Tower type identification method and device, equipment, storage medium and product

Abstract

The invention belongs to the technical field of power transmission line towers, and discloses a tower type identification method, device and equipment, a storage medium and a product. According to the method, the top view projection is carried out on the initial point cloud model, and then the tower region in the projected first image is extracted, so that the influence of tiny differences in tower volume and tower shape on tower region extraction can be eliminated through the top view projection; fusing the target point cloud model with a standard point cloud model corresponding to a preset standard pole tower, performing main view projection on the fused point cloud model, and determining a pole tower type corresponding to the target point cloud model according to a projected second image; the type of the power transmission line tower can be accurately and effectively identified according to the image coincidence degree corresponding to the projected second image, and fusion of towers of the same type is realized.

Description

Technical Field

[0001] The present application relates to the technical field of transmission line towers, and in particular to a tower type identification method, device, equipment, storage medium and product. Background Art

[0002] Drone inspections of power transmission lines have gradually become a mainstream inspection method in recent years. Drones equipped with visible light and infrared cameras take non-contact photos of transmission line towers along the lines, and then perform intelligent diagnosis of the towers based on the captured images. During the intelligent diagnosis of towers, it is necessary to pre-match the tower to be identified with the corresponding template tower. Transmission line towers are located in geographical space, and there are subtle differences in tower size and equipment mounted on them. Many seemingly identical towers are difficult to merge during the actual matching process. These difficult-to-merge towers directly lead to deviations in the waypoint routes migrated from the standard towers, resulting in errors in the final captured image data. Therefore, how to accurately and effectively identify the type of transmission line towers and merge towers of the same type has become a pressing issue. Summary of the Invention

[0003] The main purpose of this application is to provide a tower type identification method, device, equipment, storage medium and product, aiming to solve the technical problem of how to accurately and effectively identify the type of transmission line towers and achieve the integration of towers of the same type.

[0004] To achieve the above objectives, the present application provides a method for identifying tower types, which includes the following steps:

[0005] Acquire an initial point cloud model corresponding to the transmission line, and perform a top-view projection on the initial point cloud model to obtain a projected first image;

[0006] Extracting a tower area in the projected first image and determining a target point cloud model corresponding to the tower area;

[0007] Fusing the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model;

[0008] The fused point cloud model is projected in a main view, and the tower type corresponding to the target point cloud model is determined according to the projected second image.

[0009] Optionally, the step of obtaining an initial point cloud model corresponding to the transmission line and performing top-view projection on the initial point cloud model to obtain a projected first image specifically includes:

[0010] Collecting point cloud data corresponding to the transmission line, and performing point cloud modeling based on the point cloud data to obtain an initial point cloud model;

[0011] Determining the number of segments according to the line length corresponding to the transmission line and a preset cutting distance;

[0012] Segmenting the initial point cloud model according to the number of segments to obtain a segmented point cloud model;

[0013] Perform top-view projection on each segmented point cloud model to obtain a first projected image.

[0014] Optionally, the step of extracting the tower area in the projected first image and determining the target point cloud model corresponding to the tower area specifically includes:

[0015] Extracting the tower area in the projected first image by a target detection algorithm;

[0016] Determine the pixel coordinates corresponding to the tower area;

[0017] The target point cloud model corresponding to the tower area is determined according to the pixel point coordinates and a preset mapping relationship, wherein the preset mapping relationship includes a mapping relationship between the point cloud data corresponding to the segmented point cloud model and the pixel point coordinates corresponding to the projected first image.

[0018] Optionally, the step of fusing the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model specifically includes:

[0019] Taking the tower head in the target point cloud model as the starting point, cutting out a point cloud model to be identified of a preset length from the target point cloud model;

[0020] Determine the size to be identified corresponding to the point cloud model to be identified and the standard size of the standard point cloud model corresponding to the preset standard tower;

[0021] Adjusting the size of the point cloud model to be identified according to the size to be identified and the standard size to obtain an adjusted point cloud model;

[0022] The adjusted point cloud model is fused with the standard point cloud model to obtain a fused point cloud model.

[0023] Optionally, the step of performing a main view projection on the fused point cloud model and determining the tower type corresponding to the target point cloud model according to the projected second image specifically includes:

[0024] Performing a main view projection on the fused point cloud model to obtain a projected second image;

[0025] Determining, in the projected second image, a first binary image corresponding to the target point cloud model and a second binary image corresponding to the standard point cloud model;

[0026] calculating a fusion overlap between the first binary image and the second binary image;

[0027] The tower type corresponding to the target point cloud model is determined according to the fusion overlap.

