LiDAR-based scene flow estimation (SFE) and moving object segmentation (MOS) are important tasks with broad-ranging applications in autonomous driving, such as traffic surveillance, motion analysis, obstacle avoidance, etc. Most existing works address SFE and MOS separately, ignoring the underlying shared geometric constraints and their inherent correlation. This article rethinks LiDAR-based SFE and MOS tasks, providing our key insight that jointly addressing them can tackle challenges in both tasks, and their solutions can reinforce one another to improve the performance of both. Based on this insight, we introduce a novel framework that exploits shared geometric constraints by explicitly partitioning the scene into static and moving regions and subsequently estimating flow differently for these regions. A lightweight and interpretable neural network dubbed SFEMOS is proposed. It employs an encoder and two specially designed head modules for each task, achieving MOS without relying on prior poses and online point-wise flow estimation for 360-degree point clouds. Due to the absence of public datasets for concurrently evaluating both tasks, we generate ground truth flow data using MOS labels from SemanticKITTI. Additionally, we establish a new dataset using a rotational LiDAR mounted on our own autonomous vehicle. Evaluation results on both datasets validate the superior performance of our proposed SFEMOS. Our dataset and label generation method are released at https://github.com/nubot-nudt/SFEMOS.
Joint Scene Flow Estimation and Moving Object Segmentation on Rotational LiDAR Data
IEEE Transactions on Intelligent Transportation Systems ; 25 , 11 ; 17733-17743
01.11.2024
19547812 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Sparse Scene Flow Segmentation for Moving Object Detection in Urban Environments
British Library Conference Proceedings | 2011
|Motion Segmentation and Scene Classification from 3D LIDAR Data
British Library Conference Proceedings | 2008
|TOSS: Real-Time Tracking and Moving Object Segmentation for Static Scene Mapping
Springer Verlag | 2024
|