AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking
This work provides an automatic and dynamic solution for detection selection in 3D multi-object tracking, benefiting robotic perception systems like self-driving vehicles by eliminating manual threshold tuning and improving tracking performance.
This paper addresses the challenge of manually selecting detection confidence thresholds in 3D multi-object tracking, which is crucial for filtering out false positives. The authors propose an automatic and dynamic method that selects high-quality detections per frame or per object, resulting in a 45.7% reduction in false positives while maintaining recall and achieving new state-of-the-art performance on KITTI and nuScenes.
3D multi-object tracking is an important component in robotic perception systems such as self-driving vehicles. Recent work follows a tracking-by-detection pipeline, which aims to match past tracklets with detections in the current frame. To avoid matching with false positive detections, prior work filters out detections with low confidence scores via a threshold. However, finding a proper threshold is non-trivial, which requires extensive manual search via ablation study. Also, this threshold is sensitive to many factors such as target object category so we need to re-search the threshold if these factors change. To ease this process, we propose to automatically select high-quality detections and remove the efforts needed for manual threshold search. Also, prior work often uses a single threshold per data sequence, which is sub-optimal in particular frames or for certain objects. Instead, we dynamically search threshold per frame or per object to further boost performance. Through experiments on KITTI and nuScenes, our method can filter out $45.7\%$ false positives while maintaining the recall, achieving new S.O.T.A. performance and removing the need for manually threshold tuning.