A control method and system for electric power inspection drone

Abstract

The present invention belongs to the field of drone control, and discloses a control method and system for a power inspection drone, the method comprising S1, obtaining a set U of waypoints when inspecting power equipment; S2, using an improved distance calculation formula to calculate the distance between two waypoints adjacent in the inspection order; S3, obtaining the shortest flight path of all waypoints in the set U based on the distance obtained in S2; S4, controlling the drone to fly along the shortest flight path, and obtaining a set of aerial images of each waypoint respectively. In the process of obtaining the shortest flight path, the present invention does not directly use the distance calculated based on longitude and latitude as the actual distance between two waypoints, but after calculating the distance, corrects the distance between waypoints at different altitudes to obtain a more accurate shortest flight path, thereby more accurately controlling the flight path of the drone.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle control, and in particular to a control method and system for an electric power inspection unmanned aerial vehicle. Background Art

[0002] Using drones to inspect power equipment is a common technology. In the prior art, before using drones to inspect power equipment in facilities such as substations, it is usually necessary to generate the shortest flight path based on the set waypoints so that the drone can traverse all waypoints in the shortest time to improve the inspection efficiency. The waypoint is the location where the drone hovers in the air to take pictures of the power equipment.

[0003] However, the existing shortest path generation algorithm only uses the distance in longitude and latitude to represent the distance between two waypoints, and is only applicable to the case where all waypoints have the same height, that is, the shortest path is only obtained within a two-dimensional plane. It does not take into account the situation where the heights of power equipment are different and the heights of the waypoints are not the same when the drone actually takes pictures at different waypoints. Therefore, the calculated shortest path may not be the actual shortest path, which is not conducive to increasing the number of waypoints that the drone can reach in a single flight, affecting the efficiency of power inspections. Summary of the invention

[0004] The purpose of the present invention is to disclose a control method and system for a power inspection drone, so as to solve the problem of how to optimize the acquisition process of the drone's flight path, thereby improving the inspection efficiency when using the drone to inspect power equipment.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a method for controlling a power inspection drone, comprising:

[0007] S1, obtain a set U of waypoints for inspection of power equipment;

[0008] S2, using the improved distance calculation formula to calculate the distance between two adjacent waypoints in the inspection order;

[0009] The distance calculation formula between the bth waypoint and the b+1th waypoint is:

[0010]

[0011] impdist b,b+1 Indicates the distance between the b-th waypoint and the b+1-th waypoint, lon b and lat b Respectively represent the longitude and latitude of the b-th waypoint, lonb+1 and lat b+1 Respectively represent the longitude and latitude of the b+1th waypoint, θ b,b+1 Represents the angle between the straight line segment connecting the b-th waypoint and the b+1-th waypoint and the horizontal plane where the b+1-th waypoint is located;

[0012] S3, obtain the shortest flight path of all waypoints in set U based on the distance obtained in S2;

[0013] S4, controls the UAV to fly along the shortest flight path and obtains a set of aerial images of each waypoint.

[0014] Preferably, S3 includes:

[0015] S31, taking any two different waypoints in U as the starting point and end point of the inspection, traversing all flight paths;

[0016] S32, calculating the total length of each flight path obtained in S31 based on the distance obtained in S2;

[0017] S33, taking the flight path with the shortest total length as the shortest flight path.

[0018] Preferably, obtaining an aerial image of each waypoint separately includes:

[0019] S41, for the b-th waypoint, photograph the b-th waypoint according to the set shooting direction to obtain the first aerial image aerimg b,1 ;

[0020] S42, for aerimg b,1 Perform image preprocessing to obtain image aerimg b,1,opt ;

[0021] S43, based on aerimg b,1,opt And the historical aerial images of the b-th waypoint, calculate the total number of shots N of the b-th waypoint b ;

[0022] S44, use with aerimg b,1 The same shooting conditions are used to perform N b -1 shot, get N b - 1 aerial image;

[0023] S45, taking the aerial images obtained in S41 and S44 as a set of aerial images of the b-th waypoint.

