A Method and System for Foreign Object Detection on High-Altitude Power Transmission Lines Based on Laser Clearance Equipment

Abstract

This invention provides a method and system for detecting foreign objects on high-altitude power transmission lines based on a laser obstacle removal device. The method includes: real-time acquisition of images of foreign objects on the high-altitude power transmission line to be detected; image preprocessing of the foreign object images; segmentation of the foreign object region in each frame of the processed image; obtaining the minimum binding rectangle based on the morphological features of the segmented binary image; calculating the centroid position of the foreign object on the power transmission line using the gray-scale centroid method; locating the centroid cutting point; obtaining the power transmission line straight line features based on the EDlines algorithm; connecting the obtained power transmission line straight line features to obtain a complete power transmission line image; subtracting the two images; and using the endpoints of the straight lines within the minimum binding rectangle as entanglement points to obtain the entanglement point location region. The laser obstacle removal device then tracks and cuts the foreign object. This invention achieves rapid identification and calibration of foreign objects, greatly increasing the accuracy of foreign object detection and positioning, and reducing the operational difficulty and human error for operators.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field related to electric power, and particularly relates to a high-altitude power transmission line foreign object target detection method and system based on a laser obstacle clearing device. BACKGROUND

[0002] Electric power is the basis of national economic and social development. As an energy pillar supporting the development of national economy, the electric power system plays an irreplaceable role in today's social development, and is related to the stable development of the whole society. The safe and stable operation of the power grid is not only closely related to the development of national economy, but also is the basis of people's happiness and social stability. With the rapid development of China's power grid, the scale of power transmission lines is becoming larger and larger, the number of power transmission line equipment is increasing, the length of power transmission lines in complex terrain conditions and harsh environments is increasing, and the number of power transmission lines that need special inspection and maintenance is increasing. The power transmission line inspection and maintenance is difficult and has high technical content.

[0003] In such a large-scale power transmission grid, power system failures are inevitable due to various reasons. Among the various accidents of the power grid, non-insulating objects such as kites, long cloth strips, and plastic bags suspended between power transmission lines can cause short circuits between lines, causing the switch of the substation to trip. Live removal of foreign objects is the highest safety risk in live work. The traditional main methods of removing foreign objects hooked on high-voltage power lines are as follows: one is to remove them by electricians after power failure; the other is to remove them by equal potential live work. Both methods require more manpower and resources, and the operation procedure is complex, time-consuming, labor-intensive, and has low safety and reliability. At the same time, due to the variety of foreign objects and winding methods, the workers basically rely on "random response" during live work to handle foreign objects; some foreign objects that are tightly wound with power transmission line components are highly dangerous and can only be handled by power failure. However, power failure directly reduces the reliability of power supply, causes social and economic losses, and affects people's lives.

[0004] Therefore, it is necessary to improve the efficiency and quality of power transmission line inspection through innovation and integration of new technologies, to timely remove foreign objects on overhead power transmission lines using efficient methods that keep pace with the times, and to solve power transmission line safety hazards early.

[0005] Laser as a new type of foreign matter removal means, has been widely used in various industries. Unlike ordinary physical cutting, hooking and other methods, laser removes foreign matter by burning the surface of the foreign matter. The foreign matter wrapped around the power transmission line is usually plastic film, kite and other floating foreign matter. These materials are usually plastic, nylon, polyester and other low ignition combustible materials, and their ignition point is usually below 300 DEG C. Therefore, when using laser to remove foreign matter, heating and melting the foreign matter on the power transmission line will not cause substantial damage to the power transmission line. However, when using a laser to remove obstacles, manual aiming is often difficult due to bad weather, so the identification and positioning of foreign matter on the power transmission line have become a research hotspot. SUMMARY

[0006] The application aims to provide a high-altitude power transmission line foreign matter target detection method and system based on a laser obstacle removal device, which solves the problem of target identification of foreign matter wrapped around the overhead power transmission line, increases the flexibility, maneuverability and efficiency in the process of removing foreign matter from the overhead power transmission line, and thus achieves better control requirements.

