CN113077473B - Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium - Google Patents
Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium Download PDFInfo
- Publication number
- CN113077473B CN113077473B CN202010004652.8A CN202010004652A CN113077473B CN 113077473 B CN113077473 B CN 113077473B CN 202010004652 A CN202010004652 A CN 202010004652A CN 113077473 B CN113077473 B CN 113077473B
- Authority
- CN
- China
- Prior art keywords
- grid
- ground
- cluster
- clusters
- characteristic value
- 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.)
- Active
Links
- 230000011218 segmentation Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000007689 inspection Methods 0.000 claims abstract description 6
- 238000009499 grossing Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 230000006872 improvement Effects 0.000 description 11
- 238000001514 detection method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a three-dimensional laser point cloud pavement segmentation method, which comprises the following steps: constructing a fan-shaped grid map; carrying out connected domain clustering processing on the fan-shaped grid map to construct a grid cluster; analyzing the characteristic value of the grid clusters meeting the preset conditions, and extracting the grid clusters meeting the line characteristics and the surface characteristics as ground grid clusters; and carrying out smoothness inspection on the ground grid clusters in the radial direction of the fan-shaped grid map, and extracting the ground grid clusters meeting the smoothness requirement. The invention also discloses a three-dimensional laser point cloud pavement segmentation system, computer equipment and a computer readable storage medium. According to the invention, by analyzing the geometric characteristics of the three-dimensional laser point cloud, the efficient and accurate point cloud pavement segmentation of complex terrains is realized, and the accuracy and the robustness are greatly improved.
Description
Technical Field
The present invention relates to the field of unmanned technology, and in particular, to a three-dimensional laser point cloud road surface segmentation method, a three-dimensional laser point cloud road surface segmentation system, a computer device, and a computer readable storage medium.
Background
Unmanned vehicles or automatic driving are one of industries with the highest application value in the artificial intelligence industry at present, and environmental awareness is used as the core research content of the unmanned vehicles, so that the unmanned vehicles are the basis for realizing autonomous decision and path planning. The accuracy of environmental perception directly determines the intelligent level of the automobile, however, the current technology still has difficulty in accurately and rapidly perceiving the most effective external information under the complex environment, and a plurality of key technologies still need to break through.
In the prior art, laser radars are commonly used for detecting obstacles and areas where the vehicle can run. The road surface segmentation is a precondition of laser radar detection. At present, the typical laser point cloud pavement segmentation method comprises the following steps:
1. And establishing an undirected graph of the point cloud, and solving an undirected graph model by setting a loss function to divide the pavement. However, the method has strong dependence on the accuracy of the loss function, and if the loss function is not suitable, the problem of lower accuracy can be caused.
2. One or more fitted road surface models are built through a ransac method. However, the method is difficult to adapt to irregular road conditions such as uneven road surfaces, multiple slopes and the like.
3. Gradient screening is performed in a specific direction and then the ground point cloud is filtered by a smoothing function. However, the method is difficult to comprehensively utilize the combined features presented by the adjacent points, and the waste of feature information in use can be caused.
Disclosure of Invention
The invention aims to solve the technical problem of providing a three-dimensional laser point cloud pavement segmentation method, a system, computer equipment and a medium, which can realize efficient and accurate point cloud pavement segmentation on complex terrains by analyzing the geometric characteristics of three-dimensional laser point clouds.
In order to solve the technical problems, the invention provides a three-dimensional laser point cloud pavement segmentation method, which comprises the following steps: constructing a fan-shaped grid map; carrying out connected domain clustering processing on the fan-shaped grid map to construct a grid cluster; analyzing the characteristic value of the grid clusters meeting the preset conditions, and extracting the grid clusters meeting the line characteristics and the surface characteristics as ground grid clusters; and carrying out smoothness inspection on the ground grid clusters in the radial direction of the fan-shaped grid map, and extracting the ground grid clusters meeting the smoothness requirement.
As an improvement of the above solution, the three-dimensional laser point cloud pavement segmentation method further includes: and constructing smoothness constraint according to the ground grid clusters in the radial direction of the sector grid map, and taking the grids which meet the smoothness constraint in the grid clusters which do not meet the preset conditions as the ground grids.
As an improvement of the above solution, the step of constructing a fan-shaped grid map includes: projecting a three-dimensional laser point cloud of a laser radar into a fan-shaped grid map, wherein the fan-shaped grid map consists of a plurality of grids which are mutually independent; calculating the maximum height difference of all points in each grid respectively, if the maximum height difference is larger than a preset threshold value, the grid is an obstacle grid, and deleting the obstacle grid.
As an improvement of the above solution, the step of performing connected domain clustering processing on the fan-shaped grid map to construct a grid cluster includes: s11, in the sector grid map, a grid is taken as a search center, and a grid cluster is established; s12, searching grids meeting gradient requirements in a preset field, and adding the grids meeting the gradient requirements into the grid cluster; s13, taking another grid which is not used as a search center as a new search center in the grid cluster, and entering a step S12 until all grids in the grid cluster are searched; and S14, taking another grid which is not used as a search center as a new search center outside the grid cluster, establishing a new grid cluster, and entering step S12 until all grids in the fan-shaped grid map are searched.
As an improvement of the above solution, the step of determining whether the grid cluster meets the preset condition includes: converting each grid in a grid cluster into a point, and constructing a minimum bounding rectangle for the grid cluster; judging whether the number of the points in the grid cluster is smaller than a preset number or whether the diagonal length of the minimum surrounding rectangle corresponding to the grid cluster is smaller than a preset length, if so, the grid cluster does not meet the preset condition, and if not, the grid cluster meets the preset condition.
