Three-dimensional laser point cloud power line and electric tower segmentation method and system

Abstract

The invention relates to the field of high-speed railway measurement, and relates to a three-dimensional laser point cloud power line and electric tower segmentation method and system, and the method comprises the steps: obtaining first information which comprises the point cloud data of the periphery of a to-be-segmented electric tower; performing gridding processing on the first information to obtain a first grid unit; positioning the electric tower in the first grid unit to obtain the position information of the electric tower; processing the position information of the electric tower to obtain electric tower point cloud data after coarse segmentation; processing the electric tower point cloud data after coarse segmentation to obtain electric tower point cloud data after fine segmentation; and processing the point cloud data of the power tower after fine segmentation to obtain the point cloud data of the power line after segmentation, so that the automatic segmentation technology of the power line and the power tower is realized, manual segmentation processing can be replaced to a great extent, and the labor cost is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of high-speed railway measurement, and in particular to a method and system for segmenting power lines and towers using a three-dimensional laser point cloud. Background Art

[0002] During the railway survey and design phase, information such as the location, direction, and height of high-voltage power lines is an essential consideration in route selection. Currently, spatial information about high-voltage power lines and towers is acquired through field surveys using RTK satellite positioning technology or total stations in prism-free mode to obtain relatively accurate tower location, height, and power line height information. This method is labor-intensive and inefficient, and the prism-free mode used for power line height measurement also results in low accuracy.

[0003] Airborne LiDAR systems have been widely used in major railway projects. Airborne three-dimensional lasers can quickly, accurately, and comprehensively acquire centimeter-level spatial geographic information over large areas. However, the bottleneck of this technology lies in the complexity and tediousness of data processing. Manual interpretation and point mapping methods also require significant manpower and resources. Summary of the Invention

[0004] The purpose of the present invention is to provide a three-dimensional laser point cloud power line and tower segmentation method and system to improve the above-mentioned problems.

[0005] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for segmenting power lines and towers using a three-dimensional laser point cloud, the method comprising:

[0007] Acquire first information, wherein the first information includes point cloud data around the power tower to be segmented;

[0008] Performing grid processing on the first information to obtain a first grid unit;

[0009] Locating the electric tower in the first grid unit to obtain location information of the electric tower;

[0010] Processing the location information of the power tower to obtain roughly segmented power tower point cloud data;

[0011] Processing the roughly segmented tower point cloud data to obtain finely segmented tower point cloud data;

[0012] The finely segmented power tower point cloud data is processed to obtain segmented power line point cloud data.

[0013] In a second aspect, an embodiment of the present application provides a three-dimensional laser point cloud power line and tower segmentation system, the system comprising:

[0014] an acquisition module, configured to acquire first information, wherein the first information includes point cloud data around the power tower to be segmented;

[0015] A first processing module, configured to perform grid processing on the first information to obtain a first grid unit;

[0016] A second processing module is configured to locate the power tower in the first grid unit to obtain location information of the power tower;

[0017] A third processing module is used to process the location information of the power tower to obtain roughly segmented power tower point cloud data;

[0018] a fourth processing module, configured to process the roughly segmented tower point cloud data to obtain finely segmented tower point cloud data;

[0019] The fifth processing module is used to process the finely segmented power tower point cloud data to obtain segmented power line point cloud data.

[0020] In a third aspect, embodiments of the present application provide a device for segmenting power lines and towers from a 3D laser point cloud. The device includes a memory and a processor. The memory is configured to store a computer program; the processor is configured to execute the computer program to implement the steps of the aforementioned method for segmenting power lines and towers from a 3D laser point cloud.

[0021] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned three-dimensional laser point cloud power line and tower segmentation method.

[0022] The beneficial effects of the present invention are:

[0023] The present invention starts from obtaining point cloud data around the electric tower to be segmented, and through a series of steps such as gridding and tower positioning, gradually realizes the coarse segmentation and fine segmentation of the original data into the electric tower point cloud data, and finally segments the power line point cloud data, forming a complete and systematic data processing flow, which can effectively process complex point cloud data. By first coarsely segmenting and then finely segmenting the electric tower point cloud data, the point cloud data of the electric tower and the power line can be more accurately separated, providing a high-quality data foundation for subsequent analysis and application based on these data, and improving the availability and reliability of the data.