[0024] Preferably, S42 includes:

[0025] S421, for aerimg b,1Grayscale and obtain the image gaerimg b,1 ;

[0026] S422, for gaerimg b,1 Filter and get the image aerimg b,1,opt .

[0027] Preferably, S43 includes:

[0028] S431, obtaining the aerial image set U of the bth waypoint during the last inspection of the power equipment b,last ;

[0029] S432, U b,last The most representative aerial image in is taken as the historical aerial image aerimg of the bth waypoint b,last ;

[0030] S433, for aerimg b,last Grayscale and obtain the image gaerimg b,last ;

[0031] S434, for gaerimg b,last Filter and obtain the image gaerimg b,last,opt ;

[0032] S435, obtain aerimg b,1,opt Chinese and gaerimg b,last,opt The number of pixels whose grayscale difference is greater than the set grayscale threshold is M b ;

[0033] S436, calculation of aerimg b,1,opt The mean gray value of the pixels in avegray b,1,opt ;

[0034] S437, calculate the total number of shots N of b waypoints using the following formula b :

[0035]

[0036] M b,last Indicates gaerimg b,last The number of pixels in maxgray b,1,opt Indicates aerimg b,1,opt The maximum gray value in avegray b,1,opt Indicates aerimg b,1,opt The mean of the gray values ​​in pU b,1,opt Indicates aerimg b,1,opt The set of pixels in Mb,1,opt Indicates pU b,1,opt The number of pixels in grat i represents the image gradient of pixel i; avgrat represents pU b,1,opt The mean value of the image gradient in , maxgrat represents pU b,1,opt The maximum value of the image gradient in, λ1, λ2, λ3 represent the first weight, the second weight and the third weight set in advance respectively, N bs Indicates a preset quantity.

[0037] Preferably, U b,last The most representative aerial image acquisition process includes:

[0038] The first step is to b,last Select any aerial image aerimg rand ;

[0039] The second step is to aerimg rand Divided into Z1×Z2 regions of equal size;

[0040] The third step is to calculate the representative coefficients of the pixels in each area respectively;

[0041] The fourth step is to obtain the set cordU of coordinates of the pixel points in the area with the largest representative coefficient;

[0042] Step 5: Get U based on cordU b,last The no-reference image quality evaluation value of each aerial image in ;

[0043] Step 6: b,last The aerial image with the largest quality evaluation value among the reference images is taken as U b,last The most representative aerial images.

[0044] Preferably, the calculation formula of Z1 is:

[0045]

[0046] leng rand Indicates aerimg rand The number of columns of pixels, L represents the preset length;

[0047] The calculation formula of Z2 is:

[0048]

[0049] brea rand Indicates aerimg rand The number of rows of pixels.

[0050] Preferably, aerimg rand Divided into Z1×Z2 regions of equal size, including:

[0051] The length of each region is Width is

[0052] Will aerimg rand Divided into Z1×Z2 pieces with length Width is area.

[0053] Preferably, gaerimg b,1 Filter and get the image aerimg b,1,opt ,include:

[0054] Will gaerimg b,1 Divided into multiple areas to be filtered;

[0055] Based on the set of coordinates of each pixel point in the area to be filtered, gaerimg b,1 Filter and get aerimg b,1,opt .

[0056] In a second aspect, the present invention provides a power inspection drone control system, comprising a first acquisition module, a calculation module, a second acquisition module and a control module;

[0057] The first acquisition module is used to acquire a set U of waypoints when inspecting the power equipment;

[0058] The calculation module is used to calculate the distance between two adjacent waypoints in the inspection sequence using an improved distance calculation formula;

[0059] The distance calculation formula between the bth waypoint and the b+1th waypoint is:

[0060]

[0061] impdist b,b+1 Indicates the distance between the b-th waypoint and the b+1-th waypoint, lon b and lat b Respectively represent the longitude and latitude of the b-th waypoint, lon b+1 and lat b+1 Respectively represent the longitude and latitude of the b+1th waypoint, θ b,b+1 Represents the angle between the straight line segment connecting the b-th waypoint and the b+1-th waypoint and the horizontal plane where the b+1-th waypoint is located;

[0062] The second acquisition module is used to acquire the shortest flight path of all waypoints in the set U based on the distance obtained by the calculation module;

[0063] The control module is used to control the UAV to fly along the shortest flight path and obtain a set of aerial images of each waypoint.

