Method, system and equipment for detecting tree obstacle hidden danger of power channel in mountainous area based on combination of laser ranging and machine vision, and medium

Abstract

The invention discloses a mountain area electric power channel tree obstacle hidden danger detection method, system, equipment and medium based on combination of laser ranging and machine vision, and belongs to the technical field of electric power system operation and maintaining.The method comprises the following steps that 1, image data are collected through an image collection device, and wire inclination angle data are collected through an inclination angle sensor; 2, carrying out image detection on the image data, and judging whether the weather of the region is good or not; 3, if the weather is good, the distance measuring direction of a laser distance measuring instrument is controlled according to the lead inclination angle data, and laser distance measuring is carried out; and 4, setting a distance threshold value, and if the measured distance data is smaller than the distance threshold value, carrying out tree barrier hidden danger early warning. According to the invention, the early warning accuracy is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system operation and maintenance, and specifically relates to a method, system, equipment and medium for detecting tree obstacle hazards in power channels in mountainous areas based on the combination of laser ranging and machine vision. Background Art

[0002] Mountainous areas have become key areas for the promotion and construction of wind farms due to their geographical advantages. There are many trees under the corresponding power transmission channels, and tree barrier hazards are becoming increasingly prominent. The existing tree barrier hazards in power channels are firstly sorted out and checked by manpower, which has a large workload and low work efficiency, and secondly, laser point cloud ranging through drone inspection, which is costly and requires special personnel to assist in inspection. Both methods are not suitable for monitoring tree barrier hazards in mountainous areas. The identification of tree barrier hazards based on machine vision lacks depth and distance information, resulting in a large number of invalid alarms and low warning accuracy. Therefore, the existing tree barrier warning problem in power channels in mountainous areas needs to be solved urgently. Due to the slow growth of trees, the real-time rate of tree barrier hazards is not high, and most mountainous areas are prone to foggy weather. Severe weather such as fog, rain and snow have a great impact on laser ranging and machine vision. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides a method, system, device and medium for detecting tree obstacle hazards in power channels in mountainous areas based on the combination of laser ranging and machine vision.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] A method for detecting tree obstacle hazards in power channels in mountainous areas based on the combination of laser ranging and machine vision comprises the following steps:

[0006] Step 1: using an image acquisition device to collect image data, and using a tilt sensor to collect wire tilt data;

[0007] Step 2: Perform image detection on the image data to determine whether the weather in the area is good;

[0008] Step 3: If the weather is good, control the ranging direction of the laser rangefinder according to the wire inclination data to perform laser ranging;

[0009] Step 4: Set a distance threshold. If the measured distance data is less than the distance threshold, a tree obstacle hazard warning is issued.

[0010] To optimize the above technical solutions, the specific measures taken also include:

[0011] Furthermore, step 2 specifically includes:

[0012] Step 201: The image acquired by the image acquisition device is a W*H*3 RGB three-channel image. After grayscale normalization processing, a W*H two-dimensional image P is obtained. The two-dimensional image P is mean filtered to preliminarily eliminate environmental noise.

[0013] Step 202: Obtain the horizontal and vertical gradient accumulation values ​​of the filtered two-dimensional image P by using the Scharr operator, and store the horizontal gradient accumulation values ​​in the first horizontal array y of 1*H dimension. data In the vertical direction, the accumulated gradient value is stored in the first vertical array x of W*1 dimension. data middle;

[0014] Step 203: In the first vertical array x data Find the maximum value, record it as the first vertical peak point x1, and put it in the first vertical array x data Subtract 31 elements from the top and bottom of x1 to get the second vertical array x data ￠, then in the second vertical array x data Continue to find the maximum value in ￠, record it as the second vertical peak point x2, and add it in the second vertical array x data Subtract 31 elements from the top and bottom of x2 in ￠ to get the third vertical array x data ″, then in the third vertical array x data Continue to find the maximum value in ″, which is recorded as the third vertical peak point x3;

