A UAV-based Infrared Small Target Detection System for Search and Rescue Missions

Abstract

Using infrared imaging cameras mounted on unmanned aerial vehicles to assist in search and rescue missions by gathering and processing images can substantially improve the chances of survival of missing people. Indeed, infrared imaging cameras are well suited to support the detection of heat signatures in dark and cloudy conditions. The critical point herein is detecting heat signatures emitted by the human body. This stresses feasibility of application of infrared small target detection for search and rescue missions in wide areas. This paper presents and discusses a deep learning and a low-rank and sparse matrix decomposition approaches for infrared small target detection. Further, a framework tailored for unmanned aerial vehicles is developed. The proposed infrared small target detection system is capable of detecting heat signatures in images with complex backgrounds. Experimental results demonstrate that an infrared small target detection method based on deep learning is a valuable supporting system in search and rescue missions.