SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Tracking
This addresses robust tracking in sparse point cloud scenes for autonomous driving and mobile robotics, representing a novel method for a known bottleneck.
The paper tackles the problem of 3D single object tracking in autonomous driving and robotics by introducing a sequence-to-sequence paradigm to capture target motion across continuous frames, achieving state-of-the-art improvements of 6.00% on NuScenes and 14.13% on Waymo datasets.
3D single object tracking (SOT) is an important and challenging task for the autonomous driving and mobile robotics. Most existing methods perform tracking between two consecutive frames while ignoring the motion patterns of the target over a series of frames, which would cause performance degradation in the scenes with sparse points. To break through this limitation, we introduce Sequence-to-Sequence tracking paradigm and a tracker named SeqTrack3D to capture target motion across continuous frames. Unlike previous methods that primarily adopted three strategies: matching two consecutive point clouds, predicting relative motion, or utilizing sequential point clouds to address feature degradation, our SeqTrack3D combines both historical point clouds and bounding box sequences. This novel method ensures robust tracking by leveraging location priors from historical boxes, even in scenes with sparse points. Extensive experiments conducted on large-scale datasets show that SeqTrack3D achieves new state-of-the-art performances, improving by 6.00% on NuScenes and 14.13% on Waymo dataset. The code will be made public at https://github.com/aron-lin/seqtrack3d.