Autonomous Intelligent Remote Sensing System for Military Threat Object Detection

Artificial intelligence is revolutionizing many fields across the board. As new methods are proposed in the literature, they not only impose the state of the art of a specific field, but also positively influence other domains into which the results obtained can be transferred. In this paper, we propose a multi-stage system for solving a multidisciplinary problem: the identification of objects within a video stream and a measure of their threat level. The proposed system uses deep learning techniques developed in different application domains, in which great results are already widely documented.