[0015] Step 204: In the first horizontal array y data Find the maximum value, record it as the first horizontal peak point y1, and add it to the first horizontal array y data Subtract 31 elements from the left and right of y1 to get the second horizontal array y data ￠, in the second level array y data Find the maximum value in ￠ and record it as the second level peak point y2, and put it in the second level array y data Subtract 31 elements from the left and right of y2 in ￠ to get the third horizontal array y data ￠￠, in the third level array y data Find the maximum value among ￠￠, and record it as the third horizontal peak point y3;

[0016] Step 205: draw three horizontal lines in the horizontal direction of the filtered two-dimensional image P using the three peak points x1, x2 and x3 in the vertical direction, and draw three vertical lines in the vertical direction of the filtered two-dimensional image P using the three peak points y1, y2 and y3 in the horizontal direction, and define 16 regions by the intersection of the straight lines, of which 9 points are the intersection points of the horizontal and vertical directions. Draw circles with the 9 intersection points as the center and 31 pixels as the radius to obtain 9 typical regions, and calculate the gradient mean and standard deviation of the typical regions in the image;

[0017] Step 206: Calculate the average value of the gradient mean of the nine typical regions as M mean , the standard deviation of the typical area of ​​the overall image is M sd , set the gradient threshold M = M mean -2*M sd If the average value of the gradient means in each typical area of ​​the image is greater than the gradient threshold M, the image clarity is good and the weather is judged to be good.

[0018] Furthermore, step 3 specifically includes:

[0019] Step 301, obtaining inclination data measured by an inclination sensor;

[0020] Step 302, controlling the laser rangefinder to perform laser ranging in the longitudinal direction parallel to the initial inclination direction of the conductor according to the inclination data;

[0021] Step 303: Control the pan / tilt head to rotate within a range of -10° to 10° in the horizontal direction to perform horizontal space distance measurement.

[0022] Furthermore, step 4 specifically includes:

[0023] Step 401: construct a parabola fitting mathematical model of the transmission line according to the inclination data and the static data of the conductor; the static data of the conductor includes the span and the hanging point height;

[0024] A coordinate system XOY is established in the plane where the conductor line is located, with the lowest point of the sag as the coordinate origin O. The mathematical model of the transmission line is y=ax 2 ; a represents the coefficient of the mathematical model of the transmission line, x represents the abscissa, and y represents the ordinate;

[0025] Step 402: determining the lowest point of the conductor sag according to the fitted transmission line mathematical model;

[0026] Step 403, setting a distance threshold for laser ranging according to the lowest point position of the sag;

[0027] Step 404: If the measured distance data is less than the distance threshold, a tree obstacle hazard warning is issued.

[0028] Furthermore, step 402 is specifically as follows:

[0029] The conductor suspension point of the proximal tower relative to the lowest point of the conductor sag is A, with coordinates (-d, h), and we get:

[0030] a′(-d) 2 =h(1)

[0031] Where, d is the horizontal distance between the lowest point of the conductor sag and the nearest tower, h is the height difference between the lowest point of the conductor sag and the altitude of the nearest tower hanging point A, and a represents the coefficient of the mathematical model of the transmission line;

[0032] The coordinates of the conductor suspension point B on the remote tower relative to the lowest point of the conductor sag are (ld,h-h1+h2), and we get:

[0033] (ld) 2 'a=h-h1+h2(2)

[0034] Where l is the distance between towers, h1 is the altitude of the near tower suspension point A, and h2 is the altitude of the far tower suspension point B;

[0035] The calculation formula of the tangent slope at the suspension point A is:

[0036] -2′a′d=-tanθ A (3)

[0037] In the formula, θ A To measure the inclination angle at the wire suspension point A by using the inclination sensor;

[0038] The horizontal distance between the lowest point of the sag and the near-end tower is calculated by combining equations (1) to (3), as follows:

[0039]

[0040] Where d is the horizontal distance between the lowest point of the sag and the nearest tower.

[0041] Furthermore, in step 403, the distance threshold is expressed as follows:

[0042]

[0043] Where L is the distance threshold, i.e. the inclination angle θ of the laser rangefinder along the wire. A The distance measured from the longitudinal plane to the lowest point of the sag.

[0044] The present invention also proposes a tree obstacle hidden danger detection system for power channels in mountainous areas based on the combination of laser ranging and machine vision, comprising:

[0045] An intelligent monitoring module and a laser rangefinder with a pan / tilt system are arranged on a transmission line tower. The intelligent monitoring module includes an image acquisition device, a tilt sensor, and an edge computing box.