[0028] Optionally, the step of calculating the fusion overlap between the first binary image and the second binary image specifically includes:

[0029] calculating an intersection-over-union ratio of an overlapping area between the first binary image and the second binary image;

[0030] determining a non-overlapping area between the first binary image and the second binary image, the non-overlapping area being in the first binary image;

[0031] Determine a plurality of first pixel points corresponding to the non-overlapping area, and determine a second pixel point corresponding to each first pixel point from the second binary image;

[0032] Determining pixel distances according to first pixel coordinates corresponding to each first pixel and pixel coordinates corresponding to each second pixel, and obtaining a sum of the pixel distances;

[0033] The fusion overlap between the first binary image and the second binary image is calculated according to the intersection-over-union ratio and the sum of the pixel point distances.

[0034] Optionally, the step of calculating the intersection-over-union ratio of the overlapping area between the first binary image and the second binary image specifically includes:

[0035] Determining a first number of overlapping pixels and a second number of overlapping pixels between the first binary image and the second binary image;

[0036] The sum of the first number of overlapping pixels and the second number of overlapping pixels is used as the number of intersection pixels;

[0037] Determining a first total number of pixels of the first binary image and a second total number of pixels of the second binary image;

[0038] The sum of the first total number of pixels and the second total number of pixels is used as the number of pixels in the union;

[0039] The ratio of the number of intersection pixels to the number of union pixels is used as an intersection-and-union ratio of an overlapping area between the first binary image and the second binary image.

[0040] Optionally, the step of determining the tower type corresponding to the target point cloud model according to the fusion overlap specifically includes:

[0041] When the fusion overlap is greater than a preset threshold, determining that the tower type corresponding to the target point cloud model is the tower type corresponding to a preset standard tower;

[0042] When the fusion overlap is less than or equal to the preset threshold, selecting a new preset standard pole from the preset standard pole library;

[0043] Returning to the step of fusing the target point cloud model with the standard point cloud model corresponding to the preset standard tower to obtain a fused point cloud model, and obtaining a new fusion overlap;

[0044] When the new fusion overlap is greater than the preset threshold, it is determined that the tower type corresponding to the target point cloud model is the tower type corresponding to the new preset standard tower.

[0045] In addition, to achieve the above-mentioned purpose, the present application further provides a tower type identification device, the tower type identification device comprising:

[0046] a point cloud model projection module, configured to obtain an initial point cloud model corresponding to the transmission line, and perform a top view projection on the initial point cloud model to obtain a projected first image;

[0047] A tower area extraction module, configured to extract the tower area in the projected first image and determine a target point cloud model corresponding to the tower area;

[0048] A point cloud model fusion module is used to fuse the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model;

[0049] The tower type recognition module is used to perform a main view projection on the fused point cloud model and determine the tower type corresponding to the target point cloud model based on the projected second image.

[0050] In addition, to achieve the above-mentioned purpose, the present application also proposes a pole tower type identification device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the pole tower type identification method described above.

[0051] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the steps of the tower type identification method described above are implemented.

[0052] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the tower type identification method described above are implemented.

[0053] The present application obtains an initial point cloud model corresponding to a transmission line and projects the initial point cloud model in a top-view projection to obtain a first projected image. The tower area in the projected first image is then extracted and a target point cloud model corresponding to the tower area is determined. The target point cloud model is then fused with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model. The fused point cloud model is then projected in a front view and the tower type corresponding to the target point cloud model is determined based on the projected second image. The present application projects the initial point cloud model in a top-view projection and then extracts the tower area in the projected first image. The top-view projection can be used to eliminate the influence of subtle differences in tower volume and tower shape on tower area extraction. The target point cloud model is then fused with a standard point cloud model corresponding to a preset standard tower, and the fused point cloud model is then projected in a front view and the tower type corresponding to the target point cloud model is determined based on the projected second image. The type of transmission line tower can be accurately and effectively identified based on the degree of image overlap corresponding to the projected second image, thereby achieving fusion of towers of the same type. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0056] Figure 1 This is a flow chart of the first embodiment of the tower type identification method of the present application;

[0057] Figure 2 A schematic diagram of an initial point cloud model of an embodiment of a tower type identification method of the present application;

[0058] Figure 3A schematic diagram of a segmented point cloud model according to an embodiment of a tower type identification method of the present application;

[0059] Figure 4 Schematic diagram of segmented point cloud, top view projection, and two-dimensional target detection of an embodiment of the tower type identification method of the present application;

[0060] Figure 5 A schematic diagram of a target point cloud model of an embodiment of a tower type identification method of the present application;

[0061] Figure 6 A schematic diagram of a preset standard tower according to an embodiment of the tower type identification method of the present application;

[0062] Figure 7 A schematic diagram of a fused point cloud model according to an embodiment of a tower type identification method of the present application;

[0063] Figure 8 This is a flow chart of the second embodiment of the tower type identification method of the present application;

[0064] Figure 9 This is a structural block diagram of the first embodiment of the tower type identification device of the present application;

[0065] Figure 10 It is a structural diagram of a tower type identification device in the hardware operating environment involved in the embodiment of the present application.

