. The CPU has many functional modules and can adapt to complex computing environments, but such large-scale parallel calculations are time-consuming and occupy a lot of resources. In this embodiment, the embedded CUDA software and hardware platform parallel computing technology is used to perform real-time image processing on the collected image data. The remap (such as image remapping) step involving a large number of parallel repetitive calculations is handed over to the GPU for calculation using CUDA programming, and the calculation speed is reduced to tens of seconds, which increases the frame rate of the video to about 15 frames, effectively improving the detection efficiency.

[0057] In this embodiment, step S4 specifically includes:

[0058] Perform filtering on the acquired point cloud data;

[0059] The target point cloud is segmented based on the KD-tree Euclidean clustering method to obtain the clustering results;

[0060] Extract the power line information based on the clustering results;

[0061] The x value, y value, and z value of each point in the power line information are judged to obtain six groups of values, namely: minimum x value minx, maximum x value maxx, minimum y value miny, maximum y value maxy, minimum z value minz, and maximum z value maxz;

[0062] The six groups of values ​​are combined to form the eight corner points of the minimum bounding box of the power line. The coordinates of the eight corner points are: (minx, miny, minz), (minx, miny, maxz), (minx, maxy, minz), (minx, maxy, maxz), (maxx, miny, minz), (maxx, miny, maxz), (maxx, maxy, minz), (maxx, maxy, minz), (maxx, maxy, maxz).

[0063] In this embodiment, the calculation formula for the combined calibration of the binocular camera and the laser radar in step S5 is:

[0064]

[0065] Among them, P w (x w ,y w ,z w ) represents the coordinates of point P in the world coordinate system, that is, the coordinates of a point cloud P in the laser radar coordinate system, R cw and t cw represents the rotation and translation between the world coordinate system and the camera world coordinate system, T represents the external parameter matrix of the laser radar, z c Indicates the depth value of point P in the camera coordinate system, u p and v p represents the pixel coordinates corresponding to the observed point P, that is, the coordinates of the two-dimensional point to be converted from the three-dimensional point, K represents the intrinsic parameter matrix of the camera, and f x and f y They represent the focal lengths in the x-axis and y-axis directions, respectively, and c x and c y Indicates the actual position of the principal point in pixels;

[0066] Substitute the coordinates of the eight corner points of the minimum bounding box of the electric line into formula (1) to obtain the two-dimensional coordinates of the eight points on the target image.

[0067] In this embodiment, in step S6, a rectangular frame is also drawn according to the enclosing frame of the power line, specifically including: obtaining the minimum and maximum values ​​of the horizontal and vertical axis pixel coordinates in the enclosing frame of the power line, using the minimum value of the horizontal coordinate and the minimum value of the vertical coordinate to synthesize the minimum pixel point, subtracting the maximum value of the horizontal coordinate from the minimum value of the horizontal coordinate to obtain the pixel width, and subtracting the maximum value of the vertical coordinate from the minimum value of the vertical coordinate to obtain the pixel height, obtaining a rectangular frame according to the minimum pixel point, pixel height, and pixel width, and drawing the enclosing frame of the power line.

[0068] In this embodiment, step S7 specifically includes the following steps:

[0069] Traverse each point cloud in the power line information, calculate the distance between each point cloud and the monitoring equipment, sort all the point clouds, and the minimum distance is the distance between the power line and the boom of the power inspection crane;

[0070] Two safety distances are set to output two levels of alarm information, wherein the first safety distance is greater than the second safety distance.

[0071] In this embodiment, the terminal device performs visual display, that is, the target image displayed on the terminal device also includes a bounding box showing the power line, and the bounding box of the power line is framed and displayed. The distance information between the power line and the boom of the power inspection crane is displayed at the bounding box of the power line. When the distance is less than the set first safety distance, the bounding box of the power line, the drawn rectangular box and the distance information will be displayed in orange. When the distance is less than the set second safety distance, the bounding box of the power line, the drawn rectangular box and the distance information will be displayed in red. When the distance is greater than the set first safety distance, the bounding box of the power line, the drawn rectangular box and the distance information will be displayed in green. In addition, the monitoring device also issues different sound warnings according to the comparison results to improve the safety of the crane in the high-voltage power line environment. The visual display enhances the human-computer interaction experience.