[0046] The image acquisition device is used to acquire image data, and the inclination sensor is used to acquire wire inclination data;

[0047] The edge computing box is used to perform image detection on the image data to determine whether the weather in the area is good; if the weather is good, the ranging direction of the laser rangefinder is controlled according to the wire inclination data to perform laser ranging; a distance threshold is set, and if the measured distance data is less than the distance threshold, a tree obstacle hazard warning is issued.

[0048] The present invention also proposes an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for detecting tree obstacles in power channels in mountainous areas based on the combination of laser ranging and machine vision as described above.

[0049] The present invention also proposes a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the above-mentioned method for detecting tree obstacle hazards in power channels in mountainous areas based on the combination of laser ranging and machine vision.

[0050] The beneficial effects of the present invention are:

[0051] The present invention adds depth distance information of laser ranging on the basis of machine vision, improves the early warning accuracy, judges the image clarity according to the gradient, and then judges the weather conditions, reducing the influence of bad weather on the detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flow chart of a method for detecting tree obstacles in a power channel based on the combination of laser ranging and machine vision according to the present invention;

[0053] Figure 2 It is a flow chart of the machine vision image detection method of the present invention;

[0054] Figure 3 This is a data collection flow chart of the laser rangefinder with a pan / tilt platform of the present invention;

[0055] Figure 4 It is the parabolic model of the power transmission line of the present invention;

[0056] Figure 5 This is a schematic diagram of the installation of tree obstacle hazard detection in power channels based on the combination of laser ranging and machine vision in the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] Embodiment 1

[0059] The present invention proposes a method for detecting tree obstacle hazards in power channels in mountainous areas based on the combination of laser ranging and machine vision. The process of the method is as follows: Figure 1 As shown, the following steps are included:

[0060] Step 1: using an image acquisition device to collect image data, and using a tilt sensor to collect wire tilt data;

[0061] Step 2: Perform image detection on the image data to determine whether the weather in the area is good; Figure 2 , step 2 specifically includes:

[0062] Step 201: The image acquired by the image acquisition device is a W*H*3 RGB three-channel image, where W is the width of the image and H is the height of the image. After grayscale normalization processing, a W*H two-dimensional image P is obtained, and mean filtering is performed on the two-dimensional image P to preliminarily eliminate environmental noise;

[0063] Step 202: Obtain the horizontal and vertical gradient accumulation values ​​of the filtered two-dimensional image P by using the Scharr operator, and store the horizontal gradient accumulation values ​​in the first horizontal array y of 1*H dimension. data In the vertical direction, the accumulated gradient value is stored in the first vertical array x of W*1 dimension. data middle;

[0064] Step 203: In the first vertical array x data Find the maximum value, record it as the first vertical peak point x1, and put it in the first vertical array x data Subtract 31 elements from the top and bottom of x1 to get the second vertical array x data ￠, then in the second vertical array x data Continue to find the maximum value in ￠, record it as the second vertical peak point x2, and add it in the second vertical array x data Subtract 31 elements from the top and bottom of x2 in ￠ to get the third vertical array x data ″, then in the third vertical array x data Continue to find the maximum value in ″, which is recorded as the third vertical peak point x3;

[0065] Step 204: In the first horizontal array ydata Find the maximum value, record it as the first horizontal peak point y1, and add it to the first horizontal array y data Subtract 31 elements from the left and right of y1 to get the second horizontal array y data ￠, in the second level array y data Find the maximum value in ￠ and record it as the second level peak point y2, and put it in the second level array y data Subtract 31 elements from the left and right of y2 in ￠ to get the third horizontal array y data ￠￠, in the third level array y data Find the maximum value among ￠￠, and record it as the third horizontal peak point y3;

[0066] Step 205: draw three horizontal lines in the horizontal direction of the filtered two-dimensional image P using the three peak points x1, x2 and x3 in the vertical direction, and draw three vertical lines in the vertical direction of the filtered two-dimensional image P using the three peak points y1, y2 and y3 in the horizontal direction, and define 16 regions by the intersection of the straight lines, of which 9 points are the intersection points of the horizontal and vertical directions. Draw circles with the 9 intersection points as the center and 31 pixels as the radius to obtain 9 typical regions, and calculate the gradient mean and standard deviation of the typical regions in the image;

