Dynamic detection and early warning method and system for invading object of high-voltage transmission line

Abstract

The invention belongs to the technical field of disaster prevention and control of high-voltage transmission lines, and particularly relates to a dynamic detection and early warning method and system for invading objects of a high-voltage transmission line, and the method comprises the steps: obtaining a region image of the high-voltage transmission line; evaluating and updating a background image frame of the obtained high-voltage transmission line area image based on a structural similarity index; analyzing the background image frames before and after updating to obtain an intrusive object recognition contour index set; judging whether the obtained intrusive object recognition contour index set is a non-empty set or not, and determining whether an intrusive object appears in the high-voltage transmission line area image or not; and if the invading object appears, marking and alarming the invading object on the high-voltage power transmission line.

Description

Technical Field

[0001] The present invention belongs to the technical field of disaster prevention and control of high-voltage transmission lines, and particularly relates to a method and system for dynamically detecting and warning of intruding objects on high-voltage transmission lines. Background Art

[0002] The statements in this part only provide background technical information related to the present invention and do not necessarily constitute prior art.

[0003] With the expansion of the power grid scale, the length and coverage of high-voltage transmission lines are increasing day by day, which makes the external environment faced by the transmission lines more complex, and the risk of foreign objects invading around the transmission lines also increases accordingly, bringing greater challenges to the disaster prevention and control and safe operation of the transmission lines. As an important part of the power system, the safe and stable operation of high-voltage transmission lines is directly related to the reliability of power supply and the normal operation of society. However, in the surrounding environment of high-voltage transmission lines, there are often some potential safety hazards, such as birds, drones, construction equipment, and natural disasters. Once an object invades the transmission line area, it may induce chain failures such as line short circuits and tripping, and even cause large-scale power outages, bringing huge losses to the social economy. Therefore, an effective dynamic detection and warning technology is needed to prevent foreign objects from invading the transmission lines, reduce the risk of safety accidents of the transmission lines, and thus ensure the reliable operation of the transmission lines.

[0004] The traditional manual inspection method conducts manual observation at fixed intervals, which has problems such as low efficiency, poor accuracy, and being greatly affected by the environment, and it is difficult to meet the real-time operation and maintenance management requirements of high-voltage transmission lines. Especially the collision of moving objects such as birds with the line is accidental, and it is difficult to carry out early warning and prevention through fixed inspections. Therefore, it is necessary to develop an effective method for dynamically detecting and warning of intruding objects on high-voltage transmission lines, which can realize real-time and automatic monitoring of the transmission lines, timely detect intruding objects and give warnings, and improve the efficiency and accuracy of operation and maintenance management.

[0005] With the development of machine vision, the foreign object detection method for high-voltage transmission lines based on deep learning has been increasingly emphasized. The foreign object detection for high-voltage transmission lines can be carried out based on deep neural network architectures (such as: Faster R-CNN, YOLO and its variants, etc.), focusing on improving the static image processing performance after image acquisition, so as to realize the image recognition of static foreign object targets such as bird nests and dirt. However, in actual high-voltage transmission lines, the intrusion of disaster-causing objects has significant dynamic activity characteristics. The existing foreign object detection methods for high-voltage transmission lines based on deep neural network architectures are difficult to realize the whole-process monitoring of the intrusion dynamics of foreign objects, and thus cannot carry out effective dynamic detection and warning in the early stage of foreign object intrusion, which is not conducive to improving the fault risk control ability of high-voltage transmission lines. Summary of the Invention

[0006] To solve the above problems, the present invention proposes a method and system for dynamically detecting and warning of intruding objects in high-voltage transmission lines. By acquiring and processing the images of the high-voltage transmission line area frame by frame, while updating the background image frame for dynamically detecting intruding objects in real time, the intruding objects appearing in the acquired image frames of the transmission line area are dynamically detected and marked, so as to achieve high-accuracy dynamic detection and warning of intruding objects in high-voltage transmission lines and effectively reduce the risk of transmission line failures.