As an improvement of the above solution, the step of performing feature analysis on the grid clusters meeting the preset conditions, and extracting the grid clusters meeting the line features and the surface features as the ground grid clusters includes: constructing a covariance matrix according to the points in the grid clusters meeting the preset conditions; calculating eigenvalues of the covariance matrix; extracting a minimum characteristic value, a middle characteristic value and a maximum characteristic value from the characteristics, and judging according to the difference value among the minimum characteristic value, the middle characteristic value and the maximum characteristic value, wherein when the difference value between the minimum characteristic value and the middle characteristic value is not in a preset range and the difference value between the middle characteristic value and the maximum characteristic value is in the preset range, the grid cluster conforming to the preset condition is a planar grid cluster; when the difference value between the minimum characteristic value and the intermediate characteristic value is within a preset range and the difference value between the minimum characteristic value and the maximum characteristic value is not within the preset range, the grid cluster conforming to the preset condition is a linear grid cluster; when the difference value among the minimum characteristic value, the middle characteristic value and the maximum characteristic value is in a preset range, the grid cluster conforming to the preset condition is a spherical grid cluster; and taking the planar grid clusters and the linear grid clusters as ground grid clusters.
As an improvement of the above solution, the step of performing smoothness check on the ground grid cluster in the radial direction of the fan-shaped grid map, and extracting the ground grid cluster meeting the smoothness requirement includes: s21, taking a ground point where the laser radar is located as a starting point;
S22, sequentially calculating gradients between adjacent grids in the ground grid cluster in the radial direction of the fan-shaped grid map, and if the gradients do not meet gradient requirements, marking the previous grid in the adjacent grids corresponding to the gradients as a termination grid and marking the termination grid and the previous grid as ground grids; s23, marking the grids after the grid termination as non-ground grids until the height of the current grid is lower than the height of the last non-ground grid; s24, judging whether the height difference between the current grid and the last termination grid is smaller than a preset height difference, if so, taking the current grid as a new starting point, entering a step S22, and if not, marking the current grid as a non-ground grid and continuously checking the next grid, and entering the step S24; s25, until all grids in the ground grid cluster are inspected, judging whether the number of non-ground grids in the ground grid cluster is larger than the number of ground grids, deleting the ground grid cluster if yes, and reserving the ground grid cluster if no.
As an improvement of the above solution, the step of constructing a smoothness constraint according to the ground grid cluster in the radial direction of the fan-shaped grid map, and taking a grid which meets the smoothness constraint in the grid cluster and does not meet the preset condition as the ground grid includes: in the radial direction of the sector grid map, a smooth curve is constructed according to the radius length and the height of grids in the ground grid cluster; smoothing all grids in the radial direction according to the smoothing curve to generate a smoothing function; substituting the radial length of the grids in the grid cluster which does not meet the preset condition into the smoothing function to calculate the theoretical height of the current grid; judging whether the difference value between the theoretical height and the actual height of the current grid is within a preset difference value range, if so, judging that the current grid is a ground grid, and if not, judging that the current grid is a non-ground grid.
Correspondingly, the invention also provides a three-dimensional laser point cloud pavement segmentation system, which comprises: the map construction module is used for constructing a sector grid map; the clustering processing module is used for carrying out connected domain clustering processing on the fan-shaped grid map so as to construct grid clusters; the characteristic analysis module is used for carrying out characteristic value analysis on the grid clusters meeting the preset conditions and extracting the grid clusters meeting the line characteristics and the surface characteristics as ground grid clusters; and the smoothness checking module is used for checking the smoothness of the ground grid clusters in the radial direction of the sector grid map and extracting the ground grid clusters meeting the smoothness requirement.
As an improvement of the above solution, the three-dimensional laser point cloud road surface segmentation system further includes: and the smoothness constraint module is used for constructing smoothness constraint according to the ground grid clusters in the radial direction of the sector grid map, and taking the grids which are not in accordance with the preset conditions and are in accordance with the smoothness constraint in the grid clusters as the ground grids.
Correspondingly, the invention also provides computer equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the three-dimensional laser point cloud pavement segmentation method.
Accordingly, the present invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of a three-dimensional laser point cloud road surface segmentation method.
The implementation of the invention has the following beneficial effects:
According to the invention, the road point cloud is clustered to be divided into a plurality of point cloud clusters, the characteristic value analysis is carried out aiming at the geometric characteristics of the road point cloud, and then the grid is smoothly fitted by utilizing a smoothness formula, so that the efficient and accurate point cloud road segmentation of complex terrains is finally realized. Therefore, compared with the prior art, the invention has great improvement on accuracy and robustness.
Drawings
FIG. 1 is a flow chart of a first embodiment of a three-dimensional laser point cloud pavement segmentation method of the present invention;
FIG. 2 is a schematic illustration of a fan-shaped grid map of the present invention;
FIG. 3 is a schematic view of the distribution of grids in a radial direction in the present invention;
FIG. 4 is a schematic view of another distribution of grids in a radial direction in the present invention
FIG. 5 is a flow chart of a second embodiment of the three-dimensional laser point cloud pavement segmentation method of the present invention;
FIG. 6 is a schematic structural diagram of a first embodiment of the three-dimensional laser point cloud pavement segmentation system of the present invention;
Fig. 7 is a schematic structural diagram of a second embodiment of the three-dimensional laser point cloud pavement segmentation system of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent.
Depending on the imaging characteristics of the three-dimensional lidar, a larger portion of the returned point cloud is reflected back through the road surface, such point cloud being referred to as the ground point cloud. The purpose of road surface segmentation is to separate the ground point cloud from all the point clouds, and the meaning of the road surface segmentation is that on one hand, the drivable area can be extracted according to the separated ground, and on the other hand, the ground point has no meaning for obstacle detection, so that a large number of useless points can be reduced when obstacle detection is carried out. Therefore, road surface segmentation is a precondition for performing related functions such as obstacle detection and traveling area detection by using a laser radar.