[0067] Step 206: Calculate the average value of the gradient mean of the nine typical regions as M mean , the standard deviation of the typical area of ​​the overall image is M sd , set the gradient threshold M = M mean -2*M sd If the average value of the gradient mean of each typical area of ​​the image is greater than the gradient threshold M, the image clarity is good and the weather is judged to be good. Because trees need a period to grow, the detection cycle can be extended to once a month, based on the above weather judgment. No detection is performed when the weather is bad.

[0068] Step 3: If the weather is good, control the ranging direction of the laser rangefinder according to the wire inclination data to perform laser ranging; Figure 3 , step 3 specifically includes:

[0069] Step 301, obtaining inclination data measured by an inclination sensor;

[0070] Step 302: Control the laser rangefinder to perform laser ranging in the longitudinal direction (parallel to the tower direction) in a direction parallel to the initial inclination angle of the conductor according to the inclination data;

[0071] Step 303: Control the pan / tilt head to rotate within a range of -10° to 10° in the horizontal direction to perform horizontal space distance measurement.

[0072] Step 4: Set a distance threshold. If the measured distance data is less than the distance threshold, a tree obstacle hazard warning is issued. Step 4 specifically includes:

[0073] Step 401: construct a parabola fitting mathematical model of the transmission line according to the inclination data and the static data of the conductor; the static data of the conductor includes the span and the hanging point height; Figure 4 shown.

[0074] A coordinate system XOY is established in the plane where the conductor line is located, with the lowest point of the sag as the coordinate origin O. The mathematical model of the transmission line is y=ax 2 ; a represents the coefficient of the mathematical model of the transmission line, x represents the abscissa, and y represents the ordinate;

[0075] Step 402: determine the lowest point of the conductor sag according to the fitted transmission line mathematical model; Step 402 is specifically as follows:

[0076] The conductor suspension point of the proximal tower relative to the lowest point of the conductor sag is A, with coordinates (-d, h), and we get:

[0077] a′(-d) 2 =h(1)

[0078] Where, d is the horizontal distance between the lowest point of the conductor sag and the nearest tower, h is the height difference between the lowest point of the conductor sag and the altitude of the nearest tower hanging point A, and a represents the coefficient of the mathematical model of the transmission line;

[0079] The coordinates of the conductor suspension point B on the remote tower relative to the lowest point of the conductor sag are (ld,h-h1+h2), and we get:

[0080] (ld) 2 'a=h-h1+h2(2)

[0081] Where l is the distance between towers, h1 is the altitude of the near tower suspension point A, and h2 is the altitude of the far tower suspension point B;

[0082] The calculation formula of the tangent slope at the suspension point A is:

[0083] -2′a′d=-tanθ A (3)

[0084] In the formula, θ A To measure the inclination angle at the wire suspension point A by using the inclination sensor;

[0085] The horizontal distance between the lowest point of the sag and the near-end tower is calculated by combining equations (1) to (3), as follows:

[0086]

[0087] Where d is the horizontal distance between the lowest point of the sag and the nearest tower.

[0088] Step 403: Set the distance threshold for laser ranging according to the lowest point of the sag; the expression of the distance threshold is as follows:

[0089]

[0090] Where L is the distance threshold, i.e. the inclination angle θ of the laser rangefinder along the wire. A The distance measured from the longitudinal plane to the lowest point of the sag.

[0091] Step 404: If the measured distance data is less than the distance threshold, a tree obstacle hazard warning is issued, and the image obtained by the image acquisition device and the laser ranging distance data are saved. tree , feedback tree barrier relative to the tower position d tree cosθ A .

[0092] Embodiment 2

[0093] The present invention proposes a tree obstacle hazard detection system for power channels in mountainous areas based on a combination of laser ranging and machine vision, corresponding to the method of the first embodiment. Figure 5 As shown, including:

[0094] An intelligent monitoring module and a laser rangefinder with a pan / tilt system are arranged on a transmission line tower. The intelligent monitoring module includes an image acquisition device, a tilt sensor, and an edge computing box.

