Any Motion Detector: Learning Class-agnostic Scene Dynamics from a Sequence of LiDAR Point Clouds
This work addresses the problem of detecting and estimating motion for all objects in complex urban environments, which is crucial for autonomous vehicle navigation, but it appears incremental as it builds on existing temporal context aggregation strategies.
The authors tackled motion detection and motion parameter estimation from LiDAR point cloud sequences for self-driving vehicles, achieving real-time inference with performance comparable to naive odometric transforms and generalization to unseen object categories.
Object detection and motion parameters estimation are crucial tasks for self-driving vehicle safe navigation in a complex urban environment. In this work we propose a novel real-time approach of temporal context aggregation for motion detection and motion parameters estimation based on 3D point cloud sequence. We introduce an ego-motion compensation layer to achieve real-time inference with performance comparable to a naive odometric transform of the original point cloud sequence. Not only is the proposed architecture capable of estimating the motion of common road participants like vehicles or pedestrians but also generalizes to other object categories which are not present in training data. We also conduct an in-deep analysis of different temporal context aggregation strategies such as recurrent cells and 3D convolutions. Finally, we provide comparison results of our state-of-the-art model with existing solutions on KITTI Scene Flow dataset.