[0064] In the process of obtaining the shortest flight path, the present invention does not directly use the distance calculated based on longitude and latitude as the actual distance between two waypoints, but after calculating the distance, multiplies it by the cosine value of the angle between the two waypoints, thereby realizing the correction of the distance between waypoints at different altitudes, so that the calculated distance can more truly represent the distance between two different waypoints, which is conducive to obtaining a more accurate shortest flight path, and then more accurately controlling the flight path of the UAV, thereby improving the efficiency of using the UAV to inspect power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0066] Figure 1 A schematic diagram of a control method for a power inspection drone of the present invention.

[0067] Figure 2 The present invention is a schematic diagram of a power inspection UAV control system. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope parameters of the protection of the present invention.

[0069] The first aspect, such as Figure 1 In one embodiment shown, the present invention provides a method for controlling a power inspection drone, comprising:

[0070] S1, obtain a set U of waypoints for inspection of power equipment;

[0071] S2, using the improved distance calculation formula to calculate the distance between two adjacent waypoints in the inspection order;

[0072] The distance calculation formula between the bth waypoint and the b+1th waypoint is:

[0073]

[0074] impdist b,b+1 Indicates the distance between the b-th waypoint and the b+1-th waypoint, lon b and lat b Respectively represent the longitude and latitude of the b-th waypoint, lon b+1 and lat b+1 Respectively represent the longitude and latitude of the b+1th waypoint, θ b,b+1 Represents the angle between the straight line segment connecting the b-th waypoint and the b+1-th waypoint and the horizontal plane where the b+1-th waypoint is located;

[0075] S3, obtain the shortest flight path of all waypoints in set U based on the distance obtained in S2;

[0076] S4, controls the UAV to fly along the shortest flight path and obtains a set of aerial images of each waypoint.

[0077] In the process of obtaining the shortest flight path, the distance calculated based on longitude and latitude is not directly used as the actual distance between the two waypoints. Instead, after the distance is calculated, it is multiplied by the cosine value of the angle between the two waypoints. The distance calculated in this way includes the height information of the waypoints, thereby realizing the correction of the distance between waypoints at different heights, so that the calculated distance can more truly represent the distance between two different waypoints, which is conducive to obtaining a more accurate shortest flight path, and then more accurately controlling the flight path of the UAV, thereby improving the efficiency of using UAVs to inspect power equipment.

[0078] In S2, the obtained angle is less than 90°.

[0079] Preferably, S3 includes:

[0080] S31, taking any two different waypoints in U as the starting point and end point of the inspection, traversing all flight paths;

[0081] S32, calculating the total length of each flight path obtained in S31 based on the distance obtained in S2;

[0082] S33, taking the flight path with the shortest total length as the shortest flight path.

[0083] In S31, all possible flight paths can be obtained by traversing, and the total length of the flight path can be calculated by using the corrected distance to obtain a more accurate path length.

[0084] Preferably, obtaining an aerial image of each waypoint separately includes:

[0085] S41, for the b-th waypoint, photograph the b-th waypoint according to the set shooting direction to obtain the first aerial image aerimg b,1 ;

[0086] S42, for aerimg b,1 Perform image preprocessing to obtain image aerimg b,1,opt ;

[0087] S43, based on aerimg b,1,opt And the historical aerial images of the b-th waypoint, calculate the total number of shots N of the b-th waypoint b ;

[0088] S44, use with aerimg b,1 The same shooting conditions are used to perform N b -1 shot, get N b - 1 aerial image;

[0089] S45, taking the aerial images obtained in S41 and S44 as a set of aerial images of the b-th waypoint.

