TY - GEN
T1 - MF-MOS
T2 - 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
AU - Cheng, Jintao
AU - Zeng, Kang
AU - Huang, Zhuoxu
AU - Tang, Xiaoyu
AU - Wu, Jin
AU - Zhang, Chengxi
AU - Chen, Xieyuanli
AU - Fan, Rui
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/5/13
Y1 - 2024/5/13
N2 - Moving object segmentation (MOS) provides a reliable solution for detecting traffic participants and thus is of great interest in the autonomous driving field. Dynamic capture is always critical in the MOS problem. Previous methods capture motion features from the range images directly. Differently, we argue that the residual maps provide greater potential for motion information, while range images contain rich semantic guidance. Based on this intuition, we propose MF-MOS, a novel motion-focused model with a dual-branch structure for LiDAR moving object segmentation. Novelly, we decouple the spatial-temporal information by capturing the motion from residual maps and generating semantic features from range images, which are used as movable object guidance for the motion branch. Our straightforward yet distinctive solution can make the most use of both range images and residual maps, thus greatly improving the performance of the LiDAR-based MOS task. Remarkably, our MF-MOS achieved a leading IoU of 76.7% on the MOS leaderboard of the SemanticKITTI dataset upon submission, demonstrating the current state-of-the-art performance. The implementation of our MF-MOS has been released at https://github.com/SCNU-RISLAB/MF-MOS.
AB - Moving object segmentation (MOS) provides a reliable solution for detecting traffic participants and thus is of great interest in the autonomous driving field. Dynamic capture is always critical in the MOS problem. Previous methods capture motion features from the range images directly. Differently, we argue that the residual maps provide greater potential for motion information, while range images contain rich semantic guidance. Based on this intuition, we propose MF-MOS, a novel motion-focused model with a dual-branch structure for LiDAR moving object segmentation. Novelly, we decouple the spatial-temporal information by capturing the motion from residual maps and generating semantic features from range images, which are used as movable object guidance for the motion branch. Our straightforward yet distinctive solution can make the most use of both range images and residual maps, thus greatly improving the performance of the LiDAR-based MOS task. Remarkably, our MF-MOS achieved a leading IoU of 76.7% on the MOS leaderboard of the SemanticKITTI dataset upon submission, demonstrating the current state-of-the-art performance. The implementation of our MF-MOS has been released at https://github.com/SCNU-RISLAB/MF-MOS.
UR - http://www.scopus.com/inward/record.url?scp=85192283351&partnerID=8YFLogxK
U2 - 10.1109/icra57147.2024.10611400
DO - 10.1109/icra57147.2024.10611400
M3 - Conference Proceeding (Non-Journal item)
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 12499
EP - 12505
BT - 2024 IEEE International Conference on Robotics and Automation (ICRA)
PB - IEEE Press
Y2 - 13 May 2024 through 17 May 2024
ER -