[0066] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0067] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0068] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0069] It should be noted that the execution subject of this application may be a computing service device with data processing, network communication, and program execution functions, such as a computer, or an electronic device capable of implementing the above functions, a tower type identification device, etc. The following uses the tower type identification device as an example to illustrate this embodiment and the following embodiments.

[0070] Based on this, the embodiment of the present application provides a tower type identification method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the tower type identification method of the present application.

[0071] In this embodiment, the tower type identification method includes the following steps:

[0072] Step S10: obtaining an initial point cloud model corresponding to the transmission line, and performing a top view projection on the initial point cloud model to obtain a projected first image.

[0073] It is understood that this embodiment can model the transmission line area to obtain an initial point cloud model. The number of transmission line 3D point clouds is enormous, and the tower background is complex. Directly identifying tower types and extracting tower point cloud data from the initial point cloud model is extremely difficult. However, planarizing and compressing the initial point cloud model from a top-down view allows for a better visualization of the tower locations. Therefore, this embodiment can project the initial point cloud model from a top-down view, constructing a projection of the 3D point cloud onto a top-down 2D image to obtain a projected first image.

[0074] Furthermore, in order to improve the efficiency of tower type identification, in this embodiment, step S10 includes: collecting point cloud data corresponding to the transmission line, and performing point cloud modeling based on the point cloud data to obtain an initial point cloud model; determining the number of segments based on the line length corresponding to the transmission line and a preset clipping distance; segmenting the initial point cloud model according to the number of segments to obtain a segmented point cloud model; and performing top-view projection on each segmented point cloud model to obtain a projected first image.

[0075] It should be understood that the laser radar module carried by the UAV can be used to collect laser point cloud data along the transmission line. For the collected point cloud data, the scanned transmission line area can be modeled using a third-party GIS (Geographic Information System) software to obtain the initial point cloud model corresponding to the transmission line, such as Figure 2 As shown, Figure 2 This is a schematic diagram of an initial point cloud model of an embodiment of a tower type identification method of the present application.

[0076] It is understandable that due to the huge amount of point cloud data of the transmission line, the initial point cloud model can be segmented to improve the efficiency of subsequent identification of tower types. Specifically, the number of segments can be determined based on the line length corresponding to the transmission line and the preset clipping distance. The line length refers to the length of the transmission line in the initial point cloud model. The preset clipping distance can be a pre-set fixed value or a range, such as 1 meter, (2 meters, 3 meters). Then, the initial point cloud model is segmented according to the number of segments, and the number of segmented point cloud models is the same as the number of segments, such as Figure 3 As shown, Figure 3 This is a schematic diagram of a segmented point cloud model of an embodiment of the tower type identification method of this application. Figure 3Different colors in the figure represent different segmented point cloud models. The upper part represents transmission lines, towers, etc., and the lower part represents the ground, which may be mountainous and uneven. In this embodiment, the geographical location of the point cloud is clustered, and the color of the segmented ground points at the same location is consistent with the color of the transmission line point cloud.

[0077] In a specific implementation, a top view projection may be performed on each segmented point cloud model to obtain a projected first image, which is a two-dimensional image.

[0078] Step S20: extracting the tower area in the projected first image and determining a target point cloud model corresponding to the tower area.

[0079] It is understandable that referring to Figure 4 , Figure 4 This is a schematic diagram of the segmented point cloud, top view projection, and two-dimensional target detection of an embodiment of the tower type identification method of this application. The first picture is the segmented point cloud, the second picture is the first image projected from the top view, and the third picture is the image of the first image after two-dimensional target detection. The blue box is the tower area. After obtaining the two-dimensional tower area, it can be converted into a three-dimensional target point cloud model, such as Figure 5 As shown, Figure 5 This is a schematic diagram of a target point cloud model according to an embodiment of a tower type identification method of the present application.

[0080] Furthermore, in order to obtain the target point cloud model corresponding to the tower area, in this embodiment, the step S20 includes: extracting the tower area in the projected first image through a target detection algorithm; determining the pixel coordinates corresponding to the tower area; determining the target point cloud model corresponding to the tower area according to the pixel coordinates and a preset mapping relationship, and the preset mapping relationship includes the mapping relationship between the point cloud data corresponding to the segmented point cloud model and the pixel coordinates corresponding to the projected first image.

[0081] It should be understood that the object detection algorithm can be used to detect the object of interest in the image and give a bounding box for the object, that is, Figure 5 The blue bounding box in the image indicates that the target is the tower area. The target detection algorithm can be the YOLO (You Only Look Once) algorithm, the SSD (Single Shot MultiBox Detector) algorithm, etc. All pixels in the tower area in the projected first image are determined, and the pixel coordinates corresponding to all pixels are obtained.

[0082] It can be understood that the preset mapping relationship may include the mapping relationship between the point cloud data corresponding to the segmented point cloud model and the pixel coordinates of the pixel points corresponding to the projected first image, that is, the mapping relationship between three-dimensional point cloud data and two-dimensional pixel coordinates. The point cloud data corresponding to the pixel coordinates of the tower area can be found from the preset mapping relationship, and the point cloud data corresponding to the tower area can be point cloud modeled to obtain the target point cloud model.

