CN114693687A - Vehicle-mounted laser radar point cloud segmentation method and system - Google Patents
Vehicle-mounted laser radar point cloud segmentation method and system Download PDFInfo
- Publication number
- CN114693687A CN114693687A CN202011624041.XA CN202011624041A CN114693687A CN 114693687 A CN114693687 A CN 114693687A CN 202011624041 A CN202011624041 A CN 202011624041A CN 114693687 A CN114693687 A CN 114693687A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- ground
- laser radar
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000011218 segmentation Effects 0.000 title claims abstract description 36
- 230000015654 memory Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 7
- 238000012216 screening Methods 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 8
- 239000007787 solid Substances 0.000 description 6
- 230000008447 perception Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention relates to a vehicle-mounted laser radar point cloud segmentation method and a system, and belongs to the technical field of three-dimensional laser radar point cloud data processing. Rasterizing laser radar point cloud data in an area of interest, selecting seed point cloud data from each grid by using a set elevation threshold range, and determining initial ground point cloud in the area of interest by using a region growing method and the selected seed point cloud data; determining a ground fitting equation according to the initial ground point cloud, calculating the ground height corresponding to each laser radar point cloud data by using the ground fitting equation, screening the difference value between the ground height and the elevation value of the laser radar point cloud through the set ground threshold value, and judging whether each laser radar point cloud is the ground point cloud or not, thereby realizing the segmentation of the laser radar point cloud. The method has high segmentation efficiency and can meet the real-time requirement of the automatic driving vehicle.
Description
Technical Field
The invention relates to a vehicle-mounted laser radar point cloud segmentation method and a system, and belongs to the technical field of three-dimensional laser radar point cloud data processing.
Background
The perception technology is one of important components of an automatic driving system, and in the perception technology, the processing of the point cloud data of the laser radar is related to the quality of output of a perception result; the ground point cloud segmentation technology determines the perception robustness of the vehicle-mounted laser radar, guarantees the ground point cloud segmentation accuracy, simultaneously guarantees the calculation efficiency of an algorithm and a system, enables the vehicle-mounted laser radar to stably operate on a vehicle-mounted calculation platform, and has very important significance.
At present, most of laser radar point cloud ground segmentation algorithms in the industry are applied based on mechanical laser radars, and the mechanical laser radars have unique scanning characteristics, and point clouds are uniformly distributed and have certain regularity; with the development of the laser radar technology, and the requirement of an automatic driving system on the reliability of the laser radar is gradually improved, solid and semi-solid laser radars are researched and applied more and more in the industry; compared with a mechanical laser radar, the scanning modes of the solid-state laser radar and the semisolid-state laser radar are generally irregular scanning, the point cloud data is poor in structure, the difficulty of algorithm design is undoubtedly increased, the ground point cloud segmentation algorithm which is particularly suitable for the mechanical laser radar is difficult to transplant to a novel solid-state laser radar. The technical scheme achieves universality and can be suitable for all vehicle-mounted multi-line laser radars on the market at present.
The Chinese patent application document with application publication number CN109188448A provides a point cloud non-ground point filtering method, which is simple in calculation method, small in calculation amount and high in execution speed, is only suitable for mechanical rotation type laser radars, and has poor effect on solid and non-solid laser radars in the market at present.
Chinese patent application publication No. CN108596860A discloses a ground point cloud segmentation method based on three-dimensional laser radar, which requires input of GPS information to obtain initial ground data, and the method is not suitable for vehicle-mounted laser radar, and GPS information is prone to signal loss under some special road conditions such as tunnels.
The application publication number CN111192284A discloses a vehicle-mounted laser point cloud segmentation method and system, wherein in a data preprocessing stage, a K-Dtree data structure is established for original point cloud data, then block fitting is carried out on the ground, and whether iteration times are reached is judged; the method has higher complexity, lower real-time performance when running on part of vehicle-mounted computing platforms, and can not meet the requirements of an automatic driving system.