[0072] In this embodiment, the binocular camera significantly increases the field of view, so that the horizontal 180 degree angle in front can be monitored. ° Obstacles in the range. The binocular camera includes a first camera and a second camera. The center line of the first camera and the center line of the second camera are set at an angle of 120 degrees, which is convenient for collecting and stitching the front image. That is, the first camera and the second camera are both 5-megapixel high-definition camera modules with a horizontal field of view of 120 degrees and a vertical field of view of 90 degrees. While ensuring that the horizontal detection range meets 180 ° At the same time, it avoids the problem that when the image overlap range is too small, the stitching effect will be affected, and when the image overlap range is too large, the overall detection range will be reduced. It ensures that when the first image and the second image are stitched, the overlap range is greater than one quarter of a single image.

[0073] In this embodiment, before the binocular camera collects the image data in front of the boom in real time, the binocular camera parameters are set so that the current camera resolution is the same as the camera calibration resolution. This is because in the process of stitching, each frame of the camera needs to be dedistorted, and the camera intrinsic parameters calibrated in advance are needed. At different resolutions, the camera intrinsic parameters are different, so the resolution needs to be unified. In addition, the stitching effect and camera radar extrinsic parameters at different resolutions are different, so the camera resolution must be unified to facilitate image stitching.

[0074] To sum up, the real-time detection method for the safe distance of power lines of the present invention increases the field of view angle by setting up a binocular camera, and the transition at the joints of the matched and spliced ​​target images is natural and the splicing effect is good. The power line information and the safe distance of the power lines are obtained by acquiring point cloud data, and the data is aligned with the image data. The power line frames and distances are displayed on the target image. The whole process is fully automated, does not require human participation, and has a high detection accuracy.

[0075] Example 2

[0076] An embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a power line detection method based on point cloud processing as provided in the above method embodiment.

[0077] Figure 3 The hardware structure diagram of a device for implementing a power line detection method based on point cloud processing provided in an embodiment of the present application is shown. The device may participate in constituting or include the apparatus or system provided in an embodiment of the present application. Figure 3 As shown, the computer device 10 may include one or more processors 1002 (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations shown.

[0078] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer device 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0079] The memory 1004 can be used to store software programs and modules of application software, such as a program instruction / data storage device corresponding to a power line detection method based on point cloud processing in an embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, implementing the above-mentioned method. The memory 1004 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0080] The transmission device 1006 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer device 10. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 1006 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0081] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer device 10 (or mobile device).

[0082] Example 3

[0083] An embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a power line detection method based on point cloud processing in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a power line detection method based on point cloud processing provided in the above method embodiment.

[0084] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0085] Example 4

[0086] The embodiment of the present invention further provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a power line detection method based on point cloud processing provided in the above various optional embodiments.

[0087] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0089] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0090] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. A real-time detection method for power line safety distance, characterized in that: The method comprises the following steps: S1, installing a monitoring device on the boom of a power inspection crane, wherein the monitoring device includes a binocular camera and a laser radar; S2, when the boom of the electric power inspection crane is moving, the binocular camera collects image data in front of the boom in real time, and the laser radar collects point cloud data in front of the boom in real time; S3, acquiring the image data, the image data including a first image and a second image, matching and splicing the first image and the second image, and preprocessing the spliced ​​image to obtain a target image; S4, acquiring the point cloud data, processing the point cloud data and performing target recognition to obtain power line information, and extracting the minimum bounding box of the power line by using an OBB algorithm according to the power line information; S5, jointly calibrating the binocular camera and the laser radar so that eight corner points of the minimum bounding box of the power lines are mapped to the target image, that is, eight points are formed on the target image; S6, connecting the eight points on the target image according to the distribution of the cube edges to obtain a bounding box of the electric lines; S7, determining the distance between the power line and the boom of the power inspection crane, and displaying the distance in the enclosing frame of the power line; if the distance is less than the safe distance, the monitoring device outputs an alarm message.

