CN106780524B - A 3D point cloud road boundary automatic extraction method - Google Patents

A 3D point cloud road boundary automatic extraction method Download PDF

Info

Publication number
CN106780524B
CN106780524B CN201610996779.6A CN201610996779A CN106780524B CN 106780524 B CN106780524 B CN 106780524B CN 201610996779 A CN201610996779 A CN 201610996779A CN 106780524 B CN106780524 B CN 106780524B
Authority
CN
China
Prior art keywords
point
points
road boundary
algorithm
distance
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
Application number
CN201610996779.6A
Other languages
Chinese (zh)
Other versions
CN106780524A (en
Inventor
李军
宰大卫
林阳斌
郭裕兰
王程
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiamen University
National University of Defense Technology
Original Assignee
Xiamen University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiamen University filed Critical Xiamen University
Priority to CN201610996779.6A priority Critical patent/CN106780524B/en
Publication of CN106780524A publication Critical patent/CN106780524A/en
Application granted granted Critical
Publication of CN106780524B publication Critical patent/CN106780524B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10028Range image; Depth image; 3D point clouds
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30248Vehicle exterior or interior
    • G06T2207/30252Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256Lane; Road marking

Landscapes

  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

本发明涉及点云处理领域,具体公开了一种三维点云道路边界自动提取方法,包括以下步骤:S1、对获得的整个三维点云数据集P,筛选种子点进行超体素划分;S2、使用α‑shape算法提取邻近非共面的超体素之间的边界点;S3、使用基于图割的能量最小化算法提取道路边界点;S4、基于欧几里得距离聚类算法去除离群点;S5、将提取的道路边界点拟合成平滑曲线。本发明的方法可以直接运行在大规模三维点云上,可用于不同场景,计算速度快,算法鲁棒性好,可快速提取道路边界。

Figure 201610996779

The invention relates to the field of point cloud processing, and specifically discloses a three-dimensional point cloud road boundary automatic extraction method. Use the α-shape algorithm to extract the boundary points between adjacent non-coplanar supervoxels; S3. Use the graph cut-based energy minimization algorithm to extract the road boundary points; S4. Use the Euclidean distance clustering algorithm to remove outliers point; S5, fitting the extracted road boundary points into a smooth curve. The method of the invention can be directly run on a large-scale three-dimensional point cloud, can be used in different scenarios, has fast calculation speed, good algorithm robustness, and can quickly extract road boundaries.

Figure 201610996779

Description

一种三维点云道路边界自动提取方法A 3D point cloud road boundary automatic extraction method

技术领域technical field

本发明涉及点云处理领域,尤其是涉及一种三维点云道路边界自动提取方法。The invention relates to the field of point cloud processing, in particular to a method for automatically extracting road boundaries from a three-dimensional point cloud.

背景技术Background technique

道路作为交通基础设施,其数字化的管理与建设对于城市规划、交通管理以及导航等应用具有重要的意义。车载激光扫描技术作为一项发展迅速的高新测绘技术,相比于传统测绘手段,具有数据获取速度快、数据精度高、非接触主动测量、实时性强等优势,在车辆正常行进过程中能快速获取道路及两侧地物详尽的三维空间信息,对于带状分布的道路信息获取具有明显优势。As a transportation infrastructure, the digital management and construction of roads are of great significance for urban planning, traffic management, and navigation applications. As a rapidly developing high-tech surveying and mapping technology, vehicle-mounted laser scanning technology has the advantages of fast data acquisition, high data accuracy, non-contact active measurement, and strong real-time performance compared with traditional surveying and mapping methods. Obtaining detailed three-dimensional spatial information of roads and objects on both sides has obvious advantages for obtaining road information with strip distribution.

传统获取道路信息的方法主要包括人工测量和数字摄影测量两张方式。人工测量虽然能够获得较为准确的道路坐标等信息,但是测量速度较慢,道路信息更新周期较长;数字摄影测量随着科学技术的发展和计算机等高新技术的广泛应用逐渐发展和成熟起来,但是受限于影像分辨率等原因,影像中提取的道路特征信息和精度要求仍然需要进一步提高。车载激光扫描系统由全球定位系统、惯性导航系统、激光扫描仪和CCD相机等组成,成为获取三维空间数据的新手段。使用车载激光扫描技术能够有效地节省测量时间,提高测量效率,缩短道路信息更新周期,避免了交通环境下测量作业人员暴露的危险性,为城市空间资源的勘测与规划提供有力的技术保障。The traditional methods of obtaining road information mainly include manual measurement and digital photogrammetry. Although manual measurement can obtain more accurate road coordinates and other information, the measurement speed is slow and the update cycle of road information is long; digital photogrammetry has gradually developed and matured with the development of science and technology and the wide application of high and new technologies such as computers, but Limited by the image resolution and other reasons, the road feature information and accuracy requirements extracted from the image still need to be further improved. The vehicle-mounted laser scanning system consists of a global positioning system, an inertial navigation system, a laser scanner and a CCD camera, and has become a new means of acquiring three-dimensional spatial data. The use of vehicle-mounted laser scanning technology can effectively save measurement time, improve measurement efficiency, shorten the update cycle of road information, avoid the risk of exposure of measurement operators in the traffic environment, and provide a strong technical guarantee for the survey and planning of urban space resources.

然而,城市通常环境复杂,不仅附属部件复杂繁多,且被扫描目标之间相互遮挡造成数据缺失,对道路边界自动提取带来考验。此外,不同道路环境引起的复杂性(比如车辆停靠,植被环绕,栅栏等)加大了道路边界的自动提取难度。因此,从海量点云中快速、自动地提取道路边界难度大,要求高,但该技术具有重要的经济和应用需求,一直是国内外的研究热点。However, the city usually has a complex environment, not only the auxiliary components are complex and numerous, but also the data is missing due to the mutual occlusion of the scanned targets, which brings challenges to the automatic extraction of road boundaries. In addition, the complexity caused by different road environments (such as vehicle stops, vegetation surrounds, fences, etc.) increases the difficulty of automatic extraction of road boundaries. Therefore, it is difficult and demanding to quickly and automatically extract road boundaries from massive point clouds, but this technology has important economic and application requirements and has always been a research hotspot at home and abroad.

目前,车载激光扫描数据处理方面的研究大多集中在地物点云分类、建筑物立面信息提取与建模、道路附属设施提取等方面,而对道路边界信息提取的研究相对较少,主要工作可以分为间接提取和直接提取两类。At present, most of the research on vehicle laser scanning data processing focuses on the classification of ground objects and point clouds, the extraction and modeling of building facade information, and the extraction of road ancillary facilities, while the research on the extraction of road boundary information is relatively rare. It can be divided into two categories: indirect extraction and direct extraction.

间接提取的方法一般是首先使用点云的属性(高度、强度及波长等)产生深度图像,然后使用图像处理的方法(裁切、拟合以及滤波等)来检测、提取道路边界。对于间接提取的方法,即将点云转换成深度图像,然后使用图像处理的方法提取道路边界,这些方法势必会在转换过程中产生误差,很难获取准确的道路边界结果。The indirect extraction method generally uses the properties of the point cloud (height, intensity and wavelength, etc.) to generate a depth image, and then uses image processing methods (cropping, fitting and filtering, etc.) to detect and extract road boundaries. For the indirect extraction method, that is, converting the point cloud into a depth image, and then using the image processing method to extract the road boundary, these methods are bound to generate errors in the conversion process, and it is difficult to obtain accurate road boundary results.