The application publication number is CN105354811A, which discloses a filtering method of ground multiline three-dimensional laser radar point cloud data, comprising: step one, establishing a ground surface equation; firstly, judging ground points, and then establishing a ground surface equation; finally, fitting the relevant parameters to obtain a ground surface equation; step two: and filtering out misjudgment points. The method has 2 defects, a, the method can generate misjudgment when ground points are selected, if the vehicle-mounted laser radar is close to another target object or is shielded, all laser radar point clouds do not have ground points; b. the method has extremely low calculation efficiency for the multi-line laser radar, rasterization is a common thought for laser radar data processing, the method is used for outputting point clouds of multi-dimensional information, algorithm efficiency can be greatly improved by adopting two-dimensional raster processing, for the multi-line laser radar, the number of one frame of point clouds is hundreds of thousands of orders, one automatic driving vehicle is often provided with a plurality of laser radars to perform blind-area-free perception, and for hundreds of thousands of point clouds, least square solution is performed, so that the requirement on execution efficiency of an automatic driving system cannot be met.
Disclosure of Invention
The invention aims to provide a vehicle-mounted laser radar point cloud segmentation method and a system, and aims to solve the problems of low efficiency and poor real-time performance of the conventional laser radar point cloud segmentation method.
The invention provides a point cloud segmentation method for a vehicle-mounted laser radar, which aims to solve the technical problems and comprises the following steps:
1) acquiring vehicle-mounted laser radar point cloud data, and rasterizing the laser radar point cloud data in the region of interest;
2) selecting seed point cloud data from each grid by using a set elevation threshold range, and determining initial ground point cloud data in an area of interest by using a region growing method and the selected seed point cloud data;
3) establishing a ground fitting equation according to the initial ground point cloud data;
4) and calculating the ground height corresponding to each laser radar point cloud data by using a ground fitting equation, and selecting the laser radar point cloud data of which the difference value between the ground height and the elevation value is smaller than a ground threshold value as the ground point cloud data so as to realize the segmentation of the laser radar point cloud.
The invention also provides a vehicle-mounted laser radar point cloud segmentation system which comprises a processor and a memory, wherein the processor executes a computer program stored by the memory so as to realize the vehicle-mounted laser radar point cloud segmentation method.
Rasterizing laser radar point cloud data in an area of interest, selecting seed point cloud data from each grid by using a set elevation threshold range, and determining initial ground point cloud in the area of interest by using a region growing method and the selected seed point cloud data; determining a ground fitting equation according to the initial ground point cloud, calculating the ground height corresponding to each laser radar point cloud data by using the ground fitting equation, screening the difference value between the ground height and the elevation value of the laser radar point cloud through the set ground threshold value, and judging whether each laser radar point cloud is the ground point cloud or not, thereby realizing the segmentation of the laser radar point cloud. The method does not need a complex algorithm for segmentation, has high segmentation efficiency, and can meet the real-time requirement of the automatic driving vehicle.
Further, the selection process of the initial ground point cloud data in the step 2) is as follows:
A. setting an elevation threshold range;
B. selecting laser radar point cloud data with an elevation value within a set elevation threshold range from each grid as seed point cloud data;
C. and for the seed point cloud data in each grid, searching the attribute data of the point clouds of the adjacent grids by using a region growing method, calculating the similarity between the point clouds of the adjacent grids and the seed point cloud data according to the attribute data, selecting the point clouds of the adjacent grids with the similarity larger than a set threshold value as the same-class point clouds of the seed point cloud data, and taking the various sub-point cloud data and the same-class point clouds corresponding to the various sub-point cloud data as the initial ground point cloud data.
Further, in order to enhance the robustness of the algorithm, the point cloud data attributes adopted for calculating the similarity are an elevation value and reflection intensity.
Further, for convenience of subsequent calculation, before the seed point cloud data is selected, the acquired laser radar point cloud data is converted into a vehicle body coordinate system, the vehicle body coordinate system takes the advancing direction of a vehicle as an X axis, the height direction of the vehicle as a Z axis, and the origin is on the ground.
Furthermore, the elevation threshold range is-10 cm to +10 cm.
Further, in order to accurately describe the ground, the ground fitting equation established in step 3) is:
z＝a*x2+b*y2+c*x+d*y+e
wherein a, b, c, d and e are fitting parameters of the equation.
Further, in order to adapt to the segmentation of the lidar point cloud data in different scanning ranges, the ground threshold is related to the scanning range of the lidar.