[0024] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 Schematic diagram of the process of the three-dimensional laser point cloud power line and tower segmentation method described in an embodiment of the present invention.

[0027] Figure 2 Schematic diagram of the structure of the three-dimensional laser point cloud power line and tower segmentation system described in an embodiment of the present invention.

[0028] Figure 3 This is a schematic diagram of the structure of the three-dimensional laser point cloud power line and tower segmentation equipment described in an embodiment of the present invention.

[0029] Figure 4 This is the point cloud data of the power tower after rough segmentation.

[0030] Figure 5 This is a schematic diagram of the precise segmentation effect of the tower point cloud data.

[0031] Markings in the figure: 800, three-dimensional laser point cloud power line and tower segmentation equipment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component; 901, acquisition module; 902, first processing module; 903, second processing module; 904, third processing module; 905, fourth processing module; 906, fifth processing module. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0033] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0034] Example 1:

[0035] This embodiment provides a three-dimensional laser point cloud power line and tower segmentation method. It can be understood that in this embodiment, a scene can be laid out, for example: a laser radar collects point cloud data around the tower to be segmented to segment the tower and power lines.

[0036] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4, step S5 and step S6.

[0037] Step S1: Acquire first information, where the first information includes point cloud data around the power tower to be segmented;

[0038] Step S2: gridding the first information to obtain a first grid unit;

[0039] In this step, gridding the point cloud data is a technical solution well known to those skilled in the art, so it will not be described here. It should be noted that the grid step size of the first grid unit can be set to about one-third of the overall width of the tower to ensure that sufficient tower point clouds are covered and the robustness of continuous high calculations in the tower grid is ensured.

[0040] Step S3: locating the power tower in the first grid unit to obtain the location information of the power tower;

[0041] Step S3 further includes steps S31, S32, and S33, which specifically include:

[0042] Step S31, sorting the point cloud data according to the elevation of each point cloud data included in the first grid unit grid to obtain sorted point cloud data;

[0043] Step S32: determining whether the height difference between two adjacent point clouds in the sorted point cloud data is less than a preset first threshold value, and obtaining a first determination result;

[0044] Step S33: Locate the tower according to the first judgment result.

[0045] The step S33 further includes step 331, step S332 and step S333, which specifically include:

[0046] Step 331: When the first judgment result is less than the preset first threshold information, determine whether the height difference between two adjacent points in the next grid in the first grid unit is less than the preset first threshold information. If the height difference between the two adjacent points is greater than the preset first threshold information, mark the grid to obtain a discontinuous point cloud.

[0047] Step 332: Determine whether the height between the first point cloud and the discontinuous point cloud is greater than a preset second threshold value, and obtain a second determination result.

[0048] Step 333: Position the tower according to the second judgment result.

[0049] In this example, since power towers have distinct morphological characteristics within power line corridors, and high-voltage power towers are typically over 20 meters tall, setting a certain height difference threshold can eliminate many non-tower grids. Furthermore, the elevations of power tower point cloud data are generally distributed continuously. Therefore, determining whether the height differences within a grid point cloud data are continuous can basically determine the grid position of each tower, thereby achieving tower positioning.

[0050] Step S4: Processing the location information of the power tower to obtain roughly segmented power tower point cloud data;

[0051] Step S4 further includes steps S41, S42, S43, S44, and S45, which specifically include:

[0052] Step S41: acquiring point cloud data of the tower grid according to the location information of the tower to obtain first point cloud data;

[0053] Step S42: acquiring second point cloud data based on the location information of the power tower, wherein the second point cloud data includes point cloud data having a distance from the power tower grid of less than 2;

[0054] Step S43: Acquire third point cloud data based on the location information of the power tower, wherein the third point cloud data includes point cloud data whose distance from the power tower grid is greater than 2 and less than 3;

[0055] Step S44: Filtering the third point cloud data using a preset third threshold value to obtain fourth point cloud data;

[0056] In this step, the average elevation of the third point cloud data is calculated, and the point cloud data corresponding to the information that the average elevation is greater than the preset third threshold value is retained to obtain the fourth point cloud data.