[0007] According to some embodiments, the first solution of the present invention provides a method for dynamically detecting and warning of intruding objects in high-voltage transmission lines, adopting the following technical solutions:

[0008] A method for dynamically detecting and warning of intruding objects in high-voltage transmission lines, comprising:

[0009] Acquire the image of the high-voltage transmission line area;

[0010] Evaluate and update the background image frame of the acquired high-voltage transmission line area image based on the structural similarity index;

[0011] Analyze the background image frames before and after updating to obtain a set of intrusion object recognition contour indexes;

[0012] Judge whether the obtained set of intrusion object recognition contour indexes is a non-empty set to determine whether there are intrusion objects in the high-voltage transmission line area image; if there are intrusion objects, mark and alarm the intrusion objects on the high-voltage transmission line.

[0013] As a further technical limitation, before acquiring the image of the high-voltage transmission line area, initialize the image acquisition parameters and image analysis and processing parameters, and the image analysis and processing parameters at least include the RGB channel weighting coefficient value of the composite gray transformation and the transformation coefficient value of the gamma non-linear transformation.

[0014] As a further technical limitation, considering the non-linear influence of the light intensity at different time periods on the image acquisition quality, perform a composite gray transformation based on weighted color and gamma non-linear transformation on the RGB image frame of the acquired high-voltage transmission line area image to obtain a two-dimensional composite gray image; combine the set image acquisition time interval and the two-dimensional composite gray image to obtain the background image frame.

[0015] Furthermore, when the image acquisition time interval is reached, complete the acquisition of the current acquired image frame, perform intrusion object detection and marking on the current acquired image according to the high-voltage transmission line area image including the background image frame, and determine whether to update the background image frame according to the intrusion object recognition contour marking result of the current acquired image frame.

[0016] As a further technical limitation, when the set mark of the intrusion object recognition contour indexes of the currently acquired image frame is not empty, it means that there is a foreign object intrusion. The currently acquired image frame and the background image frame are subjected to image fusion. Only the area without contour marks in the currently acquired image frame is retained, and only the contour mark area corresponding to the currently acquired image frame is retained in the background image frame. The two retained images are subjected to fused image fusion to obtain an updated background image frame;

[0017] When the set mark of the intrusion object recognition contour indexes of the currently acquired image frame is empty, it means that there is no foreign object intrusion. The structural similarity index of the acquired image frame and the background image frame is evaluated, and whether to update the background image frame is determined according to the evaluation result of the structural similarity index.

[0018] As a further technical limitation, differential operation is performed on the acquired image frame and the background image frame to obtain a differential image frame; binary threshold processing is performed on the obtained differential image frame to obtain a binary image frame; morphological dilation processing is performed on the obtained binary image frame to obtain an extended binary image frame; the effective outer contour and contour points in the obtained extended binary image frame are obtained to obtain a set of intrusion object recognition contour indexes.

[0019] According to some embodiments, the second solution of the present invention provides a dynamic detection and early warning system for intrusion objects in high-voltage transmission lines, and adopts the following technical solutions:

[0020] A dynamic detection and early warning system for intrusion objects in high-voltage transmission lines, comprising:

[0021] An acquisition module, which is configured to acquire images of the high-voltage transmission line area;

[0022] An update module, which is configured to evaluate and update the background image frame of the acquired high-voltage transmission line area image based on the structural similarity index;

[0023] An analysis module, which is configured to analyze the background image frames before and after the update to obtain a set of intrusion object recognition contour indexes;

[0024] A detection module, which is configured to determine whether the obtained set of intrusion object recognition contour indexes is a non-empty set, and determine whether there is an intrusion object in the high-voltage transmission line area image; if an intrusion object appears, a mark alarm for the intrusion object is given to the high-voltage transmission line.

[0025] According to some embodiments, the third solution of the present invention provides a computer-readable storage medium, and adopts the following technical solutions:

[0026] A computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the steps in the method for dynamically detecting and early warning intrusion objects in high-voltage transmission lines described in the first solution of the present invention.

[0027] According to some embodiments, the fourth solution of the present invention provides an electronic device, adopting the following technical solution:

[0028] An electronic device includes a memory, a processor, and a program stored on the memory and running on the processor. When the processor executes the program, it implements the steps in the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines as described in the first solution of the present invention.

[0029] According to some embodiments, the fifth solution of the present invention provides a computer program product, adopting the following technical solution:

[0030] A computer program product includes software code, and the program in the software code executes the steps in the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines as described in the first solution of the present invention.

