Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection
This work addresses a difficult long-tail problem for autonomous perception in crowded scenes, though it appears incremental as it builds on existing tracking-by-detection methods with specific enhancements.
The paper tackles the problem of 3D pedestrian tracking in crowded urban environments by developing an offboard auto-labeling system and learning density-aware, relationship-aware representations, resulting in significant improvements in tracking performance and auto-labeling efficiency.
Perceiving pedestrians in highly crowded urban environments is a difficult long-tail problem for learning-based autonomous perception. Speeding up 3D ground truth generation for such challenging scenes is performance-critical yet very challenging. The difficulties include the sparsity of the captured pedestrian point cloud and a lack of suitable benchmarks for a specific system design study. To tackle the challenges, we first collect a new multi-view LiDAR-camera 3D multiple-object-tracking benchmark of highly crowded pedestrians for in-depth analysis. We then build an offboard auto-labeling system that reconstructs pedestrian trajectories from LiDAR point cloud and multi-view images. To improve the generalization power for crowded scenes and the performance for small objects, we propose to learn high-resolution representations that are density-aware and relationship-aware. Extensive experiments validate that our approach significantly improves the 3D pedestrian tracking performance towards higher auto-labeling efficiency. The code will be publicly available at this HTTP URL.