Drawings
FIG. 1 is a flow chart of a point cloud segmentation method of a vehicle-mounted laser radar of the invention;
FIG. 2 is a schematic illustration of the position of the body coordinate system of the present invention;
FIG. 3 is a schematic diagram of different scanning ranges of the laser radar of the present invention;
FIG. 4 is a schematic diagram of the vehicle lidar point cloud segmentation system of the present invention;
FIG. 5 is a schematic diagram of a point cloud segmentation system for a vehicle lidar in which a processor employs a domain controller according to the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings.
Method embodiment
The method comprises the steps of utilizing calibration parameters of the laser radar and original point cloud of the laser radar as input, rasterizing the point cloud of the laser radar, selecting seed point cloud data, then facilitating the idea of a region growing method to obtain initial ground point cloud data in an interested range, and finally utilizing surface fitting to divide all ground point clouds according to threshold comparison. The specific implementation flow of the method is shown in fig. 1, and the specific implementation process is as follows.
1. And acquiring laser radar point cloud data, and converting the coordinates of the acquired point cloud data into a vehicle body coordinate system.
The laser radar applicable to the invention can be a non-mechanical rotary laser radar, and can also be a solid state laser radar and a non-solid state laser radar. The method comprises the steps that original vehicle-mounted laser radar point cloud data are obtained through a laser radar installed on a vehicle body, the original vehicle-mounted laser radar point cloud data are a coordinate system with a laser radar installation position as an origin, and the obtained original vehicle-mounted laser radar point cloud data need to be converted into a vehicle body coordinate system in order to facilitate subsequent point cloud data processing, as shown in fig. 2, the vehicle body coordinate system takes the ground at the center right in front of the vehicle body as the origin, the x axis is the direction of the right direction (Xveh) of the vehicle body, the y axis is the direction of the front direction (Yveh) of the vehicle body, and the z axis is the direction right above; in some intelligent driving systems, a vehicle body coordinate system is defined by taking a vehicle tail central point as an original point; the radar coordinate system is a data system in which the original point cloud data is located, generally defined by a laser radar manufacturer, generally using the center of the laser radar as an origin, and directions of the coordinate system are different according to different installation positions of the radar, for example, directions Xlidar and Ylidar in fig. 2 are radar coordinate systems when the laser radar is installed at a vehicle roof position; and coordinate conversion can be realized between the radar coordinate system and the vehicle body coordinate according to the calibration parameters of the laser radar.
2. And performing initial ground point cloud selection on the vehicle-mounted laser radar point cloud data after coordinate conversion.
Firstly, rasterizing laser radar point cloud data in an area of interest, and dividing the obtained laser radar point cloud data into m × n grids; then, selecting laser radar point cloud data with the elevation value within a set elevation threshold range from each grid as seed point cloud data; and then searching the attribute data of the point clouds of the adjacent grids for the seed point cloud data in each grid by using a region growing method, calculating the similarity between the point clouds of the adjacent grids and the seed point cloud data according to the attribute data, selecting the point clouds of the adjacent grids with the similarity larger than a set threshold value as the same-class point clouds of the seed point cloud data, and taking the various sub-point cloud data and the same-class point clouds corresponding to the various sub-point cloud data as initial ground point cloud data.
Assuming that the current state of the vehicle is on a normal road, according to the vehicle body coordinate system established in the previous step, the ground point cloud elevation information of the vehicle accessories, namely the value in the z direction is 0m, therefore, the set elevation threshold range is selected to be-10 cm to +10cm, and the laser point cloud data with the z value in the set threshold range is selected from each grid to serve as the seed ground point cloud of the grid. Each point cloud data has information (attribute information) of four dimensions (x, y, z, intensity), where x is the value of the point cloud in the coordinate x direction; y is the value of the point cloud in the coordinate y direction; z is the value of the point cloud in the coordinate y direction; i is the reflection intensity value of the point cloud, typically between 0 and 255. In calculating the similarity between the point cloud data, the sizes of the corresponding attributes are compared. In order to enhance the robustness of the algorithm, the present embodiment uses the elevation z value and the reflection intensity value as the similarity comparison dimension of the region growing, i.e. the similarity is calculated by using the elevation z value and the reflection intensity value. Setting a high layer threshold value dz and a reflection intensity threshold value di; when the cloud height difference and the reflection intensity difference of two points are both within the threshold value, the two points are similar. The pseudo code is as follows:
if(abs(z1-z2)<dz&&abs(i1-i2)<di)then
p1 is similar with p2
end if。
3. and determining a fitting equation of the road surface according to the selected initial ground point cloud data.