[0031] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0032] The present invention acquires and processes the images of the high-voltage transmission line area frame by frame. While real-time updating the background image frames for dynamically detecting intruding objects, it dynamically detects and marks the intruding objects that appear in the collected image frames of the transmission line area, realizing high-accuracy dynamic detection and warning of intruding objects on high-voltage transmission lines, and effectively reducing the risk of transmission line failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings forming a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments and descriptions thereof of this embodiment are used to explain this embodiment and do not constitute an improper limitation to this embodiment.

[0034] Figure 1 It is a flowchart of the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines in Embodiment 1 of the present invention;

[0035] Figure 2 It is a schematic diagram of the steps of the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines in Embodiment 1 of the present invention;

[0036] Figure 3 It is a partial flowchart of the background image frame update in Embodiment 1 of the present invention;

[0037] Figure 4 It is a partial flowchart of obtaining the set of valid recognition contour indexes of intruding objects in the binary image frame in Embodiment 1 of the present invention;

[0038] Figure 5 It is a structural block diagram of the system for dynamically detecting and warning of intruding objects on high-voltage transmission lines in Embodiment 2 of the present invention. Detailed implementation manners

[0039] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0040] It should be noted that the following detailed description is exemplary and is intended to provide further illustration of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which the present invention belongs.

[0041] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular forms are also intended to include the plural forms. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they specify the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0042] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0043] Embodiment 1

[0044] Embodiment 1 of the present invention introduces a method for dynamically detecting and warning of intruding objects on high-voltage transmission lines.

[0045] As Figure 1 shown, a method for dynamically detecting and warning of intruding objects on high-voltage transmission lines includes:

[0046] Obtain an image of the high-voltage transmission line area;

[0047] Evaluate and update the background image frame of the obtained high-voltage transmission line area image based on the structural similarity index;

[0048] Analyze the background image frames before and after the update to obtain a set of intrusion object recognition contour indexes;

[0049] Judge whether the obtained set of intrusion object recognition contour indexes is a non-empty set to determine whether there is an intrusion object in the high-voltage transmission line area image; if there is an intrusion object, mark and alarm the high-voltage transmission line for the intrusion object.

[0050] This embodiment combines Figure 2 to introduce in detail the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines, which specifically includes the following steps:

[0051] S1. System initialization, initialize the image acquisition and image processing analysis parameters;

[0052] S2. Frame-by-frame collect the images of the transmission line area within the camera view angle, and evaluate and update the background image frames for intrusion object dynamic detection based on the structural similarity index;

[0053] S3. Based on the dynamically updated background image frames for intrusion object dynamic detection, perform intelligent analysis and processing of computer graphics on the collected images of the transmission line area frames, and then dynamically detect and mark the intrusion objects that appear in the frame-by-frame collected images of the transmission line area, and at the same time record the events of transmission line intrusion objects and give alarm reminders.

[0054] As one or more embodiments, S1 includes the following steps:

[0055] S101: Initialize the image acquisition parameters, including image frame-by-frame acquisition mode and image frame-by-frame acquisition period and other image acquisition parameters. The frame-by-frame acquisition of the transmission line area images can be configured as a single-frame acquisition mode based on synchronous image acquisition or a multi-frame acquisition mode based on asynchronous image acquisition.

[0056] S102: Initialize and set the image analysis and processing parameters for the intrusion object dynamic detection module, including the RGB channel weighting coefficient value of the composite gray transformation and the transformation coefficient value of the gamma non-linear transformation, the standard deviation and the filtering vector length of the one-dimensional Gaussian convolution kernel function in the mixture Gaussian filtering, the structural similarity index coefficient value, the constant parameter value and the evaluation control limit value, the binary processing threshold constant, the maximum coordinate increment value of the dilation processing, the pixel area threshold of the intrusion object contour detection, etc.

[0057] As one or more embodiments, S2 includes the following steps:

[0058] S201: According to the image acquisition parameters, frame-by-frame collect the images of the transmission line area within the camera view angle at a specified image frame-by-frame acquisition period, and the collected images of the transmission line area are RGB image frames;

[0059] S202: Considering the non-linear influence of the illumination intensity at different time periods on the image acquisition quality, perform a composite gray transformation based on the weighted color method and the gamma non-linear transformation on the corresponding RGB image frames of the collected images of the transmission line area.