[0083] Step S30: fusing the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model.

[0084] It should be understood that, since the types of towers for transmission lines are relatively limited, this embodiment can pre-build a template library, which can include several preset standard towers. Each preset standard tower corresponds to a different tower type. Figure 6 , Figure 6 This is a schematic diagram of a preset standard tower in an embodiment of the tower type identification method of this application. Figure 6 The five towers in the figure are of different tower types, including, from left to right, AC double-circuit tension tower, AC single-circuit tension tower, AC four-circuit linear tower, AC double-circuit tension tower, and AC double-circuit linear tower. Other types of preset standard towers may also be included.

[0085] In the specific implementation, the target point cloud model corresponding to the tower area is fused with the standard point cloud model corresponding to the preset standard tower to obtain the fused point cloud model. Figure 7 , Figure 7 This is a schematic diagram of a fused point cloud model according to an embodiment of the tower type identification method of this application. Figure 7 There are three schematic diagrams of fused point cloud models, from top to bottom: point cloud models after fusion of different types of towers, point cloud models after fusion of different types of towers, and point cloud models after fusion of the same type of towers. It can be seen that the point cloud models after fusion of the same type of towers are basically overlapping.

[0086] Furthermore, in order to achieve the fusion between the target point cloud model and the standard point cloud model, in this embodiment, step S30 includes: taking the tower head in the target point cloud model as the starting point, cutting out a point cloud model to be identified of a preset length from the target point cloud model; determining the size to be identified corresponding to the point cloud model to be identified and the standard size of the standard point cloud model corresponding to a preset standard tower; adjusting the size of the point cloud model to be identified according to the size to be identified and the standard size to obtain an adjusted point cloud model; and fusing the adjusted point cloud model with the standard point cloud model to obtain a fused point cloud model.

[0087] It is understood that for the target point cloud model, a predetermined length of the target point cloud model can be cut from the tower head to the tower body. The target size of the target point cloud model and the standard size of the preset standard tower are determined. The target size may include the height and length of the target point cloud model. The target point cloud model is then resized based on the target size and the standard size to ensure that the adjusted point cloud model is the same as the standard size. Finally, the adjusted point cloud model is fused with the standard point cloud model to obtain a fused point cloud model.

[0088] Step S40: performing main view projection on the fused point cloud model, and determining the tower type corresponding to the target point cloud model according to the projected second image.

[0089] In a specific implementation, the fused point cloud model can be projected in the main view to obtain a projected second image, which can convert the three-dimensional point cloud into a two-dimensional image, and determine the type of pole tower corresponding to the target point cloud model based on the projected second image. Specifically, it can be determined whether the two-dimensional image corresponding to the adjusted point cloud model and the standard point cloud model are basically identical in the projected second image. If so, it is determined that the pole tower type corresponding to the target point cloud model is the same as the pole tower type corresponding to the standard point cloud model.

[0090] This embodiment obtains an initial point cloud model corresponding to a transmission line and projects the initial point cloud model from a top view to obtain a projected first image. The tower region in the projected first image is then extracted, and a target point cloud model corresponding to the tower region is determined. The target point cloud model is then fused with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model. The fused point cloud model is then projected from a front view, and the tower type corresponding to the target point cloud model is determined based on the projected second image. This embodiment projects the initial point cloud model from a top view and then extracts the tower region from the projected first image. This allows the top view projection to eliminate the effects of subtle differences in tower volume and tower shape on tower region extraction. By fusing the target point cloud model with a standard point cloud model corresponding to a preset standard tower, projecting the fused point cloud model from a front view, and determining the tower type corresponding to the target point cloud model based on the projected second image, the type of transmission line tower can be accurately and effectively identified based on the degree of image overlap corresponding to the projected second image, enabling the fusion of towers of the same type.

[0091] refer to Figure 8 , Figure 8 This is a flow chart of the second embodiment of the tower type identification method of the present application.

[0092] Based on the above first embodiment, in this embodiment, step S40 includes:

[0093] Step S401: performing a main view projection on the fused point cloud model to obtain a projected second image.

[0094] It should be understood that this embodiment can perform a main view projection on the fused point cloud model, that is, project the fused point cloud model from the direction of the main view, and the obtained projected second image can include the main view of the fused point cloud model.

[0095] Step S402: determining, in the projected second image, a first binary image corresponding to the target point cloud model and a second binary image corresponding to the standard point cloud model.

[0096] It can be understood that since the projected second image is obtained by projecting the main view of the fused point cloud model, and the fused point cloud model is obtained by fusing the target point cloud model and the standard point cloud model, the projected second image may include a two-dimensional image corresponding to the target point cloud model and a two-dimensional image corresponding to the standard point cloud model, and then the two-dimensional image is converted into a binary image to obtain a first binary image corresponding to the target point cloud model and a second binary image corresponding to the standard point cloud model.

