PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
This work addresses the problem of robust 3D multi-object tracking for autonomous driving by proposing a geometry-only approach that reduces reliance on appearance cues, though it is incremental as it builds on existing graph-based methods.
The authors tackled 3D multi-object tracking by using only geometric relationships between objects for data association, achieving a new state-of-the-art on the nuScenes dataset and demonstrating strong generalization across locations and datasets.
Most (3D) multi-object tracking methods rely on appearance-based cues for data association. By contrast, we investigate how far we can get by only encoding geometric relationships between objects in 3D space as cues for data-driven data association. We encode 3D detections as nodes in a graph, where spatial and temporal pairwise relations among objects are encoded via localized polar coordinates on graph edges. This representation makes our geometric relations invariant to global transformations and smooth trajectory changes, especially under non-holonomic motion. This allows our graph neural network to learn to effectively encode temporal and spatial interactions and fully leverage contextual and motion cues to obtain final scene interpretation by posing data association as edge classification. We establish a new state-of-the-art on nuScenes dataset and, more importantly, show that our method, PolarMOT, generalizes remarkably well across different locations (Boston, Singapore, Karlsruhe) and datasets (nuScenes and KITTI).