Method for identifying and tracking multiple targets in transformer substation based on image processing technology

Abstract

The invention relates to the technical field of image processing and power monitoring, in particular to a method for identifying and tracking multiple targets in a transformer substation based on an image processing technology, which comprises the following steps of: S1, acquiring a monitoring video stream of the transformer substation in real time, and outputting a filtered image; s2, extracting a moving target contour, and generating a target contour set; s3, calculating a spatial gradient amplitude and an electromagnetic interference quantization parameter to form a feature vector; s4, inputting the feature vector into a classifier, and outputting an equipment target label or a biological target label; s5, establishing a linear prediction model, and outputting a prediction coordinate sequence; and S6, when the predicted coordinate sequence intersects with the safety area of the equipment target, generating an intrusion alarm signal. According to the invention, through combination of target classification identification and trajectory prediction, accurate identification and early warning of a biological target in a transformer substation in an electromagnetic interference environment are realized, and the response capability and the safety prevention and control level of a system to a dynamic intrusion behavior are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image processing and power monitoring, and particularly relates to a substation multi-target identification and tracking method based on image processing technology. BACKGROUND

[0002] With the continuous improvement of the intelligence and automation level of substations, the safety protection and operation and maintenance monitoring of field devices are increasingly demanded; the traditional video monitoring system mainly relies on manual patrol and simple image change detection method, and it is difficult to timely and accurately identify and track multiple types of targets in the substation, especially in a strong electromagnetic interference environment, which is prone to false positives, false negatives and response lag and other problems.

[0003] In addition, the interaction between devices and personnel, biological targets is frequent in the substation scene, and if the intrusion behavior cannot be timely distinguished, it is easy to cause device failure or safety accidents, which brings major hidden dangers to the stable operation of the power system; the existing technology in the aspects of multi-target identification and dynamic intrusion alarm generally has the problems of poor adaptability to complex electromagnetic interference, insufficient target classification accuracy, and lack of prediction and early warning mechanism, and it is difficult to meet the actual needs of the substation site for high reliability and intelligent prevention and control. Therefore, there is an urgent need for a substation multi-target identification and tracking method based on image processing technology to solve the above problems. SUMMARY

[0004] Based on the above purpose, the present application provides a substation multi-target identification and tracking method based on image processing technology.

[0005] A substation multi-target identification and tracking method based on image processing technology, comprising the following steps: S1: real-time acquisition of substation monitoring video stream, and electromagnetic interference filtering of each frame of image, output of filtered image; S2: adaptive threshold segmentation of the filtered image, extraction of the motion target contour, and generation of a target contour set; S3: calculation of the spatial gradient amplitude and electromagnetic interference quantization parameters of each contour in the target contour set, formation of a feature vector; S4: input of the feature vector into a classifier, and output of a device target label or a biological target label; S5: calculation of the motion vector for the contour with the biological target label, construction of a linear prediction model based on the historical trajectory points, and output of a predicted coordinate sequence; S6: generation of an intrusion alarm signal when the predicted coordinate sequence intersects with the safety area of the device target.

[0006] Optionally, the S1 specifically comprises: S11: deploying a high-definition camera with network transmission function in the monitoring area of the substation, the camera being configured with a synchronous clock and a frame buffer structure, and outputting video image frames to the outside through a preset frame rate parameter, the video image frames being transmitted in real time to an image processing end through a wired Ethernet interface; S12: performing electromagnetic interference filtering processing on the received video image frames, first performing two-dimensional Fourier transform on the image to obtain a frequency domain image, then suppressing the frequency spectrum components in the frequency band range within the set interference frequency band in the frequency domain image, and finally restoring the filtered image through inverse Fourier transform.

[0007] Optionally, the S2 specifically includes: S21: performing pixel-by-pixel difference operation on the filtered image obtained in S1 and the previous frame filtered image to obtain a difference image ; S22: performing adaptive threshold segmentation on the difference image , calculating the best segmentation threshold of the whole image by using the Otsu method , and marking the positions with pixel values greater than as foreground regions to generate a binary segmentation image , which is expressed as: ; S23: performing contour extraction processing on the binary segmentation image , detecting the edge pixels of the connected regions, extracting the outer boundaries of each foreground region, and constituting a target contour set.