Referring to fig. 1, fig. 1 shows a flowchart of a first embodiment of the three-dimensional laser point cloud road surface segmentation method of the present invention, which includes:
s101, constructing a sector grid map.
Specifically, the step of constructing the fan-shaped grid map includes:
(1) The three-dimensional laser point cloud of the laser radar is projected into a fan-shaped grid map, which consists of a plurality of grids that are independent of one another.
(2) Calculating the maximum height difference of all points in each grid respectively, if the maximum height difference is larger than a preset threshold value, the grid is an obstacle grid, and deleting the obstacle grid.
The maximum height difference refers to a height difference between the highest point and the lowest point in each grid. For example, if a certain grid has a point A (height of 2 mm), a point B (height of 9 mm) and a point C (height of 2.5 mm), the maximum height of the grid is 9mm, the minimum height is 2mm, and the maximum height difference is 7mm.
In the segmentation process, the three-dimensional laser point cloud of the laser radar is projected into a grid shown in fig. 2, wherein any number of laser radar points can exist in the same grid; calculating the maximum height difference Hmm of all points in the grid, if the maximum height difference Hmm is larger than a preset threshold value, indicating that the grid is an obstacle grid, and deleting the grid.
S102, carrying out connected domain clustering processing on the fan-shaped grid map to construct a grid cluster.
In reality, the geometric features of the ground are only related to the features of the adjacent ground, the ground is relatively flat, and the gradient change between the adjacent ground is small, so that grids with little gradient difference between the adjacent ground are clustered into one type by using clustering. Specifically, the step of performing connected domain clustering processing on the fan-shaped grid map to construct a grid cluster includes:
(1) In a fan-shaped grid map, a grid is used as a search center to establish a grid cluster.
A new grid cluster is established by taking a random grid as a searching center.
(2) Searching grids meeting gradient requirements in a preset field, and adding the grids meeting the gradient requirements into the grid cluster.
As shown in fig. 2, if the preset lateral range nh=1 (i.e. extending laterally by 1 grid based on the search center) and the preset longitudinal range np=2 (i.e. extending longitudinally by 2 grids based on the search center), the preset fields are "grid 1", "grid 2", "grid 3", "grid 4", "grid 5" and "grid 6".
The gradient refers to the ratio of the height difference Hg of two grids to the coordinate euclidean distance D of the two grids, namely the gradient g=hg/D, and if the gradient G is smaller than the preset gradient Gt, the grids are considered to meet the gradient requirement. Where grid height refers to the average of the heights of all points within each grid.
(3) And (3) taking another grid which is not used as a search center as a new search center in the grid cluster, and entering the step (2) until all grids in the grid cluster are searched.
And (3) after finishing gradient judgment of the current search center in the preset field, taking another new grid as a search center in the grid cluster (the grid is never used as a search center point), and repeating the search operation in the step (2) until the grids meeting the gradient requirements are all added into the grid cluster. Finally, when no grid which is not used as a search center exists in the grid cluster, the expansion of the grid cluster is ended.
(4) And (3) taking another grid which is not used as a search center as a new search center outside the grid cluster, establishing a new grid cluster, and entering the step (2) until all grids in the fan-shaped grid map are searched.
And (3) establishing a new grid cluster by taking grids outside the grid cluster as the center, and repeating the searching operation in the step (2) and the step (3) until no initial grid of the new grid cluster can be established, and forming a plurality of grid clusters at the moment to finish clustering.
Therefore, through step S102, efficient clustering of grids can be achieved to construct one or more grid clusters, so as to implement separate processing on the grids, which is highly targeted.
And S103, carrying out eigenvalue analysis on the grid clusters meeting the preset conditions, and extracting the grid clusters meeting the line characteristics and the surface characteristics as ground grid clusters.
Specifically, the step of judging whether the grid cluster meets the preset condition includes:
(1) Each grid within a grid cluster is converted to a point and a minimum bounding rectangle is constructed for the grid cluster.
Each grid within the grid cluster is approximated as a point (x, y, z), where x is the x-axis coordinate of the grid in the cartesian coordinate system, y is the y-axis coordinate of the grid in the cartesian coordinate system, and z is the grid height (grid height refers to the average of the heights of all points within each grid).
(2) Judging whether the number of the points in the grid cluster is smaller than a preset number or whether the diagonal length of the minimum surrounding rectangle corresponding to the grid cluster is smaller than a preset length, if so, the grid cluster does not meet the preset condition, and if not, the grid cluster meets the preset condition.
It should be noted that, when the number of points in the grid cluster is smaller than the preset number or the diagonal length of the minimum bounding rectangle corresponding to the grid cluster is smaller than the preset length, the scale of the grid cluster is smaller, and the method is not suitable for feature analysis. Therefore, the invention only performs characteristic analysis on the grid clusters with larger scale, and does not process or analyze the grid clusters with smaller scale in other modes.
Correspondingly, the step of performing feature analysis on the grid clusters meeting the preset conditions and extracting the grid clusters meeting the line features and the surface features as the ground grid clusters comprises the following steps:
(1) And constructing a covariance matrix according to the points in the grid cluster meeting the preset condition. Specifically, the present invention may utilize the x, y, z values of each point within a grid cluster to establish a covariance matrix.
(2) And calculating the eigenvalues of the covariance matrix, thereby obtaining the minimum eigenvalue, the middle eigenvalue and the maximum eigenvalue in the eigenvalues.
(3) Extracting a minimum feature value, a middle feature value and a maximum feature value from the features, and judging according to the difference value among the minimum feature value, the middle feature value and the maximum feature value, wherein:
When the difference value between the minimum characteristic value and the intermediate characteristic value is not in the preset range, and the difference value between the intermediate characteristic value and the maximum characteristic value is in the preset range, the grid cluster conforming to the preset condition is a planar grid cluster; that is, when the minimum eigenvalue is smaller than the other two eigenvalues (the middle eigenvalue and the maximum eigenvalue) and the other two eigenvalues (the middle eigenvalue and the maximum eigenvalue) are not different, the point cloud in the grid cluster is approximately planar, and the normal vector can be in any direction.
