An optimized dynamic object detection method using LiDAR point cloud range images for urban environment

doi:10.13474/j.cnki.11-2246.2025.0207

Abstract

Abstract: To address the problem of overgrowing regions in dynamic object detection using LiDAR range images, an optimized dynamic object detection method for urban environments is proposed in this paper. This method performs fast segmentation and rotation of 3D point cloud space in 2D range images, ensuring accurate and efficient growth of the correct object region without relying on the object model. Additionally, a classification characteristic analysis for dynamic objects in scene flow detection is conducted. The issues of missed detection of dynamic objects and false detection of excessively long objects are resolved through object clustering and object region growth. This significantly improves the detection precision and recall rate while maintaining good computational efficiency. Compared to algorithms that directly detect dynamic objects in 3D point clouds, this algorithm achieves an average frame calculation time of 1/11, with a 12.67% increase in precision and a 1.51% increase in recall rate.

Key words: autonomous vehicle, LiDAR point cloud, range image, dynamic object detection

CLC Number:

P228

WU Meng, XIONG Chao. An optimized dynamic object detection method using LiDAR point cloud range images for urban environment[J]. Bulletin of Surveying and Mapping, 2025, 0(2): 35-40.

References

[1] MA Yuchi,ANDERSON J,CROUCH S,et al. Moving object detection and tracking with Doppler LiDAR[J]. Remote Sensing,2019,11(10):1154.
[2] LIANG Ming,YANG Bin,CHEN Yun,et al. Multi-task multi-sensor fusion for 3D object detection[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach:IEEE,2019.
[3] CHAVEZ-GARCIA R O,AYCARD O. Multiple sensor fusion and classification for moving object detection and tracking[J]. IEEE Transactions on Intelligent Transportation Systems,2016,17(2):525-534.
[4] BATTRAWY R,SCHUSTER R,WASENMULLER O,et al. LiDAR-flow: dense scene flow estimation from sparse LiDAR and stereo images[C]//Proceedings of 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).Macau:IEEE,2019.
[5] BEHLEY J,STACHNISS C. Efficient surfel-based SLAM using 3D laser range data in urban environments[J].Robotics: Science and Systems,2018:59.
[6] FRANKE U,RABE C,BADINO H,et al. 6D-vision: fusion of stereo and motion for robust environment perception[M]//Lecture Notes in Computer Science. Berlin.Heidelberg: Springer Berlin Heidelberg,2005:216-223.
[7] MOOSMANN F,PINK O,STILLER C. Segmentation of 3D lidar data in non-flat urban environments using a local convexity criterion[C]//Proceedings of 2009 IEEE Intelligent Vehicles Symposium.Xi'an:IEEE,2009.
[8] YOON D,TANG T,BARFOOT T. Mapless online detection of dynamic objects in 3D LiDAR[C]//Proceedings of the 16th Conference on Computer and Robot Vision (CRV).Kingston.QC:IEEE,2019.
[9] GU Shuo,YANG Jian,KONG Hui. A cascaded LiDAR-camera fusion network for road detection[C]//Proceedings of 2021 IEEE International Conference on Robotics and Automation (ICRA).Xi'an:IEEE,2021.
[10] LEE S,LIM H,MYUNG H. Patchwork: fast and robust ground segmentation solving partial under-segmentation using 3D point cloud[C]//Proceedings of 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).Kyoto:IEEE,2022.
[11] MIN Chen,JIANG Weizhong,ZHAO Dawei,et al. ORFD: a dataset and benchmark for off-road freespace detection[C]//Proceedings of 2022 International Conference on Robotics and Automation (ICRA).Philadelphia:IEEE,2022:2532-2538.
[12] MATURANA D,CHOU Powei,UENOYAMA M,et al. Real-time semantic mapping for autonomous off-road navigation[M]//Springer Proceedings in Advanced Robotics. Cham: Springer International Publishing,2017.
[13] SHABAN A,MENG X,LEE J,et al. Semantic terrain classification for off-road autonomous driving[C]// Proceeding of the 5th Conference on Robot Learning (CoRL). London:[s.n.],2021.
[14] GUAN Tianrui,KOTHANDARAMAN D,CHANDRA R,et al. GA-nav: efficient terrain segmentation for robot navigation in unstructured outdoor environments[J]. IEEE Robotics and Automation Letters,2022,7(3):8138-8145.
[15] MENZE M,GEIGER A. Object scene flow for autonomous vehicles[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston:IEEE,2015: 3061-3070.
[16] KLASING K,WOLLHERR D,BUSS M. A clustering method for efficient segmentation of 3D laser data[C]//Proceedings of 2008 IEEE International Conference on Robotics and Automation. Pasadena:IEEE,2008.
[17] ASRL.Motion-distorted LiAR simulation dataset[EB/OL].[2024-05-20].http://asrl.utias.utoronto.ca/datasets/mdlidar/index.html#overview(2020).
[18] ASVADI A,PREMEBIDA C,PEIXOTO P,et al. 3D LiDAR-based static and moving obstacle detection in driving environments: an approach based on voxels and multi-region ground planes[J]. Robotics and Autonomous Systems,2016,83:299-311.
[19] DEWAN A,OLIVEIRA G L,BURGARD W. Deep semantic classification for 3D LiDAR data[C]//Proceedings of 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).Vancouver:IEEE,2017.