[0095] The image acquisition device is used to acquire image data, and the inclination sensor is used to acquire wire inclination data;

[0096] The edge computing box is used to perform image detection on the image data to determine whether the weather in the area is good; if the weather is good, the ranging direction of the laser rangefinder is controlled according to the wire inclination data to perform laser ranging; a distance threshold is set, and if the measured distance data is less than the distance threshold, a tree obstacle hazard warning is issued.

[0097] The implementation methods of each module and module function in the system are completely consistent with the steps of the method in Example 1, so they will not be repeated here.

[0098] Embodiment 3

[0099] The present invention proposes an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for detecting tree obstacles in power channels in mountainous areas based on a combination of laser ranging and machine vision as described in Example 1 is implemented.

[0100] Embodiment 4

[0101] The present invention provides a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the method for detecting tree obstacle hazards in power channels in mountainous areas based on the combination of laser ranging and machine vision as described in Example 1.

[0102] In the embodiments disclosed in the present application, the computer storage medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. The computer storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of computer storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should be regarded as the protection scope of the present invention.

Claims

1. A method for detecting tree obstacles in power channels in mountainous areas based on the combination of laser ranging and machine vision, characterized in that: The following steps are involved: Step 1: using an image acquisition device to collect image data, and using a tilt sensor to collect wire tilt data; Step 2: Perform image detection on the image data to determine whether the weather in the area is good; Step 3: If the weather is good, control the ranging direction of the laser rangefinder according to the wire inclination data to perform laser ranging; Step 4: Set a distance threshold. If the measured distance data is less than the distance threshold, a tree obstacle hazard warning is issued.

2. The method for detecting tree obstacles in mountainous power channels based on the combination of laser ranging and machine vision as claimed in claim 1 is characterized in that: Step 2 specifically includes: Step 201: The image acquired by the image acquisition device is a W*H*3 RGB three-channel image, where W is the width of the image and H is the height of the image. After grayscale normalization processing, a W*H two-dimensional image P is obtained, and mean filtering is performed on the two-dimensional image P to preliminarily eliminate environmental noise; Step 202: Obtain the horizontal and vertical gradient accumulation values ​​of the filtered two-dimensional image P by using the Scharr operator, and store the horizontal gradient accumulation values ​​in the first horizontal array y of 1*H dimension. data In the vertical direction, the accumulated gradient value is stored in the first vertical array x of W*1 dimension. data middle; Step 203: In the first vertical array x data Find the maximum value, record it as the first vertical peak point x1, and put it in the first vertical array x data Subtract 31 elements from the top and bottom of x1 to get the second vertical array x data ￠, then in the second vertical array x data Continue to find the maximum value in ￠, record it as the second vertical peak point x2, and add it in the second vertical array x data Subtract 31 elements from the top and bottom of x2 in ￠ to get the third vertical array x data ″, then in the third vertical array x data Continue to find the maximum value in ″, which is recorded as the third vertical peak point x3; Step 204: In the first horizontal array y data Find the maximum value, record it as the first horizontal peak point y1, and add it to the first horizontal array y data Subtract 31 elements from the left and right of y1 to get the second horizontal array y data ￠, in the second level array y data Find the maximum value in ￠ and record it as the second level peak point y2, and put it in the second level array y data Subtract 31 elements from the left and right of y2 in ￠ to get the third horizontal array y data ￠￠, in the third level array y data Find the maximum value among ￠￠, and record it as the third horizontal peak point y3; Step 205: draw three horizontal lines in the horizontal direction of the filtered two-dimensional image P using the three peak points x1, x2 and x3 in the vertical direction, and draw three vertical lines in the vertical direction of the filtered two-dimensional image P using the three peak points y1, y2 and y3 in the horizontal direction, and define 16 regions by the intersection of the straight lines, of which 9 points are the intersection points of the horizontal and vertical directions. Draw circles with the 9 intersection points as the center and 31 pixels as the radius to obtain 9 typical regions, and calculate the gradient mean and standard deviation of the typical regions in the image; Step 206: Calculate the average value of the gradient mean of the nine typical regions as M mean , the standard deviation of the typical area of ​​the whole image is M sd , set the gradient threshold M = M mean -2*M sd If the average value of the gradient means in each typical area of ​​the image is greater than the gradient threshold M, the image clarity is good and the weather is judged to be good.

