A method for efficiently identifying initial bird nests on a high-speed rail power supply system

Abstract

This invention relates to the field of high-speed rail power supply equipment detection methods, specifically a method for efficiently identifying initial bird nests on high-speed rail power supply systems. It aims to solve the problem of difficulty in identifying bird nests on power supply equipment along high-speed rail lines in existing technologies. The invention includes the following steps for efficiently identifying initial bird nests on high-speed rail power supply systems: image acquisition; finding suspected initial points of single nests on the acquired image; setting a secondary sampling range centered on the initial point to determine if it is a suspected single nest; for suspected single nests, finding the distribution of dark line segments in each row of pixels, determining the dark points at the center of the dark line segments; statistically analyzing the curves formed by the combinations of dark points to determine whether a single nest has formed, and then graphically labeling the curves. The advantages are: the method for efficiently identifying initial bird nests on high-speed rail power supply systems uses sampling along the high-speed rail line, which is convenient; it can effectively determine nest formation in its early stages; and it incorporates multiple methods to prevent false positives, effectively identifying each initial bird nest.

Description

Technical Field

[0001] This invention relates to a method for detecting high-speed rail power supply equipment, and in particular to a method for efficiently identifying early bird nests on a high-speed rail power supply system. Background Technology

[0002] A power supply system is a system that generates electrical energy and supplies and transmits it to electrical equipment, consisting of a power source system and a power transmission and distribution system. In long-distance power supply systems, such as high-voltage power transmission systems and high-speed rail power supply systems, bird control is often one of the main tasks of maintenance workers.

[0003] Currently, bird damage prevention and control mainly focuses on the following aspects: 1. Designing utility poles to prevent birds from nesting, such as those with buzzer devices or combinations of movable joints that make it difficult for birds to stand, or spraying biological repellents to drive birds away; 2. Designing tools that can efficiently remove bird nests. Such tools generally require good insulation and a high level of protection for workers; 3. Utilizing drones to achieve high-frequency real-time monitoring, with operators manually checking for bird nests on the lines and issuing early warning information.

[0004] The applicant believes that existing technologies, specifically in the field of bird nest identification, still have the following shortcomings: 1. Even with images captured by drones, manual identification requires significant manpower; 2. Drones are limited by their operating range and battery life, often only able to measure data within a 3-kilometer radius, resulting in excessively high detection costs; 3. Regarding bird nests themselves, early-stage nests are easier to clean than late-stage nests, and some late-stage nests have been proven in practice not to affect power lines and therefore do not require cleaning. Identifying early-stage nests is a key aspect of data processing, and current technologies often result in numerous misjudgments, increasing the time spent by staff and raising labor costs. Summary of the Invention

[0005] The purpose of this invention is to solve the problem of difficulty in identifying bird nests on power supply equipment along high-speed railways in the prior art.

[0006] The specific solution of this invention is:

[0007] A method for efficiently identifying early bird nests on high-speed rail power supply systems is designed, including the following steps:

[0008] (1) Image acquisition: A camera is installed on the outside of the front of the high-speed train carriage. When the high-speed train runs at speeds of 150 km / h or higher, a photograph is taken every 0.2 to 0.5 seconds to form an acquired image. The acquired image is then input into the communication system or the image processing system is input into the timed hard disk to start the recognition and screening.

[0009] (2) Find the suspected single branch initial point on the acquired image; starting from the top corner of the acquired image, check the path pixels horizontally in units of single pixels. When two or more consecutive dark points are found in a single row, the group of dark points is determined to be the suspected single branch initial point.

[0010] (3) Determine whether it is a suspected single branch: Take the center point of the dark spot group in step (2) as the center, and define the secondary sampling range with a distance of 2 to 19 pixels as the radius. Within the secondary sampling range, check the dark spot distribution data by row downwards along the investigation column in step (2). Then analyze the data. When the dark spot area of ​​the lower investigation column in the sampling area forms a closed shape, it is determined to be a suspended object in the air. When the dark spot area of ​​the lower investigation column in the sampling area extends to the edge of the secondary sampling range, it is determined to be a suspected single branch.

