Deep Learning-based Human Detection for UAVs with Optical and Infrared Cameras: System and Experiments
This work addresses human detection for UAV-based search-and-rescue operations, presenting an incremental improvement over existing methods.
The paper tackles human detection from UAVs using optical and infrared cameras, achieving over 20% reduction in missed detections by optimizing bounding box anchors and augmenting image resolution.
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.