期刊文献+

基于点云簇组合特征的激光雷达地面分割方法 被引量:15

Lidar Ground Segmentation Method Based on Point Cloud Cluster Combination Feature
原文传递
导出
摘要 针对三维激光雷达在地面分割过程中存在分割不足和过分割的问题,提出一种基于点云簇组合特征的激光雷达地面分割方法。首先将三维点云投影到扇形栅格中进行连通域聚类,将梯度相差较小的栅格聚为一类。然后根据路面点云符合平面和直线几何特征的特点,对每一簇进行特征值计算以挑选路面栅格簇的候选簇,接着对其进行径向方向上的梯度检查以剔除误判栅格。最后使用三次B样条曲线进行平滑拟合,实现地面点与非地面点的分割。在不同路面状况的场景中对所提方法进行验证。实验结果表明,所提方法在含有多障碍物路面的准确率为97.50%,计算时间为27ms,说明所提方法的地面提取准确率更高,路面适应性更强。 Aiming at the problem of insufficient segmentation and over-segmentation of 3D lidar in multi-type scene,a lidar ground segmentation method based on the combined features of point cloud clusters is proposed.First,the three-dimensional point cloud is projected into a fan-shaped grid to cluster the connected domains,and the grids with small gradients are clustered into one category.Then,according to the characteristics of the pavement point cloud conforming to the geometric characteristics of the plane and the straight line,the eigenvalue of each cluster is calculated to select the candidate clusters of the pavement grid cluster,and then the gradient in the radial direction is checked to eliminate the misjudged grid.Finally,the cubic B-spline curve is used for smooth fitting to realize the division of ground points and non-ground points.The proposed method is verified in different road conditions.The experimental results show that the accuracy of the proposed method on roads with multiple obstacles is 97.50%,and the calculation time is 27 ms,indicating that the proposed method has higher ground extraction accuracy and stronger road adaptability.
作者 邵靖滔 杜常清 邹斌 Shao Jingtao;Du Changqing;Zou Bin(Hubei Key Laboratory of Advanced Technology for Automotive Components,Wuhan University of Technology,Wuhan,Hubei 430070,China;Hubei Collaborative Innovation Center for Automotive Components Technology,Wuhan University of Technology,Wuhan,Hubei 430070,China;Hubei Research Center for New Energy&Intelligent Connected Vehicle,Wuhan University of Technology,Wuhan,Hubei 430070,China)
出处 《激光与光电子学进展》 CSCD 北大核心 2021年第4期414-422,共9页 Laser & Optoelectronics Progress
基金 湖北省技术创新重大专项(2019AEA169) 国家自然科学基金(51775393)。
关键词 传感器 激光雷达 地面分割 组合特征 连通域聚类 sensors lidar ground segmentation combination feature connected domain clustering
  • 相关文献

参考文献8

二级参考文献86

  • 1周智,蔡自兴,余伶俐.基于直线特征提取的自主车辆可通行区域检测[J].华中科技大学学报(自然科学版),2011,39(S2):188-191. 被引量:4
  • 2周伦彬.逆向非接触测量技术浅析[J].中国测试技术,2005,31(5):25-27. 被引量:10
  • 3龚友平,金涛,童水光.点云数据区域分割方法[J].工程图学学报,2006,27(4):8-13. 被引量:9
  • 4GLENNIE C. Calibration and kinematic analysis of the Vel-odyne HDL-64E S2 Lidar sensor[J]. Photogrammetric En-gineerii^ and Remote Sensii^* 2012, 78(4) * 339 - 347.
  • 5HASELICH M, BING R,PAULUS D. Calibration ofmultiple cameras to a 3D laser range finder [C]// Inter-national Conference on Emerging Signal Processing Appli-cations (ESPA). Las Vegas:IEEE,2012 : 25 - 28.
  • 6KAMMEL S, PITZER B. Lidai^based lane markerdetection and mapping[C] // Intelligent Vehicles Sympo-sium. Eindhoven: IEEE, 2008 : 1137 - 1142.
  • 7HIMMELSBACH M, HUNDELSHAUSEN F,WUEN-SCHE H. Fast segmentation of 3D point clouds for groundvehicles [C] // Intelligent Vehicles Symposium (IV). San Die-go: IEEE, 2010: 560 - 565.
  • 8GUO C,SATO W,HAN L,et al. Graph-based 2Droad representation of 3D point clouds for intelligentvehicles[C] // Intelligent Vehicles Symposium(IV). De-troit: IEEE,2011: 715-721.
  • 9MONTEMERLO M, BECHER J, BHAT S,et al. Jun-ior: The Stanford entry in the urban challenge [J], Jour-nal of Field Robotics, 2008,25(9): 569 - 597.
  • 10MOOSMANN F,PINK 0,STILLER C. Segmentationof 3D lidar data in non-flat urban environments using alocal convexity criterion [Cj // Intelligent Vehicles Sym-posium. Xi,an: IEEE, 2009 : 215 - 220.

共引文献128

同被引文献132

引证文献15

二级引证文献78

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部