2. The method for real-time detection of power line safety distance according to claim 1, characterized in that: The step S3 specifically comprises the following steps: Create a stitching Stitcher object, and use the ORB feature point detection algorithm to perform optimal feature point matching, projective transformation, seam selection, and image stitching fusion on the first image and the second image; The initUndistortRectifyMap() function in OpenCV is used to calculate the mapping relationship from the distorted image to the corrected image, that is, to calculate the parameters required for dedistortion, and then combined with the dedistortion function remap() to dedistort the spliced ​​image to obtain the target image.

3. The real-time detection method for power line safety distance according to claim 1, characterized in that: The step S4 specifically includes: Performing filtering processing on the acquired point cloud data; The target point cloud is segmented based on the KD-tree Euclidean clustering method to obtain the clustering results; Extracting the power line information according to the clustering result; The x value, y value, and z value of each point in the power line information are judged to obtain six groups of values, namely: minimum x value minx, maximum x value maxx, minimum y value miny, maximum y value maxy, minimum z value minz, and maximum z value maxz; The six groups of values ​​are combined to form the eight corner points of the minimum bounding box of the power lines, and the coordinates of the eight corner points are: (minx, miny, minz), (minx, miny, maxz), (minx, maxy, minz), (minx, maxy, maxz), (maxx, miny, minz), (maxx, miny, maxz), (maxx, maxy, minz), (maxx, maxy, minz), (maxx, maxy, maxz).

4. The method for real-time detection of power line safety distance according to claim 3, characterized in that: The calculation formula for the joint calibration of the binocular camera and the laser radar in step S5 is: Among them, P w Medium (x w ,y w ,z w ) represents the coordinates of point P in the world coordinate system, that is, the coordinates of a point cloud P in the laser radar coordinate system, R cw and t cw represents the rotation and translation matrix between the world coordinate system and the camera world coordinate system, T represents the external parameter matrix of the laser radar, z c Indicates the depth value of point P in the camera coordinate system, u p and v p represents the pixel coordinates corresponding to the observed point P, that is, the coordinates of the two-dimensional point to be converted from the three-dimensional point, K represents the intrinsic parameter matrix of the camera, and f x and f y They represent the focal lengths in the x-axis and y-axis directions, respectively, and c x and c y Indicates the actual position of the principal point in pixels; Substitute the coordinates of the eight corner points of the minimum bounding box of the electric line into formula (1) to obtain the two-dimensional coordinates of the eight points on the target image.

5. The method for real-time detection of power line safety distance according to claim 4, characterized in that: In the step S6, a rectangular frame is also drawn according to the enclosing frame of the power line, specifically including: obtaining the minimum and maximum values ​​of the horizontal and vertical axis pixel coordinates in the enclosing frame of the power line, using the minimum value of the horizontal coordinate and the minimum value of the vertical coordinate to synthesize the minimum pixel point, subtracting the maximum value of the horizontal coordinate from the minimum value of the horizontal coordinate to obtain the pixel width, and subtracting the maximum value of the vertical coordinate from the minimum value of the vertical coordinate to obtain the pixel height, obtaining a rectangular frame according to the minimum pixel point, pixel height, and pixel width, and drawing the enclosing frame of the power line.

6. The method for real-time detection of power line safety distance according to claim 1, characterized in that: The step S7 specifically includes the following steps: Traverse each point cloud in the power line information, calculate the distance between each point cloud and the monitoring device, sort all the point clouds, and the minimum distance is the distance between the power line and the boom of the power inspection crane; Set two safety distances and output two levels of alarm information.

7. The real-time detection method for power line safety distance according to claim 1, characterized in that: In step S3, the collected image data is processed in real time using the parallel computing technology of the embedded CUDA software and hardware platform.

8. The method for real-time detection of power line safety distance according to claim 1, characterized in that: The binocular camera includes a first camera and a second camera, and the center line of the first camera and the center line of the second camera are arranged at an angle, and the angle of the angle is 120 degrees.

9. The method for real-time detection of power line safety distance according to claim 8, characterized in that: The first camera and the second camera are both 5-megapixel high-definition camera modules with a horizontal field of view of 120 degrees and a vertical field of view of 90 degrees.

10. The method for real-time detection of power line safety distance according to claim 8, characterized in that: Before the binocular camera collects the image data in front of the boom in real time, the parameters of the binocular camera are set so that the current camera resolution is the same as the camera calibration resolution.

Images