用事件相机检测细如发丝的障碍物，提升无人机飞行安全
Skyshield: Event-Driven Submillimetre Thin Obstacle Detection for Drone Flight Safety
- 基于事件流特征，用轻量U-Net和新损失函数精准定位细小障碍
- 平均F1达0.7088，延迟仅21.2毫秒，适合边缘部署
- 专为钢丝、风筝线等亚毫米级障碍设计，适合无人机避障
在复杂环境中飞行的无人机面临细小障碍物（如亚毫米级的钢丝、风筝线）的严重威胁，传统传感器如RGB相机、激光雷达和深度相机难以有效检测。本文提出SkyShield，一种面向亚毫米级障碍物感知的事件驱动端到端框架。该方法利用细小障碍在事件流中呈现的独特特性，采用轻量级U-Net结构并引入创新的Dice-Contour正则化损失，实现高精度检测。实验结果表明，所提事件感知方法在保持低延迟（21.2毫秒）的同时，获得0.7088的平均F1分数，适用于边缘与移动平台部署。
原文摘要 · Abstract (English)
Drones operating in complex environments face a significant threat from thin obstacles, such as steel wires and kite strings at the submillimeter level, which are notoriously difficult for conventional sensors like RGB cameras, LiDAR, and depth cameras to detect. This paper introduces SkyShield, an event-driven, end-to-end framework designed for the perception of submillimeter scale obstacles. Drawing upon the unique features that thin obstacles present in the event stream, our method employs a lightweight U-Net architecture and an innovative Dice-Contour Regularization Loss to ensure precise detection. Experimental results demonstrate that our event-based approach achieves mean F1 Score of 0.7088 with a low latency of 21.2 ms, making it ideal for deployment on edge and mobile platforms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。