[0097] Step S403: Calculating the fusion overlap between the first binary image and the second binary image.

[0098] It should be understood that the fusion coincidence between the first binary image and the second binary image may be calculated, and the fusion coincidence may represent the degree of overlap between the first binary image and the second binary image.

[0099] Furthermore, in order to accurately calculate the fusion overlap, in this embodiment, the step S403 includes: calculating the intersection-and-union ratio of the overlapping area between the first binary image and the second binary image; determining the non-overlapping area between the first binary image and the second binary image, and the non-overlapping area is in the first binary image; determining multiple first pixel points corresponding to the non-overlapping area, and determining the second pixel points corresponding to each first pixel point from the second binary image; determining the pixel point distance according to the first pixel point coordinates corresponding to each first pixel point and the pixel point coordinates corresponding to each second pixel point, and obtaining the sum of the pixel point distances; calculating the fusion overlap between the first binary image and the second binary image according to the intersection-and-union ratio and the sum of the pixel point distances.

[0100] Understandably, Where α and β are weight constants that can be set by yourself, J is the intersection-overlap ratio of the overlapping area between the first binary image and the second binary image, and ag_dist is the sum of the pixel distances in the non-overlapping area between the first binary image and the second binary image.

[0101] It should be understood that when calculating the sum of pixel distances, a non-overlapping region between the first binary image and the second binary image can be first determined, where the non-overlapping region is on the first binary image, and a plurality of first pixels corresponding to the non-overlapping region on the first binary image are determined. Then, the second pixel closest to each first pixel is searched in the second binary image. Pixel distances are calculated based on the first pixel coordinates corresponding to the first pixel and the second pixel coordinates of the second pixel closest to the first pixel, thereby obtaining the pixel distances corresponding to each first pixel. All pixel distances are then summed to obtain the sum of the pixel distances.

[0102] Furthermore, in order to accurately calculate the intersection-and-union ratio of the overlapping area between the first binary image and the second binary image, in this embodiment, the step of calculating the intersection-and-union ratio of the overlapping area between the first binary image and the second binary image specifically includes: determining a first number of overlapping pixels and a second number of overlapping pixels between the first binary image and the second binary image; taking the sum of the first number of overlapping pixels and the second number of overlapping pixels as the number of intersection pixels; determining a first total number of pixels of the first binary image and a second total number of pixels of the second binary image; taking the sum of the first total number of pixels and the second total number of pixels as the number of union pixels; and taking the ratio of the number of intersection pixels to the number of union pixels as the intersection-and-union ratio of the overlapping area between the first binary image and the second binary image.

[0103] It is understandable that when calculating the intersection-and-union ratio, the overlapping area between the first binary image and the second binary image can be first determined, and then the first number of overlapping pixels in the overlapping area in the first binary image is determined, and the second number of overlapping pixels in the overlapping area in the second binary image is determined, and then the sum of the first number of overlapping pixels plus the second number of pixels is used as the number of intersection pixels. It is also necessary to determine the number of all pixels in the first binary image, that is, the first total number of pixels, and determine the number of all pixels in the second binary image, that is, the second total number of pixels, and then the sum of the first total number of pixels plus the second total number of pixels is used as the number of union pixels. Finally, the ratio of the number of intersection pixels to the number of union pixels is used as the intersection-and-union ratio of the overlapping area between the first binary image and the second binary image. An intersection-and-union ratio of 1 indicates that the target point cloud model and the standard point cloud model completely overlap, and an intersection-and-union ratio of 0 indicates that the target point cloud model and the standard point cloud model do not overlap.

[0104] Step S404: determining the tower type corresponding to the target point cloud model according to the fusion overlap.

[0105] It should be understood that when the fusion overlap is close to 1, it means that the target point cloud model and the standard point cloud model are basically completely overlapped, and the tower type corresponding to the target point cloud model is the same as the tower type corresponding to the standard point cloud model.

[0106] Furthermore, in this embodiment, step S404 includes: when the fusion overlap is greater than a preset threshold, determining that the tower type corresponding to the target point cloud model is the tower type corresponding to the preset standard tower; when the fusion overlap is less than or equal to the preset threshold, selecting a new preset standard tower from the preset standard tower library; returning to the step of fusing the target point cloud model with the standard point cloud model corresponding to the preset standard tower to obtain a fused point cloud model, and obtaining a new fusion overlap; when the new fusion overlap is greater than the preset threshold, determining that the tower type corresponding to the target point cloud model is the tower type corresponding to the new preset standard tower.

[0107] It is understandable that the fusion overlap may be in the range of 0 to 1. When the fusion overlap is greater than the preset threshold, it can be determined that the tower type corresponding to the target point cloud model is the same as the tower type corresponding to the preset standard tower. The preset threshold is also between 0 and 1, and can be set to 0.8, 0.85, etc.