[0011] (4) Determine the secondary sampling range with the initial point as the center: With the initial point as the center and a pixel distance as the radius, define the secondary pre-judgment sampling range, where a = 2 to 19 pixels. Within the pre-judgment sampling range, read pixel information from top to bottom and from left to right. Assume that the pixel in the bright area is 1 and the pixel in the dark area is 0. Form a sequence of 1 and 0 row by row. When the 0 values ​​in three or more rows of each row increase by a ratio greater than 1.5 while the 0 values ​​in the rows below decrease, the sampling range is deemed unreasonable. Adjust the radius to 2a or more and repeat the above steps until there are three or more rows where the change in 0 values ​​is between -1.5 and 1.5. Determine the sampling range within this step as the secondary sampling range.

[0012] (5) For suspected single-branch dark line distribution of each row of pixels, determine the dark point in the center of the dark line: In the secondary sampling range, read the pixel information. When the scan result is 0……0, 1……1, the point is XG1. When the scan result first appears 0……0, the end point is XG1'. Connect the two points and take the midpoint of the line segment as the sampling midpoint XG1' / 2. Expand the pixel distance radius again and establish a three-level sampling range. In the three-level sampling range, find the points XG2, XG2', XG2' / 2 and XG1' / 2 and XG2' / 2 in the same way. Connect the two points and obtain the trend slope L1: Y=B1X+H1. Calculate the slope b1 of the trend slope.

[0013] (6) Determine whether the curve formed by the combination of dark spots forms a single branch and perform graphic annotation: According to the slope generation method in step (4), the center point of the dark spot group is used as the center and the expanded pixel distance is used as the radius to establish a four-level sampling ring to obtain XG3, XG3', XG3' / 2 and L2: Y=B2X+H2 and b2. When b1=b2, the area is determined to be a single branch and graphic annotation is performed with a red box. At the same time, the geographical coordinates of this image are provided to the background system.

[0014] In specific implementation, according to the required level of the result, it also includes step (7) multi-level verification. The multi-level verification includes using the method of step (5) and (6) to gradually establish a multi-level sampling ring with a relative distance of not less than 30 pixels as the radius, and gradually calculate the slope bn of the trend equation of the point area corresponding to each sampling ring, and check it level by level. When there is an inconsistency, the system will remind that there is doubt about the judgment and mark it with a yellow box.

[0015] In the specific implementation, a screening step is set between step (1) and step (2). The screening step includes collecting the quadrilateral area S where each power supply column is located, and using S as the image collected in step (2).

[0016] In practice, when the tilt is 90 degrees and the bottom edge of the dark area is a horizontal line, it is determined to be a bolt based on the terminal width.

[0017] The beneficial effects of this invention are as follows:

[0018] A method for efficiently identifying early bird nests on high-speed rail power supply systems was designed. First, sampling is convenient and does not require the participation of drones. The sampling device can be directly hung outside the high-speed rail carriages. The entire line will be photographed during a single trip. Second, the early bird nests are identified and sent to the staff. After verification, the staff in the relevant station can be notified immediately for repairs, avoiding unnecessary detours and saving labor costs.

[0019] Furthermore, there is a complete image screening method, and the method can also be used to reduce the sampling area, saving image processing memory in the image processing background and improving the running speed of the device. Attached Figure Description

[0020] Figure 1 This is an example of an image acquired in step (1) of the present invention;

[0021] Figure 2 This is the book Figure 1 A schematic diagram of sampling area A in the middle;

[0022] Figure 3 In this invention Figure 2 Schematic diagram of step (4) in the district;

[0023] Figure 4 This is a schematic diagram of step (5);

[0024] Figure 5 This is a schematic diagram of step (6);

[0025] 1. Unreasonable sampling range; 2. Reasonable sampling range; O origin. Detailed Implementation

[0026] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0027] Example 1

[0028] A method for efficiently identifying early bird nests on high-speed rail power supply systems, see [link to relevant documentation]. Figures 1 to 3 ,

[0029] Includes the following steps:

[0030] (1) Image acquisition: A camera is installed on the outside of the front of the high-speed train carriage. When the high-speed train runs at speeds of 150 km / h or higher, a photograph is taken every 0.2 to 0.5 seconds to form an acquired image. The acquired image is then input into the communication system or the image processing system is input into the timed hard disk to start the recognition and screening.

[0031] (2) Find the suspected single branch initial point on the acquired image; starting from the top corner of the acquired image, check the path pixels horizontally in units of single pixels. When two or more consecutive dark points are found in a single row, the group of dark points is determined to be the suspected single branch initial point.