3. The method for detecting tree obstacles in mountainous power channels based on the combination of laser ranging and machine vision as claimed in claim 1 is characterized in that: Step 3 specifically includes: Step 301, obtaining inclination data measured by an inclination sensor; Step 302, controlling the laser rangefinder to perform laser ranging in the longitudinal direction parallel to the initial inclination direction of the conductor according to the inclination data; Step 303: Control the pan / tilt head to rotate within a range of -10° to 10° in the horizontal direction to perform horizontal space distance measurement.

4. The method for detecting tree obstacles in power channels in mountainous areas based on the combination of laser ranging and machine vision as claimed in claim 1, characterized in that: Step 4 specifically includes: Step 401: construct a parabola fitting mathematical model of the transmission line according to the inclination data and the static data of the conductor; the static data of the conductor includes the span and the hanging point height; A coordinate system XOY is established in the plane where the conductor line is located, with the lowest point of the sag as the coordinate origin O. The mathematical model of the transmission line is y=ax 2 ; a represents the coefficient of the mathematical model of the transmission line, x represents the abscissa, and y represents the ordinate; Step 402: determining the lowest point of the conductor sag according to the fitted transmission line mathematical model; Step 403, setting a distance threshold for laser ranging according to the position of the lowest point of the sag; Step 404: If the measured distance data is less than the distance threshold, a tree obstacle hazard warning is issued.

5. The method for detecting tree obstacles in power channels in mountainous areas based on the combination of laser ranging and machine vision as claimed in claim 4 is characterized in that: Step 402 is specifically as follows: The conductor suspension point of the proximal tower relative to the lowest point of the conductor sag is A, with coordinates (-d, h), and we get: a′(-d) 2 =h (1) Where, d is the horizontal distance between the lowest point of the conductor sag and the nearest tower, h is the height difference between the lowest point of the conductor sag and the altitude of the nearest tower hanging point A, and a represents the coefficient of the mathematical model of the transmission line; The coordinates of the conductor suspension point B on the remote tower relative to the lowest point of the conductor sag are (ld,h-h1+h2), and we get: (ld) 2 ′a=h-h1+h2 (2) Where l is the distance between towers, h1 is the altitude of the near tower suspension point A, and h2 is the altitude of the far tower suspension point B; The calculation formula of the tangent slope at the suspension point A is: -2′a′d=-tanθ A (3) In the formula, θ A To measure the inclination angle at the wire suspension point A by using the inclination sensor; The horizontal distance between the lowest point of the sag and the near-end tower is calculated by combining equations (1) to (3), as follows: Where d is the horizontal distance between the lowest point of the sag and the nearest tower.

6. The method for detecting tree obstacles in mountainous power channels based on the combination of laser ranging and machine vision as claimed in claim 4 is characterized in that: In step 403, the distance threshold is expressed as follows: Where L is the distance threshold, i.e. the inclination angle θ of the laser rangefinder along the wire. A The distance measured from the longitudinal plane to the lowest point of the sag.

7. A tree obstacle detection system for power channels in mountainous areas based on the combination of laser ranging and machine vision, characterized in that: include: An intelligent monitoring module and a laser rangefinder with a pan / tilt system are arranged on a transmission line tower. The intelligent monitoring module includes an image acquisition device, a tilt sensor, and an edge computing box. The image acquisition device is used to acquire image data, and the inclination sensor is used to acquire wire inclination data; The edge computing box is used to perform image detection on the image data to determine whether the weather in the area is good; if the weather is good, the ranging direction of the laser rangefinder is controlled according to the wire inclination data to perform laser ranging; Set a distance threshold. If the measured distance data is less than the distance threshold, a tree obstacle hazard warning will be issued.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for detecting tree obstacles in power channels in mountainous areas based on the combination of laser ranging and machine vision as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: The computer program enables the computer to execute the method for detecting tree obstacle hazards in mountainous power channels based on the combination of laser ranging and machine vision as described in any one of claims 1 to 6.

Images