[0008] Optionally, the S23 specifically includes: S231: performing eight-neighbor connected region scanning on the binary segmentation image obtained in S22, sequentially traversing the foreground pixel points with a value of 1 by using a breadth-first search algorithm, marking all the pixels connected with the corresponding pixel as the same connected region, and constructing a foreground region set; S232: for each connected region, constructing its boundary contour, detecting its outer edge by using a boundary tracking algorithm, starting from the starting foreground pixel point in the clockwise direction, judging whether there is a pixel with a value of 1 and not visited in the eight-neighbor domain of the current pixel, if there is, adding the current contour path and continuing to search until returning to the starting point to form a complete contour path; S233: taking the set of all contour paths as the target contour set, and performing two-level screening processing on each contour; The first level is to calculate the number of contour points , if the number of contour points is less than a preset threshold, the corresponding contour is removed; The second level is to calculate the area of the minimum circumscribed rectangle of the contour , if the area of the minimum circumscribed rectangle of the contour is greater than a preset threshold, the corresponding contour is removed; ​Similarly, the corresponding contours are also removed; among them, This is the minimum threshold for the number of contour points; This is the minimum threshold for the area of ​​the circumscribed rectangle.

[0009] Optionally, S3 specifically includes: S31: Perform grayscale spatial gradient calculation on the image region corresponding to each contour in the target contour set. Use the Sobel operator to extract the image gradients in the horizontal and vertical directions respectively, and calculate the spatial gradient magnitude of the corresponding pixel. ; S32: Spatial gradient magnitude for all pixels within the contour By averaging, the average spatial gradient of the contour is obtained. , as a structural feature indicator of the target contour; S33: Perform a two-dimensional Fourier transform on the contour region image and extract the spectral energy within the interference frequency band as the electromagnetic interference quantization parameter. It is defined as the sum of the power spectral density of the band-stop frequency band in the frequency domain; S34: Calculate the average spatial gradient corresponding to the contour. Electromagnetic interference quantization parameters Combining to form a two-dimensional feature vector .

[0010] Optionally, S4 specifically includes: S41: Construct a binary classification model based on support vector machine, using feature vector samples labeled in historical images as the training set, including two categories: biological targets and device targets. Each sample consists of a feature vector and its corresponding label. S42: Solve for the optimal classification hyperplane based on the training set using the maximum margin criterion to obtain the model parameters. Construct the discriminant function Its expression is ,in, The two-dimensional feature vector of the contour to be classified; Let be the normal vector parameter of the hyperplane; For bias terms; S43: Extract the feature vector from S3 Input the trained classifier, if it satisfies If the condition is met, then output the biological target label; if the condition is met, then output the biological target label. Then, the device target label is output, thereby completing the target type determination.

[0011] Optionally, S5 specifically includes: S51: for the contour judged as the biological target label in S4, first extract its contour centroid coordinates in the current frame, and time sequence pairing corresponding coordinates with the centroid coordinates of the corresponding contour in the last frame; based on the change of the centroid position of the two consecutive frames, the motion vector of the current biological target is calculated; S52: for each contour with a biological target label, record the centroid coordinates of the last several frames as a historical trajectory point sequence, and arrange them in time sequence; based on the trajectory data, a linear prediction model of time position relationship is established; S53: apply the constructed linear prediction model to the future several time points, predict the centroid coordinates of the target in the next several frames, and output these predicted coordinates as a predicted coordinate sequence in time sequence.

[0012] Optionally, the S52 specifically comprises: S521: for each contour with a biological target label, extract its centroid coordinates in consecutive frame images, and construct a historical trajectory point sequence , wherein represents the frame number, represents the centroid horizontal and vertical coordinates in the corresponding frame; S522: respectively take time as the independent variable, and take the horizontal coordinate and the vertical coordinate as the dependent variable, construct two independent linear fitting models, calculate the slope and intercept of the linear function by using the least square method, and obtain the linear relationship between time and spatial position; The horizontal prediction model is: ; The vertical prediction model is: ; wherein, represents the predicted centroid coordinates at the future time ; is the estimated value of the horizontal and vertical motion speed; is the initial position offset.