直接提取的方法一般是使用道路特征(比如平面、路牙子等)来检测、提取道路边界。常用的方法为用基于随机抽样一致(RANSAC)的方法提取道路面,然后用线性拟合的算法来得到道路边界。用高斯滤波的方法或者滑动窗口的方法来检测路牙子,由此获得道路边界。对于直接提取的方法而言,则对场景的应用范围有较大局限。使用基于随机抽样一致(RANSAC)的方法提取道路面,在面对道路起伏的情况时会有困难,往往提取的道路面也会损失一些细节。而使用高斯滤波的方法或者滑动窗口的方法来检测路牙子的方法,往往在面对不规则道路边界(比如墙,栅栏)或者植被环绕的情况时会有挑战。The direct extraction method generally uses road features (such as planes, curbs, etc.) to detect and extract road boundaries. The commonly used method is to extract the road surface with the method based on random sampling agreement (RANSAC), and then use the linear fitting algorithm to obtain the road boundary. Use the Gaussian filtering method or the sliding window method to detect the curbs, thereby obtaining the road boundary. For the method of direct extraction, the scope of application of the scene is relatively limited. Using the method based on random sampling consensus (RANSAC) to extract road surfaces will have difficulties in the face of road undulations, and the extracted road surfaces will often lose some details. However, the method of using Gaussian filtering method or sliding window method to detect curbs often has challenges in the face of irregular road boundaries (such as walls, fences) or surrounded by vegetation.

发明内容SUMMARY OF THE INVENTION

本发明的目的在于克服上述现有技术的不足,本发明提供一种三维点云道路边界自动提取方法,该方法可以直接运行在大规模三维点云上,可用于不同场景,计算速度快,算法鲁棒性好,可快速提取道路边界。The purpose of the present invention is to overcome the above-mentioned deficiencies of the prior art. The present invention provides a method for automatically extracting road boundaries from a 3D point cloud. The method can be directly run on a large-scale 3D point cloud and can be used in different scenarios. The calculation speed is fast, and the algorithm It has good robustness and can quickly extract road boundaries.

具体技术方案如下:The specific technical solutions are as follows:

一种三维点云道路边界自动提取方法,包括以下步骤:A three-dimensional point cloud road boundary automatic extraction method, comprising the following steps:

S1、对获得的整个三维点云数据集P,筛选种子点进行超体素划分;S1. For the entire obtained three-dimensional point cloud data set P, filter the seed points to perform super-voxel division;

S2、使用α-shape算法提取邻近非共面的超体素之间的边界点;S2. Use the α-shape algorithm to extract the boundary points between adjacent non-coplanar supervoxels;

S3、使用基于图割的能量最小化算法提取道路边界点;S3. Use a graph cut-based energy minimization algorithm to extract road boundary points;

S4、基于欧几里得距离聚类算法去除离群点;S4, remove outliers based on Euclidean distance clustering algorithm;

S5、将提取的道路边界点拟合成平滑曲线。S5. Fit the extracted road boundary points into a smooth curve.

优选地,步骤S1对超体素的划分过程,具体如下:Preferably, the division process of step S1 to the supervoxel is as follows:

S11、求解拟合平面Tp(pi):S11. Solve the fitting plane T p ( pi ):

对于整个三维点云数据集P的每个输入点pi,其切平面Tp(pi)可以表示为由其中心点oi和法向量nl组成的二元组,即For each input point pi of the entire 3D point cloud dataset P, its tangent plane Tp( pi ) can be represented as a two-tuple consisting of its center point o i and normal vector n l , namely

Figure BDA0001150616040000031
Figure BDA0001150616040000031

三维空间内的任一点p到Tp(pi)的距离可以表示为The distance from any point p in the three-dimensional space to Tp( pi ) can be expressed as

Figure BDA0001150616040000032
Figure BDA0001150616040000032

记pi的K近邻构成的集合为Nbk(pi),通过求解下式可以得到最小二乘意义下的最佳拟合平面 Denote the set of K nearest neighbors of pi as Nb k ( pi ), and the best fitting plane in the sense of least squares can be obtained by solving the following formula

Figure BDA0001150616040000033
Figure BDA0001150616040000033

然后采用迭代重加权的最小二乘法来优化拟合的平面Then an iteratively reweighted least squares method is used to optimize the fitted plane

Figure BDA0001150616040000034
Figure BDA0001150616040000034

解带权最小二乘方程即可得到优化后的拟合平面Tp(pi)The optimized fitting plane Tp( pi ) can be obtained by solving the weighted least squares equation

Figure BDA0001150616040000035
Figure BDA0001150616040000035

对平面Tp(pi)重复上述过程,直到算法收敛。The above process is repeated for the plane Tp( pi ) until the algorithm converges.

S12、去除非地面点:S12. Remove non-ground points:

记最终构成切平面Tp(pi)的点集的协方差矩阵的三个特征值为λ12,和λ3,且满足λ1≥λ2≥λ3。则点pi的平滑度s(pi)可以表示为Note that the three eigenvalues of the covariance matrix of the point set finally constituting the tangent plane Tp(pi) are λ 1 , λ 2 , and λ 3 , and satisfy λ 1 ≥λ 2 ≥λ 3 . Then the smoothness s ( pi ) of point pi can be expressed as

Figure BDA0001150616040000041
Figure BDA0001150616040000041

使用下面两个限制来去除非地面点:Use the following two constraints to remove non-ground points:

A、去除明显高于路面的点(zi≥5m)(zi为点pi的高度值);A. Remove the points that are obviously higher than the road surface (z i ≥ 5m) (z i is the height value of point p i );

B、去除其法向量与Z轴夹角大于22.5°的点。B. Remove the points whose normal vector and the Z-axis angle are greater than 22.5°.

S13、计算超体素fiS13. Calculate the supervoxel f i :

将去除非地面点以后的点集Pg按照每个点的平滑度排序,首先选择平滑度大的点作为种子点。从种子点开始进行区域增长的方式来计算超体素。将超体素fi形式化的定义为一个有所属点集Pi,中心点oi,和法向量nl所构成的三元组

Figure BDA0001150616040000042
对每个种子点seedi,令其初始的超体素fi的初始点集为{pi},中心点和法向量分别是Tp(pi).oi和Tp(pi).nl。然后,采用宽度优先的原则对fi进行区域增长。对每个候选点pj,如果满足(1)pj到pi的距离小于阈值Rseed;(2)向量Tp(pj).nl与Tp(pi).nl的夹角小于22.5°;(3)pj到Tp(pi)的距离小于阈值∈;则将pj加入到fi的点集中。当fi无法再扩展时,根据fi.pi使用最小二乘法拟合平面,并将fi.nlg更新为拟合平面的法向量。在这些初始小平面的基础上采用局部K均值聚类来将点赋值于超体素,并保证每个点到其所属的超体素的距离小于到其他超体素的距离。这里的距离函数定义为:The point set Pg after removing the non-ground points is sorted according to the smoothness of each point, and the point with the largest smoothness is selected as the seed point first. The supervoxel is calculated by region growing from the seed point. The supervoxel f i is formally defined as a triplet consisting of the belonging point set P i , the center point o i , and the normal vector n l
Figure BDA0001150616040000042
For each seed point seed i , let the initial point set of its initial supervoxel f i be { pi }, the center point and normal vector are Tp( pi ).o i and Tp( pi ).n respectively l . Then, use the breadth-first principle to perform regional growth on f i . For each candidate point p j , if (1) the distance from p j to p i is less than the threshold R seed ; (2) the angle between the vector Tp(p j ).n l and Tp( pi ).n l is less than 22.5°; (3) the distance from p j to Tp( pi ) is less than the threshold ∈; then add p j to the point set of f i . When f i can no longer be extended, use the least squares method to fit the plane according to f i .pi , and update f i .n l g to the normal vector of the fitted plane. On the basis of these initial facets, local K-means clustering is used to assign points to supervoxels, and the distance from each point to the supervoxel to which it belongs is guaranteed to be smaller than the distance to other supervoxels. The distance function here is defined as:

Figure BDA0001150616040000043
Figure BDA0001150616040000043

其中Ds,Dn和Di分别是欧几里得距离,法向量距离以及强度距离。ωsn和ωi分别是对应的权值。where D s , D n and D i are the Euclidean distance, the normal vector distance and the intensity distance, respectively. ω s , ω n and ω i are the corresponding weights, respectively.

优选地,步骤S2使用α-shape算法提取邻近非共面的超体素之间的边界点的具体步骤为:Preferably, step S2 uses the α-shape algorithm to extract the boundary points between adjacent non-coplanar supervoxels as follows:

将点云分割成超体素以后,对于每个超体素,可以使用α-shape算法来提取边界点,同时,去除两个彼此共面的超体素之间的边界点,即如果两个超体素的法向量夹角小于22.5°,则删除这两个超体素之间的边界点,此时的边界点Pb包括道路边界点和非道路边界点。After dividing the point cloud into supervoxels, for each supervoxel, the α-shape algorithm can be used to extract the boundary points, and at the same time, the boundary points between two supervoxels that are coplanar with each other are removed, that is, if the two If the angle between the normal vectors of the super voxels is less than 22.5°, the boundary points between the two super voxels are deleted, and the boundary points P b at this time include road boundary points and non-road boundary points.

优选地,步骤S3使用基于图割的能量最小化算法提取道路边界点,具体如下:Preferably, step S3 uses a graph cut-based energy minimization algorithm to extract road boundary points, as follows:

由车载激光扫描系统提供车辆行驶轨迹线数据,将轨迹线数据作为图割算法的初始观测模型。能量公式定义为:The vehicle driving trajectory data is provided by the vehicle laser scanning system, and the trajectory data is used as the initial observation model of the graph cut algorithm. The energy formula is defined as:

E(f)=Edata(f)+λ·Esmooth(f)E(f)=E data (f)+λ·E smooth (f)

Figure BDA0001150616040000051
Figure BDA0001150616040000051

Figure BDA0001150616040000052
Figure BDA0001150616040000052

Figure BDA0001150616040000053
Figure BDA0001150616040000053

这里Pb是指步骤2中提取到的边界点的集合。n是pi所属超体素的点集的势。Δdj是指点pj到直线Lpi的距离。Δdi是指点pi邻域内所有点到直线Lpi的平均冗余。σ1是指所有点的平均冗余。直线Lpi定义为经过点pi且方向与距离pi最近的轨迹线的方向。Here P b refers to the set of boundary points extracted in step 2. n is the potential of the point set of the supervoxel to which pi belongs. Δd j is the distance from the point p j to the straight line L pi . Δd i refers to the average redundancy of all points in the neighborhood of point pi to the line L pi . σ 1 refers to the average redundancy of all points. The straight line L pi is defined as the direction of the trajectory line passing through the point pi and in the direction closest to the distance pi .

Figure BDA0001150616040000054
Figure BDA0001150616040000054

Figure BDA0001150616040000055
Figure BDA0001150616040000055

Figure BDA0001150616040000056
Figure BDA0001150616040000056

Figure BDA0001150616040000057
Figure BDA0001150616040000057

(xi,yi,zi),(xj,yj,zj)分别是点pi和pj的三维坐标,

Figure BDA0001150616040000058
是指点pi和pj的欧式距离。这里
Figure BDA0001150616040000059
表示的是如果点pi和pj分配的标签一致的话,代价为零,反之代价为
Figure BDA0001150616040000061
(x i , y i , z i ), (x j , y j , z j ) are the three-dimensional coordinates of points p i and p j respectively,
Figure BDA0001150616040000058
is the Euclidean distance between points p i and p j . here
Figure BDA0001150616040000059
It means that if the labels assigned by points p i and p j are the same, the cost is zero, otherwise the cost is
Figure BDA0001150616040000061

这里σ2指的是点集Pb的空间分辨率。使用图割算法求得上述能量公式最小值的结果即将边界点分为两类,一类是道路边界点,另一类是非道路边界点。Here σ 2 refers to the spatial resolution of the point set P b . Using the graph cut algorithm to obtain the minimum value of the above energy formula, the boundary points are divided into two categories, one is road boundary points, and the other is non-road boundary points.

本发明的方案与现有技术相比,具有如下优点:Compared with the prior art, the scheme of the present invention has the following advantages:

(1)本发明可以直接运行在大规模三维点云上,为道路边界的提取与定位提供一套快速有效地自动化解决方案。需要人为设置的参数非常少,减少了人为主观干预。与现有技术相比,本发明采用超体素分割和基于图割的最小化能量算法,在复杂的城市环境情况下依然可以有效提取道路边界,由于结合使用了车载系统轨迹线数据进行计算,克服了点云数据遮挡,密度分布不均等缺点,使得结果稳定鲁棒,对不同场景都具有普适性,易于实际运用。(1) The present invention can directly run on a large-scale three-dimensional point cloud, and provides a fast and effective automatic solution for the extraction and positioning of road boundaries. Very few parameters need to be set manually, reducing human subjective intervention. Compared with the prior art, the present invention adopts super-voxel segmentation and a graph-cut-based energy minimization algorithm, and can still effectively extract road boundaries in a complex urban environment. It overcomes the shortcomings of point cloud data occlusion and uneven density distribution, making the results stable and robust, universal to different scenarios, and easy to use in practice.

(2)本发明充分挖掘了点云的基础属性(空间距离,几何性质以及强度信息),将点云进行超体素分割,同时去除非地面点,提高了后续的计算效率。由于将种子点进行排序,优先选择的方法,超体素分割的结果非常好得保存了边界信息,提高了后续提取道路边界算法的鲁棒性。(2) The present invention fully exploits the basic properties (spatial distance, geometric properties and intensity information) of the point cloud, performs super-voxel segmentation on the point cloud, and removes non-ground points at the same time, thereby improving the subsequent calculation efficiency. Due to the method of sorting and prioritizing the seed points, the result of super-voxel segmentation is very good to preserve the boundary information, which improves the robustness of the subsequent road boundary extraction algorithm.

(3)本发明在模型算法上进行了创新优化,首次提出基于图割的能量最小化算法,利用车载系统提供的轨迹线数据,结合道路边界的内在特征来建立图割模型,有效快速地提取到道路边界。(3) The present invention has carried out innovative optimization on the model algorithm, and proposed the energy minimization algorithm based on graph cut for the first time, using the trajectory data provided by the vehicle system, combined with the inherent characteristics of the road boundary to establish a graph cut model, effectively and quickly extracting to the road boundary.