[0057] Step S45: Obtain roughly segmented tower point cloud data based on the first point cloud data, the second point cloud data, and the fourth point cloud data.

[0058] In this step, the tower point cloud data after rough segmentation is as follows: Figure 4 As shown in the figure, the red grid is the tower grid, the yellow grid is the grid with a distance less than 2, and the blue grid is the grid with a distance greater than 2 and less than 3. The point cloud composed of these grids is the coarse segmentation of the tower point cloud.

[0059] In this embodiment, considering that the sizes of power towers in reality vary, and are wider at the top and narrower at the bottom, in order to avoid missing the data of the tops of larger power towers, the point cloud data of the power tower grid and the grids within a certain range around it are obtained as the coarsely segmented power tower point cloud data.

[0060] Step S5: processing the roughly segmented tower point cloud data to obtain finely segmented tower point cloud data;

[0061] Step S5 further includes steps S51, S52, S53, S54, S55, and S56, which specifically include:

[0062] Step S51, dividing the roughly segmented tower point cloud data to obtain upper half tower point cloud data and lower half tower point cloud data;

[0063] In this step, the roughly segmented tower point cloud data is divided with the total height of the tower as a threshold to obtain the upper half of the tower point cloud data and the lower half of the tower point cloud data.

[0064] Step S52: selecting a seed point, wherein the seed point includes the lowest point in the upper half of the tower point cloud data;

[0065] Step S53: searching for points near the seed point according to a preset search radius to obtain adjacent points;

[0066] Step S54: When the elevation of the adjacent point is greater than the seed point, determine whether the adjacent point has not been visited. If not, use the adjacent point as a new seed point for a new search, and continue searching until all point cloud data in the upper half of the tower have been visited, thereby obtaining the first point cloud data after fine segmentation.

[0067] Since the elevation values of the newly included neighboring points in each search are higher than the seed points, it can ensure that the point cloud clustering process only grows upward and does not expand downward. Even if the search contains a small part of the power line point cloud, the power line points are below the seed points and will not be used as new neighboring points, preventing the search from growing towards the power line point cloud. In this step, the neighboring points visited during the entire search process are the first point cloud data after fine segmentation.

[0068] Step S55: performing fine segmentation on the lower half of the tower point cloud data to obtain finely segmented second point cloud data;

[0069] In this step, for the lower half of the tower point cloud, considering that there are always parts of the tower that are not attached by vegetation, we first construct the initial search point based on the lowest point in the tower grid, and then use the search process of the first point cloud data after fine segmentation to obtain the lower half of the fine segmentation tower point cloud. Then, with one-sixth of the tower point cloud height as a step length, we gradually intercept the lower half of the coarse segmentation tower point cloud from high to low according to the elevation threshold range, and build the bounding box one by one. Finally, using the obtained minimum bounding box as a benchmark, the minimum bounding box is enlarged by 1.3 times and the lower half of the coarse segmentation tower point cloud is framed. The bounding box is very large in the part with vegetation attached (brown point cloud). Using the minimum bounding box (blue point cloud) as a benchmark can greatly reduce the vegetation point cloud attached to the tower. Figure 5 shown.

[0070] Step S56: Obtain finely segmented point cloud data of the power tower according to the finely segmented first point cloud data and the finely segmented second point cloud data.

[0071] In this embodiment, since the electric tower is connected to the power line through an insulator and is often in an environment with regrowing vegetation, in order to avoid identifying too many power line point clouds and vegetation point clouds attached to the electric tower as electric tower point clouds, the present invention divides the roughly segmented electric tower point cloud data into the upper half of the electric tower point cloud data and the lower half of the electric tower point cloud data, and performs fine segmentation processing on them respectively.