[0108] It should be understood that when the fusion overlap is less than or equal to the preset threshold, it indicates that the tower type corresponding to the target point cloud model is different from the tower type corresponding to the preset standard tower. A new preset standard tower can be selected from the preset standard tower library, that is, a preset standard tower that has not undergone model fusion. The preset standard tower library may include different types of preset standard towers. The above steps are then returned to recalculate the new fusion overlap. When the new fusion overlap exceeds the preset threshold, the tower type corresponding to the target point cloud model is determined to be the tower type corresponding to the new preset standard tower. If the new fusion overlap is still less than or equal to the preset threshold, a new preset standard tower needs to be selected again until the new fusion overlap corresponding to the new preset standard tower exceeds the preset threshold.

[0109] This embodiment projects the fused point cloud model from a main view to obtain a projected second image, then determines, in the projected second image, the first binary image corresponding to the target point cloud model and the second binary image corresponding to the standard point cloud model, then calculates the fusion overlap between the first binary image and the second binary image, and then determines the type of tower corresponding to the target point cloud model based on the fusion overlap. This embodiment projects the fused point cloud model from a main view and then calculates the fusion overlap between the first binary image and the second binary image in the projected second image. Based on the fusion overlap, it is possible to determine whether the tower type corresponding to the target point cloud model is the same as the tower type corresponding to the standard point cloud model, thereby accurately and effectively identifying the type of transmission line tower.

[0110] Reference Figure 9 , Figure 9 This is a structural block diagram of the first embodiment of the tower type identification device of this application.

[0111] like Figure 9 As shown, the tower type identification device proposed in the embodiment of the present application includes:

[0112] The point cloud model projection module 10 is used to obtain an initial point cloud model corresponding to the transmission line, and perform a top view projection on the initial point cloud model to obtain a projected first image;

[0113] A tower region extraction module 20 is configured to extract the tower region in the projected first image and determine a target point cloud model corresponding to the tower region;

[0114] The point cloud model fusion module 30 is used to fuse the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model;

[0115] The tower type recognition module 40 is configured to perform a main view projection on the fused point cloud model and determine the tower type corresponding to the target point cloud model according to the projected second image.

[0116] This embodiment obtains an initial point cloud model corresponding to a transmission line and projects the initial point cloud model from a top view to obtain a projected first image. The tower region in the projected first image is then extracted, and a target point cloud model corresponding to the tower region is determined. The target point cloud model is then fused with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model. The fused point cloud model is then projected from a front view, and the tower type corresponding to the target point cloud model is determined based on the projected second image. This embodiment projects the initial point cloud model from a top view and then extracts the tower region from the projected first image. This allows the top view projection to eliminate the effects of subtle differences in tower volume and tower shape on tower region extraction. By fusing the target point cloud model with a standard point cloud model corresponding to a preset standard tower, projecting the fused point cloud model from a front view, and determining the tower type corresponding to the target point cloud model based on the projected second image, the type of transmission line tower can be accurately and effectively identified based on the degree of image overlap corresponding to the projected second image, enabling the fusion of towers of the same type.

[0117] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this application. In actual applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of this embodiment scheme, and no restrictions are imposed here.

[0118] In addition, for technical details not fully described in this embodiment, please refer to the tower type identification method provided in any embodiment of the present application, and will not be repeated here.

[0119] Based on the first embodiment of the pole tower type identification device of the present application, a second embodiment of the pole tower type identification device of the present application is proposed.

[0120] In this embodiment, the point cloud model projection module 10 is also used to collect point cloud data corresponding to the transmission line, and perform point cloud modeling based on the point cloud data to obtain an initial point cloud model; determine the number of segments based on the line length corresponding to the transmission line and a preset clipping distance; segment the initial point cloud model according to the number of segments to obtain a segmented point cloud model; and perform a top-view projection on each segmented point cloud model to obtain a projected first image.

[0121] Furthermore, the tower area extraction module 20 is also used to extract the tower area in the projected first image through a target detection algorithm; determine the pixel coordinates corresponding to the tower area; determine the target point cloud model corresponding to the tower area based on the pixel coordinates and a preset mapping relationship, and the preset mapping relationship includes the mapping relationship between the point cloud data corresponding to the segmented point cloud model and the pixel coordinates corresponding to the projected first image.

[0122] Furthermore, the point cloud model fusion module 30 is also used to cut out a point cloud model to be identified of a preset length from the target point cloud model with the tower head in the target point cloud model as the starting point; determine the size to be identified corresponding to the point cloud model to be identified and the standard size of the standard point cloud model corresponding to a preset standard tower; adjust the size of the point cloud model to be identified according to the size to be identified and the standard size to obtain an adjusted point cloud model; and fuse the adjusted point cloud model with the standard point cloud model to obtain a fused point cloud model.