附图说明Description of drawings

图1本发明技术方案的的流程示意图;Fig. 1 is the schematic flow chart of the technical solution of the present invention;

图2本发明实施例原始点云数据;Fig. 2 embodiment of the present invention original point cloud data;

图3处理后的效果图。Figure 3. Effect diagram after processing.

具体实施方式Detailed ways

为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

实施例Example

本发明提出的基于车载激光扫描点云数据进行道路边界提取方法的具体实施方案如下(总的技术方案流程可见图1):The specific implementation scheme of the road boundary extraction method based on the vehicle-mounted laser scanning point cloud data proposed by the present invention is as follows (see Figure 1 for the overall technical scheme flow):

S1、对获得的整个三维点云数据集P,筛选种子点进行超体素划分(本实施例的原始点云数据可见图2);S1, to the obtained whole three-dimensional point cloud data set P, screen seed points and carry out supervoxel division (the original point cloud data of the present embodiment can be seen in Figure 2);

超体素划分是指将邻近的性质一致的点聚拢为一个超级点,以此来减少数据处理的复杂度;Supervoxel division refers to gathering adjacent points with the same properties into a super point to reduce the complexity of data processing;

S11、求解拟合平面Tp(pi):S11. Solve the fitting plane T p ( pi ):

对于整个三维点云数据集P的每个输入点pi,其切平面Tp(pi)可以表示为由其中心点oi和法向量nl组成的二元组,即For each input point pi of the entire 3D point cloud dataset P, its tangent plane Tp( pi ) can be represented as a two-tuple consisting of its center point o i and normal vector n l , namely

Figure BDA0001150616040000071
Figure BDA0001150616040000071

三维空间内的任一点p到Tp(pi)的距离可以表示为The distance from any point p in the three-dimensional space to Tp( pi ) can be expressed as

Figure BDA0001150616040000072
Figure BDA0001150616040000072

记pi的K近邻构成的集合为Nbk(pi),通过求解下式可以得到最小二乘意义下的最佳拟合平面 Denote the set of K nearest neighbors of pi as Nb k ( pi ), and the best fitting plane in the sense of least squares can be obtained by solving the following formula

Figure BDA0001150616040000073
Figure BDA0001150616040000073

然后采用迭代重加权的最小二乘法来优化拟合的平面Then an iteratively reweighted least squares method is used to optimize the fitted plane

Figure BDA0001150616040000074
Figure BDA0001150616040000074

解带权最小二乘方程即可得到优化后的拟合平面Tp(pi)The optimized fitting plane Tp( pi ) can be obtained by solving the weighted least squares equation

Figure BDA0001150616040000075
Figure BDA0001150616040000075

对平面Tp(pi)重复上述过程,直到算法收敛。The above process is repeated for the plane Tp( pi ) until the algorithm converges.

S12、去除非地面点:S12. Remove non-ground points:

记最终构成切平面Tp(pi)的点集的协方差矩阵的三个特征值为λ12,和λ3,且满足λ1≥λ2≥λ3。则点pi的平滑度s(pi)可以表示为Note that the three eigenvalues of the covariance matrix of the point set finally constituting the tangent plane Tp(pi) are λ 1 , λ 2 , and λ 3 , and satisfy λ 1 ≥λ 2 ≥λ 3 . Then the smoothness s ( pi ) of point pi can be expressed as

Figure BDA0001150616040000081
Figure BDA0001150616040000081

使用下面两个限制来去除非地面点:Use the following two constraints to remove non-ground points:

A、去除明显高于路面的点(zi≥5m)(zi为点pi的高度值);A. Remove the points that are obviously higher than the road surface (z i ≥ 5m) (z i is the height value of point p i );

B、去除其法向量与Z轴夹角大于22.5°的点。B. Remove the points whose normal vector and the Z-axis angle are greater than 22.5°.

S13、计算超体素fiS13. Calculate the supervoxel f i :

由此,将去除非地面点以后的点集Pg按照每个点的平滑度排序,首先选择平滑度大的点作为种子点。从种子点开始进行区域增长的方式来计算超体素。将超体素fi形式化的定义为一个有所属点集Pi,中心点oi,和法向量nl所构成的三元组

Figure BDA0001150616040000082
对每个种子点seedi,令其初始的超体素fi的初始点集为{pi},中心点和法向量分别是Tp(pi).oi和Tp(pi).nl。然后,采用宽度优先的原则对fi进行区域增长。对每个候选点pj,如果满足(1)pj到pi的距离小于阈值Rseed;(2)向量Tp(pj).nl与Tp(pi).nl的夹角小于22.5°;(3)pj到Tp(pi)的距离小于阈值∈;则将pj加入到fi的点集中。当fi无法再扩展时,根据fi.pi使用最小二乘法拟合平面,并将fi.nlg更新为拟合平面的法向量。在这些初始小平面的基础上采用局部K均值聚类来将点赋值于超体素,并保证每个点到其所属的超体素的距离小于到其他超体素的距离。这里的距离函数定义为:Therefore, the point set P g after removing the non-surface points is sorted according to the smoothness of each point, and the point with the largest smoothness is selected as the seed point first. The supervoxel is calculated by region growing from the seed point. The supervoxel f i is formally defined as a triplet consisting of the belonging point set P i , the center point o i , and the normal vector n l
Figure BDA0001150616040000082
For each seed point seed i , let the initial point set of its initial supervoxel f i be { pi }, the center point and normal vector are Tp( pi ).o i and Tp( pi ).n respectively l . Then, use the breadth-first principle to perform regional growth on f i . For each candidate point p j , if (1) the distance from p j to p i is less than the threshold R seed ; (2) the angle between the vector Tp(p j ).n l and Tp( pi ).n l is less than 22.5°; (3) the distance from p j to Tp( pi ) is less than the threshold ∈; then add p j to the point set of f i . When f i can no longer be extended, use the least squares method to fit the plane according to f i .pi , and update f i .n l g to the normal vector of the fitted plane. On the basis of these initial facets, local K-means clustering is used to assign points to supervoxels, and the distance from each point to the supervoxel to which it belongs is guaranteed to be smaller than the distance to other supervoxels. The distance function here is defined as:

Figure BDA0001150616040000083
Figure BDA0001150616040000083

其中Ds,Dn和Di分别是欧几里得距离,法向量距离以及强度距离。ωsn和ωi分别是对应的权值。where D s , D n and D i are the Euclidean distance, the normal vector distance and the intensity distance, respectively. ω s , ω n and ω i are the corresponding weights, respectively.

S2、使用α-shape算法提取邻近非共面的超体素之间的边界点;S2. Use the α-shape algorithm to extract the boundary points between adjacent non-coplanar supervoxels;

将点云分割成超体素以后,对于每个超体素,可以使用α-shape算法来提取边界点。同时,去除两个彼此共面的超体素之间的边界点,即如果两个超体素的法向量夹角小于22.5°,则删除这两个超体素之间的边界点。此时的边界点Pb包括道路边界点和非道路边界点。After segmenting the point cloud into supervoxels, for each supervoxel, an α-shape algorithm can be used to extract boundary points. At the same time, the boundary points between two supervoxels that are coplanar with each other are removed, that is, if the angle between the normal vectors of the two supervoxels is less than 22.5°, the boundary points between the two supervoxels are removed. The boundary point P b at this time includes a road boundary point and a non-road boundary point.

