MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors
This improves tracking for applications like autonomous driving, but it is incremental as it builds on existing methods with memory networks and box priors.
The paper tackles 3D single object tracking by addressing appearance variation from occlusion and size differences, resulting in MBPTrack achieving state-of-the-art performance on major datasets like KITTI, nuScenes, and Waymo Open Dataset at 50 FPS.
3D single object tracking has been a crucial problem for decades with numerous applications such as autonomous driving. Despite its wide-ranging use, this task remains challenging due to the significant appearance variation caused by occlusion and size differences among tracked targets. To address these issues, we present MBPTrack, which adopts a Memory mechanism to utilize past information and formulates localization in a coarse-to-fine scheme using Box Priors given in the first frame. Specifically, past frames with targetness masks serve as an external memory, and a transformer-based module propagates tracked target cues from the memory to the current frame. To precisely localize objects of all sizes, MBPTrack first predicts the target center via Hough voting. By leveraging box priors given in the first frame, we adaptively sample reference points around the target center that roughly cover the target of different sizes. Then, we obtain dense feature maps by aggregating point features into the reference points, where localization can be performed more effectively. Extensive experiments demonstrate that MBPTrack achieves state-of-the-art performance on KITTI, nuScenes and Waymo Open Dataset, while running at 50 FPS on a single RTX3090 GPU.