[0123] Furthermore, the tower type identification module 40 is also used to perform a main view projection on the fused point cloud model to obtain a projected second image; determine the first binary image corresponding to the target point cloud model and the second binary image corresponding to the standard point cloud model in the projected second image; calculate the fusion overlap between the first binary image and the second binary image; and determine the tower type corresponding to the target point cloud model based on the fusion overlap.

[0124] Furthermore, the tower type identification module 40 is also used to calculate the intersection-and-union ratio of the overlapping area between the first binary image and the second binary image; determine the non-overlapping area between the first binary image and the second binary image, and the non-overlapping area is in the first binary image; determine multiple first pixel points corresponding to the non-overlapping area, and determine the second pixel points corresponding to each first pixel point from the second binary image; determine the pixel point distance according to the first pixel point coordinates corresponding to each first pixel point and the pixel point coordinates corresponding to each second pixel point, and obtain the sum of the pixel point distances; calculate the fusion overlap between the first binary image and the second binary image according to the intersection-and-union ratio and the sum of the pixel point distances.

[0125] Furthermore, the tower type identification module 40 is also used to determine a first number of overlapping pixels and a second number of overlapping pixels between the first binary image and the second binary image; take the sum of the first number of overlapping pixels and the second number of overlapping pixels as the number of intersection pixels; determine a first total number of pixels of the first binary image and a second total number of pixels of the second binary image; take the sum of the first total number of pixels and the second total number of pixels as the number of union pixels; and take the ratio of the number of intersection pixels to the number of union pixels as the intersection-union ratio of the overlapping area between the first binary image and the second binary image.

[0126] Furthermore, the tower type identification module 40 is also used to determine that the tower type corresponding to the target point cloud model is the tower type corresponding to the preset standard tower when the fusion overlap is greater than a preset threshold; select a new preset standard tower from the preset standard tower library when the fusion overlap is less than or equal to the preset threshold; return to the step of fusing the target point cloud model with the standard point cloud model corresponding to the preset standard tower to obtain a fused point cloud model, and obtain a new fusion overlap; when the new fusion overlap is greater than the preset threshold, determine that the tower type corresponding to the target point cloud model is the tower type corresponding to the new preset standard tower.

[0127] Other embodiments or specific implementations of the tower type identification device of the present application can refer to the above-mentioned method embodiments and will not be repeated here.

[0128] The present application provides a tower type identification device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the tower type identification method in the above-mentioned embodiment 1.

[0129] Reference below Figure 10 , which shows a schematic diagram of the structure of a tower type identification device suitable for implementing the embodiments of the present application. The tower type identification device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 10 The tower type identification device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0130] like Figure 10As shown, the tower type identification device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the tower type identification device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input devices 1007, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. The communication device 1009 can allow the tower type identification device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a tower type identification device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0131] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0132] The tower type identification device provided in this application, utilizing the tower type identification method described in the aforementioned embodiment, can address the technical problem of accurately and effectively identifying the types of transmission line towers and enabling the integration of towers of the same type. Compared to the prior art, the tower type identification device provided in this application achieves the same beneficial effects as the tower type identification method described in the aforementioned embodiment. Other technical features of the tower type identification device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0133] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0134] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0135] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the tower type identification method in the above embodiment.

[0136] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0137] The computer-readable storage medium may be included in the pole tower type identification device; or may exist independently without being assembled into the pole tower type identification device.

[0138] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the tower type identification device, the tower type identification device is enabled to: obtain an initial point cloud model corresponding to the transmission line, and perform a top-view projection on the initial point cloud model to obtain a projected first image; extract the tower area in the projected first image, and determine the target point cloud model corresponding to the tower area; fuse the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model; perform a main view projection on the fused point cloud model, and determine the tower type corresponding to the target point cloud model based on the projected second image.

[0139] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0140] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0141] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0142] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned tower type identification method. This computer-readable storage medium addresses the technical problem of accurately and effectively identifying the types of transmission line towers and enabling the integration of towers of the same type. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the tower type identification method provided in the aforementioned embodiment and are not further elaborated here.

[0143] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned tower type identification method when executed by a processor.

[0144] The computer program product provided in this application solves the technical problem of accurately and effectively identifying the types of transmission line towers and enabling the integration of towers of the same type. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the tower type identification method provided in the above-mentioned embodiment, and are not further elaborated here.

[0145] The above description is only part of the embodiments of the present application and does not limit the scope of protection of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the scope of protection of the present application.

Claims

1. A tower type identification method, characterized in that: The tower type identification method comprises the following steps: Acquire an initial point cloud model corresponding to the transmission line, and perform a top-view projection on the initial point cloud model to obtain a projected first image; Extracting a tower area in the projected first image and determining a target point cloud model corresponding to the tower area; Fusing the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model; The fused point cloud model is projected in a main view, and the tower type corresponding to the target point cloud model is determined according to the projected second image.

