Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces JitTrack, a novel active onboard multi-object tracking framework designed for agile UAVs that addresses the challenges posed by viewpoint jitter due to camera ego-motion. By integrating a query-based transformer tracker with semantic refinement, motion-aware query rectification, and a motion-inspired denoising training strategy, JitTrack enhances target detection and tracking accuracy in dynamic environments. Extensive evaluations on public benchmarks and real-world flight tests show significant performance improvements over existing methods, highlighting its practical applicability for robust visual tracking in UAV operations.
JitTrack achieves robust multi-object tracking in agile UAVs, overcoming viewpoint jitter to ensure accurate target following in real-time scenarios.
Multi-object tracking (MOT) onboard agile unmanned aerial vehicles (UAVs) remains challenging due to severe viewpoint jitter induced by camera ego-motion. Rapid attitude changes during flight often lead to significant target displacement across frames, causing inaccurate target association and degraded tracking performance. Existing UAV MOT methods are primarily evaluated on offline benchmarks and seldom address the practical requirements of real-world onboard deployment, including robustness to camera motion and active target following. To address these challenges, we propose JitTrack, an active onboard multi-object tracking framework that accommodates drone dynamics and camera ego-motion. Built upon a query-based transformer tracker, JitTrack introduces semantic refinement to improve the detection of emerging targets, motion-aware query rectification to compensate for target misalignment caused by viewpoint jitter, and a motion-inspired denoising training strategy that simulates camera motion patterns for robust supervision. Furthermore, we develop a perception-planning-control closed-loop tracking pipeline for real-world deployment, enabling collision-free and physically feasible target following on agile UAVs. Extensive experiments on public UAV MOT benchmarks demonstrate consistent improvements over the baseline method, while real-world flight experiments validate the effectiveness and practicality of JitTrack for robust onboard visual tracking under viewpoint jitter.