RangeSeg: Range-Aware Real Time Segmentation of 3D LiDAR Point Clouds
This work addresses the problem of efficient and accurate scene understanding for autonomous driving systems, representing an incremental improvement with specific gains in speed and small object detection.
The paper tackles the challenge of semantic and instance segmentation of 3D LiDAR point clouds for autonomous driving by proposing RangeSeg, a range-aware network that improves detection of small and far objects while achieving real-time performance. Experiments on the KITTI dataset show it outperforms state-of-the-art methods with a speed of 19 frames per second on an NVIDIA JETSON AGX Xavier.
Semantic outdoor scene understanding based on 3D LiDAR point clouds is a challenging task for autonomous driving due to the sparse and irregular data structure. This paper takes advantages of the uneven range distribution of different LiDAR laser beams to propose a range aware instance segmentation network, RangeSeg. RangeSeg uses a shared encoder backbone with two range dependent decoders. A heavy decoder only computes top of a range image where the far and small objects locate to improve small object detection accuracy, and a light decoder computes whole range image for low computational cost. The results are further clustered by the DBSCAN method with a resolution weighted distance function to get instance-level segmentation results. Experiments on the KITTI dataset show that RangeSeg outperforms the state-of-the-art semantic segmentation methods with enormous speedup and improves the instance-level segmentation performance on small and far objects. The whole RangeSeg pipeline meets the real time requirement on NVIDIA\textsuperscript{\textregistered} JETSON AGX Xavier with 19 frames per second in average.