α-shape算法可以看作是闭包Convex Hull的扩展,它可以通过调整α参数计算更精细的闭包从而大致描述平面或空间上一群点的外形,具体是用某个固定半径的圆去套一对一对的点,当一对点都刚好落在圆上而且圆内不包含任何其他点的时候,这两个点就是形状的边界点。通过这样的方法找出所有的边界点,便描述出了Alpha shape。The α-shape algorithm can be regarded as an extension of the closure Convex Hull. It can calculate a finer closure by adjusting the α parameter to roughly describe the shape of a group of points on a plane or space. Specifically, a circle with a fixed radius is used to cover it. A pair of points, when a pair of points both fall exactly on the circle and the circle does not contain any other points, these two points are the boundary points of the shape. By finding all the boundary points in this way, the Alpha shape is described.

S3、使用基于图割的能量最小化算法提取道路边界点;S3. Use a graph cut-based energy minimization algorithm to extract road boundary points;

接下来使用基于图割的能量最小化算法来提取道路边界点。车载激光扫描系统提供车辆行驶轨迹线数据,观察到轨迹线数据与测量道路位置方向保持基本一致。由此将轨迹线数据作为图割算法的初始观测模型。能量公式定义为:Next, a graph-cut based energy minimization algorithm is used to extract road boundary points. The vehicle-mounted laser scanning system provides vehicle driving trajectory data, and the observed trajectory data is basically consistent with the measured road position and direction. Therefore, the trajectory data is used as the initial observation model of the graph cut algorithm. The energy formula is defined as:

E(f)=Edata(f)+λ·Esmooth(f)E(f)=E data (f)+λ·E smooth (f)

Figure BDA0001150616040000091
Figure BDA0001150616040000091

Figure BDA0001150616040000092
Figure BDA0001150616040000092

Figure BDA0001150616040000093
Figure BDA0001150616040000093

这里Pb是指步骤2中提取到的边界点的集合。n是pi所属超体素的点集的势。Δdj是指点pj到直线

Figure BDA0001150616040000094
的距离。Δdi是指点pi邻域内所有点到直线
Figure BDA0001150616040000095
的平均冗余。σ1是指所有点的平均冗余。直线
Figure BDA0001150616040000096
定义为经过点pi且方向与距离pi最近的轨迹线的方向。Here P b refers to the set of boundary points extracted in step 2. n is the potential of the point set of the supervoxel to which pi belongs. Δd j is the point p j to the line
Figure BDA0001150616040000094
the distance. Δd i refers to all points in the neighborhood of point p i to the line
Figure BDA0001150616040000095
average redundancy. σ 1 refers to the average redundancy of all points. straight line
Figure BDA0001150616040000096
Defined as the direction of the trajectory line that passes through point pi and whose direction is closest to pi .

Figure BDA0001150616040000097
Figure BDA0001150616040000097

Figure BDA0001150616040000098
Figure BDA0001150616040000098

Figure BDA0001150616040000101
Figure BDA0001150616040000101

Figure BDA0001150616040000102
Figure BDA0001150616040000102

(xi,yi,zi),(xj,yj,zj)分别是点pi和pj的三维坐标,

Figure BDA0001150616040000103
是指点pi和pj的欧式距离。这里
Figure BDA0001150616040000104
表示的是如果点pi和pj分配的标签一致的话,代价为零,反之代价为
Figure BDA0001150616040000105
(x i , y i , z i ), (x j , y j , z j ) are the three-dimensional coordinates of points p i and p j respectively,
Figure BDA0001150616040000103
is the Euclidean distance between points p i and p j . here
Figure BDA0001150616040000104
It means that if the labels assigned by points p i and p j are the same, the cost is zero, otherwise the cost is
Figure BDA0001150616040000105

这里σ2指的是点集Pb的空间分辨率。使用图割算法求得上述能量公式最小值的结果即将边界点分为两类,一类是道路边界点,另一类是非道路边界点。Here σ 2 refers to the spatial resolution of the point set P b . Using the graph cut algorithm to obtain the minimum value of the above energy formula, the boundary points are divided into two categories, one is road boundary points, and the other is non-road boundary points.

S4、基于欧几里得距离聚类算法去除离群点;S4, remove outliers based on Euclidean distance clustering algorithm;

使用欧几里得距离聚类算法将上述获得的道路边界点进行聚类,并删除点数很小的类别,即聚类以后,如果一个类别包含的点的个数小于5,则删除这个类别。Use the Euclidean distance clustering algorithm to cluster the road boundary points obtained above, and delete the category with a small number of points, that is, after clustering, if the number of points contained in a category is less than 5, then delete this category.

S5、将提取的道路边界点拟合成平滑曲线。S5. Fit the extracted road boundary points into a smooth curve.

将剩下的类分别拟合成光滑的曲线,由此就得到了道路边界。这里使用三次样条插值(Cubic Spline Interpolation)来拟合直线。The remaining classes are fitted to smooth curves, respectively, and the road boundaries are obtained. Here we use Cubic Spline Interpolation to fit straight lines.

其中,图3为处理后的效果图,表示提取的道路。Among them, Fig. 3 is an effect diagram after processing, showing the extracted road.

以上所述,仅为本发明较佳的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到的变化或替换,都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应该以权利要求的保护范围为准。The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited to this. Substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (5)