Considering the slope road surface and the actual operation open road, the middle of the road has a certain radian compared with the two sides of the road, and the middle of the road is slightly higher than the two sides of the road, therefore, the ground fitting equation adopted by the invention is as follows:
z＝a*x2+b*y2+c*x+d*y+e
and in order to better fit the road surface, the method adopts a least square method, and the initial ground point cloud data selected in the step 3 is used to bring the initial ground point cloud data into the ground fitting equation, so that each fitting parameter in the equation can be obtained, and the ground fitting equation is obtained.
4. And screening all ground point clouds from the laser point cloud data according to a ground fitting equation.
And (3) bringing any laser radar point cloud data (x, y and z) into a ground fitting equation, calculating the corresponding ground height, making a difference between the obtained ground height and the elevation z value of the point cloud data, and judging whether the laser radar point cloud data is the ground point cloud or not according to the relation between the difference and a ground threshold. When the laser radar point cloud data satisfies the following relationship, the laser radar point cloud data is described as a ground point cloud.
|zground-z|＜threshold
The ground height is calculated through a ground fitting equation, z is an elevation value of laser radar point cloud data, and threshold is a ground threshold. The ground threshold value threshold needs to be set according to the scanning range of the laser radar, the ground threshold values of the laser radars in different scanning ranges are different, as shown in fig. 3, the scanning ranges of the radars are represented by different colors, different ground threshold values are set in different ranges, and each ground threshold value threshold needs to be obtained by carrying out statistical analysis on point cloud data according to different laser radar ranging accuracies and point cloud longitudinal distances.
Assuming that the scanning range of the lidar is divided into the following areas, namely, an area 1 within 20m from the laser, an area 2 within 20-40m from the laser, and an area 3 greater than 40m, as shown in fig. 3, since the lidar is an optical device, the ranging accuracy may be deteriorated as the ranging is increased, so that the ground threshold cannot be a fixed value, and may be set as follows:
threshold is 0.1m, when the point cloud belongs to region 1;
threshold is 0.2m, when the point cloud belongs to the area 2;
threshold is 0.3m, when the point cloud belongs to the area 3;
it should be noted that:
the region division mode is flexibly divided according to the characteristics of the laser radar in practical application and is not necessarily equal in spacing; the ground threshold value threshold needs to be reasonably set according to the statistic, and the distance measurement precision of radar products of different manufacturers is different;
system embodiment
The vehicle-mounted lidar point cloud segmentation system of the present invention, as shown in fig. 4, includes a processor and a memory, wherein the processor executes a computer program stored by the memory to implement the method of the present invention for implementing the above-mentioned method embodiments. That is, the method in the above method embodiment should be understood that the flow of the method for evaluating the operation risk of the active power distribution network may be implemented by computer program instructions. These computer program instructions may be provided to a processor such that execution of the instructions by the processor results in the implementation of the functions specified in the method flow described above.
The processor referred to in this embodiment refers to a processing device such as a microprocessor MCU or a programmable logic device FPGA; the memory referred to in this embodiment includes a physical device for storing information, and generally, information is digitized and then stored in a medium using an electric, magnetic, optical, or the like. For example: various memories for storing information by using an electric energy mode, such as RAM, ROM and the like; various memories for storing information by magnetic energy, such as hard disk, floppy disk, magnetic tape, magnetic core memory, bubble memory, and U disk; various types of memory, CD or DVD, that store information optically. Of course, there are other ways of memory, such as quantum memory, graphene memory, and so forth.
The apparatus comprising the memory, the processor and the computer program is realized by the processor executing corresponding program instructions in the computer, and the processor can be loaded with various operating systems, such as windows operating system, linux system, android, iOS system and the like.
As other embodiments, the device can also comprise a display, and the display is used for displaying the diagnosis result for the reference of workers.
Specifically, the processor in this embodiment adopts a domain controller, as shown in fig. 5, the laser radar point cloud data acquired by the laser radar is sent to the domain controller through vehicle-mounted exchange, and the domain controller divides the received vehicle-mounted laser radar point cloud data according to the method in the embodiment of the method to obtain corresponding ground point cloud data.