[0072] Step S6: Process the finely segmented power tower point cloud data to obtain segmented power line point cloud data.

[0073] Step S6 further includes steps S61, S62, S63, S64, S65, and S66, which specifically include:

[0074] Step S61: Eliminate the finely segmented tower point cloud to obtain fifth point cloud data;

[0075] In this step, considering that power lines are often connected to each other through power towers, the power tower point cloud after fine segmentation is extracted and then removed through indexing. Then, the power lines in the original point cloud will be separated from each other, and the point cloud data after removing the power towers will be obtained, and the fifth point cloud data will be obtained. The fifth point cloud data still includes a large amount of irrelevant point cloud data such as the surface and vegetation.

[0076] Step S62: gridding the fifth point cloud data to obtain a second grid unit;

[0077] In this step, since the fifth point cloud data includes a large amount of irrelevant point cloud data, in order to improve the efficiency of the next step of power line point cloud segmentation, it is necessary to construct a second grid unit and further segment the power line point cloud according to the distribution characteristics of the power line point cloud.

[0078] Step S63: obtaining terrain information;

[0079] Step S64: determining whether the power line is located above water based on the terrain information, and obtaining a third determination result;

[0080] In this step, when power lines are located above water, the water surface cannot reflect the laser, which will cause holes in the point cloud. Therefore, it is necessary to first determine the position of the power lines based on the terrain information to avoid a decrease in the accuracy of the subsequent segmentation of the power line point cloud.

[0081] Step S65: When the third judgment result is that the power line is covered above the water area, preprocessing the second grid unit to obtain a preprocessed second grid unit;

[0082] In this step, preprocessing includes calculating the mean of the number of point clouds corresponding to other grids adjacent to the grid to obtain mean information; judging whether the number of grid point clouds is less than half of the mean information, where if it is less than, the grid is assigned ground point attributes and the height difference of the grid is updated to perform deviation correction, thereby improving the subsequent power line segmentation accuracy.

[0083] Step S66 : Segment the power line point cloud data in the pre-processed second grid unit to obtain segmented power line point cloud data.

[0084] In this step, the power line point cloud data is first coarsely segmented in the second grid unit after preprocessing to obtain coarsely segmented power line point cloud data; the coarsely segmented power line point cloud data is then finely segmented to obtain segmented power line point cloud data, wherein the coarse segmentation of the power line point cloud data specifically includes: obtaining the maximum elevation and minimum elevation in the second grid unit; calculating the height of the tower according to the maximum elevation and minimum elevation in the second grid unit; screening the grids that are greater than half the height of the tower to obtain the screened grids; arranging the point clouds in the screened grids from large to small according to elevation to obtain arranged point cloud data; calculating the elevation difference between adjacent point clouds in the arranged point cloud data in sequence, if the elevation difference is greater than 2m, it is determined that there is a jump in the elevation of the grid point cloud, and the average elevation of the adjacent point clouds is taken as the jump elevation; coarse segmentation of the power line point cloud data is performed according to the jump elevation to obtain coarsely segmented power line point cloud data. Understandably, in a tower point cloud, there may be a sudden drop in elevation from a point on the tower structure to an adjacent power line or other lower point, or a sudden rise in elevation from a ground point cloud to a point cloud at the base of the tower. This sudden change in elevation is called a jump elevation. Therefore, using the jump elevation of each grid cell can help better understand the spatial distribution of the point cloud data and achieve a coarse segmentation of the power line point cloud.