[0060] The calculation method of the weighted color method in this embodiment is:

[0061]

[0062] Wherein, is the pixel value of the pixel point corresponding to the coordinate (i,j) in the gray image frame after applying the weighted color method; They are respectively the pixel values of the red, green, and blue channels of the pixel at the (i, j) coordinate in the RGB image frame before applying the weighted color method; {α R , α G , α B} are the weighted coefficient values corresponding to the pixel values of the red, green, and blue channels.

[0063] In this embodiment, gamma non - linear transformation is performed on the obtained gray image frame after applying the weighted color method; the calculation method of gamma non - linear transformation is:

[0064]

[0065] Among them, is the pixel value of the pixel at the (i, j) coordinate in the composite gray image frame after applying gamma non - linear transformation; c g and α γ are respectively the transformation coefficient values of gamma non - linear transformation.

[0066] To reduce the adverse effects of composite noise in the image acquisition process, which is caused by natural vibration, peripheral electromagnetic interference, camera operation disturbance, etc., on the dynamic detection of intruding objects, a mixture Gaussian filter is performed on the composite gray image frame.

[0067] The calculation method of the mixture Gaussian filter is:

[0068] For a two - dimensional composite gray image frame, its one - dimensional Gaussian convolution kernel function in the x - direction is,

[0069]

[0070] Among them, x0 is the central pixel coordinate value of the two - dimensional composite gray image frame corresponding to the one - dimensional Gaussian filter vector in the x - direction, and σ x is the standard deviation of the one - dimensional Gaussian convolution kernel function in the x - direction.

[0071] The one - dimensional Gaussian filter vector in the x - direction corresponding to the one - dimensional Gaussian convolution kernel function in the x - direction is

[0072]

[0073] Among them, k x is the length of the one - dimensional Gaussian filter vector in the said direction, and k x needs to be an odd number.

[0074] Thus, it can be obtained that:

[0075]

[0076] Among them, is the one - dimensional Gaussian filter vector in the x - direction The (i + k)-th element.

[0077] The one-dimensional Gaussian convolution kernel function of the two-dimensional composite gray image frame in the y direction is

[0078]

[0079] where y0 is the central pixel coordinate value of the two-dimensional composite gray image frame corresponding to the one-dimensional Gaussian filtering vector in the y direction, and σ y is the standard deviation of the one-dimensional Gaussian convolution kernel function in the y direction.

[0080] The one-dimensional Gaussian filtering vector in the y direction corresponding to the one-dimensional Gaussian convolution kernel function in the y direction is

[0081]

[0082] where k y is the length of the one-dimensional Gaussian filtering vector in the direction, and k y needs to be an odd number.

[0083] The pixel value of the pixel point corresponding to the (i, j) coordinate of the two-dimensional composite gray image frame after hybrid Gaussian filtering is

[0084]

[0085] where is the one-dimensional Gaussian filtering vector in the y direction The (j + k)-th element.

[0086] In this embodiment, the hybrid Gaussian filtering method fully considers the difference in the distribution of noise data characteristics between the horizontal pixels and vertical pixels of the image. It uses two one-dimensional Gaussian convolution kernels corresponding to the horizontal direction and vertical direction of the image respectively to replace the one two-dimensional Gaussian convolution kernel used in the traditional two-dimensional Gaussian filtering, and can better achieve the image denoising and filtering effect.

[0087] S203: Background image frame update, and its local process schematic diagram is as Figure 3 shown.

[0088] When the system initializes and performs the first image acquisition, the two-dimensional composite gray image obtained from the first acquired image frame obtained in steps S201 and S202 is directly set as the background image frame.

[0089] When the image acquisition time interval is reached to complete the acquisition of the current image frame, after detecting and marking the intrusion object of the current image frame based on the existing background image frame, determine whether to update the background image frame according to the marking result of the intrusion object contour of the current image frame.

[0090] When the intrusion object contour mark of the currently acquired image frame is not empty, there is a foreign object intrusion at this time, and the currently acquired image frame is fused with the existing background image frame. Only the area without contour marks in the currently acquired image frame is retained, while only the contour mark area corresponding to the currently acquired image frame in the existing background image frame is retained, and the above retained images are fused into a complete image and used as a new background image frame.