Claims (8)
1. A point cloud segmentation method for a vehicle-mounted laser radar is characterized by comprising the following steps:
1) acquiring vehicle-mounted laser radar point cloud data, and rasterizing the laser radar point cloud data in the region of interest;
2) selecting seed point cloud data from each grid by using a set elevation threshold range, and determining initial ground point cloud data in an area of interest by using a region growing method and the selected seed point cloud data;
3) establishing a ground fitting equation according to the initial ground point cloud data;
4) and calculating the ground height corresponding to each laser radar point cloud data by using a ground fitting equation, and selecting the laser radar point cloud data of which the difference value between the ground height and the elevation value is smaller than a ground threshold value as the ground point cloud data so as to realize the segmentation of the laser radar point cloud.
2. The vehicle-mounted lidar point cloud segmentation method according to claim 1, wherein the selection process of the initial ground point cloud data in the step 2) is as follows:
A. setting an elevation threshold range;
B. selecting laser radar point cloud data with an elevation value within a set elevation threshold range from each grid as seed point cloud data;
C. and for the seed point cloud data in each grid, searching the attribute data of the point clouds of the adjacent grids by using a region growing method, calculating the similarity between the point clouds of the adjacent grids and the seed point cloud data according to the attribute data, selecting the point clouds of the adjacent grids with the similarity larger than a set threshold value as the same-class point clouds of the seed point cloud data, and taking the various sub-point cloud data and the same-class point clouds corresponding to the various sub-point cloud data as the initial ground point cloud data.
3. The vehicle-mounted lidar point cloud segmentation method of claim 2, wherein the point cloud data attributes used for similarity calculation are elevation values and reflection intensities.
4. The vehicle-mounted lidar point cloud segmentation method according to claim 2, wherein before the seed point cloud data is selected, the obtained lidar point cloud data is converted into a vehicle body coordinate system, the vehicle body coordinate system takes the advancing direction of a vehicle as an X axis, the height direction of the vehicle as a Z axis, and the origin is on the ground.
5. The vehicle-mounted lidar point cloud segmentation method of claim 4, wherein the elevation threshold range is between-10 cm and +10 cm.
6. The vehicle-mounted lidar point cloud segmentation method according to claim 1, wherein the ground fitting equation established in the step 3) is as follows:
z＝a*x2+b*y2+c*x+d*y+e
wherein a, b, c, d and e are fitting parameters of the equation.
7. The vehicle-mounted lidar point cloud segmentation method according to any of claims 1-6, wherein the ground threshold is related to a scanning range of the lidar.
8. An on-vehicle lidar point cloud segmentation system comprising a processor and a memory, the processor executing a computer program stored by the memory to implement the on-vehicle lidar point cloud segmentation method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011624041.XA CN114693687A (en) | 2020-12-31 | 2020-12-31 | Vehicle-mounted laser radar point cloud segmentation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011624041.XA CN114693687A (en) | 2020-12-31 | 2020-12-31 | Vehicle-mounted laser radar point cloud segmentation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114693687A true CN114693687A (en) | 2022-07-01 |
Family
ID=82133830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011624041.XA Pending CN114693687A (en) | 2020-12-31 | 2020-12-31 | Vehicle-mounted laser radar point cloud segmentation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114693687A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115719354A (en) * | 2022-11-17 | 2023-02-28 | 同济大学 | Method and device for extracting vertical rod based on laser point cloud |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204705A (en) * | 2016-07-05 | 2016-12-07 | 长安大学 | A kind of 3D point cloud segmentation method based on multi-line laser radar |
| CN109785261A (en) * | 2019-01-11 | 2019-05-21 | 辽宁工程技术大学 | A kind of airborne LIDAR three-dimensional filtering method based on gray scale volume element model |
| CN110208815A (en) * | 2019-05-10 | 2019-09-06 | 江苏大学 | A kind of large area maturation crop harvest information fast acquiring method based on airborne laser radar |
| CN110738223A (en) * | 2018-07-18 | 2020-01-31 | 郑州宇通客车股份有限公司 | Point cloud data clustering method and device for laser radars |
