Method and system for recognizing opening and closing angle of isolator based on video image

Abstract

The application discloses a kind of based on video image to disconnecting switch opening and closing angle identification method and system, belong to disconnecting switch state monitoring technical field.The method of the present application comprises: obtaining rotating arm sequence image;Rotating arm sequence image is aligned, to determine the feature point on rotating arm sequence image, and determine the three-dimensional coordinates of the feature point;The feature point is connected, to determine the spatial position of rotating arm, based on the three-dimensional coordinates and the spatial position of the rotating arm, determine the opening and closing angle of disconnecting switch;Determine the opening and closing angle and the rotating arm sequence image are associated, as reference calibration image;After obtaining the target rotating arm sequence image of target disconnecting switch, the target rotating arm sequence image and reference calibration image are matched, to identify the opening and closing angle of target disconnecting switch.The three-dimensional coordinates of the present application are determined by video image, and the opening and closing angle on space is determined according to three-dimensional coordinates, low in cost, and it is convenient to execute.

Description

A method and system for identifying the opening and closing angles of disconnecting switches based on video images Technical Field

[0001] This invention relates to the field of disconnector switch status monitoring technology, and more specifically, to a method and system for identifying the opening and closing angles of disconnectors based on video images. Background Technology

[0002] With the continuous and accelerated construction of new power systems, the number of substations in operation under the State Grid has grown rapidly. Due to the high requirements of the power grid for continuous and reliable power supply and safe and stable operation, as well as the strong randomness of new energy sources, a large number of disconnecting switches in substations need to be frequently switched. One-button sequential control is an advanced technology that can ensure that disconnecting switches are switched in a logical sequence. The key to its realization is the accurate confirmation signal of the switch opening and closing position. Traditional sensors such as attitude sensors and microswitches that monitor the opening and closing angles of disconnecting switches require power outages for installation and maintenance. However, power outage maintenance approvals for substations are complex, time-consuming, and difficult to perform, requiring a large number of personnel to operate each switch individually, and there are also safety risks involved.

[0003] While remote video monitoring can save manpower to some extent by automatically identifying the opening and closing angles, existing deep learning-based automatic identification methods still fall short of reliability requirements in terms of accuracy. This necessitates secondary confirmation of the switch status by maintenance personnel, increasing monitoring workload, consuming significant time, and failing to detect issues of incomplete opening or closing. Furthermore, some three-dimensional position measurement technologies, such as 3D LiDAR, can achieve precise measurement of opening and closing angles, but their large size and weight, massive computational demands leading to poor real-time performance, and high cost make them unsuitable for large-scale applications. Summary of the Invention

[0004] To address the above problems, this invention proposes a method for identifying the opening and closing angles of disconnecting switches based on video images, comprising:

[0005] The opening and closing process of the disconnecting switch is filmed to obtain multiple sets of video images under different lighting conditions. Based on the video images, an image sequence of the opening and closing process of the disconnecting switch is obtained. The image sequence is then extracted from the image of the rotating arm of the disconnecting switch to obtain the rotating arm sequence image.

[0006] Align the spiral arm sequence images to determine feature points on the spiral arm sequence images, and determine the three-dimensional coordinates of the feature points;

[0007] Connect the feature points to determine the spatial position of the rotating arm, and determine the opening and closing angles of the disconnecting switch based on the three-dimensional coordinates and the spatial position of the rotating arm.

[0008] The opening and closing angles are determined and correlated with the rotating arm sequence image as a reference calibration image;

[0009] After acquiring the target swing arm sequence image of the target disconnector, the target swing arm sequence image is matched with the reference calibration image to identify the opening and closing angles of the target disconnector.

[0010] Optionally, the image sequence can be extracted for the rotating arm portion of the disconnector switch based on the differential image method to obtain the rotating arm sequence image.

[0011] Optionally, aligning the rotating arm sequence images includes: acquiring the internal, external, and distortion parameters of the imaging device that captures the opening and closing process of the disconnecting switch; performing stereo calibration and stereo correction on the imaging device based on the internal, external, and distortion parameters; and aligning the rotating arm sequence images based on the stereo calibration and stereo correction of the imaging device.

