A Topology-Aware Spatiotemporal Handover Framework for Continuous Multi-UAV Tracking

Researchers introduced a real-time multi-UAV vehicle tracking framework for traffic monitoring that preserves identities across camera views.

The system uses topology-aware spatiotemporal handover and a deterministic queue-based matching method instead of appearance-based re-identification.

Built on YOLO11 and ByteTrack, it supports high-throughput processing and achieves 99.8% handover success in urban tests.

The approach outperforms Re-ID baselines and improves continuous, scalable vehicle tracking for traffic analysis and origin-destination estimation.