A Fast Point Cloud Ground Segmentation Approach Based on Block-Sparsely Connected Coarse-to-Fine Markov Random Field

• Published in: IEEE robotics and automation letters Vol. 10; no. 4; pp. 3843 - 3850
• Main Authors: Huang, Weixin, Lin, Linglong, Wang, Shaobo, Fan, Zhun, Yu, Biao, Chen, Jiajia
• Format: Journal Article
• Language: English
• Published: IEEE 01.04.2025
• Subjects: Accuracy; block-sparsely connected MRF; Data mining; Feature extraction; graph cut in parallel; Ground segmentation; Image segmentation; Laser radar; Markov random fields; Motion segmentation; Point cloud compression; Three-dimensional displays; Training
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2025.3546071

Ground segmentation is an essential preprocessing task for autonomous vehicles with 3D LiDARs. Nevertheless, current methods for ground segmentation fall short of achieving optimal performance, primarily hindered by under-segmentation, over-segmentation, slow-segmentation, and poor adaptability. This letter proposes a fast block-sparsely connected coarse-to-fine Markov Random Field (MRF) point cloud ground segmentation approach to address the above challenges. It starts with a ring-shaped elevation continuity map for non-ground segmentation, followed by a range image-based algorithm to separate high-confidence and uncertain points to complete the coarse segmentation. Finally, it uses a block-sparsely connected MRF construct method to organize the point cloud and employs the graph cut method to solve the MRFs for fine segmentation in parallel. Comparison with other state-of-the-art methods on the SemanticKITTI dataset demonstrates that the proposed algorithm achieves the highest accuracy among non-deep learning methods. Experiments on the 32-beam and 128-beam datasets demonstrate its advantages in terms of generalization capability. Additionally, our method processes Velodyne HDL-64E data frames in real-time (10.33 ms) on an Intel i9-11900 K CPU, which is significantly faster than other MRF-based methods.