Gradient Enhancement Techniques and Motion Consistency Constraints for Moving Object Segmentation in 3D LiDAR Point Clouds

被引:0
|
作者
Tang, Fangzhou [1 ]
Zhu, Bocheng [1 ]
Sun, Junren [1 ,2 ]
机构
[1] Peking Univ, Sch Elect, Beijing 100871, Peoples R China
[2] China Univ Min & Technol Beijing, Sch Artificial Intelligence, Beijing 100083, Peoples R China
关键词
LiDAR point cloud; moving object segmentation; range image; gradient enhancement; motion consistency;
D O I
10.3390/rs17020195
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The ability to segment moving objects from three-dimensional (3D) LiDAR scans is critical to advancing autonomous driving technology, facilitating core tasks like localization, collision avoidance, and path planning. In this paper, we introduce a novel deep neural network designed to enhance the performance of 3D LiDAR point cloud moving object segmentation (MOS) through the integration of image gradient information and the principle of motion consistency. Our method processes sequential range images, employing depth pixel difference convolution (DPDC) to improve the efficacy of dilated convolutions, thus boosting spatial information extraction from range images. Additionally, we incorporate Bayesian filtering to impose posterior constraints on predictions, enhancing the accuracy of motion segmentation. To handle the issue of uneven object scales in range images, we develop a novel edge-aware loss function and use a progressive training strategy to further boost performance. Our method is validated on the SemanticKITTI-based LiDAR MOS benchmark, where it significantly outperforms current state-of-the-art (SOTA) methods, all while working directly on two-dimensional (2D) range images without requiring mapping.
引用
收藏
页数:25
相关论文
共 50 条
  • [41] Urban 3D segmentation and modelling from street view images and LiDAR point clouds
    Pouria Babahajiani
    Lixin Fan
    Joni-Kristian Kämäräinen
    Moncef Gabbouj
    Machine Vision and Applications, 2017, 28 : 679 - 694
  • [42] SoftGroup for 3D Instance Segmentation on Point Clouds
    Thang Vu
    Kim, Kookhoi
    Luu, Tung M.
    Thanh Nguyen
    Yoo, Chang D.
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 2698 - 2707
  • [43] SEGCloud: Semantic Segmentation of 3D Point Clouds
    Tchapmi, Lyne P.
    Choy, Christopher B.
    Armeni, Iro
    Gwak, JunYoung
    Savarese, Silvio
    PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2017, : 537 - 547
  • [44] Retraction Note: Moving object detection algorithm and motion capture based on 3D LiDAR
    Jian Jiang
    Optical and Quantum Electronics, 56 (10)
  • [45] Biomass Prediction with 3D Point Clouds from LiDAR
    Pan, Liyuan
    Liu, Liu
    Condon, Anthony G.
    Estavillo, Gonzalo M.
    Coe, Robert A.
    Bull, Geoff
    Stone, Eric A.
    Petersson, Lars
    Rolland, Vivien
    2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, : 1716 - 1726
  • [46] UNSUPERVISED STREAM LEARNING FOR 3D LIDAR POINT CLOUDS
    Shreelakshmi, C. R.
    Durbha, Surya S.
    Shinde, Rajat C.
    Talreja, Pratyush V.
    Singh, Gaganpreet
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 4451 - 4454
  • [47] Progressive generation of 3D point clouds with hierarchical consistency
    Li, Peipei
    Liu, Xiyan
    Huang, Jizhou
    Xia, Deguo
    Yang, Jianzhong
    Lu, Zhen
    PATTERN RECOGNITION, 2023, 136
  • [48] Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions
    Mersch, Benedikt
    Chen, Xieyuanli
    Vizzo, Ignacio
    Nunes, Lucas
    Behley, Jens
    Stachniss, Cyrill
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (03) : 7503 - 7510
  • [49] Robust object segmentation and parametrization of 3D lidar data
    Kapp, A
    2005 IEEE INTELLIGENT VEHICLES SYMPOSIUM PROCEEDINGS, 2005, : 694 - 699
  • [50] Object class segmentation of massive 3D point clouds of urban areas using point cloud topology
    Richter, Rico
    Behrens, Markus
    Doellner, Juergen
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2013, 34 (23) : 8408 - 8424