New framework enables continuous multi-drone tracking with 99.8% handover success

Researchers have developed a new framework for tracking multiple drones continuously in urban environments. This system addresses the challenge of trajectory fragmentation, where drone views lose vehicle identity. The proposed topology-aware spatiotemporal handover mechanism uses a deterministic queue-based algorithm to predictively manage identity handover, achieving a 99.8% handover success rate. This approach significantly outperforms traditional re-identification methods and is feasible for edge deployment. AI

影响 This framework could improve the reliability of AI-powered surveillance and traffic monitoring systems that rely on multi-drone coordination.

排序理由 The cluster contains an academic paper detailing a new technical framework. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• ByteTrack
• YOLOv11

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →