1.大连理工大学 汽车工程学院 工业装备结构分析优化与CAE软件全国重点实验室, 辽宁 大连 116024
2.大连理工大学 宁波研究院,浙江 宁波 315000
3.比亚迪汽车工业有限公司,广东 深圳 518118
[ "张佩翔(1997-),男,硕士研究生,主要研究方向为激光雷达点云的目标检测。" ]
[ "高仁璟(1964-),女,博士,教授,博士生导师,主要研究领域为无线通讯技术、智能网联控制技术、电机优化设计、电池管理系统设计与应用。E-mail: renjing@dlut.edu.cn" ]
扫 描 看 全 文
张佩翔, 王奇, 高仁璟, 等. 局部阈值自适应的地面点云分割[J]. 光学精密工程, 2023,31(17):2564-2572.
ZHANG Peixiang, WANG Qi, GAO Renjing, et al. Ground point cloud segmentation based on local threshold adaptive method[J]. Optics and Precision Engineering, 2023,31(17):2564-2572.
张佩翔, 王奇, 高仁璟, 等. 局部阈值自适应的地面点云分割[J]. 光学精密工程, 2023,31(17):2564-2572. DOI: 10.37188/OPE.20233117.2564.
ZHANG Peixiang, WANG Qi, GAO Renjing, et al. Ground point cloud segmentation based on local threshold adaptive method[J]. Optics and Precision Engineering, 2023,31(17):2564-2572. DOI: 10.37188/OPE.20233117.2564.
为了进一步提高自动驾驶感应模块中激光雷达点云地面分割算法的分割精度,提出一种基于种子点距离阈值和路面波动加权幅值自适应的地面点云分割算法。该算法在极坐标栅格地图划分的基础上,将种子点的选取判断阈值与二维平面的水平距离特征相关联,通过点云间的水平距离变化控制种子点集的更新;在道路模型拟合过程中,为解决斜坡路面模型更新停滞问题引入坡度连续性判断准则,根据路面波动加权幅值的变化建立点云的分割阈值方程,最终实现关于点云距离特征的自适应阈值分割。对开源数据集Semantic KITTI进行点云二分类数据处理,并在此基础上测试算法性能。实验结果表明:与现有算法相比,本文所述地面分割算法的精确率和召回率均提升了2%~4%,具有较高的准确性。
The LIDAR point cloud ground segmentation algorithm in the autonomous driving sensing module has low segmentation accuracy that requires further improvement. To address this problem, a ground point cloud segmentation algorithm is proposed based on a seed point distance threshold and road fluctuation weighted amplitude adaptive approach. Firstly, the method establishes a correlation between the selection threshold of seed points and the horizontal distance feature of the two-dimensional plane based on polar coordinate raster map division and controls the update of the seed point set through the change in horizontal distance between point clouds. Subsequently, in the process of road model fitting, the slope continuity judgment criterion is introduced to solve the stagnation problem of the slope pavement model update. Finally, the segmentation threshold equation of point clouds is established according to the change in the weighted amplitude of road surface fluctuation. This enables the achievement of adaptive threshold segmentation with respect to the distance feature of point clouds. In this paper, point cloud binary classification data processing on the open-source dataset Semantic KITTI is performed, and the performance of the algorithm is tested. The experimental results demonstrate that the ground segmentation algorithm described in this paper exhibits an improvement of 2%-4% in precision and recall when compared to existing algorithms. This substantiates the high accuracy of the algorithm proposed in this study.