| CN111026150A (en) * | 2019-11-25 | 2020-04-17 | 国家电网有限公司 | System and method for pre-warning geological disasters of power transmission line by using unmanned aerial vehicle |
| CN111598780A (en) * | 2020-05-14 | 2020-08-28 | 山东科技大学 | Terrain adaptive interpolation filtering method suitable for airborne LiDAR point cloud |
-
2020
- 2020-12-31 CN CN202011624041.XA patent/CN114693687A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204705A (en) * | 2016-07-05 | 2016-12-07 | 长安大学 | A kind of 3D point cloud segmentation method based on multi-line laser radar |
| CN110738223A (en) * | 2018-07-18 | 2020-01-31 | 郑州宇通客车股份有限公司 | Point cloud data clustering method and device for laser radars |
| CN109785261A (en) * | 2019-01-11 | 2019-05-21 | 辽宁工程技术大学 | A kind of airborne LIDAR three-dimensional filtering method based on gray scale volume element model |
| CN110208815A (en) * | 2019-05-10 | 2019-09-06 | 江苏大学 | A kind of large area maturation crop harvest information fast acquiring method based on airborne laser radar |
| CN111026150A (en) * | 2019-11-25 | 2020-04-17 | 国家电网有限公司 | System and method for pre-warning geological disasters of power transmission line by using unmanned aerial vehicle |
| CN111598780A (en) * | 2020-05-14 | 2020-08-28 | 山东科技大学 | Terrain adaptive interpolation filtering method suitable for airborne LiDAR point cloud |
Non-Patent Citations (1)
| Title |
|---|
| 安瑶军: "车载激光点云数据结构化道路及标线提取", 《中国优秀硕士学位论文全文数据库 基础科学辑》, 15 December 2019 (2019-12-15), pages 008 - 74 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115719354A (en) * | 2022-11-17 | 2023-02-28 | 同济大学 | Method and device for extracting vertical rod based on laser point cloud |
| CN115719354B (en) * | 2022-11-17 | 2024-03-22 | 同济大学 | Method and device for extracting vertical rod based on laser point cloud |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112634181B (en) | Method and device for detecting ground point cloud points | |
| WO2021016751A1 (en) | Method for extracting point cloud feature points, point cloud sensing system, and mobile platform | |
| CN111598034B (en) | Obstacle detection method, obstacle detection device and storage medium | |
| CN112526513B (en) | Millimeter wave radar environment map construction method and device based on clustering algorithm | |
| CN109190573B (en) | Ground detection method applied to unmanned vehicle, electronic equipment and vehicle | |
| CN108629231B (en) | Obstacle detection method, apparatus, device and storage medium | |
| CN111179274B (en) | Map ground segmentation method, device, computer equipment and storage medium | |
| KR20210063841A (en) | Method of clustering 3d point cloud data and apparatuses operating the same | |
| US20230386076A1 (en) | Target detection method, storage medium, electronic device, and vehicle | |
| CN113569958B (en) | Laser point cloud data clustering method, device, equipment and medium | |
| CN111932943A (en) | Dynamic target detection method and device, storage medium and roadbed monitoring equipment | |
| CN112789521B (en) | Method and device for determining perception area, storage medium and vehicle | |
| CN115436910B (en) | Data processing method and device for performing target detection on laser radar point cloud | |
| CN114966651A (en) | Drivable region detection method, computer device, storage medium, and vehicle | |
| CN113970734A (en) | Method, device and equipment for removing snowing noise of roadside multiline laser radar | |
| CN114693687A (en) | Vehicle-mounted laser radar point cloud segmentation method and system | |
| CN113052892A (en) | Vehicle cargo volume calculation method and device and storage medium | |
| CN116299315A (en) | Method and device for detecting road surface obstacle in real time by using laser radar | |
| CN117475398B (en) | Ground segmentation optimization method and device based on voxel sampling | |
| CN113870337A (en) | Ground point cloud segmentation method based on polar coordinate grid and plane fitting | |
| CN112558035B (en) | Method and device for estimating the ground | |
| CN115909277A (en) | Obstacle detection method, obstacle detection device, electronic device and computer-readable storage medium | |
| CN112630798A (en) | Method and apparatus for estimating ground | |
| CN114549764A (en) | Obstacle identification method, device, equipment and storage medium based on unmanned vehicle | |
| CN113763308A (en) | Ground detection method, device, server and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: No. 6 Yutong Road, Guancheng Hui District, Zhengzhou City, Henan Province Applicant after: Yutong Bus Co.,Ltd. Address before: No.1 Yutong Road, Shibali River, Guancheng Hui District, Zhengzhou City, Henan Province Applicant before: ZHENGZHOU YUTONG BUS Co.,Ltd. Country or region before: China |
|
| CB02 | Change of applicant information |