[0013] Optionally, the S6 specifically comprises: S61: based on the preset device target region in the monitoring picture, extract the two-dimensional boundary coordinates of each specified device, and construct the corresponding safety region boundary box; S62: for the biological target prediction coordinate sequence obtained in S5, judge whether it falls into any device safety region frame by frame, if any coordinate point in the prediction coordinate sequence is located in the boundary box corresponding to a device safety region, it is considered that the biological target invades the device region, and it is judged as the intersection state; S63: When at least one predicted coordinate point has a spatial intersection relationship with any device safety area, immediately send an intrusion alarm signal to the system.

[0014] Optionally, the alarm signal includes the number of the biological target, the predicted path, and the identification information of the potential intrusion device area.

[0015] Advantages of the present application: The present application, by performing frequency domain filtering processing on the monitoring image in a strong electromagnetic interference environment, combining adaptive threshold segmentation and contour extraction, constructs a stable target contour set, and through the spatial gradient feature and the frequency spectrum energy feature to form a feature vector, uses a support vector machine model to realize high-precision classification and identification of device targets and biological targets, solves the problem of poor target detection accuracy of existing methods in a complex interference background.

[0016] The present application, by combining the historical trajectory point to calculate the motion vector of the biological target, constructing a linear prediction model to output the coordinate sequence at the future time, and judging the spatial intersection with the safety boundary of the device, triggering the intrusion alarm signal in advance, forms an intelligent protection process of identification, prediction and alarm linkage, effectively improves the response timeliness and identification reliability of the dynamic intrusion target of the substation. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only a part of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0018] Fig. 1 The schematic diagram of the multi-target identification and tracking method of the embodiment of the present application; Fig. 2 The schematic diagram of the output predicted coordinate sequence process of the embodiment of the present application. DETAILED DESCRIPTION

[0019] The present application will be described in detail below in combination with the drawings and specific embodiments. It should be noted here that in order to make the embodiments more detailed, the following embodiments are the best, preferred embodiments, and other alternative ways can also be used by those skilled in the art to implement; and the drawings are only used to describe the embodiments more specifically, and are not intended to specifically limit the present application.

[0020] It is to be noted that references herein to "one embodiment", "an embodiment", "example embodiment", "some embodiments" etc. indicate that the embodiment described can include a particular feature, structure, or characteristic, but every embodiment can not necessarily include the particular feature, structure, or characteristic. Moreover, the descriptions of the features, structures, or characteristics can be implemented in combination with other embodiments whether or not explicitly described in combination with the particular embodiment.

[0021] Generally, the terminology can be understood at least in part from a context of a use of the terminology. For example, the term "one or more" as used herein, depending at least in part upon a context of a use of the term, can be used to describe any feature, structure, or characteristic in a singular sense or can be used to describe combinations of features, structures or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors and can instead allow for additional factors not necessarily explicitly described.

[0022] As shown in Figs. 1-2 A substation multi-target recognition and tracking method based on image processing technology, comprising the following steps: S1: Real-time acquisition of substation monitoring video stream, and electromagnetic interference filtering is performed on each frame of image, and the filtered image is output; S1 specifically includes: S11: Deploying a high-definition camera with network transmission function in the substation monitoring area, the camera is configured with a synchronous clock and a frame buffer structure, and the video image frame is output externally through a preset frame rate parameter, and the video image frame is transmitted in real time to the image processing end through a wired Ethernet interface; S12: Perform electromagnetic interference filtering processing on the received video image frame, first perform two-dimensional Fourier transform on the image to obtain a frequency domain image, then suppress the frequency spectrum components in the frequency band range within the set interference frequency band in the frequency domain image, and finally restore it to a filtered image through inverse Fourier transform; Through the above scheme, high-quality monitoring video can be stably collected in the strong electromagnetic environment of the substation, and the influence of the specific electromagnetic interference frequency band can be effectively suppressed through frequency domain bandpass filtering, ensuring the accuracy and stability of subsequent image segmentation and target recognition processing.