[0007] The technical solution of the application is as follows: a high-altitude power transmission line foreign matter target detection method based on a laser obstacle removal device, comprising the following steps:

[0008] Step 1: real-time acquisition and amplification of the video image of the foreign matter target area of the power transmission line, image preprocessing of the video image, and marking the frame as the initial frame of the picture when the target foreign matter is successfully identified;

[0009] Step 2: image segmentation of the image obtained after image preprocessing, taking the target foreign matter area as foreground information and other areas as background information, and obtaining a binary image containing the foreign matter area after segmentation;

[0010] Step 3: morphological processing of the foreign matter image containing morphological features, extraction of the morphological features of the foreign matter, drawing of the minimum bounding rectangle frame through the length and width information of the maximum connected region, and calculation of the centroid point position through the gray centroid method;

[0011] Step 4: extraction of the straight line feature of the power transmission line, connection of the intermittent power transmission straight line, acquisition of the complete power transmission line edge, and further acquisition of the winding point position and winding area of the foreign matter of the power transmission line;

[0012] Step 5: laser obstacle removal instrument tracking and cutting of foreign matter.

[0013] A system for high-altitude power transmission line foreign matter target detection based on the laser obstacle removal device, comprising an image acquisition module, a foreign matter coordinate acquisition module, a foreign matter tracking module and a foreign matter processing module, wherein:

[0014] The image acquisition module is used for acquiring a target area video image in real time, enlarging a target area video image where a target is located, and pre-processing the image, and when a target object is recognized, the frame picture is set as an initial frame.

[0015] The foreign matter coordinate acquisition module is used for further accurate identification of the pre-processed image, solving image information, and acquiring coordinate information of the foreign matter target and coordinate information of a winding position of the foreign matter target on the overhead transmission line.

[0016] The foreign matter tracking module is used for tracking the foreign matter target, and identifying position state information of the foreign matter target in the video image, including a winding point, a center of mass position and a winding area of the foreign matter target and a foreign matter target area.

[0017] The foreign matter processing module cuts the foreign matter by using a laser.

[0018] Compared with the prior art, the present application has the following advantages:

[0019] (1) The technical scheme of the present application adopts an improved image recognition algorithm, and improves the accuracy and precision of foreign matter target detection and positioning.

[0020] (2) The technical scheme of the present application innovatively proposes a foreign matter winding point and foreign matter winding area detection algorithm.

[0021] (3) The technical scheme of the present application is combined with a laser obstacle removal device for application, and has wide application value. The following further explanation and description are made in combination with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 The present application is a flowchart for high-altitude transmission line foreign matter target area and center of mass point detection.

[0023] Figure 2 The present application is a flowchart for high-altitude transmission line foreign matter winding point area and winding point coordinate realization. DETAILED DESCRIPTION

[0024] The present application is further explained and described in combination with the accompanying drawings.

[0025] In combination with Figure 1 , the present embodiment provides a high-altitude transmission line foreign matter detection method based on a laser obstacle removal device, including the following steps:

[0026] Step 1: acquiring and enlarging a transmission line foreign matter target area video image in real time, and pre-processing the video image, and when a target foreign matter is successfully recognized, marking the frame as an initial frame;

[0027] Step 1-1: for the color image containing the foreign object target area and the power transmission line, the image is grayed;

[0028] I(x,y) = 0.2989*I R (x,y) + 0.5870*I G (x,y) + 0.1140*I B (x,y)

[0029] Wherein, I(x,y) represents the pixel point coordinate value, I R (x,y), I G (x,y), I B (x,y) represents R, G, B three channel components;

[0030] Step 1-2: based on the gray image, the gray histogram equalization is carried out, and the image enhancement is carried out on the gray image;