[0090] Before aerial photography, the shooting direction of each waypoint is determined in advance. Specifically, the shooting direction is set according to the positional relationship between the power equipment and the waypoint. For example, if the waypoint is on the right side of the power equipment to be photographed, the shooting direction is to shoot to the left. When shooting in the shooting direction, the aerial image obtained contains the power equipment that needs to be inspected.

[0091] b is a positive integer greater than or equal to 1.

[0092] The shooting conditions include shooting direction, aperture, etc. Maintaining the same shooting conditions is conducive to reducing the differences in shooting conditions of aerial images obtained at the same waypoint, so that the present invention can obtain accurate calculation results at a faster speed in the subsequent acquisition process of the most representative aerial images.

[0093] Preferably, S42 includes:

[0094] S421, for aerimg b,1 Grayscale and obtain the image gaerimg b,1 ;

[0095] S422, for gaerimg b,1 Filter and get the image aerimg b,1,opt .

[0096] Filtering the image can suppress the noise in the image, which is beneficial for obtaining more accurate results when calculating the total number of shots later.

[0097] Preferably, S43 includes:

[0098] S431, obtaining the aerial image set U of the bth waypoint during the last inspection of the power equipment b,last ;

[0099] S432, U b,last The most representative aerial image in is taken as the historical aerial image aerimg of the bth waypoint b,last ;

[0100] S433, for aerimg b,last Grayscale and obtain the image gaerimg b,last ;

[0101] S434, for gaerimg b,last Filter and obtain the image gaerimg b,last,opt ;

[0102] S435, obtain aerimg b,1,opt Chinese and gaerimg b,last,opt The number of pixels whose grayscale difference is greater than the set grayscale threshold is M b ;

[0103] S436, calculation of aerimg b,1,opt The mean gray value of the pixels in avegray b,1,opt ;

[0104] S437, calculate the total number of shots N of b waypoints using the following formula b :

[0105]

[0106] M b,last Indicates gaerimg b,last The number of pixels in maxgray b,1,opt Indicates aerimg b,1,opt The maximum gray value in avegray b,1,opt Indicates aerimg b,1,opt The mean of the gray values ​​in pU b,1,opt Indicates aerimg b,1,opt The set of pixels in M b,1,opt Indicates pU b,1,opt The number of pixels in grat irepresents the image gradient of pixel i; avgrat represents pU b,1,opt The mean value of the image gradient in , maxgrat represents pU b,1,opt The maximum value of the image gradient in, λ1, λ2, λ3 represent the first weight, the second weight and the third weight set in advance respectively, N bs Indicates a preset quantity.

[0107] The total number of shots for each waypoint is not fixed, but varies with the degree of change between the first aerial image obtained during this inspection and the historical aerial images, the aerimg b,1,opt The mean of the grayscale values ​​in aerimg b,1,opt The image gradient distribution characteristics of the pixels in the image are adaptively changed. The greater the degree of change, the smaller the mean of the grayscale value, the more uneven the image gradient distribution, and the greater the total number of shots. This calculation method can obtain more aerial images when the degree of change of the power equipment is greater, the lighting conditions of the shooting environment are worse, and the shape of the power equipment is more complex. Therefore, when the aerial images are used to identify the status of the power equipment, image synthesis can be performed based on more aerial images to more accurately identify the power identification status.

[0108] Preferably, the grayscale value threshold is set to 15.

[0109] Preferably, when N calculated in S437 b When N is an integer, b to process;

[0110] When N calculated in S437 b If N is not an integer, b The value obtained after rounding is regarded as the total number of shots.

[0111] Preferably, the preset first weight, second weight and third weight are 0.3, 0.4 and 0.3 respectively.

[0112] In practical applications, these weights can be adjusted accordingly as needed, and whichever aspect is emphasized will be given greater weight.

[0113] Preferably, the preset number is 20.