[0023] The steps of performing electromagnetic interference filtering processing are as follows: Two-dimensional Fourier transform: Perform two-dimensional Fourier transform on the received video image frame to obtain a frequency domain image, and the calculation formula is: Wherein, is the gray value of the original image in the spatial domain; is the width and height of the image; is the complex spectrum of the image in the frequency domain; is the frequency coordinate; is an exponential term, used to map the image from spatial domain to frequency domain, each parameter is defined as follows, is the imaginary unit, representing ; is the constant of the circle, representing ; is the frequency component in horizontal and vertical direction, respectively; is the spatial domain coordinate, representing the position of the pixel in the image; is the total number of pixels in the horizontal direction (width) of the image; is the total number of pixels in the vertical direction (height) of the image; is the normalized mapping relationship between spatial position and frequency in horizontal and vertical direction, respectively; Band-stop filter design: for substation specific electromagnetic interference frequency band , construct a band-stop filter function , which is defined as: , respectively, are the inner and outer diameter threshold of the interference frequency band, set according to the field interference spectrum; represents the suppression of spectral components in the band-stop region, and the original spectrum is preserved in the remaining region; Spectrum filtering processing: point-by-point multiplication operation of the frequency domain image and the band-stop filter, to obtain the filtered frequency domain image ; Two-dimensional inverse Fourier transform: perform two-dimensional inverse Fourier transform on the filtered frequency domain image , to restore the spatial domain image , which is the filtered image.

[0024] S2: adaptive threshold segmentation is performed on the filtered image to extract the motion target contour and generate the target contour set; S2 specifically includes: S21: perform pixel-by-pixel difference operation on the filtered image obtained in S1 and its previous frame filtered image to obtain the difference image , the calculation formula is: , wherein, is the gray value of the current frame image; is the gray value of the previous frame image; S22: perform adaptive threshold segmentation on the difference image , calculate the best segmentation threshold of the whole image using Otsu method , and mark the positions with pixel value greater than as foreground region to generate binary segmentation image , expressed as: ; wherein, A global threshold value calculated adaptively by the maximum inter-class variance criterion; S23: binary segmentation image The contour extraction process is performed to detect the edge pixels of the connected regions, extract the outer boundary of each foreground region, and form a target contour set. Through the above steps, the accurate target region extraction operation can be performed on the continuous monitoring image frames without manual intervention. The foreground extraction based on the frame difference is adapted to the dynamic scene, the global optimal segmentation threshold of the Otsu method ensures the stability of the foreground region, and finally the contour set provides a structured input basis for the subsequent feature extraction and classification recognition steps.

[0025] The Otsu method is used to calculate the optimal segmentation threshold of the whole image The steps are as follows: All pixel values of the difference image are counted to construct a gray level histogram. The image gray level is (taking 256 as the value), the gray value is , and the number of pixels corresponding to each gray level is , and the total number of image pixels is: ; the corresponding normalized probability distribution is: , wherein represents the probability of the gray level , satisfying ; The gray value is divided into foreground and background two categories according to the threshold . For each possible , the following statistics are calculated: The total probability of foreground pixels: ; The total probability of background pixels: ; The foreground mean value: ; The background mean value: ; The overall mean value of the image: ; For each , the inter-class variance is calculated, and the expression is: ; All are traversed to find the threshold that maximizes the inter-class variance, and the expression is: , wherein The global threshold value is the best global threshold value for image segmentation; by using the Otsu method to calculate the adaptive threshold value, the optimal segmentation point can be automatically selected based on the image gray scale distribution, so that the threshold value is dynamically adjusted under different light conditions and electromagnetic interference environments, the robust foreground extraction of the moving target is realized, and the accuracy and consistency of the subsequent contour detection are enhanced.