When the difference value between the minimum characteristic value and the intermediate characteristic value is within a preset range and the difference value between the minimum characteristic value and the maximum characteristic value is not within the preset range, the grid cluster conforming to the preset condition is a linear grid cluster; that is, when the minimum feature value and the intermediate feature value are not greatly different and the minimum feature value and the maximum feature value are greatly different, the point cloud in the grid cluster is approximately linear, and the normal vector can be in any direction.
When the difference value among the minimum characteristic value, the middle characteristic value and the maximum characteristic value is in a preset range, the grid cluster conforming to the preset condition is a spherical grid cluster; that is, when the three values (minimum eigenvalue, intermediate eigenvalue, and maximum eigenvalue) are substantially equal, the point cloud in the grid cluster is substantially spherical.
(4) And taking the planar grid clusters and the linear grid clusters as ground grid clusters.
Therefore, the step S103 utilizes the two-dimensional feature information, not just combines the information of a single direction or two directions, has very high accuracy in feature extraction, can effectively classify the grid clusters, and performs feature value analysis on the grid clusters with larger scale to extract the planar grid clusters and the linear grid clusters as the ground grid clusters, and has high accuracy and strong accuracy.
S104, performing smoothness check on the ground grid clusters in the radial direction of the fan-shaped grid map, and extracting the ground grid clusters meeting the smoothness requirement.
It should be noted that, through the screening in step S103, the grid cluster with the feature value meeting the condition is reserved as the ground grid cluster, but further inspection is necessary to be performed on the ground grid cluster, because if a higher platform appears in front of the vehicle (such as a truck with a container type suddenly appearing in front), the point cloud of the laser radar projected on such an object is also relatively flat, so that the erroneous judgment grid similar to the case needs to be removed.
The invention proposes to eliminate the erroneous judgment grid by calculating the gradient in the radial direction. Specifically, the step of performing smoothness inspection on the ground grid clusters in the radial direction of the fan-shaped grid map, and extracting the ground grid clusters meeting the smoothness requirement includes:
(1) Taking the ground point where the laser radar is located as a starting point.
(2) And sequentially calculating gradients between adjacent grids in the ground grid cluster in the radial direction of the fan-shaped grid map, wherein if the gradients do not meet gradient requirements, the previous grid in the adjacent grids corresponding to the gradients is a termination grid, and the termination grid and the previous grid are marked as ground grids.
As shown in fig. 3, the gradient α of two adjacent grids is sequentially calculated by taking the ground point where the laser radar is located as a starting point, and if the gradient α is greater than the preset gradient α max, the previous grid in the two adjacent grids is the termination grid, and the termination grid and the previous grid are marked as the ground grids, wherein the gradient calculating method is that the height difference of the two adjacent grids is divided by the length difference in the radial direction. For example, grid C in FIG. 3 is a termination grid and grids A, B, C are all ground grids.
(3) And marking the grids after the termination grid as non-ground grids until the height of the current grid is lower than the height of the last non-ground grid.
(4) Judging whether the height difference between the current grid and the last termination grid is smaller than the preset height difference, taking the current grid as a new starting point when the height difference is judged to be smaller than the preset height difference, entering the step (2), marking the current grid as a non-ground grid when the height difference is judged to be not smaller than the preset height difference, continuing to check the next grid, and entering the step (4).
The grids following the termination grid are in turn marked as non-ground grids until the height of the current grid is lower than the last non-ground grid. At this time, the height of the current grid is compared with the height of the last termination grid, if the height difference between the current grid and the last termination grid is smaller than the preset height difference, the current grid is used as a new starting point, otherwise, the current grid is marked as a non-ground grid, and the next grid is continuously checked.
As shown in fig. 4, the last termination grid is B, even though grid E is lower than the last non-floor grid D, grid E cannot be the new starting grid because the height h 1 of grid E is greater than the height Gao Taiduo of the last termination grid B (h 1>hmin); the next grid F is judged in order, and the grid F meets the requirement of being a new starting grid (i.e., the height difference h 2 between the grid F and the last terminating grid B is smaller than the preset height difference h min), so that the grid F can be used as a new starting grid.
(5) And until all grids in the ground grid cluster are inspected, judging whether the number of non-ground grids in the ground grid cluster is larger than the number of ground grids, deleting the ground grid cluster if so, and reserving the ground grid cluster if not.
Therefore, by calculating the gradient in the radial direction in step S104, the erroneous judgment grid can be effectively eliminated, and the accuracy of the segmentation is further ensured.
From the above, the invention can better judge the shape of the point cloud cluster by analyzing the geometric characteristics (point, line and surface) of the three-dimensional laser point cloud to segment the road surface, thereby judging whether the point cloud cluster belongs to the ground point according to the shape of the point cloud cluster; therefore, compared with the prior art, the invention has great improvement on accuracy and robustness.
Referring to fig. 5, fig. 5 shows a flowchart of a second embodiment of the three-dimensional laser point cloud road surface segmentation method of the present invention, which includes:
S201, constructing a sector grid map.
S202, carrying out connected domain clustering processing on the fan-shaped grid map to construct a grid cluster.
S203, performing eigenvalue analysis on the grid clusters meeting the preset conditions, and extracting the grid clusters meeting the line characteristics and the surface characteristics as ground grid clusters.
S204, performing smoothness check on the ground grid clusters in the radial direction of the fan-shaped grid map, and extracting the ground grid clusters meeting the smoothness requirement.