[0012] Optionally, the three-dimensional coordinates of the feature points can be determined based on the principle of parallax positioning.

[0013] Optionally, the opening and closing angles of the disconnecting switch can be determined by using the method of finding the three-dimensional inverse cosine of space.

[0014] Furthermore, this invention also proposes a system for recognizing the opening and closing angles of disconnecting switches based on video images, comprising:

[0015] The camera unit is used to capture the opening and closing process of the disconnecting switch to obtain multiple sets of video images under different lighting conditions. Based on the video images, an image sequence of the opening and closing process of the disconnecting switch is obtained. The image sequence is then used to extract the image of the rotating arm portion of the disconnecting switch to obtain the rotating arm sequence image.

[0016] A feature extraction unit is used to align the spiral arm sequence image to determine feature points on the spiral arm sequence image and to determine the three-dimensional coordinates of the feature points;

[0017] The calculation unit is used to connect the feature points to determine the spatial position of the rotating arm, and to determine the opening and closing angle of the disconnecting switch based on the three-dimensional coordinates and the spatial position of the rotating arm.

[0018] The association unit is used to determine the association between the opening and closing angles and the rotating arm sequence image, serving as a reference calibration image;

[0019] The identification unit is used to match the target swing arm sequence image with a reference calibration image after acquiring the target swing arm sequence image of the target disconnector switch, so as to identify the opening and closing angle of the target disconnector switch.

[0020] Optionally, the imaging unit extracts images of the disconnector switch arm portion of the image sequence based on the differential image method to obtain the arm sequence image.

[0021] Optionally, the feature extraction unit aligns the rotating arm sequence images, including: acquiring the internal, external, and distortion parameters of the imaging device that captures the opening and closing process of the disconnecting switch; performing stereo calibration and stereo correction on the imaging device based on the internal, external, and distortion parameters; and aligning the rotating arm sequence images based on the stereo calibration and stereo correction of the imaging device.

[0022] Optionally, a feature extraction unit determines the three-dimensional coordinates of feature points based on the principle of disparity positioning.

[0023] Optionally, the calculation unit uses the method of finding the three-dimensional inverse cosine in space to determine the opening and closing angles of the disconnecting switch.

[0024] In another aspect, the present invention also provides a computing device, comprising: one or more processors;

[0025] A processor is used to execute one or more programs;

[0026] When the one or more programs are executed by the one or more processors, the method described above is implemented.

[0027] In another aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the method described above.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0029] This invention provides a method for identifying the opening and closing angles of disconnecting switches based on video images. The method includes: capturing multiple sets of video images under different lighting conditions during the opening and closing process of the disconnecting switch; obtaining an image sequence of the opening and closing process based on the video images; extracting images of the rotating arm portion of the disconnecting switch from the image sequence to obtain a rotating arm sequence image; aligning the rotating arm sequence image to determine feature points on the rotating arm sequence image and determining the three-dimensional coordinates of the feature points; connecting the feature points to determine the spatial position of the rotating arm; determining the opening and closing angles of the disconnecting switch based on the three-dimensional coordinates and the spatial position of the rotating arm; associating the determined opening and closing angles with the rotating arm sequence image as a reference calibration image; and matching the target rotating arm sequence image of the target disconnecting switch with the reference calibration image after obtaining the target rotating arm sequence image of the target disconnecting switch to identify the opening and closing angles of the target disconnecting switch. This invention determines the three-dimensional coordinates of the rotating arm through video images and then determines the spatial opening and closing angles based on the three-dimensional coordinates, which is low-cost and easy to implement. Attached Figure Description

[0030] Figure 1 is a flowchart illustrating the method of the present invention;

[0031] Figure 2 is a schematic diagram of the implementation process of the method of the present invention;

[0032] Figure 3 is a schematic diagram of the identification device used in the implementation of the method of the present invention;

[0033] Figure 4 is a schematic diagram of the system of the present invention. Detailed Implementation

[0034] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0035] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0036] Example 1:

[0037] This invention proposes a method for identifying the opening and closing angles of disconnecting switches based on video images, as shown in Figure 1, including:

[0038] Step 1: Capture the opening and closing process of the disconnecting switch to obtain multiple sets of video images under different lighting conditions. Based on the video images, obtain an image sequence of the opening and closing process of the disconnecting switch. Extract the image sequence of the disconnecting switch rotating arm portion to obtain the rotating arm sequence image.