[0026] S23 specifically comprises: S231: performing binaryzation on the image obtained in S22 to obtain a binaryzation image performing eight-neighbor connected region scanning, sequentially traversing the foreground pixel points with a value of 1 by using a breadth-first search algorithm, marking all the pixels connected with the corresponding pixel as the same connected region, and constructing a foreground region set; S232: for each connected region, constructing a boundary contour thereof, detecting the outer edge thereof by using a boundary tracking algorithm, starting from a starting foreground pixel point in a clockwise direction, judging whether there is a pixel with a value of 1 and not visited in the eight neighbors of the current pixel, if there is, adding the current contour path and continuing to search until returning to the starting point to form a complete contour path; S233: taking all the contour path sets as a target contour set, and performing two-stage screening processing on each contour; In the first stage, the number of contour points is calculated , if the following condition is met , the corresponding contour is removed; In the second stage, the area of the minimum circumscribed rectangle of the contour is calculated , if the following condition is met , the corresponding contour is also removed; wherein, is the minimum threshold value of the number of contour points; is the minimum threshold value (in pixels) of the area of the circumscribed rectangle; the above steps can accurately separate the independent moving target in the binary image and extract the complete outer boundary contour by using the combination of connected domain scanning and boundary tracking, avoid the contour information loss caused by edge breakage or polygon loss, lay a precise contour foundation for subsequent target feature extraction and classification recognition, and improve the overall recognition accuracy of the system.

[0027] S3: calculating the spatial gradient amplitude and the electromagnetic interference quantization parameter of each contour in the target contour set to form a feature vector; S3 specifically comprises: S31: performing gray scale spatial gradient calculation on the image region corresponding to each contour in the target contour set, extracting the image gradients in the horizontal direction and the vertical direction by using a Sobel operator, and calculating the spatial gradient amplitude of the corresponding pixel , the expression of which is: , wherein, is the spatial gradient amplitude of the pixel point . horizontal gradient value calculated by Sobel operator; vertical gradient value calculated by Sobel operator; pixel coordinates in the corresponding contour; S32: average the spatial gradient amplitudes of all pixels in the contour to obtain the average spatial gradient of the contour S33: perform two-dimensional Fourier transform on the contour region image, and extract the frequency spectrum energy in the interference frequency band as the electromagnetic interference quantization parameter , which is expressed as: , wherein, is the average spatial gradient of the contour; is the total number of pixel points in the contour; S33: perform two-dimensional Fourier transform on the contour region image, and extract the frequency spectrum energy in the interference frequency band as the electromagnetic interference quantization parameter , which is defined as the total power spectrum density of the band-stop frequency band in the frequency domain; the calculation formula is: , wherein, is the electromagnetic interference quantization parameter of the contour; is the two-dimensional Fourier transform result of the contour region image; is the horizontal and vertical frequency coordinate in the frequency domain; is the lower limit and upper limit of the preset electromagnetic interference frequency band range; is the modulus of the frequency amplitude, used for filtering the frequency band; S34: combine the average spatial gradient of the contour corresponding to the electromagnetic interference quantization parameter to form a two-dimensional feature vector ; the above steps jointly extract the spatial structure feature and the frequency domain interference feature in each contour region to construct a two-dimensional feature vector with discriminability, which can effectively improve the classification accuracy and environmental adaptability of subsequent device targets and biological targets in the complex background of the substation.