[0091] When the intrusion object contour mark of the currently acquired image frame is empty, there is no foreign object intrusion at this time, and the structural similarity index evaluation is performed on the acquired image frame and the existing background image frame. Denote the two-dimensional composite gray image frame of the acquired image frame as image X, and the two-dimensional composite gray image frame of the existing background image frame as image Y. Then the calculation method of the structural similarity index MSSIM(X, Y) is

[0092]

[0093] where SSIM(x k , y k ) is the numerical value of the Gaussian structural similarity index between the k-th local sub-image x k of image X and the k-th local sub-image y k of image Y, and M is the number of local sub-images in image X and image Y.

[0094] The calculation method of the Gaussian structural similarity index SSIM(x k , y k ) is

[0095]

[0096] where C1 and C2 are the constant coefficients of the Gaussian structural similarity index respectively; μ x,k and σ x,k are the Gaussian mean and Gaussian variance of all pixels of the k-th local sub-image x k of image X respectively, μ y,k and σ y,k are the Gaussian mean and Gaussian variance of all pixels of the k-th local sub-image y k of image Y respectively, σ xy,k is the Gaussian covariance of all pixels between the k-th local sub-image x k of image X and the k-th local sub-image y k of image Y respectively, and the calculation methods of the above parameters are

[0097]

[0098] where the number of pixels of the local sub-image x k of image X and the local sub-image y k of image Y are both N×N; x is a local sub - image of image X after composite gray - scale transformation and hybrid Gaussian filtering k The pixel value corresponding to the coordinate (i, j) in y is a local sub - image of image Y after composite gray - scale transformation and hybrid Gaussian filtering k The pixel value corresponding to the coordinate (i, j) in; ω ij ω is the value of the normalized two - dimensional Gaussian convolution kernel function corresponding to the coordinate (i, j), and its calculation method is

[0099]

[0100] where σ y is the standard deviation of the two - dimensional Gaussian convolution kernel function

[0101] When the calculation result of the structural similarity index MSSIM(X, Y) satisfies

[0102] MSSIM(X, Y) ≤ ∈ xy (13)

[0103] It indicates that there are large differences between the current sampled image frame without foreign object intrusion and the existing background image frame due to factors such as environmental light changes. Therefore, it is necessary to replace the background image frame with the current sampled image frame; otherwise, the existing background image frame is still retained. Where ∈ xy is the control limit constant of the structural similarity index

[0104] As one or more embodiments, step S3 includes the following steps:

[0105] S301: Perform a difference operation on the sampled image frame and the existing background image frame after composite gray - scale transformation and hybrid Gaussian filtering to obtain a difference image frame, and its calculation method is

[0106]

[0107] where is the pixel value at the coordinate (i, j) of the sampled image frame is the pixel value at the coordinate (i, j) of the background image frame is the pixel difference between the sampled image frame and the background image frame at the coordinate (i, j) obtained

[0108] S302: Perform a binary thresholding process on the difference image frame obtained by performing a difference operation on the sampled image frame and the existing background image frame after composite gray - scale transformation and hybrid Gaussian filtering to highlight the pixel features of moving objects in the difference image frame, and its calculation method is

[0109]

[0110] Wherein, is the pixel value at the coordinate (i, j) of the binary image frame after the binarization threshold processing of the differential image frame, ∈ D is the binarization processing threshold constant.

[0111] S303: Perform morphological dilation processing on the binary image frame obtained after the binarization threshold processing to obtain the final extended binary image frame corresponding to the current captured image frame, so as to eliminate the intrusion object detection holes and ensure the integrity of the subsequent dynamic detection contour of the intrusion object. The calculation method is

[0112] When there is

[0113]

[0114] Wherein, i0 and j0 respectively represent the coordinate increments of the binary image frame relative to the coordinate (i, j), and the increment range is,

[0115]

[0116] Wherein, N B is the maximum value of the coordinate increment.