[0039] Step 2: Align the spiral arm sequence images to determine the feature points on the spiral arm sequence images and determine the three-dimensional coordinates of the feature points;

[0040] Step 3: Connect the feature points to determine the spatial position of the rotating arm. Based on the three-dimensional coordinates and the spatial position of the rotating arm, determine the opening and closing angles of the disconnecting switch.

[0041] Step 4: Determine the correlation between the opening and closing angles and the rotating arm sequence image, and use it as a reference calibration image;

[0042] Step 5: After acquiring the target swing arm sequence image of the target disconnector, match the target swing arm sequence image with the reference calibration image to identify the opening and closing angles of the target disconnector.

[0043] Specifically, the differential image method is used to extract the image of the disconnector switch arm portion of the image sequence to obtain the arm sequence image.

[0044] The alignment of the rotating arm sequence images includes: acquiring the internal, external, and distortion parameters of the imaging device that captures the opening and closing process of the disconnecting switch; performing stereo calibration and stereo correction on the imaging device based on the internal, external, and distortion parameters; and aligning the rotating arm sequence images based on the stereo calibration and stereo correction of the imaging device.

[0045] Among them, the three-dimensional coordinates of the feature points are determined based on the principle of parallax positioning.

[0046] Among them, the opening and closing angles of the disconnecting switch are determined by using the method of finding the three-dimensional inverse cosine of space.

[0047] The present invention will be further described below with reference to embodiments:

[0048] The implementation process, as shown in Figure 2, includes:

[0049] Step 101: Set up an identification device at the measurement point (the identification device is used to mount the shooting device; the shooting device used in this implementation is a dual-camera 3D perception platform). As shown in Figure 3, use the dual-camera 3D perception platform to capture multiple sets of image sequences of the entire process of opening and closing the disconnecting switch under different lighting conditions.

[0050] Step 102: The differential image method is used to initially extract the rotating arm part of the disconnecting switch movement. As prior knowledge, further features are extracted, and the rotating arm part in each frame of the image is accurately and clearly identified based on the deep learning algorithm.

[0051] Step 103: At the measurement point, use the outdoor calibration field to calibrate the internal, external, and distortion parameters of all cameras.

[0052] Step 104: Perform stereo calibration and stereo correction on the two cameras of the dual-camera 3D perception platform, aligning the sequence image pairs of the switch arm. Perform stereo calibration on the single-camera continuous monitoring terminal and the dual-camera 3D perception platform to achieve geometric correction of the single-camera camera.

[0053] Step 105: Locate feature points on the corrected spiral arm sequence image pair and determine the three-dimensional coordinates of the feature points based on the parallax positioning principle.

[0054] Step 106: Determine the spatial positions of the two rotating arms based on the lines connecting the feature points, and calculate the opening and closing angles of the switches in the action sequence diagram using the method of finding the three-dimensional inverse cosine of space.

[0055] Step 107: Save the image of the rotating arm and record the correspondence between each angle and the image, as a reference calibration for real-time video monitoring.

[0056] Step 108: Based on target detection technology, extract the image of the disconnector switch arm in real time from the video footage captured by the single camera, and match it with the image of the switch arm recorded by the dual cameras to obtain the precise opening and closing angle of the disconnector switch in real time.

[0057] The identification device includes:

[0058] Dual-camera 3D perception platform, single-camera continuous monitoring terminal, outdoor calibration field, communication module, data analysis host;

[0059] The dual-camera 3D perception platform includes two cameras capable of recording 1080P high-definition visible light images and a fixed support with a slide rail. The dual cameras can be firmly fixed on the slide rail and the camera spacing can be freely adjusted to obtain the 3D position information of the disconnector switch arm surface.

[0060] The single-camera continuous monitoring terminal is used to capture real-time status images of the switch arm.