[0028] S4: input the feature vector into the classifier to output a device target label or a biological target label; S4 specifically includes: S41: construct a binary classification model based on support vector machine, and use the labeled feature vector samples in the historical images as the training set, including two types of biological targets and device targets, each sample is composed of a feature vector and its corresponding label ; the expression is: , wherein, is the training sample set; is the two-dimensional feature vector of the th training sample; For the corresponding target category label, +1 represents biological targets and -1 represents equipment targets; S42: Solve for the optimal classification hyperplane based on the training set using the maximum margin criterion to obtain the model parameters. Construct the discriminant function Its expression is ,in, The two-dimensional feature vector of the contour to be classified; Let be the normal vector parameter of the hyperplane; For bias terms; S43: Extract the feature vector from S3 Input the trained classifier, if it satisfies If the condition is met, then output the biological target label; if the condition is met, then output the biological target label. Then, the device target label is output, thereby completing the target type determination. The above steps use the support vector machine model to construct the decision boundary, and input the two-dimensional feature vector containing structural information and electromagnetic interference characteristics into the trained classifier for discrimination. It can stably distinguish between equipment targets and intrusive biological targets in substations under different interference backgrounds, providing an accurate classification basis for subsequent tracking and alarm processing.

[0029] S5: For contours with biological target labels, calculate motion vectors, construct a linear prediction model based on historical trajectory points, and output the predicted coordinate sequence; S5 specifically includes: S51: For the contour identified as a biological target in S4, firstly, extract its centroid coordinates in the current frame, and then temporally pair these coordinates with the centroid coordinates of the corresponding contour in the previous frame; based on the change in centroid position between two consecutive frames, calculate the motion vector of the current biological target, reflecting its direction and velocity; the calculation formula is as follows: ,in, For biological targets Motion vector in the current frame; For the current frame Biological Targets The coordinates of the centroid; Previous frame Biological Targets The coordinates of the centroid; S52: For each contour with a biological target label, record the centroid coordinates of its most recent several frames as a historical trajectory point sequence and arrange them in chronological order; based on the trajectory data, establish a linear prediction model of temporal position relationship, using the historical centroid position as input sample to fit the spatial position change trend of the target at subsequent times. S53: Apply the constructed linear prediction model to the future time, predict the centroid coordinates of the target in the next multiple frames, and output the prediction coordinates in time sequence as a prediction coordinate sequence for subsequent judgment whether to enter the device safety area.

[0030] S52 specifically includes: S521: For each contour labeled with a biological target, extract its centroid coordinates in consecutive frame images to construct a historical trajectory point sequence , wherein represents the frame number, represents the centroid horizontal and vertical coordinates in the corresponding frame; S522: Respectively take time as the independent variable, and take horizontal coordinate and vertical coordinate as the dependent variable, construct two independent linear fitting models, and calculate the slope and intercept of the linear function by least squares method to obtain the linear relationship between time and spatial position; The horizontal prediction model is: ; The vertical prediction model is: ; wherein, represents the predicted centroid coordinates at future time ; is the estimated value of the horizontal and vertical motion speed (i.e. slope); is the initial position offset (i.e. intercept); The above parameters are calculated by least squares method, and the calculation expressions of the horizontal slope and intercept are as follows: , and the calculation method of the vertical is the same as the above form, only replacing with ; the above steps can efficiently establish the prediction model of the target centroid position changing with time by applying least squares method to linear fitting of historical centroid trajectory points, realize the time sequence inference of the future position of the biological target, and improve the forward-looking judgment ability of the system to dynamic intrusion behavior.

[0031] S6: When the prediction coordinate sequence intersects with the safety area of the device target, generate an intrusion alarm signal; S6 specifically includes: S61: Based on the preset device target area in the monitoring picture, extract the two-dimensional boundary coordinates of each specified device, and construct the corresponding safety area boundary box. The boundary box is set with a fixed buffer distance based on the geometric outer edge of the device to form a rectangular or polygonal area with spatial constraints, which is used to judge whether there is an intrusion behavior; S62: judging whether the biological target prediction coordinate sequence obtained in S5 falls into any device safety area frame by frame, if any coordinate point in the prediction coordinate sequence is located in the boundary box corresponding to a device safety area, it is considered that the biological target invades the device area, and the intersection state is determined; S63: when at least one prediction coordinate point and any device safety area have a spatial intersection relationship, an invasion alarm signal is immediately sent to the system; the above step can predict the potential invasion risk of the biological target before it really approaches the device by judging the spatial intersection of the prediction coordinate sequence and the device safety boundary, and timely generate an alarm signal, realize early intervention and response control, and improve the identification and disposal ability of the substation security system to dynamic invasion targets.