[0114] Preferably, U b,last The most representative aerial image acquisition process includes:

[0115] The first step is to b,last Select any aerial image aerimg rand ;

[0116] The second step is to aerimg rand Divided into Z1×Z2 regions of equal size;

[0117] The third step is to calculate the representative coefficients of the pixels in each area respectively;

[0118] The fourth step is to obtain the set cordU of coordinates of the pixel points in the area with the largest representative coefficient;

[0119] Step 5: Get U based on cordU b,last The no-reference image quality evaluation value of each aerial image in ;

[0120] Step 6: b,last The aerial image with the largest quality evaluation value among the reference images is taken as U b,last The most representative aerial images.

[0121] Because U b,last There are a large number of aerial photos in the image. Therefore, when the most representative aerial image needs to be selected, if the calculation is based on all the pixels in the aerial image, it will take a long time to obtain the most representative aerial image due to the large number of pixels. This results in the need for higher performance equipment when using the solution of the present invention, which increases the cost of use. Therefore, the present invention utilizes the fact that the shooting conditions of aerial images of the same waypoint are the same. After selecting the most representative area from an aerial image, the reference-free image quality evaluation value of all aerial images is obtained based on the coordinates of the regional pixel points. A small number of pixels can be used to effectively represent the true quality of the aerial image, thereby greatly improving the efficiency of obtaining the most representative aerial images.

[0122] Preferably, the calculation formula of Z1 is:

[0123]

[0124] leng rand Indicates aerimg rand The number of columns of pixels, L represents the preset length;

[0125] The calculation formula of Z2 is:

[0126]

[0127] brea rand Indicates aerimg rand The number of rows of pixels.

[0128] The size of the region is closely related to the value of L. The larger L is, the larger the region is.

[0129] Preferably, the value of L is 9.

[0130] Preferably, aerimg rand Divided into Z1×Z2 regions of equal size, including:

[0131] The length of each region is Width is

[0132] Will aerimg rand Divided into Z1×Z2 pieces with length Width is area.

[0133] Preferably, the representative coefficient is calculated using the following formula:

[0134]

[0135] repcef v Represents the representative coefficient of the pixel in region v, miv and mxv are the minimum and maximum grayscale values ​​of the pixel in region v, respectively, N j is the number of pixels with grayscale value equal to j in region v, N v is the total number of pixels in region v.

[0136] The representative coefficient of the present invention is obtained by calculating the comprehensive difference between the numbers of pixels of different gray values. The larger the comprehensive difference, the greater the representativeness, indicating that the region v contains more effective image details and is more representative.

[0137] Preferably, based on cordU, U is obtained respectively. b,last The no-reference image quality evaluation value of each aerial image in includes:

[0138] For any aerial image, the no-reference quality evaluation algorithm is used to calculate the area where all pixels whose coordinates belong to cordU in the aerial image are located to obtain the no-reference image quality evaluation value.

[0139] Preferably, the no-reference image quality evaluation value is calculated by a NIQE algorithm, and the calculation result of the NIQE algorithm is used as the no-reference image quality evaluation value.

[0140] Preferably, gaerimg b,1 Filter and get the image aerimg b,1,opt ,include:

[0141] Will gaerimg b,1 Divided into multiple areas to be filtered;

[0142] Based on the set of coordinates of each pixel point in the area to be filtered, gaerimg b,1 Filter and get aerimg b,1,opt .

[0143] Preferably, gaerimg b,1 Divided into multiple areas to be filtered, including:

[0144] Will gaerimg b,1 It is divided into multiple overlapping filtering areas of size 3×3.

[0145] There is one column of overlapping pixels between two adjacent left and right areas to be filtered, and there is one row of overlapping pixels between two adjacent upper and lower areas to be filtered.

[0146] Preferably, based on the set of coordinates of the pixel points in each area to be filtered, gaerimg b,1 Filter and get aerimg b,1,opt ,include:

[0147] Each area to be filtered is numbered consecutively in descending order of gray value standard deviation. The larger the standard deviation, the smaller the number.