[0061] The outdoor calibration field is used to calibrate the internal and external parameters and correct distortion of the dual-camera 3D perception platform and the single-camera continuous monitoring terminal.

[0062] The communication module is used to transmit the video image information captured by the camera to the analysis host, and is also used for information transmission between the analysis host and the host computer.

[0063] The analysis host is used for data processing and the implementation of functional algorithms.

[0064] The dual-camera 3D perception platform can calibrate the angle information of multiple disconnect switches. After that, each disconnect switch only needs a single camera to continuously monitor the terminal to identify the opening and closing angles in real time.

[0065] Step 102 specifically includes the differential image method calculating the moving spiral arm portion in the image by performing a difference operation between the current frame image and the background image. The background image refers to a monitoring image that does not contain the spiral arm, and can be obtained by averaging and stacking the image sequence. The implementation of the image sequence averaging and stacking is as follows:

[0066]

[0067] Among them, gt g is the grayscale value of pixel t in the background image. i Let t be the grayscale value of pixel t in the i-th frame of the image sequence, and k represent the number of images in the image sequence.

[0068] Using the obtained images of the moving rotating arm as prior knowledge, the edge features of the images are extracted using the Canny algorithm, and morphological operations are used to fill the gaps to further obtain features such as shape and texture. These features are then used to train a deep learning-based object detection algorithm model, thereby identifying clearer and more accurate images of the rotating arm in each frame. At the same time, the algorithm model can also be directly used to identify the rotating arm in real-time monitoring videos from a single camera.

[0069] Step 103 specifically includes: using a dual-camera 3D perception platform to capture checkerboard images from different angles, thereby calibrating the internal parameters of the two cameras, such as the pixel focal length and the offset from the origin of the pixel coordinate system to the optical axis, as well as the external parameters such as the rotation matrix and translation vector, and the distortion parameters.

[0070] Step 104 specifically includes: obtaining the positional relationship between the coordinate systems of the two cameras of the dual-camera 3D perception platform through the stereo calibration, and aligning the sequence image pairs of the switch arm horizontally through stereo correction, so as to facilitate image processing using a stereo matching algorithm.

[0071] The positional relationship between the single-camera continuous monitoring terminal camera coordinate system and the dual-camera three-dimensional perception platform camera coordinate system is obtained through the stereo calibration, and the single-camera camera is geometrically corrected using the affine transformation method.

[0072] Step 105 specifically includes: In this embodiment, the centroid of the grayscale image, the connection point of the disconnector arm and the support column are used as feature points. The centroid pixel coordinates of the corrected arm sequence image to the grayscale image are calculated, the pixel coordinates of the two connection points of the disconnector arm and the support column are manually calibrated, and the three-dimensional coordinates of each point are accurately calculated based on the parallax positioning principle.

[0073] The pixel coordinates of the centroid of the spiral arm grayscale image are obtained by calculating the zeroth moment and the first moments in the row and column directions of the grayscale image.

[0074] Zeroth moment M 00 =∑ i ∑ j g(i,j), where g(i,j) represents the gray value of a pixel;

[0075] First moment M of the direction 01 =∑ i ∑ j j·g(i,j);

[0076] First-order moment M of the column 10 =∑ i ∑j i·g(i,j);

[0077] centroid x-coordinate ordinate

[0078] Step 106 specifically includes: determining the spatial positions of the two rotating arms by connecting the connection point to the center of mass of the rotating arms. Based on the difference in the three-dimensional coordinates of the two centers of mass, the two connecting lines are translated to be coplanar, and the achievable closing angle is calculated using a three-dimensional inverse cosine function.

[0079] Step 107 specifically includes: saving an image of a rectangular region that is as small as possible, which can cover the entire process of the rotating arm movement and leave a certain margin.

[0080] Step 108 specifically includes:

[0081] Step 108-1, Construct a rectangular template: Extract the center of the switch arm image extracted from the single-camera video frame based on the k-means clustering algorithm, and use it as the region center to construct a rectangular template;

[0082] Step 108-2: Take an image of the same size as the template from the rectangular region image saved in step 107 and use it as the calculation window;

[0083] Step 108-3: Calculate the correlation coefficient between the template and the pixels in the calculation window based on the grayscale matrix to measure the degree of similarity;

[0084] Step 108-4: Repeat steps 108-2 and 108-3 until all calculation windows have been traversed;

[0085] Step 108-5: Select the image corresponding to the calculation window with the largest correlation coefficient, and extract the angle corresponding to the image as the opening and closing angle of the disconnecting switch at this time.