[0032] The alarm signal includes the number of the biological target, the prediction path and the identification information of the potential invasion device area.

[0033] The present application covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present application. In order to make the public have a thorough understanding of the present application, specific details are described in the following preferred embodiments of the present application, and the present application can also be fully understood without the description of these details for those skilled in the art. In addition, in order to avoid unnecessary confusion to the essence of the present application, well-known methods, processes, procedures, elements and circuits are not described in detail.

[0034] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principle of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the present application.

Claims

1. A method for multi-target recognition and tracking in a substation based on image processing technology, characterized in that, Includes the following steps: S1: Real-time acquisition of substation monitoring video stream, electromagnetic interference filtering of each frame, and output of filtered image; S2: Perform adaptive threshold segmentation on the filtered image to extract the contours of moving targets and generate a set of target contours; S3: Calculate the spatial gradient magnitude and electromagnetic interference quantization parameters of each contour in the target contour set to form a feature vector; S4: Input the feature vector into the classifier and output the device target label or biological target label; S5: For contours with biological target labels, calculate motion vectors, construct a linear prediction model based on historical trajectory points, and output the predicted coordinate sequence; S6: When the predicted coordinate sequence intersects with the safe area of ​​the device target, an intrusion alarm signal is generated.

2. The method for multi-target recognition and tracking in a substation based on image processing technology according to claim 1, characterized in that, S1 specifically includes: S11: Deploy high-definition cameras with network transmission capabilities in the substation monitoring area. The cameras are equipped with a synchronous clock and frame buffer structure, and output video image frames to the outside through preset frame rate parameters. The video image frames are transmitted to the image processing terminal in real time through a wired Ethernet interface. S12: Perform electromagnetic interference filtering on the received video image frame. First, perform a two-dimensional Fourier transform on the image to obtain a frequency domain image. Then, suppress the spectral components in the frequency domain image whose frequency band is within the set interference frequency band. Finally, restore the filtered image through an inverse Fourier transform.

3. The method for multi-target recognition and tracking in a substation based on image processing technology according to claim 1, characterized in that, S2 specifically includes: S21: Perform a pixel-by-pixel difference operation between the filtered image obtained in S1 and the filtered image of the previous frame to obtain the difference image. ; S22: For the difference image Adaptive thresholding is performed, and the optimal segmentation threshold for the entire image is calculated using Otsu's method. and pixel values ​​greater than The location is marked as the foreground region, and a binary segmentation image is generated. Its expression is: ; S23: Segmenting the binary image Perform contour extraction processing, detect the edge pixels of connected regions, extract the outer boundary of each foreground region, and form a target contour set.

4. The method for multi-target recognition and tracking in a substation based on image processing technology according to claim 3, characterized in that, S23 specifically includes: S231: The binary segmented image obtained in S22 Perform an eight-neighbor connected region scan, and use a breadth-first search algorithm to traverse the foreground pixels with a value of 1 in turn, mark all pixels connected to the corresponding pixel as the same connected region, and construct a set of foreground regions; S232: For each connected region, construct its boundary contour, use the boundary tracking algorithm to detect its outer edge, start from the starting foreground pixel in a clockwise direction, determine whether there is a pixel with a value of 1 that has not been visited in the eight neighborhoods of the current pixel, if so, add it to the current contour path and continue searching until returning to the starting point to form a complete contour path. S233: Use all contour paths as the target contour set, and perform two-level filtering on each contour; Level 1: Calculate the number of contour points If satisfied If so, the corresponding outline will be removed; The second level calculates the area of ​​the minimum bounding rectangle of the contour. If satisfied Similarly, the corresponding contours are also removed; among them, This is the minimum threshold for the number of contour points; This is the minimum threshold for the area of ​​the circumscribed rectangle.