[0032] (3) Determine whether it is a suspected single branch: Take the center point of the dark spot group in step (2) as the center, and define the secondary sampling range with a distance of 2 to 19 pixels as the radius. Within the secondary sampling range, check the dark spot distribution data by row downwards along the investigation column in step (2). Then analyze the data. When the dark spot area of ​​the lower investigation column in the sampling area forms a closed shape, it is determined to be a suspended object in the air. When the dark spot area of ​​the lower investigation column in the sampling area extends to the edge of the secondary sampling range, it is determined to be a suspected single branch.

[0033] (4) Determine the secondary sampling range with the initial point as the center: With the initial point as the center and a pixel distance as the radius, define the secondary pre-judgment sampling range, where a = 2 to 19 pixels. Within the pre-judgment sampling range, read pixel information from top to bottom and from left to right. Assume that the pixel in the bright area is 1 and the pixel in the dark area is 0. Form a sequence of 1 and 0 row by row. When the 0 values ​​in three or more rows of each row increase by a ratio greater than 1.5 while the 0 values ​​in the rows below decrease, the sampling range is deemed unreasonable. Adjust the radius to 2a or more and repeat the above steps until there are three or more rows where the change in 0 values ​​is between -1.5 and 1.5. Determine the sampling range within this step as the secondary sampling range.

[0034] (5) For suspected single-branch dark line distribution of each row of pixels, determine the dark point in the center of the dark line: In the secondary sampling range, read the pixel information. When the scan result is 0……0, 1……1, the point is XG1. When the scan result first appears 0……0, the end point is XG1'. Connect the two points and take the midpoint of the line segment as the sampling midpoint XG1' / 2. Expand the pixel distance radius again and establish a three-level sampling range. In the three-level sampling range, find the points XG2, XG2', XG2' / 2 and XG1' / 2 and XG2' / 2 in the same way. Connect the two points and obtain the trend slope L1: Y=B1X+H1. Calculate the slope b1 of the trend slope.

[0035] (6) Determine whether the curve formed by the combination of dark spots forms a single branch and perform graphic annotation: According to the slope generation method in step (4), the center point of the dark spot group is used as the center and the expanded pixel distance is used as the radius to establish a four-level sampling ring to obtain XG3, XG3', XG3' / 2 and L2: Y=B2X+H2 and b2. When b1=b2, the area is determined to be a single branch and graphic annotation is performed with a red box. At the same time, the geographical coordinates of this image are provided to the background system.

[0036] In this embodiment, according to the required level of the result, step (7) multi-level verification is also included. The multi-level verification includes establishing multi-level sampling rings with a relative distance of not less than 30 pixels as the radius, using the methods in steps (5) and (6), and gradually calculating the slope bn of the trend equation of the point area corresponding to each sampling ring. The verification is performed level by level. When an inconsistency occurs, the system will remind that the judgment is questionable and mark it with a yellow box. The judgment is made within a certain length to prevent misjudgment by the system under short poles rather than long branches.

[0037] In this application, the tree branches have the characteristic that the slope and thickness of the straight line in the dark area of ​​the image are basically the same, that is, in the inserted state or in the inclined state. Considering that the diameter of the tree branches itself has a certain degree of thickness gradient, the method of calculating the center point of each line segment and comparing the slope is adopted. When the slope is consistent and the single end is the endpoint, it can be determined that the branch is the branch that makes up the bird's nest, that is, the initial bird's nest, which can be provided to the staff for cleaning.

[0038] The algorithm in this application first identifies dark spots in the image, then focuses on scanning around these dark spots. If the area containing the dark spot is found to be circular or a closed shape, it can be determined that it is not an initial bird's nest. If the overall shape is a long, thin rod, it can be determined that it is an initial bird's nest. The method primarily emphasizes measuring whether there is a uniform slope. Due to the small pixel sampling range, it can be as small as 2 pixels, greatly avoiding the influence of branching branches on the measurement results. The applicant, with years of experience working on the front lines, has found that initial bird nests are generally structures with branches of a certain length and polysegmented lines, so comparing slopes is a relatively simple method. The purpose of this method is to maximize the probability of not missing any suspected initial bird's nests in the image material.

[0039] In this embodiment, a screening step is provided between steps (1) and (2). The screening step includes collecting the quadrilateral region S where each power supply column is located, and using S as the image collected in step (2). This design can reduce the amount of data extraction and improve the operating efficiency of the equipment.

