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

2026-05-15

AI Summary

This work addresses the challenge of fragmented vehicle trajectories and identity loss caused by field-of-view switching in multi-UAV traffic monitoring, which hinders network-level analysis. The authors propose a real-time, appearance-free multi-camera multi-vehicle tracking system that ensures cross-view identity continuity through a topology-aware spatiotemporal handover mechanism. The core innovation lies in a lightweight, deterministic queue-matching algorithm that integrates geometric overlap with discretized virtual lanes, coupled with a high-throughput parallel processing pipeline built upon YOLOv8 and ByteTrack. Predictive identity handover is achieved via FIFO queues. Evaluated in complex urban scenarios, the system supports concurrent processing of four 4K video streams and achieves a handover success rate of 99.8%, substantially outperforming a re-identification baseline at 74.1%, thereby demonstrating its efficiency and practical utility.

Abstract

The integration of Unmanned Aerial Vehicles(UAVs) into Intelligent Transportation Systems (ITS) offers synoptic visibility for traffic monitoring, yet scalable deployment is hindered by trajectory fragmentation, where vehicle identity persistence is lost across multi-UAV Fields of View (FOV). While state-of-the-art frameworks excel in optimizing local trajectory extraction and stability for single-drone imagery, they often function as isolated data silos that generate disjointed trajectories, thereby precluding network-level analysis such as Origin-Destination estimation. This paper presents a real-time Multi-Camera Multi-Vehicle Tracking (MCMT) system designed to handle global identity persistence. Addressing the visual ambiguity and computational cost of appearance-based Re-Identification (Re-ID) in nadir views, we introduce a lightweight Topology-Based Spatiotemporal Handover mechanism. We implement a high-throughput parallel pipeline leveraging YOLO11 and ByteTrack to process concurrent 4K streams. Our core contribution is a deterministic queue-based matching algorithm that utilizes geometric overlaps and virtual lane discretization to predictively manage identity handover via FIFO queues. Experimental results on complex urban environments, including intersections and merging traffic, demonstrate a Handover Success Rate (HOSR) of 99.8% in continuous traffic flows, significantly outperforming Re-ID baselines (74.1%) while validating edge deployment feasibility. The source code is available at https://github.com/JYe9/multi-camera-multi-vehicle-tracking-system.

Problem

• trajectory fragmentation
• identity persistence
• multi-UAV tracking
• handover
• Intelligent Transportation Systems

Innovation

• Topology-Based Spatiotemporal Handover
• Multi-UAV Tracking
• Identity Persistence
• Queue-Based Matching
• Edge-Deployable MCMT