[0148] For the first area to be filtered, the filtering process is as follows:

[0149] In gaerimg b,1 In the first filter area, the standard deviation of the gray value is judged to be greater than the set standard deviation threshold. If so, in gaerimg b,1 The first filtering algorithm is used to filter the pixels in the first filtering area to obtain lwimg1; if not, then in gaerimg b,1 The second filtering algorithm is used to filter the pixels in the first filtering area to obtain lwimg1;

[0150] For the dth area to be filtered, the filtering process is as follows:

[0151] Use pU d represents the set of pixel coordinates of the dth area to be filtered, where d is an integer greater than 1 and less than or equal to the maximum value of the number;

[0152] At LWIMG d-1 Judgment pU d Is the standard deviation of the grayscale value of the pixel corresponding to the coordinate in greater than the set standard deviation threshold? If so, then in lwimg d-1 The first filtering algorithm is used to filter pU d Filter the pixel points corresponding to the coordinates in lwimg dIf not, then in gaerimg b,1 The second filtering algorithm is used to filter pU d Filter the pixel points corresponding to the coordinates in lwimg d .

[0153] In the present invention, the filtering processes are not independent of each other, but the latter filtering can refer to the previous filtering results. As the filtering process proceeds, the correct grayscale values ​​that can be referenced by the latter filtering are increasing, thereby making the filtering process more accurate. In addition, the present invention also selects the filtering algorithm by calculating the standard deviation. At the beginning of filtering, since there are fewer correct grayscale values ​​that can be referenced, the standard deviation may be relatively large. At this time, when selecting the filtering algorithm, the present invention gives priority to the filtering performance. As the filtering proceeds, more and more correct grayscale values ​​can be referenced, and the filtering difficulty becomes lower and lower, so that when obtaining the filtering algorithm, the filtering time consumption can be given priority.

[0154] The entire filtering process comprehensively considers the filtering performance and filtering efficiency, avoiding the use of a single filtering algorithm to filter all pixels, and can achieve a better balance between filtering performance and efficiency. In this way, the accuracy of the filtering results can be guaranteed while improving the filtering efficiency.

[0155] Preferably, the time consumption of the second filtering algorithm is greater than the time consumption of the first filtering algorithm.

[0156] The second filtering algorithm includes a median filter, and the first filtering algorithm includes a Kalman filter or a Kuwahara filter.

[0157] Preferably, gaerimg b,last Filter and obtain the image gaerimg b,last,opt When the filtering scheme used is the same as that of gaerimg b,1 Filter and get the image aerimg b,1,opt The same scheme.

[0158] The second aspect, such as Figure 2 As shown, the present invention provides a power inspection drone control system, including a first acquisition module, a calculation module, a second acquisition module and a control module;

[0159] The first acquisition module is used to acquire a set U of waypoints when inspecting the power equipment;

[0160] The calculation module is used to calculate the distance between two adjacent waypoints in the inspection sequence using an improved distance calculation formula;

[0161] The distance calculation formula between the bth waypoint and the b+1th waypoint is:

[0162]

[0163] impdist b,b+1 Indicates the distance between the b-th waypoint and the b+1-th waypoint, lon b and lat b Respectively represent the longitude and latitude of the b-th waypoint, lon b+1 and lat b+1 Respectively represent the longitude and latitude of the b+1th waypoint, θ b,b+1 Represents the angle between the straight line segment connecting the b-th waypoint and the b+1-th waypoint and the horizontal plane where the b+1-th waypoint is located;

[0164] The second acquisition module is used to acquire the shortest flight path of all waypoints in the set U based on the distance obtained by the calculation module;

[0165] The control module is used to control the UAV to fly along the shortest flight path and obtain a set of aerial images of each waypoint.