[0117] S304: Obtain and mark the intrusion object contour in the binary image frame. The local process schematic diagram is as Figure 4 shown:

[0118] Obtain all valid outer contours in the final extended binary image frame and store the contour points, obtain all the recognition contour index sets corresponding to the final extended binary image frame, and record the number of recognition contours as N R .

[0119] Traverse the recognition contour index set;

[0120] Let the initialized contour index i = 1, and judge whether the effective area of the i-th recognition contour is less than the detection area threshold. When the effective pixel area of the contour points stored corresponding to the i-th recognition contour index is less than the initialized pixel area threshold parameter, directly let i = i + 1; when the effective pixel area of the contour points stored corresponding to the i-th recognition contour index is not less than the initialized pixel area threshold parameter, add the i-th recognition contour index to the effective recognition contour index set, and let i = i + 1; repeat the above process of traversing the recognition contour index set until i = i max up to, terminate the process of traversing the recognition contour index set.

[0121] Output the effective recognition contour index set obtained when the above traversal process terminates.

[0122] S305: Alarm for the intrusion object and record the information of the intrusion event.

[0123] According to the obtained set of effective recognition contour indices, visualize the stored contour points corresponding to the corresponding effective outer contours. At the same time, give early warnings and record events for the image acquisition time periods corresponding to the power transmission line area images with intrusion object markings.

[0124] In this embodiment, the images of the high-voltage power transmission line area are acquired and processed frame by frame. While the background image frame for dynamic detection of intrusion objects is updated in real time, dynamic detection and marking of intrusion objects appearing in the acquired power transmission line area image frames are performed, realizing high-accuracy dynamic detection and early warning of intrusion objects on high-voltage power transmission lines and effectively reducing the risk of power transmission line failures.

[0125] Embodiment Two

[0126] Embodiment Two of the present invention introduces a dynamic detection and early warning system for intrusion objects on high-voltage power transmission lines.

[0127] As Figure 5 shown, a dynamic detection and early warning system for intrusion objects on high-voltage power transmission lines includes:

[0128] An acquisition module configured to acquire images of the high-voltage power transmission line area;

[0129] An update module configured to evaluate and update the background image frame of the acquired high-voltage power transmission line area image based on the structural similarity index;

[0130] An analysis module configured to analyze the background image frames before and after update to obtain a set of intrusion object recognition contour indices;

[0131] A detection module configured to determine whether the obtained set of intrusion object recognition contour indices is a non-empty set to determine whether there are intrusion objects in the high-voltage power transmission line area image; if there are intrusion objects, give a marking alarm for the intrusion objects on the high-voltage power transmission line.

[0132] The detailed steps are the same as those of the dynamic detection and early warning method for intrusion objects on high-voltage power transmission lines provided in Embodiment One, and will not be elaborated here.

[0133] Embodiment Three

[0134] Embodiment Three of the present invention provides a computer-readable storage medium.

[0135] A computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the steps in the dynamic detection and early warning method for intrusion objects on high-voltage power transmission lines as described in Embodiment One of the present invention.

[0136] The detailed steps are the same as those of the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines provided in the first embodiment, and will not be elaborated here.

[0137] Embodiment 4

[0138] Embodiment 4 of the present invention provides an electronic device.

[0139] An electronic device includes a memory, a processor, and a program stored on the memory and running on the processor. When the processor executes the program, it implements the steps in the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines as described in Embodiment 1 of the present invention.

[0140] The detailed steps are the same as those of the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines provided in the first embodiment, and will not be elaborated here.

[0141] Embodiment 5

[0142] Embodiment 5 of the present invention provides a computer program product.

[0143] A computer program product includes software code, and the program in the software code implements the steps in the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines as described in Embodiment 1 of the present invention.

[0144] The detailed steps are the same as those of the method for dynamically detecting and warning of intruding objects on high-voltage transmission lines provided in the first embodiment, and will not be elaborated here.

[0145] Those skilled in the art should understand that the 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 complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, 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 memories, CD-ROMs, optical memories, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript, etc.

[0146] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the processFigure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0147] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that implements the functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 specified in one block or multiple blocks.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 one process or multiple processes and / or blocks Figure 1 specified in one block or multiple blocks.

[0149] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0150] Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

[0151] The above description is only the preferred embodiments of this embodiment and is not used to limit this embodiment. For those skilled in the art, this embodiment can have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this embodiment shall be included within the protection scope of this embodiment.