点云地面分割种子点距离自适应阈值分割
point cloudground segmentationseed points distanceadaptive threshold segmentation
WANG P Z, YAO W. A new weakly supervised approach for ALS point cloud semantic segmentation[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 188: 237-254. doi: 10.1016/j.isprsjprs.2022.04.016http://dx.doi.org/10.1016/j.isprsjprs.2022.04.016
ZHANG Z Y, SUN J D, DAI Y C, et al. VRNet: learning the rectified virtual corresponding points for 3D point cloud registration[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(8): 4997-5010. doi: 10.1109/tcsvt.2022.3143151http://dx.doi.org/10.1109/tcsvt.2022.3143151
张银波, 李昊阳, 孙剑峰, 等. Gm-APD激光雷达的双参量估计透烟雾成像算法[J]. 光学 精密工程, 2022, 30(19): 2370-2378. doi: 10.37188/ope.20223019.2370http://dx.doi.org/10.37188/ope.20223019.2370
ZHANG Y B, LI H Y, SUN J F, et al. Imaging algorithm of dual-parameter estimation through smoke using Gm-APD lidar[J]. Opt. Precision Eng., 2022, 30(19): 2370-2378.(in Chinese). doi: 10.37188/ope.20223019.2370http://dx.doi.org/10.37188/ope.20223019.2370
郝雯, 张雯静, 梁玮, 等. 面向三维点云的场景识别方法综述[J]. 光学 精密工程, 2022, 30(16): 1988-2005. doi: 10.37188/OPE.20223016.1988http://dx.doi.org/10.37188/OPE.20223016.1988
HAO W, ZHANG W J, LIANG W, et al. Scene recognition for 3D point clouds: a review[J]. Opt. Precision Eng., 2022, 30(16): 1988-2005.(in Chinese). doi: 10.37188/OPE.20223016.1988http://dx.doi.org/10.37188/OPE.20223016.1988
CHENG J, HE D, LEE C. A simple ground segmentation method for LiDAR 3D point clouds[C]. 2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC 2020).12,2020, Suzhou, Jiangsu, CHINA, 2020: 171-175. doi: 10.1109/ctisc49998.2020.00034http://dx.doi.org/10.1109/ctisc49998.2020.00034
徐国艳, 牛欢, 郭宸阳, 等. 基于三维激光点云的目标识别与跟踪研究[J]. 汽车工程, 2020, 42(1): 38-46. doi: 10.19562/j.chinasae.qcgc.2020.01.006http://dx.doi.org/10.19562/j.chinasae.qcgc.2020.01.006
XU G Y, NIU H, GUO CH Y, et al. Research on target recognition and tracking based on 3D laser point cloud[J]. Automotive Engineering, 2020, 42(1): 38-46.(in Chinese). doi: 10.19562/j.chinasae.qcgc.2020.01.006http://dx.doi.org/10.19562/j.chinasae.qcgc.2020.01.006
THRUN S, MONTEMERLO M, DAHLKAMP H, et al. Stanley: The robot that won the DARPA Grand Challenge[J]. Journal of Field Robotics, 2006, 23(9): 661-692. doi: 10.1002/rob.20147http://dx.doi.org/10.1002/rob.20147
CHU P, CHO S, SIM S, et al. A fast ground segmentation method for 3D point cloud[J]. Journal of Information Processing Systems, 2017, 13(3): 491-499.
蒋剑飞, 李其仲, 黄妙华, 等. 基于三维激光雷达的障碍物及可通行区域实时检测[J]. 激光与光电子学进展, 2019, 56(24): 242801. doi: 10.3788/lop56.242801http://dx.doi.org/10.3788/lop56.242801
JIANG J F, LI Q ZH, HUANG M H, et al. Real-time detection of obstacles and passable areas based on three-dimensional lidar[J]. Laser & Optoelectronics Progress, 2019, 56(24): 242801.(in Chinese). doi: 10.3788/lop56.242801http://dx.doi.org/10.3788/lop56.242801
李炯, 赵凯, 白睿, 等. 基于射线坡度阈值的城市地面分割算法[J]. 光学学报, 2019, 39(9): 0928004. doi: 10.3788/aos201939.0928004http://dx.doi.org/10.3788/aos201939.0928004
LI J, ZHAO K, BAI R, et al. Urban ground segmentation algorithm based on ray slope threshold[J]. Acta Optica Sinica, 2019, 39(9): 0928004.(in Chinese). doi: 10.3788/aos201939.0928004http://dx.doi.org/10.3788/aos201939.0928004
NARKSRI P, TAKEUCHI E, NINOMIYA Y, et al. A slope-robust cascaded ground segmentation in 3D point cloud for autonomous vehicles[C].2018 21st International Conference on Intelligent Transportation Systems (ITSC).47,2018, Maui, HI, USA. IEEE, 2018: 497-504. doi: 10.1109/itsc.2018.8569534http://dx.doi.org/10.1109/itsc.2018.8569534
冯绍权, 花向红, 段成文, 等. 一种自适应的坡度阈值地面点云分割方法[J]. 测绘科学, 2021, 46(1): 156-161.