[0085] It should be noted that after the coarse segmentation of the power line point cloud, the coarsely segmented power line point cloud data is obtained. The point cloud data still includes some miscellaneous points such as ground objects and vegetation. Therefore, further fine segmentation is required to achieve accurate segmentation of the power lines. The specific process is: using a clustering algorithm to cluster the point cloud data connected to each other in the geometric space to obtain several point cloud blocks; processing several point cloud blocks to obtain processed point cloud blocks, and the processed point cloud blocks remove the tower point cloud data and vegetation point cloud data that have not been completely extracted. The processing method includes but is not limited to the least squares method. The processed point cloud blocks are further segmented, wherein the specific process is as follows: obtaining a horizontal length threshold; screening the processed point cloud blocks according to the horizontal length threshold to obtain screened point cloud blocks, wherein the screened point cloud blocks include point cloud blocks whose horizontal lengths are greater than the horizontal length threshold; calculating the number of points per unit length of each point cloud block in the screened point cloud blocks, sorting the number of points per unit length of each point cloud block, eliminating the values within the range of 3 times the mean, recalculating the mean, and using 2 times the mean as the threshold for the number of points per unit length; then using the threshold for the number of points per unit length to make a judgment, when the number of points per unit length of the processed point cloud block is greater than the threshold for the number of points per unit length, the point cloud block can be determined to be non- Power line point cloud; when the length of the processed point cloud block is greater than the horizontal length threshold and the number of points per unit length is less than the number of points per unit length threshold, the point cloud block can be identified as a power line point cloud block; when the length of the processed point cloud block is less than the horizontal length threshold and the number of points per unit length is less than the number of points per unit length threshold, the least squares method is required to remove the non-power line point cloud blocks in the processed point cloud block. Through the above process, the overall point cloud data segmentation of the high-voltage power lines and towers is completed. After the segmentation, the power line and tower point cloud data can be obtained through simple calculations. Common tower positions, tower heights, accurate power line suspension heights and other information can be obtained, which can accurately, conveniently and efficiently serve railway survey and design projects. It is understandable that the use of the least squares method to remove non-power line point cloud blocks in the processed point cloud block is a technical solution well known to those skilled in the art, so it will not be described in detail here. It should be noted that the number of points per unit length is the ratio of the horizontal length of the point cloud block to the number of point clouds.

[0086] Example 2:

[0087] like Figure 2 As shown, this embodiment provides a three-dimensional laser point cloud power line and tower segmentation system, which includes an acquisition module 901, a first processing module 902, a second processing module 903, a third processing module 904, a fourth processing module 905, and a fifth processing module 906, which specifically include:

[0088] An acquisition module 901 is configured to acquire first information, wherein the first information includes point cloud data around the power tower to be segmented;

[0089] A first processing module 902 is configured to perform grid processing on the first information to obtain a first grid unit;

[0090] A second processing module 903 is configured to locate the power tower in the first grid unit to obtain the location information of the power tower;

[0091] The third processing module 904 is used to process the location information of the power tower to obtain roughly segmented power tower point cloud data;

[0092] The fourth processing module 905 is used to process the roughly segmented tower point cloud data to obtain finely segmented tower point cloud data;

[0093] The fifth processing module 906 is used to process the finely segmented power tower point cloud data to obtain segmented power line point cloud data.

[0094] In a specific embodiment of the present disclosure, the second processing module includes a first processing unit, a first judgment unit, and a second processing unit, which specifically include:

[0095] a first processing unit, configured to sort the point cloud data according to the elevation of each point cloud data included in the first grid unit grid to obtain sorted point cloud data;

[0096] The first judgment unit is used to judge whether the height difference between two adjacent point clouds in the sorted point cloud data is less than a preset first threshold information, and obtain a first judgment result;

[0097] The second processing unit is configured to locate the electric tower according to the first judgment result.

[0098] In a specific embodiment of the present disclosure, the second processing unit includes a third processing unit, a second judgment unit, and a fourth processing unit, which specifically include:

[0099] a third processing unit, configured to, when the first judgment result is less than a preset first threshold information, determine whether a height difference between two adjacent points in a next grid in the first grid unit is less than the preset first threshold information, and mark the grid to obtain a discontinuous point cloud until the height difference between the two adjacent points is greater than the preset first threshold information;

[0100] A second judgment unit is used to judge whether the height between the first point cloud and the discontinuous point cloud is greater than a preset second threshold information, and obtain a second judgment result;

[0101] The fourth processing unit is used to locate the electric tower according to the second judgment result.