5. The method for multi-target recognition and tracking in a substation based on image processing technology according to claim 1, characterized in that, S3 specifically includes: S31: Perform grayscale spatial gradient calculation on the image region corresponding to each contour in the target contour set. Use the Sobel operator to extract the image gradients in the horizontal and vertical directions respectively, and calculate the spatial gradient magnitude of the corresponding pixel. ; S32: Spatial gradient magnitude for all pixels within the contour By averaging, the average spatial gradient of the contour is obtained. , as a structural feature indicator of the target contour; S33: Perform a two-dimensional Fourier transform on the contour region image and extract the spectral energy within the interference frequency band as the electromagnetic interference quantization parameter. It is defined as the sum of the power spectral density of the band-stop frequency band in the frequency domain; S34: Calculate the average spatial gradient corresponding to the contour. Electromagnetic interference quantization parameters Combining to form a two-dimensional feature vector .

6. The method for multi-target recognition and tracking in a substation based on image processing technology according to claim 1, characterized in that, S4 specifically includes: S41: Construct a binary classification model based on support vector machine, using feature vector samples labeled in historical images as the training set, including two categories: biological targets and device targets. Each sample consists of a feature vector and its corresponding label. S42: Solve for the optimal classification hyperplane based on the training set using the maximum margin criterion to obtain the model parameters. Construct the discriminant function Its expression is ,in, The two-dimensional feature vector of the contour to be classified; Let be the normal vector parameter of the hyperplane; For bias terms; S43: Extract the feature vector from S3 Input the trained classifier, if it satisfies If the condition is met, then output the biological target label; if the condition is met, then output the biological target label. Then, the device target label is output, thereby completing the target type determination.

7. A method for multi-target recognition and tracking in a substation based on image processing technology according to claim 1, characterized in that, S5 specifically includes: S51: For the contour identified as a biological target in S4, first extract its centroid coordinates in the current frame, and then perform temporal pairing between the corresponding coordinates and the centroid coordinates of the corresponding contour in the previous frame; based on the change in centroid position between two consecutive frames, calculate the motion vector of the current biological target. S52: For each contour with a biological target label, record the centroid coordinates of its most recent few frames as a historical trajectory point sequence and arrange them in chronological order; based on the trajectory data, establish a linear prediction model of the temporal and positional relationship. S53: Apply the constructed linear prediction model to several future moments to predict the centroid coordinates of the target in the next few frames, and output these predicted coordinates as a predicted coordinate sequence in chronological order.

8. A method for multi-target recognition and tracking in a substation based on image processing technology according to claim 7, characterized in that, Specifically, S52 includes: S521: For each contour labeled with a biological target, extract its continuous... Centroid coordinates in frame images are used to construct a sequence of historical trajectory points. ,in Indicates the frame number. Indicates the horizontal and vertical coordinates of the centroid in the corresponding frame; S522: By time As the independent variable, with the horizontal axis as the coordinate. with vertical coordinate With the dependent variable as the variable, two independent linear fitting models are constructed. The slope and intercept of the linear function are calculated using the least squares method to obtain the linear relationship between time and spatial location. The lateral prediction model is: ; The longitudinal prediction model is as follows: ;in, Indicates a future moment The predicted centroid coordinates; These are estimates of the lateral and longitudinal motion velocities; This is the initial position offset.

9. A method for multi-target recognition and tracking in a substation based on image processing technology according to claim 1, characterized in that, S6 specifically includes: S61: Based on the preset target area of ​​the device in the monitoring screen, extract the two-dimensional boundary coordinates of each specified device and construct the corresponding safe area boundary box; S62: For the biological target prediction coordinate sequence obtained in S5, determine frame by frame whether it falls into any device security area. If any coordinate point in the prediction coordinate sequence is located within the bounding box corresponding to a certain device security area, it is considered that the biological target has invaded the device area and is judged as an intersection state. S63: When at least one predicted coordinate point spatially intersects with the security zone of any device, an intrusion alarm signal is immediately sent to the system.

10. A method for multi-target recognition and tracking in a substation based on image processing technology according to claim 9, characterized in that, The alarm signal includes the biological target's ID, predicted path, and identification information of the potential intrusion device area.

Images