[0040] In this embodiment, when the tilt is 90 degrees and the bottom edge of the dark area is a horizontal line, it is determined to be a bolt based on the terminal width.

[0041] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for efficiently identifying early bird nests on a high-speed rail power supply system, characterized in that, Includes the following steps: (1) Image acquisition: A camera is installed on the outside of the front of the high-speed train carriage. When the high-speed train runs at speeds of 150 km / h or higher, a photograph is taken every 0.2 to 0.5 seconds to form an acquired image. The acquired image is then input into the communication system or the image processing system is input into the timed hard disk to start the recognition and screening. (2) Find the suspected single branch initial point on the acquired image; starting from the upper left corner of the acquired image, check the path pixels horizontally in units of single pixels. When two or more consecutive dark points are found in a single row, the group of dark points is determined to be the suspected single branch initial point. (3) Determine whether it is a suspected single branch: Take the center point of the dark spot group in step (2) as the center, and define the secondary sampling range with a distance of 2 to 19 pixels as the radius. Within the secondary sampling range, check the dark spot distribution data by row downwards along the investigation column in step (2). Then analyze the data. When the dark spot area of ​​the lower investigation column in the sampling area forms a closed shape, it is determined to be a suspended object in the air. When the dark spot area of ​​the lower investigation column in the sampling area extends to the edge of the secondary sampling range, it is determined to be a suspected single branch. (4) Determine the secondary sampling range with the initial point as the center: With the initial point as the center and a pixel distance as the radius, define the secondary pre-judgment sampling range, where a = 2 to 19 pixels. Within the pre-judgment sampling range, read pixel information from top to bottom and from left to right. Assume that the pixel in the bright area is 1 and the pixel in the dark area is 0. Form a sequence of 1 and 0 row by row. When the 0 values ​​in three or more rows of each row increase by a ratio greater than 1.5 while the 0 values ​​in the rows below decrease, the sampling range is deemed unreasonable. Adjust the radius to 2a or more and repeat the above steps until there are three or more rows where the change in 0 values ​​is between -1.5 and 1.

5. Determine the sampling range within this step as the secondary sampling range. (5) For suspected single-branch dark line distribution of each row of pixels, determine the dark point in the center of the dark line: In the secondary sampling range, read the pixel information. When the scanning result is 0……0, 1……1, the point is XG1. When the scanning result first appears 0…0, the end point is XG1'. Connect the two points and take the midpoint of the line segment as the sampling midpoint XG1' / 2. Expand the pixel distance radius again and establish a three-level sampling range. In the three-level sampling range, find the points XG2, XG2', XG2' / 2 and XG1' / 2 and XG2' / 2 in the same way. The trend line L1 is obtained: Y=B1X+H1. Calculate the slope b1 of the trend line. (6) Determine whether the curve formed by the combination of dark spots forms a single branch and perform graphic annotation: According to the slope generation method in step (4), the center point of the dark spot group is used as the center and the expanded pixel distance is used as the radius to establish a four-level sampling ring to obtain XG3, XG3', XG3' / 2 and L2: Y=B2X+H2 and b2. When b1=b2, the area is determined to be a single branch and graphic annotation is performed with a red box. At the same time, the geographical coordinates of this image are provided to the background system.

2. The method for efficiently identifying initial bird nests on a high-speed rail power supply system as described in claim 1, characterized in that: According to the required level of the result, it also includes step (7) multi-level verification. The multi-level verification includes using the methods of steps (5) and (6) to gradually establish a multi-level sampling ring with a relative distance of not less than 30 pixels as the radius, and gradually calculate the slope bn of the trend equation of the point area corresponding to each sampling ring, and check it level by level. When there is an inconsistency, the system will remind that there is doubt about the judgment and mark it with a yellow box.

3. The method for efficiently identifying early bird nests on a high-speed rail power supply system as described in claim 1, characterized in that: A screening step is provided between steps (1) and (2). The screening step includes collecting the quadrilateral area S where each power supply column is located, and using S as the image collected in step (2).

4. The method for efficiently identifying initial bird nests on a high-speed rail power supply system as described in claim 1, characterized in that: When the tilt is 90 degrees and the bottom edge of the dark area is a horizontal line, it is determined to be a bolt based on the terminal width.

Images