[0102] In a specific embodiment of the present disclosure, the third processing module includes a first acquisition unit, a second acquisition unit, a third acquisition unit, a fifth processing unit, and a sixth processing unit, which specifically include:

[0103] A first acquiring unit is configured to acquire point cloud data of a tower grid according to the location information of the tower to obtain first point cloud data;

[0104] A second acquiring unit is configured to acquire second point cloud data according to the location information of the power tower, wherein the second point cloud data includes point cloud data having a distance from the power tower grid of less than 2;

[0105] a third acquiring unit, configured to acquire third point cloud data according to the location information of the power tower, wherein the third point cloud data includes point cloud data having a distance from the power tower grid that is greater than 2 and less than 3;

[0106] a fifth processing unit, configured to filter the third point cloud data using preset third threshold information to obtain fourth point cloud data;

[0107] The sixth processing unit is configured to obtain roughly segmented tower point cloud data based on the first point cloud data, the second point cloud data, and the fourth point cloud data.

[0108] In a specific embodiment of the present disclosure, the fourth processing module includes a seventh processing unit, an eighth processing unit, a ninth processing unit, a tenth processing unit, an eleventh processing unit, and a twelfth processing unit, which specifically include:

[0109] a seventh processing unit, configured to divide the roughly segmented tower point cloud data into upper tower point cloud data and lower tower point cloud data;

[0110] an eighth processing unit, configured to select a seed point, wherein the seed point includes the lowest point in the upper half of the tower point cloud data;

[0111] a ninth processing unit, configured to search points near the seed point according to a preset search radius to obtain adjacent points;

[0112] A tenth processing unit is configured to, when the elevation of the adjacent point is greater than the seed point, determine whether the adjacent point has not been visited. If so, use the adjacent point as a new seed point to search again, until all point cloud data in the upper half of the tower are visited, thereby obtaining first point cloud data after fine segmentation;

[0113] an eleventh processing unit, configured to perform fine segmentation on the point cloud data of the lower half of the tower to obtain finely segmented second point cloud data;

[0114] The twelfth processing unit is configured to obtain the finely segmented point cloud data of the power tower according to the finely segmented first point cloud data and the finely segmented second point cloud data.

[0115] In a specific embodiment of the present disclosure, the fifth processing module includes a thirteenth processing unit, a fourteenth processing unit, a fourth acquisition unit, a third judgment unit, a fifteenth processing unit, and a sixteenth processing unit, which specifically include:

[0116] The thirteenth processing unit is used to remove the tower point cloud after fine segmentation to obtain fifth point cloud data;

[0117] a fourteenth processing unit, configured to grid the fifth point cloud data to obtain a second grid unit;

[0118] a fourth acquiring unit, configured to acquire terrain information;

[0119] a third judging unit, configured to judge whether the power line is located above water according to the terrain information, and obtain a third judging result;

[0120] a fifteenth processing unit, configured to, when the third judgment result is that the power line covers the water area, pre-process the second grid unit to obtain a pre-processed second grid unit;

[0121] The sixteenth processing unit is configured to segment the power line point cloud data in the pre-processed second grid unit to obtain segmented power line point cloud data.

[0122] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0123] Example 3:

[0124] Corresponding to the above method embodiment, this embodiment also provides a three-dimensional laser point cloud power line and tower segmentation device. The three-dimensional laser point cloud power line and tower segmentation device described below and the three-dimensional laser point cloud power line and tower segmentation method described above can be referenced to each other.