[0086] This invention solves the problems of existing sensor-based methods for detecting the opening and closing angles of disconnecting switches, such as difficult installation, complex maintenance, high labor costs, low accuracy, large computational load, poor real-time performance, and expensive equipment. Through three-dimensional positioning and image recognition, it can achieve real-time, high-precision identification of the opening and closing angles of disconnecting switches in substations at low cost, thus contributing to the intelligent and automated operation and maintenance of substations.

[0087] Example 2:

[0088] This invention also proposes a system 200 for identifying the opening and closing angles of disconnecting switches based on video images, as shown in Figure 4, comprising:

[0089] The shooting unit 201 is used to shoot the opening and closing process of the disconnecting switch to obtain multiple sets of video images under different lighting conditions. Based on the video images, an image sequence of the opening and closing process of the disconnecting switch is obtained. The image sequence is used to extract the image of the rotating arm part of the disconnecting switch to obtain the rotating arm sequence image.

[0090] The feature extraction unit 202 is used to align the spiral arm sequence image to determine feature points on the spiral arm sequence image and determine the three-dimensional coordinates of the feature points;

[0091] The calculation unit 203 is used to connect the feature points to determine the spatial position of the rotating arm, and to determine the opening and closing angle of the disconnecting switch based on the three-dimensional coordinates and the spatial position of the rotating arm.

[0092] Association unit 204 is used to determine the association between the opening and closing angles and the rotating arm sequence image as a reference calibration image;

[0093] The identification unit 205 is used to match the target swing arm sequence image with a reference calibration image after acquiring the target swing arm sequence image of the target disconnecting switch, so as to identify the opening and closing angle of the target disconnecting switch.

[0094] The imaging unit 201 extracts images of the isolating switch arm portion of the image sequence based on the differential image method to obtain the arm sequence image.

[0095] The feature extraction unit 202 aligns the rotating arm sequence images, including: acquiring the internal, external, and distortion parameters of the imaging device that captures the opening and closing process of the disconnecting switch; performing stereo calibration and stereo correction on the imaging device based on the internal, external, and distortion parameters; and aligning the rotating arm sequence images based on the stereo calibration and stereo correction of the imaging device.

[0096] Among them, the feature extraction unit 202 determines the three-dimensional coordinates of the feature points based on the principle of parallax positioning.

[0097] Among them, the calculation unit 203 uses the method of finding the three-dimensional inverse cosine in space to determine the opening and closing angle of the disconnecting switch.

[0098] This invention determines the three-dimensional coordinates of the rotating arm through video images, and then determines the opening and closing angles in space based on the three-dimensional coordinates. It is low-cost and easy to implement.

[0099] Example 3:

[0100] Based on the same inventive concept, this invention also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement corresponding method flows or corresponding functions, thereby implementing the steps of the methods in the above embodiments.

[0101] Example 4:

[0102] Based on the same inventive concept, this invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the method in the above embodiments.