1.一种三维点云道路边界自动提取方法,其特征在于:包括以下步骤:1. a three-dimensional point cloud road boundary automatic extraction method, is characterized in that: comprise the following steps: S1、对获得的整个三维点云数据集P,筛选种子点进行超体素划分;S1. For the entire obtained three-dimensional point cloud data set P, filter the seed points to perform super-voxel division; S2、使用α-shape算法提取邻近非共面的超体素之间的边界点;S2. Use the α-shape algorithm to extract the boundary points between adjacent non-coplanar supervoxels; S3、使用基于图割的能量最小化算法提取道路边界点;S3. Use a graph cut-based energy minimization algorithm to extract road boundary points; S4、基于欧几里得距离聚类算法去除离群点;S4, remove outliers based on Euclidean distance clustering algorithm; S5、将去除离群点后的道路边界点拟合成平滑曲线;S5, fitting the road boundary points after removing outliers into a smooth curve; 其中,步骤S1对超体素的划分过程包括如下步骤:Wherein, the division process of the supervoxel in step S1 includes the following steps: S11、求解拟合平面Tp(Pi),其中,Pi为整个三维点云数据集P的每个输入点;S11, solve the fitting plane T p (P i ), wherein P i is each input point of the entire three-dimensional point cloud data set P; S12、去除非地面点;S12, remove the non-ground point; S13、计算超体素fiS13. Calculate the supervoxel f i ; 并且,求解拟合平面Tp(Pi)具体步骤如下:And, the specific steps for solving the fitting plane T p (P i ) are as follows: 对于整个三维点云数据集P的每个输入点Pi,其切平面Tp(Pi)可以表示为由其中心点oi和法向量nl组成的二元组,即:For each input point P i of the entire 3D point cloud dataset P, its tangent plane T p (P i ) can be represented as a two-tuple consisting of its center point o i and normal vector n l , namely:
Figure FDA0002349358200000011
其中,
Figure FDA0002349358200000012
为法向量nl的估算值,
Figure FDA0002349358200000011
in,
Figure FDA0002349358200000012
is the estimated value of the normal vector n l ,
三维空间内的任一点p到Tp(Pi)的距离可以表示为:The distance from any point p in the three-dimensional space to T p (P i ) can be expressed as:
Figure FDA0002349358200000013
Figure FDA0002349358200000013
记Pi的K近邻构成的集合为NbK(Pi),通过求解下式可以得到最小二乘意义下的最佳拟合平面:Denote the set of K nearest neighbors of P i as Nb K (P i ), and the best fitting plane in the sense of least squares can be obtained by solving the following formula:
Figure FDA0002349358200000014
Figure FDA0002349358200000014
然后采用迭代重加权的最小二乘法来优化拟合的平面:Then an iteratively reweighted least squares method is used to optimize the fitted plane:
Figure FDA0002349358200000021
Figure FDA0002349358200000021
解带权最小二乘方程即可得到优化后的拟合平面Tp(Pi):The optimized fitting plane T p (P i ) can be obtained by solving the weighted least squares equation:
Figure FDA0002349358200000022
Figure FDA0002349358200000022
对优化后的拟合平面Tp(Pi)重复上述求解过程,直到解带权最小二乘方程的算法收敛。The above solving process is repeated for the optimized fitting plane T p (P i ) until the algorithm for solving the weighted least squares equation converges.
2.根据权利要求1所述的一种三维点云道路边界自动提取方法,其特征在于:步骤S2使用α-shape算法提取邻近非共面的超体素之间的边界点的具体步骤为:2. a kind of three-dimensional point cloud road boundary automatic extraction method according to claim 1, is characterized in that: the concrete steps that step S2 uses α-shape algorithm to extract the boundary point between adjacent non-coplanar supervoxels are: 将点云分割成超体素以后,对于每个超体素,可以使用α-shape算法来提取边界点,同时,去除两个彼此共面的超体素之间的边界点,即如果两个超体素的法向量夹角小于22.5°,则删除这两个超体素之间的边界点,此时的边界点Pb包括道路边界点和非道路边界点。After dividing the point cloud into supervoxels, for each supervoxel, the α-shape algorithm can be used to extract the boundary points, and at the same time, the boundary points between two supervoxels that are coplanar with each other are removed, that is, if the two If the angle between the normal vectors of the supervoxels is less than 22.5°, the boundary points between the two supervoxels are deleted, and the boundary points P b at this time include road boundary points and non-road boundary points. 3.根据权利要求1所述的一种三维点云道路边界自动提取方法,其特征在于:3. a kind of three-dimensional point cloud road boundary automatic extraction method according to claim 1, is characterized in that: S12、去除非地面点的具体步骤如下:S12. The specific steps for removing non-ground points are as follows: 记最终构成拟合平面Tp(Pi)的点集的协方差矩阵的三个特征值为λ1,λ2,和λ3,且满足λ1≥λ2≥λ3,则点Pi的平滑度s(Pi)可以表示为:Note that the three eigenvalues of the covariance matrix of the point set that finally constitute the fitting plane T p (P i ) are λ 1 , λ 2 , and λ 3 , and satisfy λ 1 ≥λ 2 ≥λ 3 , then the point P i The smoothness s(P i ) of can be expressed as:
Figure FDA0002349358200000023
Figure FDA0002349358200000023
使用下面两个限制来去除非地面点:Use the following two constraints to remove non-ground points: A、去除明显高于路面的点,即zi≥5m的点,zi为点Pi的高度值;A. Remove the points that are obviously higher than the road surface, that is, the points where zi i ≥ 5m, and zi i is the height value of point P i ; B、去除其法向量与Z轴夹角大于22.5°的点。B. Remove the points whose normal vector and the Z-axis angle are greater than 22.5°.
4.根据权利要求2所述的一种三维点云道路边界自动提取方法,其特征在于:4. a kind of three-dimensional point cloud road boundary automatic extraction method according to claim 2 is characterized in that: S13、计算超体素fi的具体步骤如下:S13. The specific steps for calculating the supervoxel f i are as follows: 将去除非地面点以后的点集Pg按照每个点的平滑度排序,首先选择平滑度大于预设值的点作为种子点,从种子点开始进行区域增长的方式来计算超体素;将超体素fi形式化的定义为一个由所属点Pi,中心点oi,和法向量nl所构成的三元组
Figure FDA0002349358200000031
对每个种子点seedi,令其初始的超体素fi的初始点集为{Pi},中心点和法向量分别是Tp(Pi).oi和Tp(Pi).nl;然后,采用宽度优先的原则对fi进行区域增长,对每个候选点Pj,如果同时满足(1)Pj到Pi的距离小于阈值Rseed;(2)向量Tp(Pj).nl与Tp(Pi).nl的夹角小于22.5°;(3)Pj到Tp(Pi)的距离小于阈值∈;则将Pj加入到fi的点集中,当fi无法再扩展时,根据三元组fi中的Pi这一项fi.Pi使用最小二乘法拟合平面,并将三元组fi中的
Figure FDA0002349358200000032
这一项
Figure FDA0002349358200000033
更新为拟合平面的法向量;在计算得到的所有fi三元组的基础上采用局部K均值聚类来将点赋值于超体素,并保证每个点到其所属的超体素的距离小于到其他超体素的距离,这里的距离函数定义为:
Sort the point set Pg after removing the non-ground points according to the smoothness of each point, first select the point whose smoothness is greater than the preset value as the seed point, and calculate the supervoxel by regional growth from the seed point; A supervoxel f i is formally defined as a triplet consisting of the belonging point P i , the center point o i , and the normal vector n l
Figure FDA0002349358200000031