FENG SH Q, HUA X H, DUAN C W, et al. An adaptive slope threshold method for ground point cloud segmentation[J]. Science of Surveying and Mapping, 2021, 46(1): 156-161.(in Chinese)
VELAS M, SPANEL M, HRADIS M, et al. CNN for very fast ground segmentation in velodyne LiDAR data[C].2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC).2527,2018, Torres Vedras, Portugal. IEEE, 2018: 97-103. doi: 10.1109/icarsc.2018.8374167http://dx.doi.org/10.1109/icarsc.2018.8374167
释小松, 程英蕾, 薛豆豆, 等. 基于Point-Net的多源融合点云地物分类方法[J]. 激光与光电子学进展, 2020, 57(8): 081019. doi: 10.3788/lop57.081019http://dx.doi.org/10.3788/lop57.081019
SHI X S, CHENG Y L, XUE D D, et al. Object classification method for multi-source fusion point clouds based on point-net[J]. Laser & Optoelectronics Progress, 2020, 57(8): 081019.(in Chinese). doi: 10.3788/lop57.081019http://dx.doi.org/10.3788/lop57.081019
PAIGWAR A, ERKENT Ö, SIERRA-GONZALEZ D, et al. GndNet: fast ground plane estimation and point cloud segmentation for autonomous vehicles[C].2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). October 24 - January 24, 2021, Las Vegas, NV, USA. IEEE, 2021: 2150-2156. doi: 10.1109/iros45743.2020.9340979http://dx.doi.org/10.1109/iros45743.2020.9340979
HIMMELSBACH M, HUNDELSHAUSEN F V, WUENSCHE H J. Fast segmentation of 3D point clouds for ground vehicles[C].2010 IEEE Intelligent Vehicles Symposium. 2124,2010, La Jolla, CA, USA. IEEE, 2010: 560-565. doi: 10.1109/ivs.2010.5548059http://dx.doi.org/10.1109/ivs.2010.5548059
ZERMAS D, IZZAT I, PAPANIKOLOPOULOS N. Fast segmentation of 3D point clouds: a paradigm on LiDAR data for autonomous vehicle applications[C].2017 IEEE International Conference on Robotics and Automation (ICRA). May 29 - June 3, 2017, Singapore. IEEE, 2017: 5067-5073. doi: 10.1109/icra.2017.7989591http://dx.doi.org/10.1109/icra.2017.7989591
BEHLEY J, GARBADE M, MILIOTO A, et al. SemanticKITTI: a dataset for semantic scene understanding of LiDAR sequences[C].2019 IEEE/CVF International Conference on Computer Vision (ICCV). October 27 - November 2, 2019, Seoul, Korea (South). IEEE, 2020: 9296-9306. doi: 10.1109/iccv.2019.00939http://dx.doi.org/10.1109/iccv.2019.00939
LEE S, LIM H, MYUNG H. Patchwork: fast and robust ground segmentation solving partial under-segmentation using 3D point cloud[C].2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).2327,2022, Kyoto, Japan. IEEE, 2022: 13276-13283. doi: 10.1109/iros47612.2022.9981561http://dx.doi.org/10.1109/iros47612.2022.9981561
邵靖滔, 杜常清, 邹斌. 基于点云簇组合特征的激光雷达地面分割方法[J]. 激光与光电子学进展, 2021, 58(4): 0428001. doi: 10.3788/lop202158.0428001http://dx.doi.org/10.3788/lop202158.0428001
SHAO J T, DU CH Q, ZOU B. Lidar ground segmentation method based on point cloud cluster combination feature[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0428001.(in Chinese). doi: 10.3788/lop202158.0428001http://dx.doi.org/10.3788/lop202158.0428001
张凯, 于春磊, 赵亚丽, 等. 基于自适应阈值的三维激光点云地面分割算法研究[J]. 汽车工程, 2021, 43(7): 1005-1012.
ZHANG K, YU CH L, ZHAO Y L, et al. Research on ground segmentation algorithm based on adaptive thresholds for 3D laser point clouds[J]. Automotive Engineering, 2021, 43(7): 1005-1012. (in Chinese)
0
浏览量
15
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构