arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.08423cs.CVcs.RO
收藏

TransVisDrone: 面向航拍视频中基于视觉的无人机对无人机检测的时空Transformer

TransVisDrone: Spatio-Temporal Transformer for Vision-based Drone-to-Drone Detection in Aerial Videos

University of Central Florida(中佛罗里达大学);Information Technology University of the Punjab(旁遮普信息技术大学)

Tushar Sangam, Ishan Rajendrakumar Dave, Waqas Sultani, Mubarak Shah

AI总结:

针对现有无人机对无人机检测方法计算成本高、难部署于边缘设备的问题,提出端到端框架TransVisDrone,结合CSPDarkNet-53与VideoSwin提取时空特征,在三个数据集上取得SOTA性能且吞吐量更高,可部署于边缘设备。

摘要:

利用视觉输入的无人机对无人机检测在无人机碰撞检测、无人机攻击检测或与其他无人机协同飞行等场景中具有关键应用。然而,现有方法计算成本高、采用非端到端优化且多阶段流水线复杂,不太适合在边缘设备上实时部署。在本研究中,我们提出了一个简单且有效的框架TransVisDrone,它提供了计算效率更高的端到端解决方案。我们利用CSPDarkNet-53网络学习与目标相关的空间特征,并利用VideoSwin模型通过学习无人机运动的时空依赖关系,提升复杂场景下的无人机检测效果。我们的方法在三个具有挑战性的真实数据集上取得了最优性能(Average Precision@0.5IOU):NPS为0.95,FLDrones为0.75,AOT为0.80,且吞吐量高于此前的方法。我们还验证了其在边缘设备上的部署能力,以及在检测无人机碰撞(遭遇)场景中的实用性。项目页面:https://tusharsangam.github.io/TransVisDrone-project-page/

英文摘要:

Drone-to-drone detection using visual feed has crucial applications, such as detecting drone collisions, detecting drone attacks, or coordinating flight with other drones. However, existing methods are computationally costly, follow non-end-to-end optimization, and have complex multi-stage pipelines, making them less suitable for real-time deployment on edge devices. In this work, we propose a simple yet effective framework, \textit{TransVisDrone}, that provides an end-to-end solution with higher computational efficiency. We utilize CSPDarkNet-53 network to learn object-related spatial features and VideoSwin model to improve drone detection in challenging scenarios by learning spatio-temporal dependencies of drone motion. Our method achieves state-of-the-art performance on three challenging real-world datasets (Average Precision@0.5IOU): NPS 0.95, FLDrones 0.75, and AOT 0.80, and a higher throughput than previous methods. We also demonstrate its deployment capability on edge devices and its usefulness in detecting drone-collision (encounter). Project: \url{https://tusharsangam.github.io/TransVisDrone-project-page/}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