For each seed point seed i , let the initial point set of its initial supervoxel f i be {P i }, the center point and the normal vector are respectively T p (P i ).o i and T p (P i ) .n l ; then, adopt the principle of breadth priority to carry out regional growth on f i , for each candidate point P j , if (1) the distance from P j to P i is less than the threshold R seed at the same time; (2) the vector T p The angle between (P j ).n l and T p (P i ).n l is less than 22.5°; (3) the distance from P j to T p (P i ) is less than the threshold ∈; then add P j to f i In the point set of , when f i can no longer be extended , use the least squares method to fit the plane according to the term P i in the triple f i .
Figure FDA0002349358200000032
this item
Figure FDA0002349358200000033
Update to the normal vector of the fitted plane; use local K-means clustering on the basis of all calculated f i triples to assign points to supervoxels, and ensure that each point is the same as the supervoxel to which it belongs. The distance is less than the distance to other supervoxels, where the distance function is defined as:
Figure FDA0002349358200000034
Figure FDA0002349358200000034
其中Ds,Dn和Di分别是欧几里得距离,法向量距离以及强度距离,ωs,ωn和ωi分别是这三个距离值对应的权值。where D s , D n and D i are the Euclidean distance, the normal vector distance and the intensity distance, respectively, and ω s , ω n and ω i are the weights corresponding to the three distance values, respectively.
5.根据权利要求4所述的三维点云道路边界自动提取方法,其特征在于:步骤S3使用基于图割的能量最小化算法提取道路边界点,具体如下:5. three-dimensional point cloud road boundary automatic extraction method according to claim 4, is characterized in that: step S3 uses the energy minimization algorithm based on graph cut to extract road boundary point, is specifically as follows: 将车载激光扫描系统提供的车辆行驶轨迹线数据,作为初始观测模型,利用图割算法将边界点分为以下两类{“道路边界点”,“非道路边界点”},即图割算法的目标是,求得一个分类函数f给每个点分配一个标签fp∈L,L为类别集合{“道路边界点”,“非道路边界点”},使得付出的代价最小,即使得能量公式最小化,The vehicle driving trajectory data provided by the vehicle laser scanning system is used as the initial observation model, and the graph cut algorithm is used to divide the boundary points into the following two categories {"road boundary points", "non-road boundary points"}, that is, the graph cut algorithm. The goal is to find a classification function f to assign a label f p ∈ L to each point, where L is the category set {"road boundary points", "non-road boundary points"}, so that the cost is the smallest, that is, the energy formula is obtained. minimize, 这里能量公式定义为:Here the energy formula is defined as: E(f)=Edata(f)+λ·Esmooth(f)E(f)=E data (f)+λ·E smooth (f) 这里Edata(f),即能量公式中的数据项,指的是分类结果与初始观测模型比较的误差,是分类过程中给每个点分配标签的代价,Esmooth(f),即能量公式中的光滑项,指的是分类函数f非光滑的程度,具体是指分类过程中每个点与邻近点之间分类结果不一致的代价,λ是光滑项Esmooth(f)的权重,这里按经验设置为32,其中,Here E data (f), the data item in the energy formula, refers to the error between the classification result and the initial observation model, and is the cost of assigning labels to each point in the classification process, E smooth (f), the energy formula The smooth item in , refers to the degree of non-smoothness of the classification function f, specifically refers to the cost of inconsistency between the classification results between each point and the adjacent points in the classification process, λ is the weight of the smooth item E smooth (f), here press experience is set to 32, where,
Figure FDA0002349358200000041
Figure FDA0002349358200000041
Figure FDA0002349358200000042
Figure FDA0002349358200000042
Figure FDA0002349358200000043
Figure FDA0002349358200000043
这里Pb是指步骤S2中提取到的边界点的集合,n是Pi所属超体素的点集的势,Δdj是指点Pj到直线
Figure FDA0002349358200000044
的距离,Δdi是指点Pi邻域内所有点到直线
Figure FDA0002349358200000045
的平均冗余,σ1是指点集Pg中所有点的平均冗余,直线
Figure FDA00023493582000000414
定义为经过点Pi且方向向量与距离Pi最近的轨迹线方向一致,
Here P b refers to the set of boundary points extracted in step S2, n is the potential of the point set of the supervoxel to which Pi belongs, and Δd j refers to the line from point P j to the line
Figure FDA0002349358200000044
The distance of Δd i refers to all points in the neighborhood of point P i to the line
Figure FDA0002349358200000045
The average redundancy of , σ 1 refers to the average redundancy of all points in the point set P g , the straight line
Figure FDA00023493582000000414
Defined as passing through point Pi and the direction vector is consistent with the direction of the trajectory line closest to Pi ,
Figure FDA0002349358200000046
Figure FDA0002349358200000046
Figure FDA0002349358200000047
Figure FDA0002349358200000047
Figure FDA0002349358200000048
Figure FDA0002349358200000048
Figure FDA0002349358200000049
Figure FDA0002349358200000049
Figure FDA00023493582000000410
为Pi的标签,
Figure FDA00023493582000000411
为Pj的标签,(xi,yi,zi),(xj,yj,zj)分别是点Pi和Pj的三维坐标,
Figure FDA00023493582000000412
是指点Pi和Pj的欧几里得距离,这里
Figure FDA00023493582000000413
表示的是如果点Pi和Pj分配的标签一致的话,代价为零,反之代价为B{Pi,Pj},
Figure FDA00023493582000000410
is the label of Pi ,
Figure FDA00023493582000000411
is the label of P j , (x i , y i , z i ), (x j , y j , z j ) are the three-dimensional coordinates of points P i and P j , respectively,
Figure FDA00023493582000000412
is the Euclidean distance between points P i and P j , where
Figure FDA00023493582000000413
It means that if the labels assigned by points P i and P j are consistent, the cost is zero, otherwise the cost is B{P i , P j },
这里σ2指的是点集Pb的空间分辨率,使用图割算法求得上述能量公式最小值的结果即将边界点分为两类,一类是道路边界点,另一类是非道路边界点。Here σ 2 refers to the spatial resolution of the point set P b . Using the graph cut algorithm to obtain the minimum value of the above energy formula, the boundary points are divided into two categories, one is the road boundary point, and the other is the non-road boundary point .
CN201610996779.6A 2016-11-11 2016-11-11 A 3D point cloud road boundary automatic extraction method Active CN106780524B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610996779.6A CN106780524B (en) 2016-11-11 2016-11-11 A 3D point cloud road boundary automatic extraction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610996779.6A CN106780524B (en) 2016-11-11 2016-11-11 A 3D point cloud road boundary automatic extraction method