S205, in the radial direction of the sector grid map, constructing a smoothness constraint according to the ground grid cluster, and taking the grid which accords with the smoothness constraint in the grid cluster which does not accord with the preset condition as the ground grid.
It should be noted that, in the grid clusters which do not meet the preset conditions (i.e., the grid clusters which do not perform the eigenvalue analysis), there are still more scattered sparse grids, and in these grids, there may be ground grids, so that a smoothing function is set in the radial direction to establish a smoothing constraint, and the constraint conditions are satisfied, so that the grid clusters can be added to the ground grids. In the invention, the sparse grid can be treated by adopting the following method:
(1) In the radial direction of the sector grid map, a smooth curve is constructed according to the radius length and the height of grids in the ground grid cluster;
(2) Smoothing all grids in the radial direction according to the smoothing curve to generate a smoothing function;
(3) Substituting the radial length of the grids in the grid cluster which does not meet the preset condition into the smoothing function to calculate the theoretical height of the current grid;
(4) Judging whether the difference value between the theoretical height and the actual height of the current grid is within a preset difference value range, if so, judging that the current grid is a ground grid, and if not, judging that the current grid is a non-ground grid.
And establishing a cubic B-spline curve in each radial direction by taking the radius length of grids belonging to the ground grid cluster as an abscissa and the height as an ordinate, taking the cubic B-spline curve as smoothing cancellation, smoothing the grids in the whole radial direction by utilizing the smoothing curve, and obtaining a smoothing function of each section. Then substituting the radial length of the grids in the small-scale grid cluster (i.e. the grid cluster without eigenvalue analysis) as the abscissa into a smoothing function, comparing the obtained theoretical height H s with the actual height H i, and if # H s-Hi # is smaller than a preset difference value H diff, the grids belong to the ground grids, wherein the preset difference value H diff can be a difference value threshold.
Therefore, unlike the first embodiment shown in fig. 1, the ground grid can be extracted accurately by adding further classification processing to the sparse grid in the present embodiment.
Referring to fig. 6, fig. 6 shows a first embodiment of the three-dimensional laser point cloud pavement segmentation system 100 of the present invention, comprising:
The map construction module 1 is used for constructing a sector grid map. Specifically, the map construction module 1 projects a three-dimensional laser point cloud of the laser radar into a fan-shaped grid map, then calculates maximum height differences of all points in each grid respectively, and if the maximum height differences are larger than a preset threshold value, the grid is an obstacle grid, and the obstacle grid is deleted.
And the clustering processing module 2 is used for carrying out connected domain clustering processing on the fan-shaped grid map so as to construct a grid cluster. Specifically, the clustering processing module 2 establishes a grid cluster in a sector grid map by taking a grid as a search center; then searching grids meeting gradient requirements in a preset field, and adding the grids meeting the gradient requirements into the grid clusters; then, in the grid cluster, searching with another grid which is not used as a searching center as new searching center, and re-searching information until all grids in the grid cluster are searched; and finally, taking another grid which is not used as a search center as a new search center outside the grid cluster, establishing a new grid cluster, and searching again until all grids in the fan-shaped grid map are searched.
And the characteristic analysis module 3 is used for carrying out characteristic value analysis on the grid clusters meeting the preset conditions and extracting the grid clusters meeting the line characteristics and the surface characteristics as ground grid clusters. It should be noted that, the method for judging whether the grid cluster meets the preset condition includes: (1) Each grid within a grid cluster is converted to a point and a minimum bounding rectangle is constructed for the grid cluster. (2) Judging whether the number of the points in the grid cluster is smaller than a preset number or whether the diagonal length of the minimum surrounding rectangle corresponding to the grid cluster is smaller than a preset length, if so, the grid cluster does not meet the preset condition, and if not, the grid cluster meets the preset condition. Specifically, the feature analysis module 3 constructs a covariance matrix according to the points in the grid clusters meeting the preset conditions; then, calculating the eigenvalues of the covariance matrix, so as to obtain the minimum eigenvalue, the middle eigenvalue and the maximum eigenvalue in the eigenvalues; and then, extracting the minimum feature value, the middle feature value and the maximum feature value in the features, and judging according to the difference value among the minimum feature value, the middle feature value and the maximum feature value, wherein: when the difference value between the minimum characteristic value and the intermediate characteristic value is not in the preset range, and the difference value between the intermediate characteristic value and the maximum characteristic value is in the preset range, the grid cluster conforming to the preset condition is a planar grid cluster; that is, when the minimum eigenvalue is smaller than the other two eigenvalues (the middle eigenvalue and the maximum eigenvalue) and the other two eigenvalues (the middle eigenvalue and the maximum eigenvalue) are not different, the point cloud in the grid cluster is approximately planar, and the normal vector can be in any direction. When the difference value between the minimum characteristic value and the intermediate characteristic value is within a preset range and the difference value between the minimum characteristic value and the maximum characteristic value is not within the preset range, the grid cluster conforming to the preset condition is a linear grid cluster; that is, when the minimum feature value and the intermediate feature value are not greatly different and the minimum feature value and the maximum feature value are greatly different, the point cloud in the grid cluster is approximately linear, and the normal vector can be in any direction. When the difference value among the minimum characteristic value, the middle characteristic value and the maximum characteristic value is in a preset range, the grid cluster conforming to the preset condition is a spherical grid cluster; that is, when the three values (minimum eigenvalue, intermediate eigenvalue, and maximum eigenvalue) are approximately equal, the point cloud in the grid cluster is approximately spherical; and finally, taking the planar grid clusters and the linear grid clusters as ground grid clusters.