[0031] Step 1-3: using Gaussian filter to denoise the enhanced image, filtering out Gaussian noise in the image, and using median filter to filter out salt and pepper noise in the image, obtaining the denoised gray image;

[0032] The size of the window template is set to (2k+1)×(2k+1), and the weight coefficient of each element in the template is:

[0033]

[0034] The median filter formula is represented as: g(x,y) = med{f(x-k,y-i), (k,i∈W)}

[0035] Wherein, the template size is set to 3×3, wherein x and y are standard coordinate system coordinates, and sigma is a standard deviation;

[0036] Step 2: image segmentation is carried out on the image obtained after image preprocessing, the target foreign object area is taken as foreground information, and other areas are taken as background information, a binary image containing the foreign object area after segmentation is obtained, and specifically:

[0037] Step 2-1: using OTSU adaptive threshold segmentation algorithm to preliminarily segment the foreign object area of the power transmission line;

[0038] Let the pixel distribution probability of the target area be p O , the mean value be mu O , the background pixel distribution probability be p B , and the mean value be mu B , then the inter-class variance is:

[0039] sigma 2 = mu O ×(mu O-μ) 2 +p B ×(μ B -μ) 2

[0040] σ 2 Threshold value t with the maximum value * Threshold value t with the maximum value

[0041] Step 2-2: based on the SVM binary classification algorithm, the foreign matter area is segmented again to obtain a segmented foreign matter area binary image;

[0042] Step 3: the foreign matter image containing morphological features is morphologically processed to extract the morphological features of the foreign matter, and the minimum binding rectangular frame is drawn based on the length and width information of the maximum connected region, and the centroid point position is calculated by the gray centroid method, specifically:

[0043] Step 3-1: the foreign matter area binary image is morphologically processed, including erosion, dilation, morphological opening operation, morphological closing operation, so as to perform opening operation, closing operation, closing operation and opening operation on the image;

[0044] Step 3-2: the maximum connected region after morphological processing is extracted;

[0045] Step 3-3: based on the length and width information of the maximum connected region, the minimum binding rectangular frame is drawn, and the foreign matter target position is marked;

[0046] Step 3-4: the centroid point position is calculated by the gray centroid method:

[0047] Let the binary image connected region pixel point coordinates be (x, y), and the centroid point coordinates be:

[0048]

[0049] Step 4: extract the power line straight line feature, connect the intermittent power line straight line, obtain the complete power line edge, further obtain the winding point position and winding area of the power line foreign matter, and combine Figure 2 , the specific work is:

[0050] Step 4-1: use the EDlines straight line extraction algorithm to extract the straight line feature image of the power line, and the specific content is:

[0051] Use the Edge Drawing algorithm to perform edge detection on the preprocessed image using the Sobel operator;

[0052] Fit the straight line edge by the least square method to obtain the complete straight line;

[0053] The acquired fitting straight line is verified using Helmholtz principle, and a shortest threshold pixel point of the straight line segment is set;

[0054] If the straight line does not satisfy the minimum length pixel point of the line segment, the straight line segment is deleted, otherwise, the straight line segment is retained;

[0055] Step 4-2: The discontinuous part of the straight line feature is connected and recovered to obtain a fitting and recovered straight line image, and the specific content includes:

[0056] All detected straight lines are grouped two by two, and the straight line equation is represented as:

[0057]

[0058] The shortest distances d1, d2, d3, and d4 of the four end points of the straight line segment to another straight line are calculated to determine whether the two straight lines are broken straight lines on the same power transmission line, and the determination condition is:

[0059] And

[0060] ε, ξ1, and ξ2 are selected according to actual conditions, and the nearest end points of the two groups of straight lines are connected if the condition is met, otherwise, no processing is performed;

[0061] Step 4-3: The fitting and recovered straight line image is subtracted from the original straight line feature image to obtain the position of the suspected winding area;