Publications (2)

Publication Number Publication Date
CN106780524A CN106780524A (en) 2017-05-31
CN106780524B true CN106780524B (en) 2020-03-06

Family

ID=58973201

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610996779.6A Active CN106780524B (en) 2016-11-11 2016-11-11 A 3D point cloud road boundary automatic extraction method

Country Status (1)

Country Link
CN (1) CN106780524B (en)

Families Citing this family (37)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107390152B (en) * 2017-07-14 2020-02-18 歌尔科技有限公司 Calibration method and device for magnetometer and electronic equipment
CN107516098B (en) * 2017-07-30 2021-08-10 华南理工大学 Target contour three-dimensional information extraction method based on edge curvature angle
CN107657659A (en) * 2017-08-14 2018-02-02 南京航空航天大学 The Manhattan construction method for automatic modeling of scanning three-dimensional point cloud is fitted based on cuboid
CN110044371A (en) * 2018-01-16 2019-07-23 华为技术有限公司 A kind of method and vehicle locating device of vehicle location
CN110068834B (en) * 2018-01-24 2023-04-07 北京京东尚科信息技术有限公司 Road edge detection method and device
CN108831146A (en) * 2018-04-27 2018-11-16 厦门维斯云景信息科技有限公司 Generate semi-automatic cloud method of three-dimensional high-definition mileage chart intersection lane
CN108615242B (en) * 2018-05-04 2021-07-27 重庆邮电大学 A high-speed guardrail tracking method
CN109241978B (en) * 2018-08-23 2021-09-07 中科光绘(上海)科技有限公司 Method for rapidly extracting plane piece in foundation three-dimensional laser point cloud
CN109299739A (en) * 2018-09-26 2019-02-01 速度时空信息科技股份有限公司 The method that vehicle-mounted laser point cloud is filtered based on the surface fitting of normal vector
CN109635641B (en) * 2018-11-01 2020-06-09 百度在线网络技术(北京)有限公司 Method, device and equipment for determining road boundary line and storage medium
CN109584294B (en) * 2018-11-23 2020-08-28 武汉中海庭数据技术有限公司 Pavement point cloud extraction method and device based on laser point cloud
CN109815943B (en) * 2019-03-18 2021-02-09 北京石油化工学院 Hazardous chemical storage stacking picture sample generation method and system
CN110046661A (en) * 2019-04-10 2019-07-23 武汉大学 A kind of vehicle-mounted cloud clustering method cutting algorithm based on contextual feature and figure
CN110060338B (en) * 2019-04-25 2020-11-10 重庆大学 Prefabricated part point cloud identification method based on BIM model
CN110243369A (en) * 2019-04-30 2019-09-17 北京云迹科技有限公司 Drawing method and device are remotely built suitable for robot localization
CN110249741B (en) * 2019-06-05 2020-07-28 中国农业大学 A method of potato seed potato dicing based on point cloud model
CN110222642B (en) * 2019-06-06 2021-07-16 上海黑塞智能科技有限公司 Plane building component point cloud contour extraction method based on global graph clustering
CN110349252B (en) * 2019-06-30 2020-12-08 华中科技大学 A method for constructing actual machining curves of small curvature parts based on point cloud boundaries
CN110458083B (en) * 2019-08-05 2022-03-25 武汉中海庭数据技术有限公司 Lane line vectorization method, device and storage medium
CN110673107B (en) * 2019-08-09 2022-03-08 北京智行者科技有限公司 Road edge detection method and device based on multi-line laser radar
CN110967024A (en) * 2019-12-23 2020-04-07 苏州智加科技有限公司 Method, device, equipment and storage medium for detecting travelable area
CN111563457A (en) * 2019-12-31 2020-08-21 成都理工大学 Road scene segmentation method for unmanned automobile
CN111340935A (en) * 2020-01-23 2020-06-26 北京市商汤科技开发有限公司 Point cloud data processing method, intelligent driving method, related device and electronic equipment
CN111815776B (en) * 2020-02-04 2024-10-25 深圳留形科技有限公司 Fine geometric reconstruction method for three-dimensional building integrating airborne and vehicle-mounted three-dimensional laser point clouds and street view images
CN111487646A (en) * 2020-03-31 2020-08-04 安徽农业大学 A method for online detection of corn plant morphology
CN111553946B (en) * 2020-04-17 2023-04-18 中联重科股份有限公司 Method and device for removing ground point cloud and method and device for detecting obstacle
CN111768421A (en) * 2020-07-03 2020-10-13 福州大学 An edge-aware semi-automatic point cloud target segmentation method
CN111783721B (en) * 2020-07-13 2021-07-20 湖北亿咖通科技有限公司 Lane line extraction method of laser point cloud and electronic equipment
CN112561808B (en) * 2020-11-27 2023-07-18 中央财经大学 Road boundary line restoration method based on vehicle-mounted laser point cloud and satellite image
CN112560747B (en) * 2020-12-23 2024-08-20 园测信息科技股份有限公司 Lane boundary interactive extraction method based on vehicle-mounted point cloud data
CN112731338A (en) * 2020-12-30 2021-04-30 潍柴动力股份有限公司 Storage logistics AGV trolley obstacle detection method, device, equipment and medium
CN112733696B (en) * 2021-01-04 2023-08-15 长安大学 Vehicle-mounted LIDAR road edge extraction method based on multi-model fitting
CN113409332B (en) * 2021-06-11 2022-05-27 电子科技大学 Building plane segmentation method based on three-dimensional point cloud
CN113378800B (en) * 2021-07-27 2021-11-09 武汉市测绘研究院 Automatic classification and vectorization method for road sign lines based on vehicle-mounted three-dimensional point cloud
CN114972377B (en) * 2022-05-24 2024-07-19 厦门大学 3D point cloud segmentation method and device based on mobile least square method and super-voxel
CN117576144B (en) * 2024-01-15 2024-03-29 湖北工业大学 Laser point cloud power line extraction method, device and electronic device
CN117726775A (en) * 2024-02-07 2024-03-19 法奥意威(苏州)机器人系统有限公司 Point cloud preprocessing method and device based on grid downsampling

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103559737A (en) * 2013-11-12 2014-02-05 中国科学院自动化研究所 Object panorama modeling method

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2532948B (en) * 2014-12-02 2021-04-14 Vivo Mobile Communication Co Ltd Object Recognition in a 3D scene

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103559737A (en) * 2013-11-12 2014-02-05 中国科学院自动化研究所 Object panorama modeling method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
3D ROAD SURFACE EXTRACTION FROM MOBILE LASER SCANNING POINT CLOUDS;Dawei Zai et al;《2016 IEEE international geoscience and remote sensing symposium》;20160715;第1595-1598页 *
A parallel point cloud clustering algorithm for subset segmentation and outlier detection;Christian Teutsch et al;《SPIE Optical Metrology》;20111231;第8085卷;第1-6 *
Robust Piecewise-Planar 3D Reconstruction and Completion from Large-Scale Unstructured Point Data;Anne-Laure Chauve et al;《2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition》;20100618;第1261-1268页 *

Also Published As

Publication number Publication date
CN106780524A (en) 2017-05-31

Similar Documents

Publication Publication Date Title
CN106780524B (en) A 3D point cloud road boundary automatic extraction method
CN112489212B (en) An intelligent 3D mapping method for buildings based on multi-source remote sensing data
CN110443836B (en) A method and device for automatic registration of point cloud data based on plane features
CN110717983B (en) Building elevation three-dimensional reconstruction method based on knapsack type three-dimensional laser point cloud data
CN107092877B (en) Roof contour extraction method of remote sensing image based on building base vector
CN108197583B (en) Building change detection method based on graph cut optimization and image structure characteristics
CN105260737B (en) A kind of laser scanning data physical plane automatization extracting method of fusion Analysis On Multi-scale Features
CN111047695B (en) Method for extracting height spatial information and contour line of urban group
CN106525000B (en) Roadmarking automation extracting method based on laser scanning discrete point intensity gradient
CN107093205A (en) A kind of three dimensions building window detection method for reconstructing based on unmanned plane image
CN106408581B (en) A Fast Line Extraction Method for 3D Point Clouds
CN110033484A (en) Set high extracting method to the high closed forest sample of a kind of combination UAV image and TLS point cloud
CN101726255A (en) Method for extracting interesting buildings from three-dimensional laser point cloud data
CN104915672B (en) A kind of Rectangle building extracting method and system based on high-resolution remote sensing image
CN107862735B (en) RGBD three-dimensional scene reconstruction method based on structural information
CN105139379A (en) Airborne Lidar point cloud building top surface gradual extraction method based on classifying and laying
CN110910435B (en) Building point cloud extraction method and device, computer equipment and readable storage medium
CN113409332B (en) Building plane segmentation method based on three-dimensional point cloud
CN117152215A (en) Automatic registration method for fast vehicle-mounted laser point cloud in complex urban environment
Chen et al. An efficient global constraint approach for robust contour feature points extraction of point cloud
Rufei et al. Research on a pavement pothole extraction method based on vehicle-borne continuous laser scanning point cloud
CN114742968B (en) A method for generating elevation map based on building elevation point cloud
CN112184725A (en) A method for extracting the center of structured light strips from asphalt pavement images
CN107564024B (en) SAR image aggregation region extraction method based on single-side aggregation line segment
Ni et al. Applications of 3d-edge detection for als point cloud

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
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20231214

Address after: 361000 Siming South Road, Xiamen, Fujian Province, No. 422

Patentee after: XIAMEN University

Patentee after: National University of Defense Technology

Address before: 361000 Siming South Road, Xiamen, Fujian Province, No. 422

Patentee before: XIAMEN University

TR01 Transfer of patent right