And the smoothness checking module 4 is used for checking the smoothness of the ground grid clusters in the radial direction of the sector grid map and extracting the ground grid clusters meeting the smoothness requirement. Specifically, the smoothness check module 4 takes the ground point where the laser radar is located as a starting point; then, sequentially calculating gradients between adjacent grids in the ground grid cluster in the radial direction of the fan-shaped grid map, if the gradients do not meet gradient requirements, the previous grid in the adjacent grids corresponding to the gradients is a termination grid, and marking the termination grid and the previous grid as the ground grid; marking the grids after the termination grid as non-ground grids until the height of the current grid is lower than the height of the last non-ground grid; judging whether the height difference between the current grid and the last termination grid is smaller than the preset height difference, if so, taking the current grid as a new starting point, detecting again, and if not, marking the current grid as a non-ground grid and continuously checking the next grid; and until all grids in the ground grid cluster are inspected, judging whether the number of non-ground grids in the ground grid cluster is larger than the number of ground grids, deleting the ground grid cluster if so, and reserving the ground grid cluster if not.
From the above, the invention can better judge the shape of the point cloud cluster by analyzing the geometric characteristics (point, line and surface) of the three-dimensional laser point cloud to segment the road surface, thereby judging whether the point cloud cluster belongs to the ground point according to the shape of the point cloud cluster; therefore, compared with the prior art, the invention has great improvement on accuracy and robustness.
Referring to fig. 7, fig. 7 shows a second embodiment of the three-dimensional laser point cloud pavement segmentation system 100 of the present invention, and unlike the first embodiment shown in fig. 6, the three-dimensional laser point cloud pavement segmentation system 100 further includes: and the smoothness constraint module 5 is used for constructing smoothness constraint according to the ground grid clusters in the radial direction of the sector grid map, and taking the grids which meet the smoothness constraint in the grid clusters which do not meet the preset conditions as the ground grids.
Specifically, the smoothness constraint module 5 constructs a smoothness curve according to the radius length and the height of the grids in the ground grid cluster in the radial direction of the sector grid map; carrying out smoothing treatment on all grids in the radial direction according to the smoothing curve to generate a smoothing function; then substituting the radial length of the grids in the grid cluster which does not meet the preset condition into the smoothing function to calculate the theoretical height of the current grid; and finally, judging whether the difference value between the theoretical height and the actual height of the current grid is within a preset difference value range, if so, judging that the current grid is a ground grid, and if not, judging that the current grid is a non-ground grid.
Therefore, the invention can accurately extract the ground grids by adding further classification processing to the sparse grids through the smoothness constraint module 5.
In this embodiment, by adding further classification processing to the sparse grid, the ground grid can be accurately extracted. Correspondingly, the invention also provides computer equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the three-dimensional laser point cloud pavement segmentation method when executing the computer program. Meanwhile, the invention also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, realizes the steps of the three-dimensional laser point cloud pavement segmentation method.
Therefore, the method and the device divide the road point cloud into a plurality of point cloud clusters by carrying out cluster analysis on the road point cloud, carry out eigenvalue analysis on geometric features of the road point cloud, carry out smooth fitting on grids by utilizing a smoothness formula, and further classify and process sparse grids, thereby finally realizing efficient and accurate point cloud road segmentation on complex terrains.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (12)
1. The three-dimensional laser point cloud pavement segmentation method is characterized by comprising the following steps of:
Constructing a fan-shaped grid map;
carrying out connected domain clustering processing on the fan-shaped grid map according to gradient requirements to construct grid clusters;
Analyzing the characteristic value of the grid clusters meeting the preset conditions, and extracting the grid clusters meeting the line characteristics and the surface characteristics as ground grid clusters; the grid clusters meeting the preset conditions are grid clusters with the pointing number smaller than the preset number or grid clusters with the diagonal length of the minimum bounding rectangle smaller than the preset length; the method comprises the following specific steps: constructing a covariance matrix according to the points in the grid clusters meeting the preset conditions; calculating eigenvalues of the covariance matrix; extracting a minimum characteristic value, a middle characteristic value and a maximum characteristic value from the characteristics, and taking a grid cluster, wherein the difference value between the minimum characteristic value and the middle characteristic value is not in a preset range and the difference value between the middle characteristic value and the maximum characteristic value is in the preset range, and a grid cluster, wherein the difference value between the minimum characteristic value and the middle characteristic value is in the preset range and the difference value between the minimum characteristic value and the maximum characteristic value is not in the preset range, as a ground grid cluster;
and carrying out smoothness inspection on the ground grid clusters in the radial direction of the fan-shaped grid map, and extracting the ground grid clusters meeting the smoothness requirement.
2. The three-dimensional laser point cloud road surface segmentation method as set forth in claim 1, further comprising: and constructing smoothness constraint according to the ground grid clusters in the radial direction of the sector grid map, and taking the grids which meet the smoothness constraint in the grid clusters which do not meet the preset conditions as the ground grids.
3. The three-dimensional laser point cloud road surface segmentation method according to claim 1 or 2, characterized in that the step of constructing a sector-shaped grid map comprises:
Projecting a three-dimensional laser point cloud of a laser radar into a fan-shaped grid map, wherein the fan-shaped grid map consists of a plurality of grids which are mutually independent;
Calculating the maximum height difference of all points in each grid respectively, if the maximum height difference is larger than a preset threshold value, the grid is an obstacle grid, and deleting the obstacle grid.
4. The three-dimensional laser point cloud pavement segmentation method according to claim 1 or 2, wherein the step of performing connected domain clustering processing on the sector-shaped grid map to construct a grid cluster comprises:
S11, in the sector grid map, a grid is taken as a search center, and a grid cluster is established;
S12, searching grids meeting gradient requirements in a preset field, and adding the grids meeting the gradient requirements into the grid cluster;
s13, taking another grid which is not used as a search center as a new search center in the grid cluster, and entering a step S12 until all grids in the grid cluster are searched;
And S14, taking another grid which is not used as a search center as a new search center outside the grid cluster, establishing a new grid cluster, and entering step S12 until all grids in the fan-shaped grid map are searched.