[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0104] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0107] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0108] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for identifying the opening and closing angles of disconnecting switches based on video images, characterized in that, The method includes: capturing video images of the opening and closing process of the disconnecting switch under different lighting conditions; obtaining an image sequence of the opening and closing process of the disconnecting switch based on the video images; extracting images of the rotating arm portion of the disconnecting switch from the image sequence to obtain a rotating arm sequence image; aligning the rotating arm sequence image to determine feature points on the rotating arm sequence image and determining the three-dimensional coordinates of the feature points; connecting the feature points to determine the spatial position of the rotating arm; determining the opening and closing angle of the disconnecting switch based on the three-dimensional coordinates and the spatial position of the rotating arm; and determining the relationship between the opening and closing angle and the rotating arm sequence image. The target swing arm sequence image is used as a reference calibration image. After acquiring the target swing arm sequence image of the target disconnector, the target swing arm sequence image is matched with the reference calibration image to identify the opening and closing angles of the target disconnector. The centroid of the grayscale image and the connection points between the disconnector swing arm and the support are used as feature points. The pixel coordinates of the centroid of the corrected swing arm sequence image relative to the grayscale image are calculated, and the pixel coordinates of the two connection points between the disconnector swing arm and the support are calibrated. The three-dimensional coordinates of each point are accurately calculated based on the parallax positioning principle. The pixel coordinates of the centroid of the swing arm grayscale image are obtained by calculating the zero-order moment and the first-order moments in the row and column directions of the grayscale image. The calculation formula is as follows: Zero-order moment... ， The grayscale value of a pixel; first-order moment in the row direction First-order moment of the collinear direction ; Centroid x-coordinate y-axis 。 2. The method according to claim 1, characterized in that, The differential image method is used to extract the image of the disconnector switch arm portion of the image sequence to obtain the arm sequence image.

3. The method according to claim 1, characterized in that, The alignment of the rotating arm sequence images includes: acquiring the internal, external, and distortion parameters of the imaging device that captures the opening and closing process of the disconnecting switch; performing stereo calibration and stereo correction on the imaging device based on the internal, external, and distortion parameters; and aligning the rotating arm sequence images based on the stereo calibration and stereo correction of the imaging device.

4. The method according to claim 1, characterized in that, The opening and closing angles of the disconnecting switch are determined by using the method of finding the three-dimensional inverse cosine of space.

5. A system for recognizing the opening and closing angles of disconnecting switches based on video images, characterized in that, The system includes: a camera unit for capturing images of the opening and closing process of the disconnecting switch to obtain multiple sets of video images under different lighting conditions; based on the video images, acquiring an image sequence of the opening and closing process of the disconnecting switch; and extracting images of the rotating arm portion of the disconnecting switch from the image sequence to obtain a rotating arm sequence image; a feature extraction unit for aligning the rotating arm sequence image to determine feature points on the rotating arm sequence image and determining the three-dimensional coordinates of the feature points; a calculation unit for connecting the feature points to determine the spatial position of the rotating arm; and determining the opening and closing angle of the disconnecting switch based on the three-dimensional coordinates and the spatial position of the rotating arm; and an association unit for determining the opening and closing angle. The image is associated with the rotating arm sequence image as a reference calibration image; the recognition unit is used to match the target rotating arm sequence image with the reference calibration image after acquiring the target disconnecting switch to identify the opening and closing angles of the target disconnecting switch; wherein, the centroid of the grayscale image and the connection point between the disconnecting switch rotating arm and the support are used as feature points; the pixel coordinates of the centroid of the corrected rotating arm sequence image relative to the grayscale image are calculated, the pixel coordinates of the two connection points of the disconnecting switch rotating arm and the support are calibrated, and the three-dimensional coordinates of each point are accurately calculated according to the parallax positioning principle; wherein, the pixel coordinates of the centroid of the rotating arm grayscale image are obtained by calculating the zero-order moment and the first-order moments in the row and column directions of the grayscale image, and the calculation formula is as follows: zero-order moment ， The grayscale value of a pixel; first-order moment in the row direction First-order moment of the collinear direction ; Centroid x-coordinate y-axis 。 6. The system according to claim 5, characterized in that, The imaging unit extracts images of the isolating switch arm portion of the image sequence based on the differential image method to obtain the arm sequence image.

7. The system according to claim 5, characterized in that, The feature extraction unit aligns the rotating arm sequence images by: acquiring the internal, external, and distortion parameters of the imaging device that captures the opening and closing process of the disconnecting switch; performing stereo calibration and stereo correction on the imaging device based on the internal, external, and distortion parameters; and aligning the rotating arm sequence images based on the stereo calibration and stereo correction of the imaging device.

8. The system according to claim 5, characterized in that, The calculation unit uses the method of calculating the three-dimensional inverse cosine in space to determine the opening and closing angles of the disconnecting switch.

9. A computer device, characterized in that, include: One or more processors; A processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the method described in any one of claims 1-4 is implemented.

10. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the method as described in any one of claims 1-4.

Images