arXiv:2609.34302 · v3

CAT-Free: Calibration-, Annotation-, and Target-Training-Free Multi-View BEV Pedestrian Detection and Tracking

首次提交 2026-09-28 12:47

版本更新 2026-11-12 15:13

雷达观测 2026-11-13 14:15

摘要

Multi-camera pedestrian detection and tracking often require camera calibration, position annotations, and target-scene training. CAT-Free removes all three requirements and uses only synchronized RGB video. From this video, CAT-Free estimates camera poses and the ground plane. With the estimated poses and ground plane, CAT-Free triangulates detections across cameras and links pedestrian positions into tracks. However, camera errors and mismatched detections produce false positions. Two geometric filters remove these false positions: one rejects unstable estimates, and the other rejects positions off the ground. Both filter thresholds are estimated from the unlabeled video. Without calibration, annotations, or target-scene training, CAT-Free achieves 89.2, 84.1, and 76.1 MODA on WildTrack, MultiviewX, and GMVD. CAT-Free is also less affected by camera errors than methods that assume known camera parameters, and it outperforms a domain adaptation method without any adaptation.