5. The three-dimensional laser point cloud pavement segmentation method according to claim 1 or 2, wherein the step of judging whether the grid cluster meets a preset condition comprises:
converting each grid in a grid cluster into a point, and constructing a minimum bounding rectangle for the grid cluster;
Judging whether the number of the points in the grid cluster is smaller than a preset number or whether the diagonal length of the minimum surrounding rectangle corresponding to the grid cluster is smaller than a preset length,
If yes, the grid cluster does not accord with the preset condition,
And if not, the grid cluster accords with a preset condition.
6. The method for three-dimensional laser point cloud pavement segmentation according to claim 5, wherein the step of performing feature analysis on the grid clusters meeting the preset condition and extracting the grid clusters meeting the line features and the surface features as the ground grid clusters comprises:
constructing a covariance matrix according to the points in the grid clusters meeting the preset conditions;
Calculating eigenvalues of the covariance matrix;
Extracting the minimum feature value, the intermediate feature value and the maximum feature value from the features, and judging according to the difference value among the minimum feature value, the intermediate feature value and the maximum feature value,
When the difference value between the minimum characteristic value and the intermediate characteristic value is not in the preset range, and the difference value between the intermediate characteristic value and the maximum characteristic value is in the preset range, the grid cluster conforming to the preset condition is a planar grid cluster;
When the difference value between the minimum characteristic value and the intermediate characteristic value is within a preset range and the difference value between the minimum characteristic value and the maximum characteristic value is not within the preset range, the grid cluster conforming to the preset condition is a linear grid cluster;
When the difference value among the minimum characteristic value, the middle characteristic value and the maximum characteristic value is in a preset range, the grid cluster conforming to the preset condition is a spherical grid cluster;
and taking the planar grid clusters and the linear grid clusters as ground grid clusters.
7. The three-dimensional laser point cloud pavement segmentation method according to claim 1 or 2, wherein the step of performing smoothness inspection on the ground grid clusters in the radial direction of the sector grid map, and extracting the ground grid clusters meeting the smoothness requirement comprises:
S21, taking a ground point where the laser radar is located as a starting point;
S22, sequentially calculating gradients between adjacent grids in the ground grid cluster in the radial direction of the fan-shaped grid map, and if the gradients do not meet gradient requirements, marking the previous grid in the adjacent grids corresponding to the gradients as a termination grid and marking the termination grid and the previous grid as ground grids;
S23, marking the grids after the grid termination as non-ground grids until the height of the current grid is lower than the height of the last non-ground grid;
s24, judging whether the height difference between the current grid and the last termination grid is smaller than a preset height difference,
If yes, the process proceeds to step S22 with the current grid as a new starting point,
If not, marking the current grid as a non-ground grid and continuously checking the next grid, and entering step S24;
S25, until all grids in the ground grid cluster are inspected, judging whether the number of non-ground grids in the ground grid cluster is larger than the number of ground grids, deleting the ground grid cluster if yes, and reserving the ground grid cluster if no.
8. The method for three-dimensional laser point cloud pavement segmentation according to claim 2, wherein the step of constructing a smoothness constraint according to the ground grid cluster in the radial direction of the sector-shaped grid map, and taking a grid which meets the smoothness constraint among the grid clusters which does not meet a preset condition as the ground grid comprises:
in the radial direction of the sector grid map, a smooth curve is constructed according to the radius length and the height of grids in the ground grid cluster;
Smoothing all grids in the radial direction according to the smoothing curve to generate a smoothing function;
substituting the radial length of the grids in the grid cluster which does not meet the preset condition into the smoothing function to calculate the theoretical height of the current grid;
Judging whether the difference value between the theoretical height and the actual height of the current grid is within a preset difference value range, if so, judging that the current grid is a ground grid, and if not, judging that the current grid is a non-ground grid.
9. A three-dimensional laser point cloud road surface segmentation system, comprising:
The map construction module is used for constructing a sector grid map;
The clustering processing module is used for carrying out connected domain clustering processing on the fan-shaped grid map according to gradient requirements so as to construct grid clusters;
The characteristic analysis module is used for carrying out characteristic value analysis on the grid clusters meeting the preset conditions and extracting the grid clusters meeting the line characteristics and the surface characteristics as ground grid clusters; the grid clusters meeting the preset conditions are grid clusters with the pointing number smaller than the preset number or grid clusters with the diagonal length of the minimum bounding rectangle smaller than the preset length; the feature analysis module constructs a covariance matrix according to the points in the grid clusters meeting the preset conditions; calculating eigenvalues of the covariance matrix; extracting a minimum characteristic value, a middle characteristic value and a maximum characteristic value from the characteristics, and taking a grid cluster, wherein the difference value between the minimum characteristic value and the middle characteristic value is not in a preset range and the difference value between the middle characteristic value and the maximum characteristic value is in the preset range, and a grid cluster, wherein the difference value between the minimum characteristic value and the middle characteristic value is in the preset range and the difference value between the minimum characteristic value and the maximum characteristic value is not in the preset range, as a ground grid cluster;
and the smoothness checking module is used for checking the smoothness of the ground grid clusters in the radial direction of the sector grid map and extracting the ground grid clusters meeting the smoothness requirement.
10. The three-dimensional laser point cloud road segmentation system as set forth in claim 9, further comprising: and the smoothness constraint module is used for constructing smoothness constraint according to the ground grid clusters in the radial direction of the sector grid map, and taking the grids which are not in accordance with the preset conditions and are in accordance with the smoothness constraint in the grid clusters as the ground grids.
11. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.
12. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010004652.8A CN113077473B (en) | 2020-01-03 | 2020-01-03 | Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010004652.8A CN113077473B (en) | 2020-01-03 | 2020-01-03 | Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113077473A CN113077473A (en) | 2021-07-06 |
| CN113077473B true CN113077473B (en) | 2024-06-18 |
Family
ID=76608617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010004652.8A Active CN113077473B (en) | 2020-01-03 | 2020-01-03 | Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113077473B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113569958B (en) * | 2021-07-29 | 2024-04-12 | 清华大学苏州汽车研究院（吴江） | Laser point cloud data clustering method, device, equipment and medium |
| CN114675290A (en) * | 2022-02-25 | 2022-06-28 | 中国第一汽车股份有限公司 | Ground data detection method, detection device and processor |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8396293B1 (en) * | 2009-12-22 | 2013-03-12 | Hrl Laboratories, Llc | Recognizing geometrically salient objects from segmented point clouds using strip grid histograms |
| DE102010022726B4 (en) * | 2010-06-04 | 2019-05-16 | Hensoldt Sensors Gmbh | Device for displaying terrain on a display device of a missile |
| CN105404844B (en) * | 2014-09-12 | 2019-05-31 | 广州汽车集团股份有限公司 | A kind of Method for Road Boundary Detection based on multi-line laser radar |
| US10024957B2 (en) * | 2015-09-17 | 2018-07-17 | Navico Holding As | Adaptive beamformer for sonar imaging |
| CN105404898B (en) * | 2015-11-26 | 2018-11-06 | 福州华鹰重工机械有限公司 | A kind of loose type point cloud data segmentation method and equipment |
| WO2017149526A2 (en) * | 2016-03-04 | 2017-09-08 | May Patents Ltd. | A method and apparatus for cooperative usage of multiple distance meters |
| CN106204705B (en) * | 2016-07-05 | 2018-12-07 | 长安大学 | A kind of 3D point cloud dividing method based on multi-line laser radar |
| CN106530380B (en) * | 2016-09-20 | 2019-02-26 | 长安大学 | A kind of ground point cloud dividing method based on three-dimensional laser radar |
| CN106652640A (en) * | 2016-11-22 | 2017-05-10 | 天津舟晗科技有限公司 | Operation teaching system based on electric vehicle battery power management |
| US10536860B2 (en) * | 2017-05-10 | 2020-01-14 | Facebook, Inc. | Multi-hop wireless network planning |
| CN108983248A (en) * | 2018-06-26 | 2018-12-11 | 长安大学 | It is a kind of that vehicle localization method is joined based on the net of 3D laser radar and V2X |
| CN109101892B (en) * | 2018-07-17 | 2021-08-10 | 南京航空航天大学 | Laser radar target object detection method based on grid and density clustering algorithm |
| CN109255302A (en) * | 2018-08-15 | 2019-01-22 | 广州极飞科技有限公司 | Object recognition methods and terminal, mobile device control method and terminal |
| CN110502973B (en) * | 2019-07-05 | 2023-02-07 | 同济大学 | Automatic extraction and identification method for road marking based on vehicle-mounted laser point cloud |
| CN110320504B (en) * | 2019-07-29 | 2021-05-18 | 浙江大学 | Unstructured road detection method based on laser radar point cloud statistical geometric model |
-
2020
- 2020-01-03 CN CN202010004652.8A patent/CN113077473B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 基于时空关联的激光雷达障碍物识别技术研究;邵靖滔;中国优秀硕士学位论文全文数据库;全文 * |
| 基于点云簇组合特征的激光雷达地面分割方法;邵靖滔 等;激光与光电子学进展;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113077473A (en) | 2021-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110320504B (en) | Unstructured road detection method based on laser radar point cloud statistical geometric model | |
| CN111192284B (en) | Vehicle-mounted laser point cloud segmentation method and system | |
| CN107766405B (en) | Automatic vehicle road model definition system | |
| CN102248947B (en) | Object and vehicle detecting and tracking using a 3-D laser rangefinder | |
| CN112184736B (en) | Multi-plane extraction method based on European clustering | |
| CN106599808B (en) | Hidden target extraction method based on full-waveform laser radar data | |
| CN111325138B (en) | Road boundary real-time detection method based on point cloud local concave-convex characteristics | |
| CN113077473B (en) | Three-dimensional laser point cloud pavement segmentation method, system, computer equipment and medium | |
| CN110532963B (en) | Vehicle-mounted laser radar point cloud driven road marking accurate extraction method | |
| CN113569958B (en) | Laser point cloud data clustering method, device, equipment and medium | |
| CN113936215A (en) | Mining area road surface pit identification method and system and unmanned truck | |
| CN113933859A (en) | Pavement and two-side retaining wall detection method for unmanned mine card driving scene | |
| Cheng et al. | Ground segmentation algorithm based on 3D LiDAR point cloud | |
| CN114609609A (en) | Speed estimation method for extracting static point cloud by FMCW laser radar random sampling | |
| CN112070787B (en) | Aviation three-dimensional point cloud plane segmentation method based on opponent reasoning theory | |
| CN113269889A (en) | Self-adaptive point cloud target clustering method based on elliptical domain | |
| CN117253205A (en) | Road surface point cloud rapid extraction method based on mobile measurement system | |
| CN115453570A (en) | Multi-feature fusion mining area dust filtering method | |
| CN112989946B (en) | Lane line determining method, device, equipment and vehicle | |
| CN111338336B (en) | Automatic driving method and device | |
| CN115792958A (en) | Unmanned mine car obstacle detection method based on 3D laser radar | |
| Sun et al. | Mathematical Method for Lidar-based Obstacle Detection of Intelligent Vehicle | |
| JP2023533140A (en) | How to improve location estimation accuracy for self-driving cars | |
| Mattson et al. | Reducing ego vehicle energy-use by LiDAR-based lane-level positioning | |
| Yang et al. | Extraction of straight field roads between farmlands based on agricultural vehicle-mounted LiDAR |
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 | ||
| GR01 | Patent grant |