2. The tower type identification method according to claim 1, wherein: The step of obtaining an initial point cloud model corresponding to the transmission line and performing top-view projection on the initial point cloud model to obtain a projected first image specifically includes: Collecting point cloud data corresponding to the transmission line, and performing point cloud modeling based on the point cloud data to obtain an initial point cloud model; Determining the number of segments according to the line length corresponding to the transmission line and a preset cutting distance; Segmenting the initial point cloud model according to the number of segments to obtain a segmented point cloud model; Perform top-view projection on each segmented point cloud model to obtain a first projected image.

3. The tower type identification method according to claim 2, characterized in that: The step of extracting the tower area in the projected first image and determining the target point cloud model corresponding to the tower area specifically includes: Extracting the tower area in the projected first image by a target detection algorithm; Determine the pixel coordinates corresponding to the tower area; The target point cloud model corresponding to the tower area is determined according to the pixel point coordinates and a preset mapping relationship, wherein the preset mapping relationship includes a mapping relationship between the point cloud data corresponding to the segmented point cloud model and the pixel point coordinates corresponding to the projected first image.

4. The tower type identification method according to claim 1, wherein: The step of fusing the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model specifically includes: Taking the tower head in the target point cloud model as the starting point, cutting out a point cloud model to be identified of a preset length from the target point cloud model; Determine the size to be identified corresponding to the point cloud model to be identified and the standard size of the standard point cloud model corresponding to the preset standard tower; Adjusting the size of the point cloud model to be identified according to the size to be identified and the standard size to obtain an adjusted point cloud model; The adjusted point cloud model is fused with the standard point cloud model to obtain a fused point cloud model.

5. The tower type identification method according to claim 1, wherein: The step of performing a main view projection on the fused point cloud model and determining the tower type corresponding to the target point cloud model according to the projected second image specifically includes: Performing a main view projection on the fused point cloud model to obtain a projected second image; Determining, in the projected second image, a first binary image corresponding to the target point cloud model and a second binary image corresponding to the standard point cloud model; calculating a fusion overlap between the first binary image and the second binary image; The tower type corresponding to the target point cloud model is determined according to the fusion overlap.

6. The tower type identification method according to claim 5, characterized in that: The step of calculating the fusion overlap between the first binary image and the second binary image specifically includes: calculating an intersection-over-union ratio of an overlapping area between the first binary image and the second binary image; determining a non-overlapping area between the first binary image and the second binary image, the non-overlapping area being in the first binary image; Determine a plurality of first pixel points corresponding to the non-overlapping area, and determine a second pixel point corresponding to each first pixel point from the second binary image; Determining pixel distances according to first pixel coordinates corresponding to each first pixel and pixel coordinates corresponding to each second pixel, and obtaining a sum of the pixel distances; The fusion overlap between the first binary image and the second binary image is calculated according to the intersection-over-union ratio and the sum of the pixel point distances.

7. The tower type identification method according to claim 6, characterized in that: The step of calculating the intersection-over-union ratio of the overlapping area between the first binary image and the second binary image specifically includes: Determining a first number of overlapping pixels and a second number of overlapping pixels between the first binary image and the second binary image; The sum of the first number of overlapping pixels and the second number of overlapping pixels is used as the number of intersection pixels; Determining a first total number of pixels of the first binary image and a second total number of pixels of the second binary image; The sum of the first total number of pixels and the second total number of pixels is used as the number of pixels in the union; The ratio of the number of intersection pixels to the number of union pixels is used as an intersection-and-union ratio of an overlapping area between the first binary image and the second binary image.

8. The tower type identification method according to claim 5, characterized in that: The step of determining the tower type corresponding to the target point cloud model according to the fusion overlap specifically includes: When the fusion overlap is greater than a preset threshold, determining that the tower type corresponding to the target point cloud model is the tower type corresponding to a preset standard tower; When the fusion overlap is less than or equal to the preset threshold, selecting a new preset standard pole from the preset standard pole library; Returning to the step of fusing the target point cloud model with the standard point cloud model corresponding to the preset standard tower to obtain a fused point cloud model, and obtaining a new fusion overlap; When the new fusion overlap is greater than the preset threshold, it is determined that the tower type corresponding to the target point cloud model is the tower type corresponding to the new preset standard tower.

9. A tower type identification device, characterized in that: The tower type identification device comprises: a point cloud model projection module, configured to obtain an initial point cloud model corresponding to the transmission line, and perform a top view projection on the initial point cloud model to obtain a projected first image; A tower region extraction module, configured to extract the tower region in the projected first image and determine a target point cloud model corresponding to the tower region; A point cloud model fusion module is used to fuse the target point cloud model with a standard point cloud model corresponding to a preset standard tower to obtain a fused point cloud model; The tower type recognition module is used to perform a main view projection on the fused point cloud model and determine the tower type corresponding to the target point cloud model based on the projected second image.

10. A tower type identification device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the tower type identification method according to any one of claims 1 to 8.

11. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the tower type identification method according to any one of claims 1 to 8 are implemented.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the tower type identification method according to any one of claims 1 to 8 are implemented.

Images