The role of Unmanned Aerial Vehicles (UAV) in everyday activities has become bolder during the late years. They can be utilized in a bunch of useful sectors, which include inspection and monitoring; surveying and mapping; and precision agriculture, to name a few. In particular, in this project, the primary objective has been the integration of an utterly autonomous aerial rescue support system, capable of detecting, locating, and rescuing humans in peril during crisis events occurrence. The UAV performs and navigates completely autonomously, guided solely by data provided by the potential victim’s wearable equipment. The system aims to provide critical and multifaceted support in Search and Rescue (SAR) operations by significantly reducing the response time as well as backing up first responders. System’s implementation details concerning both software-hardware include an Android app for human’s in peril distress signal transmission and reception, suitable algorithms for the fully autonomous UAV’s flight, several Global Positioning System (GPS) methods for both UAV’s and distressed human’s precise positioning and finally an embedded vision system for the punctual and precise real-time human detection and the aid supply. Furthermore, in order to identify hazardous emerging behaviors in SAR missions with UAVs, a System Theoretic Process Analysis (STPA) has been applied in two different system’s operational modes. The novelty of the proposed system banks on the combination of both GPS and deep learning techniques.