Claims

1. A method for dynamically detecting and warning of intruding objects in high-voltage transmission lines, characterized in that, Including: Obtain the image of the high-voltage transmission line area; Evaluate and update the background image frame of the obtained high-voltage transmission line area image based on the structural similarity index; Analyze the background image frames before and after the update to obtain the intrusion object recognition contour index set; Judge whether the obtained intrusion object recognition contour index set is a non-empty set to determine whether an intrusion object appears in the high-voltage transmission line area image; If an intrusion object appears, mark and alarm for the intrusion object on the high-voltage transmission line.

2. The dynamic detection and early warning method for intruding objects on high-voltage transmission lines as described in claim 1, characterized in that, Before obtaining the high-voltage transmission line area image, initialize the image acquisition parameters and image analysis and processing parameters, and the image analysis and processing parameters at least include the RGB channel weighting coefficient value of the composite gray transformation and the transformation coefficient value of the gamma non-linear transformation.

3. A method for dynamically detecting and warning of intruding objects in a high-voltage transmission line as described in claim 1, characterized in that, Comprehensively consider the non-linear influence of the illumination intensity at different time periods on the image acquisition quality, perform a composite gray transformation based on weighted color and gamma non-linear transformation on the RGB image frame of the obtained high-voltage transmission line area image to obtain a two-dimensional composite gray image; combine the set image acquisition time interval and the two-dimensional composite gray image to obtain the background image frame.

4. A method for dynamically detecting and warning of intruding objects in a high-voltage transmission line as described in claim 3, characterized in that When the image acquisition time interval is reached, complete the acquisition of the current acquisition image frame, perform intrusion object detection and marking on the current acquisition image based on the high-voltage transmission line area image containing the background image frame, and determine whether to update the background image frame according to the intrusion object recognition contour marking result of the current acquisition image frame.

5. A dynamic detection and early warning method for intruding objects in a high-voltage transmission line as described in claim 1, characterized in that, If the intrusion object recognition contour index set of the current acquisition image frame is marked as non-empty, there is a foreign object intrusion. Fuse the current acquisition image frame with the image containing the background image frame, only retain the area without contour marking for the current acquisition image frame, and only retain the contour marking area corresponding to the current acquisition image frame for the image containing the background image frame. Perform image fusion on the two retained images to obtain the updated background image frame; If the intrusion object recognition contour index set of the current acquisition image frame is marked as empty, there is no foreign object intrusion. Evaluate the structural similarity index of the acquisition image frame and the background image frame, and determine whether to update the background image frame according to the evaluation result of the structural similarity index.

6. The dynamic detection and early warning method for intruding objects on high-voltage transmission lines as described in claim 1, characterized in that, Perform a difference operation on the obtained acquisition image frame and background image frame to obtain a difference image frame; Perform binary threshold processing on the obtained difference image frame to obtain a binary image frame; Perform morphological dilation processing on the obtained binary image frame to obtain an extended binary image frame; Obtain the effective outer contour and contour points in the obtained extended binary image frame to obtain the intrusion object recognition contour index set.

7. A dynamic detection and early warning system for intruding objects on high-voltage transmission lines, characterized in that, Including: An acquisition module configured to obtain the image of the high-voltage transmission line area; An update module configured to evaluate and update the background image frame of the obtained high-voltage transmission line area image based on the structural similarity index; An analysis module configured to analyze the background image frames before and after the update to obtain the intrusion object recognition contour index set; A detection module configured to judge whether the obtained intrusion object recognition contour index set is a non-empty set to determine whether an intrusion object appears in the high-voltage transmission line area image; If an intrusion object appears, mark and alarm for the intrusion object on the high-voltage transmission line.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of a method for dynamically detecting and warning of intruding objects on a high-voltage transmission line as described in any one of claims 1-6.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, When the processor executes the program, it implements the steps of a method for dynamically detecting and warning of intruding objects on a high-voltage transmission line as described in any one of claims 1-6.

10. A computer program product comprising software code, characterized in that, The program in the software code executes the steps of a method for dynamically detecting and warning of intruding objects on a high-voltage transmission line as described in any one of claims 1-6.

Images