ARGUSTRACK: A Multi-View Annotation System for Multi-Object Tracking
For researchers needing multi-view tracking annotations, ARGUSTRACK addresses the bottleneck of cross-view labeling without LiDAR, though the evaluation is limited to a specific domain.
ARGUSTRACK introduces a multi-camera annotation system that uses a bird's-eye-view plane to project single ground-plane annotations into 2D bounding boxes across all views, reducing annotation time for multi-object tracking. A pilot study on broiler tracking showed substantial time savings compared to single-camera workflows.
Multi-Camera Multi-Target (MCMT) tracking has emerged as a critical capability for applications ranging from autonomous driving to animal behavior monitoring. While recent advances have yielded sophisticated tracking algorithms, the availability of annotated multi-view data remains a significant bottleneck. Existing annotation tools predominantly support single-camera workflows or rely on LiDAR sensors, making cross-view labeling tedious and impractical for camera-only setups. We present ARGUS-TRACK, a multi-camera annotation system that addresses these limitations by enabling annotators to work directly on a bird's-eye-view (BEV) plane. Given calibrated camera parameters, a single ground-plane annotation is automatically projected into 2D bounding boxes across all relevant views, inherently ensuring identity consistency without manual cross-view alignment. To further accelerate the labeling process, ARGUSTRACK incorporates two complementary mechanisms: a Temporal Aware module that propagates annotations from preceding frames to initialize new ones, requiring only minor positional adjustments; and a Multi-camera Semi-annotation module that leverages off-the-shelf 2D detectors combined with foot-point estimation to automatically generate candidate BEV positions for annotator verification. We evaluate ARGUSTRACK through a pilot study on multi-camera broiler tracking and demonstrate that it substantially reduces annotation time compared to conventional single-camera labeling workflows.