Deep Learning Approach in Aerial Imagery for Supporting Land Search and Rescue Missions

In this paper, we propose a novel approach to person detection in UAV aerial images for search and rescue tasks in Mediterranean and Sub-Mediterranean landscapes. Person detection in very high spatial resolution images involves target objects that are relatively small and often camouflaged within the environment; thus, such detection is a challenging and demanding task. The proposed method starts by reducing the search space through a visual attention algorithm that detects the salient or most prominent segments in the image. To reduce the number of non-relevant salient regions, we selected those regions most likely to contain a person using pre-trained and fine-tuned convolutional neural networks (CNNs) for detection. We established a special database called HERIDAL to train and test our model. This database was compiled for training purposes, and it contains over 68,750 image patches of wilderness acquired from an aerial perspective as well as approximately 500 labelled full-size real-world images intended for testing purposes. The proposed method achieved a detection rate of 88.9% and a precision of 34.8%, which demonstrates better effectiveness than the system currently used by Croatian Mountain search and rescue (SAR) teams (IPSAR), which is based on mean-shift segmentation. We also used the HERIDAL database to train and test a state-of-the-art region proposal network, Faster R-CNN (Ren et al. in Faster R-CNN: towards real-time object detection with region proposal networks, 2015. CoRR arXiv:1506.01497), which achieved comparable but slightly worse results than those of our proposed method.