[0166] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0167] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0169] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope parameters of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling a power inspection drone, characterized in that: include: S1, obtain a set U of waypoints for inspection of power equipment; S2, using the improved distance calculation formula to calculate the distance between two adjacent waypoints in the inspection order; The distance calculation formula between the bth waypoint and the b+1th waypoint is: impdist b,b+1 Indicates the distance between the b-th waypoint and the b+1-th waypoint, lon b and lat b Respectively represent the longitude and latitude of the b-th waypoint, lon b+1 and lat b+1 Respectively represent the longitude and latitude of the b+1th waypoint, θ b,b+1 Indicates that the angle between the straight line segment connecting the bth waypoint and the b+1th waypoint and the horizontal plane where the b+1th waypoint is located is less than 90°; S3, obtain the shortest flight path of all waypoints in set U based on the distance obtained in S2; S4, controlling the UAV to fly along the shortest flight path and obtaining a set of aerial images of each waypoint; Get aerial images of each waypoint separately, including: S41, for the bth waypoint, photograph the bth waypoint according to the set shooting direction to obtain the first aerial image aerimg b,1 ; S42, for aerimg b,1 Perform image preprocessing to obtain image aerimg b,1,opt ; S43, based on aerimg b,1,opt And the historical aerial images of the b-th waypoint, calculate the total number of shots N of the b-th waypoint b ; S44, use with aerimg b,1 The same shooting conditions are used to perform N b -1 shot, get N b - 1 aerial image; S45, using the aerial images obtained in S41 and S44 as a set of aerial images of the b-th waypoint; S42 includes: S421, for aerimg b,1 Grayscale and obtain the image gaerimg b,1 ; S422, for gaerimg b,1 Filter and get the image aerimg b,1,opt ; S43 includes: S431, obtaining the aerial image set U of the bth waypoint during the last inspection of the power equipment b,last ; S432, U b,last The most representative aerial image in is taken as the historical aerial image aerimg of the bth waypoint b,last ; S433, for aerimg b,last Grayscale and obtain the image gaerimg b,last ; S434, for gaerimg b,last Filter and obtain the image gaerimg b,last,opt ; S435, obtain aerimg b,1,opt Chinese and gaerimg b,last,opt The number of pixels whose grayscale difference is greater than the set grayscale threshold is M b ; S436, calculation of aerimg b,1,opt The mean gray value of the pixels in avegray b,1,opt ; S437, calculate the total number of shots N of b waypoints using the following formula b : M b,last Indicates gaerimg b,last The number of pixels in maxgray b,1,opt Indicates aerimg b,1,opt The maximum gray value in avegray b,1,opt Indicates aerimg b,1,opt The mean of the gray values ​​in pU b,1,opt Indicates aerimg b,1,opt The set of pixels in M b,1,opt Indicates pU b,1,opt The number of pixels in grat i represents the image gradient of pixel i; avgrat represents pU b,1,opt The mean value of the image gradient in , maxgrat represents pU b,1,opt The maximum value of the image gradient in, λ1, λ2, λ3 represent the first weight, second weight and third weight set in advance respectively, N bs Indicates a preset quantity.

2. The control method of a power inspection drone according to claim 1, characterized in that S3 include: S31, taking any two different waypoints in U as the starting point and end point of the inspection, traversing all flight paths; S32, calculating the total length of each flight path obtained in S31 based on the distance obtained in S2; S33, taking the flight path with the shortest total length as the shortest flight path.

3. The control method of a power inspection drone according to claim 1 is characterized in that: U b,last The most representative aerial image acquisition process includes: The first step is to b,last Select any aerial image aerimg rand ; The second step is to aerimg rand Divided into Z1×Z2 regions of equal size; The third step is to calculate the representative coefficients of the pixels in each area respectively; The fourth step is to obtain the set cordU of coordinates of the pixel points in the area with the largest representative coefficient; Step 5: Get U based on cordU b,last The no-reference image quality evaluation value of each aerial image in ; Step 6: b,last The aerial image with the largest quality evaluation value among the reference images is taken as U b,last The most representative aerial images.