[0125] Figure 3 FIG. 8 is a block diagram of a 3D laser point cloud power line and tower segmentation device 800 according to an exemplary embodiment. Figure 3 As shown, the 3D laser point cloud power line and tower segmentation device 800 may include: a processor 801, a memory 802. The 3D laser point cloud power line and tower segmentation device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0126] The processor 801 is used to control the overall operation of the 3D laser point cloud power line and tower segmentation device 800 to complete all or part of the steps in the above-mentioned 3D laser point cloud power line and tower segmentation method. The memory 802 is used to store various types of data to support the operation of the 3D laser point cloud power line and tower segmentation device 800. This data may include, for example, instructions for any application or method operating on the 3D laser point cloud power line and tower segmentation device 800, as well as application-related data such as contact information, sent and received messages, images, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the three-dimensional laser point cloud power line and tower segmentation device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more thereof, so the corresponding communication component 805 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0127] In an exemplary embodiment, the three-dimensional laser point cloud power line and tower segmentation device 800 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-mentioned three-dimensional laser point cloud power line and tower segmentation method.

[0128] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, the program instructions implement the steps of the above-described 3D laser point cloud power line and tower segmentation method. For example, the computer-readable storage medium may be the aforementioned memory 802 including the program instructions. The program instructions may be executed by the processor 801 of the 3D laser point cloud power line and tower segmentation device 800 to perform the above-described 3D laser point cloud power line and tower segmentation method.

[0129] Example 4:

[0130] Corresponding to the above method embodiment, this embodiment further provides a readable storage medium. The readable storage medium described below and the three-dimensional laser point cloud power line and tower segmentation method described above can refer to each other.

[0131] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the three-dimensional laser point cloud power line and tower segmentation method of the above method embodiment.

[0132] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0133] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

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

Claims

1. A 3D laser point cloud power line and tower segmentation method, characterized in that: include: Acquire first information, wherein the first information includes point cloud data around the power tower to be segmented; Performing grid processing on the first information to obtain a first grid unit; Locating the power tower in the first grid unit to obtain location information of the power tower; Processing the location information of the power tower to obtain roughly segmented power tower point cloud data; Processing the roughly segmented tower point cloud data to obtain finely segmented tower point cloud data; The finely segmented power tower point cloud data is processed to obtain segmented power line point cloud data.

2. The method for segmenting power lines and towers from a 3D laser point cloud according to claim 1, wherein: Locating the electric tower in the first grid unit to obtain location information of the electric tower includes: sorting the point cloud data according to the elevation of each point cloud data included in the first grid unit grid to obtain sorted point cloud data; Determine whether a height difference between two adjacent point clouds in the sorted point cloud data is less than a preset first threshold value, and obtain a first determination result; The electric tower is located according to the first judgment result.

3. The method for segmenting power lines and towers from a 3D laser point cloud according to claim 2, wherein: Locating the electric tower according to the first judgment result includes: When the first judgment result is less than the preset first threshold information, determine whether the height difference between two adjacent points in the next grid in the first grid unit is less than the preset first threshold information, until the height difference between the two adjacent points is greater than the preset first threshold information, mark the grid to obtain a discontinuous point cloud; Determine whether the height between the first point cloud and the discontinuous point cloud is greater than a preset second threshold information, and obtain a second determination result; The electric tower is located according to the second judgment result.

4. The method for segmenting power lines and towers from a 3D laser point cloud according to claim 1, wherein: Processing the roughly segmented tower point cloud data to obtain finely segmented tower point cloud data includes: Dividing the roughly segmented tower point cloud data to obtain upper tower point cloud data and lower tower point cloud data; Selecting a seed point, wherein the seed point includes the lowest point in the upper half of the tower point cloud data; Searching for points near the seed point according to a preset search radius to obtain nearby points; When the elevation of the adjacent point is greater than the seed point, determine whether the adjacent point has not been visited. If not, use the adjacent point as a new seed point to search again until all point cloud data of the upper half of the tower are visited, and obtain the first point cloud data after fine segmentation; Performing fine segmentation on the lower half of the tower point cloud data to obtain finely segmented second point cloud data; According to the first point cloud data after fine segmentation and the second point cloud data after fine segmentation, the finely segmented power tower point cloud data is obtained.

