arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.04197cs.CVcs.RO
收藏

基于深度学习的光学和红外无人机人体检测:系统与实验

Deep Learning-based Human Detection for UAVs with Optical and Infrared Cameras: System and Experiments

ETH Zurich(苏黎世联邦理工学院);Mantis Technologies(曼蒂斯科技公司)

Timo Hinzmann, Tobias Stegemann, Cesar Cadena, Roland Siegwart

摘要:

在本文中,我们介绍了我们基于深度学习的人体检测系统,该系统使用光学(RGB)和长波红外(LWIR)相机来检测,跟踪,定位和重新识别高空飞行的无人机中的人体。在每个频谱中,具有ResNet主干的定制RetinaNet网络提供了人类检测,随后将其融合以最大限度地降低整体误检率。我们表明,通过优化的限界框锚和增强的图像分辨率,从高海拔地区的错过检测的数量可以减少百分之二十以上。我们提出的网络与不同的RetinaNet和YOLO变体进行了比较,并与使用手工制作功能的经典光学红外人体检测框架进行了比较。此外,随着本文的发表,我们发布了一系列在搜索和救援现场测试期间使用不同无人机记录的注释光学红外数据集以及实现的注释工具的源代码。

英文摘要:

In this paper, we present our deep learning-based human detection system that uses optical (RGB) and long-wave infrared (LWIR) cameras to detect, track, localize, and re-identify humans from UAVs flying at high altitude. In each spectrum, a customized RetinaNet network with ResNet backbone provides human detections which are subsequently fused to minimize the overall false detection rate. We show that by optimizing the bounding box anchors and augmenting the image resolution the number of missed detections from high altitudes can be decreased by over 20 percent. Our proposed network is compared to different RetinaNet and YOLO variants, and to a classical optical-infrared human detection framework that uses hand-crafted features. Furthermore, along with the publication of this paper, we release a collection of annotated optical-infrared datasets recorded with different UAVs during search-and-rescue field tests and the source code of the implemented annotation tool.

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。

↑