4. A method for controlling a power inspection drone according to claim 3, characterized in that: The calculation formula of Z1 is: leng rand Indicates aerimg rand The number of columns of pixels, L represents the preset length; The calculation formula of Z2 is: brea rand Indicates aerimg rand The number of rows of pixels.

5. A method for controlling a power inspection drone according to claim 4, characterized in that: Will aerimg rand Divided into Z1×Z2 regions of equal size, including: The length of each region is Width is Will aerimg rand Divided into Z1×Z2 pieces with length Width is area.

6. A method for controlling a power inspection drone according to claim 4, characterized in that: About gaerimg b,1 Filter and get the image aerimg b,1,opt ,include: Will gaerimg b,1 Divided into multiple areas to be filtered; Based on the set of coordinates of each pixel point in the area to be filtered, gaerimg b,1 Filter and get aerimg b,1,opt .

7. A power inspection drone control system, characterized in that: It includes a first acquisition module, a calculation module, a second acquisition module and a control module; The first acquisition module is used to acquire a set U of waypoints when inspecting the power equipment; The calculation module is used to calculate the distance between two adjacent waypoints in the inspection sequence using an improved distance calculation formula; The distance calculation formula between the bth waypoint and the b+1th waypoint is: impdist b,b+1 Indicates the distance between the b-th waypoint and the b+1-th waypoint, lon b and lat b Respectively represent the longitude and latitude of the b-th waypoint, lon b+1 and lat b+1 Respectively represent the longitude and latitude of the b+1th waypoint, θ b,b+1 Indicates that the angle between the straight line segment connecting the bth waypoint and the b+1th waypoint and the horizontal plane where the b+1th waypoint is located is less than 90°; The second acquisition module is used to acquire the shortest flight path of all waypoints in the set U based on the distance obtained by the calculation module; The control module is used to control the UAV to fly along the shortest flight path and obtain a set of aerial images of each waypoint; Get aerial images of each waypoint separately, including: S41, for the bth waypoint, photograph the bth waypoint according to the set shooting direction to obtain the first aerial image aerimg b,1 ; S42, for aerimg b,1 Perform image preprocessing to obtain image aerimg b,1,opt ; S43, based on aerimg b,1,opt And the historical aerial images of the b-th waypoint, calculate the total number of shots N of the b-th waypoint b ; S44, use with aerimg b,1 The same shooting conditions are used to perform N b -1 shot, get N b - 1 aerial image; S45, using the aerial images obtained in S41 and S44 as a set of aerial images of the b-th waypoint; S42 includes: S421, for aerimg b,1 Grayscale and obtain the image gaerimg b,1 ; S422, for gaerimg b,1 Filter and get the image aerimg b,1,opt ; S43 includes: S431, obtaining the aerial image set U of the bth waypoint during the last inspection of the power equipment b,last ; S432, U b,last The most representative aerial image in is taken as the historical aerial image aerimg of the bth waypoint b,last ; S433, for aerimg b,last Grayscale and obtain the image gaerimg b,last ; S434, for gaerimg b,last Filter and obtain the image gaerimg b,last,opt ; S435, obtain aerimg b,1,opt Chinese and gaerimg b,last,opt The number of pixels whose grayscale difference is greater than the set grayscale threshold is M b ; S436, calculation of aerimg b,1,opt The mean gray value of the pixels in avegray b,1,opt ; S437, calculate the total number of shots N of b waypoints using the following formula b : M b,last Indicates gaerimg b,last The number of pixels in maxgray b,1,opt Indicates aerimg b,1,opt The maximum gray value in avegray b,1,opt Indicates aerimg b,1,opt The mean of the gray values ​​in pU b,1,opt Indicates aerimg b,1,opt The set of pixels in M b,1,opt Indicates pU b,1,opt The number of pixels in grat i represents the image gradient of pixel i; avgrat represents pU b,1,opt The mean value of the image gradient in , maxgrat represents pU b,1,opt The maximum value of the image gradient in, λ1, λ2, λ3 represent the first weight, second weight and third weight set in advance respectively, N bs Indicates a preset quantity.

Images