[0062] Step 4-4: The straight line end point coordinates in the smallest binding rectangular area are extracted as the foreign object winding point positions, and a winding point area rectangular frame is drawn according to the two positions farthest from the winding points;

[0063] Step 4-5: The foreign object winding interval and the foreign object winding point position are drawn;

[0064] Step 5: The laser obstacle clearing instrument tracks and cuts the foreign object;

[0065] A system of a high-altitude power transmission line foreign object detection method based on a laser obstacle clearing device, comprising an image acquisition module, a foreign object coordinate acquisition module, a foreign object tracking module, and a foreign object processing module, wherein:

[0066] The image acquisition module is used to acquire real-time target area video images, enlarge the target area video images, and pre-process the images, and when a target object is recognized, the frame is set as an initial frame;

[0067] The foreign object coordinate acquisition module is used to further accurately identify the pre-processed images, solve the image information, and acquire the coordinate information of the foreign object target and the coordinate information of the foreign object target winding position on the overhead power transmission line.

[0068] The foreign matter tracking module is used for tracking the foreign matter target, identifying the position state information of the foreign matter target in the video image, including image winding points, mass center positions and foreign matter target winding areas and foreign matter target areas; the foreign matter processing module cuts the foreign matter by using laser.

[0069] The system contains all the technical features of the high-voltage power transmission line foreign matter target detection method based on the laser obstacle clearing equipment, which will not be repeated here.

[0070] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses or adaptive changes of this disclosure that follow the general principles of the disclosure and include known or customary practices in the art of this disclosure not specifically disclosed. The specification and examples are to be regarded as illustrative only, and the true scope and spirit of the disclosure are indicated by the claims.

[0071] It should be understood that the present disclosure is not limited to the drawings already described above, and various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for detecting foreign object on high-voltage transmission line based on a laser-based obstacle clearing device, characterized in that, The method comprises the following steps: Step 1: real-time acquisition and amplification of a video image of a foreign object target area of a power transmission line, image preprocessing of the video image, marking of a frame as an initial frame of a picture when a target foreign object is successfully identified; Step 2: image segmentation of the image obtained after image preprocessing, taking the target foreign object area as foreground information and other areas as background information, and obtaining a binary image containing the foreign object area after segmentation; Step 3: morphological processing of the binary image containing the foreign object area, extraction of morphological features of the foreign object, drawing of a minimum bounding rectangle through length and width information of a maximum connected region, and calculation of a centroid point position through a gray centroid method; Step 4: extraction of a straight line feature of the power transmission line, connection of intermittent power transmission straight lines, acquisition of a complete power transmission line edge, and further acquisition of a winding point position and a winding area of the foreign object of the power transmission line; Step 5: tracking and cutting of the foreign object by a laser obstacle clearing instrument. The step 4 specifically comprises the following steps: Step 4-1: extraction of a straight line feature image of the power transmission line using an EDlines straight line extraction algorithm; Step 4-2: fitting and recovery of intermittent parts of the straight line feature to obtain a straight line image after fitting and recovery; Step 4-3: subtraction of the straight line image after fitting and recovery from the original straight line feature image to obtain a suspected winding area position; Step 4-4: extraction of straight line end point coordinates in a minimum bounding rectangle area as a foreign object winding point position; Step 4-5: drawing of a foreign object winding interval and a foreign object winding point position; The step 4-2 specifically comprises: grouping all detected straight lines in pairs, and setting a straight line equation of the straight lines as: respectively solving shortest distances d1, d2, d3, d4 of four end points of a straight line segment to another straight line; determining whether the two straight lines are broken straight lines on the same power transmission line, and a determination condition is that: ε, ξ1 and ξ2 are selected according to actual conditions, and the two groups of straight lines are connected by the nearest end points, otherwise, no processing is performed.

2. The method of detecting foreign objects on high-voltage transmission lines using a laser-based obstacle-removing device according to claim 1, wherein, The step 1 of image preprocessing of the video image specifically comprises the following steps: Step 1-1: for a color image containing a foreign object target area and a power transmission line, performing gray scale processing on the image; and I(x, y) = 0.2989 * I R (x, y) + 0.5870 * I G (x, y) + 0.1140 * I B (x, y) wherein I(x, y) represents the pixel point coordinate value, I R (x, y), I G (x, y), I B (x, y) represents R, G, B three channel components; Step 1-2: performing gray scale histogram equalization based on the gray scale image to perform image enhancement on the gray scale image; Step 1-3: performing noise reduction processing on the enhanced image using a Gaussian filter to filter out Gaussian noise in the image, and then performing salt and pepper noise filtering on the image using a median filter to obtain a denoised gray scale image. 3.The foreign object target detection method for overhead transmission line based on the laser obstacle clearing equipment according to claim 2, characterized in that, The step 1-3 comprises: setting a size of a window template as (2k+1)×(2k+1), and a weight coefficient of an element in the i-th row and j-th column of the template is: The median filter is g(x,y)=med{f(x-k,y-i),(k,i∈W)} where x and y are standard coordinate system coordinates, and σ is a standard deviation. 4.The method of detecting foreign object on high-voltage transmission line based on the laser obstacle removing equipment according to claim 1, characterized in that, The step 2 of image segmentation of the image obtained after image preprocessing comprises the following steps: Step 2-1: using an OTSU adaptive threshold segmentation algorithm to preliminarily segment the foreign object area of the power transmission line; Step 2-2: the foreign object area is segmented again based on the SVM binary classification algorithm to obtain a segmented foreign object area binary image. 5.The foreign object target detection method for overhead transmission line based on the laser obstacle clearing equipment according to claim 4, characterized in that, The step 2-1 specifically comprises: Let the probability distribution of the target region pixels be p O , and the mean be μ O . Let the probability distribution of the background pixels be p B , and the mean be μ B . Then the inter-class variance is: σ 2 = p O × (μ O - μ) 2 + p B × (μ B - μ) 2 σ 2 threshold value t with the largest value * is the segmentation threshold value. 6.The method of detecting foreign object on high-voltage transmission line based on the laser obstacle removing equipment according to claim 1, characterized in that, The step 3 specifically comprises: Step 3-1: morphological processing is performed on the binary image containing the foreign object area; Step 3-2: the maximum connected region after morphological processing is extracted; Step 3-3: a minimum binding rectangle is drawn based on the length and width information of the maximum connected region, and the foreign object target position is marked; Step 3-4: the centroid point position is calculated by the gray centroid method as: wherein the centroid position coordinates are m, n represent the number of rows and columns of pixels, respectively, and (x i ,y j ) represents the coordinate position of a pixel. 7.The foreign object target detection method for overhead transmission line based on the laser obstacle clearing equipment according to claim 6, characterized in that, The morphological processing on the binary image containing the foreign object area in the step 3-1 comprises erosion, dilation, morphological opening operation and morphological closing operation.

8. A system for detecting foreign objects on a high-voltage power transmission line based on the laser obstacle clearing device of any one of claims 1-7, wherein, The system comprises an image acquisition module, a foreign object coordinate acquisition module, a foreign object tracking module and a foreign object processing module, wherein: The image acquisition module is used for acquiring target area video images in real time, enlarging the target area video images, and pre-processing the images, and when a target object is recognized, the frame picture is set as an initial frame; The foreign object coordinate acquisition module is used for further accurate identification of the pre-processed images, solving image information, acquiring coordinate information of the foreign object target and coordinate information of the foreign object target winding position on the overhead transmission line; The foreign object tracking module is used for tracking the foreign object target, identifying the position state information of the foreign object target in the video images, including the image winding point, the centroid position and the foreign object target winding area and the foreign object target area; The foreign object processing module uses laser to cut the foreign object.

Images