5. The method for segmenting power lines and towers from a 3D laser point cloud according to claim 1, wherein: Processing the finely segmented tower point cloud data to obtain segmented power line point cloud data includes: Eliminate the tower point cloud after fine segmentation to obtain the fifth point cloud data; Gridding the fifth point cloud data to obtain a second grid unit; Get terrain information; determining whether the power line is located above water based on the terrain information to obtain a third determination result; When the third judgment result is that the power line covers the water area, preprocessing the second grid unit to obtain a preprocessed second grid unit; The power line point cloud data is segmented in the preprocessed second grid unit to obtain segmented power line point cloud data.

6. A 3D laser point cloud power line and tower segmentation system, characterized in that: include: an acquisition module, configured to acquire first information, wherein the first information includes point cloud data around the power tower to be segmented; A first processing module, configured to perform grid processing on the first information to obtain a first grid unit; A second processing module is configured to locate the power tower in the first grid unit to obtain location information of the power tower; A third processing module is used to process the location information of the power tower to obtain roughly segmented power tower point cloud data; a fourth processing module, configured to process the roughly segmented tower point cloud data to obtain finely segmented tower point cloud data; The fifth processing module is used to process the finely segmented power tower point cloud data to obtain segmented power line point cloud data.

7. The 3D laser point cloud power line and tower segmentation system according to claim 6, characterized in that: The second processing module includes: a first processing unit, configured to sort the point cloud data according to the elevation of each point cloud data included in the first grid unit grid to obtain sorted point cloud data; The first judgment unit is used to judge whether the height difference between two adjacent point clouds in the sorted point cloud data is less than a preset first threshold information, and obtain a first judgment result; The second processing unit is configured to locate the electric tower according to the first judgment result.

8. The 3D laser point cloud power line and tower segmentation system according to claim 7, characterized in that: The second processing unit includes: a third processing unit, configured to, when the first judgment result is less than a preset first threshold information, determine whether a height difference between two adjacent points in a next grid in the first grid unit is less than the preset first threshold information, and mark the grid to obtain a discontinuous point cloud until the height difference between the two adjacent points is greater than the preset first threshold information; A second judgment unit is used to judge whether the height between the first point cloud and the discontinuous point cloud is greater than a preset second threshold information, and obtain a second judgment result; The fourth processing unit is used to locate the electric tower according to the second judgment result.

9. The 3D laser point cloud power line and tower segmentation system according to claim 6, characterized in that: The fourth processing module includes: a seventh processing unit, configured to divide the roughly segmented tower point cloud data into upper tower point cloud data and lower tower point cloud data; an eighth processing unit, configured to select a seed point, wherein the seed point includes the lowest point in the upper half of the tower point cloud data; a ninth processing unit, configured to search points near the seed point according to a preset search radius to obtain adjacent points; A tenth processing unit is configured to, when the elevation of the adjacent point is greater than the seed point, determine whether the adjacent point has not been visited. If so, use the adjacent point as a new seed point to search again, until all point cloud data in the upper half of the tower are visited, thereby obtaining first point cloud data after fine segmentation; an eleventh processing unit, configured to perform fine segmentation on the point cloud data of the lower half of the tower to obtain finely segmented second point cloud data; The twelfth processing unit is configured to obtain the finely segmented point cloud data of the power tower according to the finely segmented first point cloud data and the finely segmented second point cloud data.

10. The 3D laser point cloud power line and tower segmentation system according to claim 6, characterized in that: The fifth processing module further includes: The thirteenth processing unit is used to remove the tower point cloud after fine segmentation to obtain fifth point cloud data; a fourteenth processing unit, configured to grid the fifth point cloud data to obtain a second grid unit; a fourth acquiring unit, configured to acquire terrain information; a third judging unit, configured to judge whether the power line is located above water according to the terrain information, and obtain a third judging result; a fifteenth processing unit, configured to, when the third judgment result is that the power line covers the water area, pre-process the second grid unit to obtain a pre-processed second grid unit; The sixteenth processing unit is configured to segment the power line point cloud data in the pre-processed second grid unit to obtain segmented power line point cloud data.

Images