Locating victims in hot environments using combined thermal and optical imaging

Abstract This work presents an autonomous system based on an Unmanned Aerial Vehicle (UAV) for victim detection using shape template matching. The system blends an optical image into a thermograph to overcome limitations inherent in the visible and infrared spectra. The system also implements image enhancements to counter thermal image degradation in warm climates. All processing is performed in real-time on-board the UAV to maximize autonomy. The outcome is a set of coordinates allowing direct access to the detected victims by rescue crews. An evaluation vehicle was constructed using a readily available drone with standard off-the-shelf components. The prototype accurately detected all victims in the test area, with rare false positives. The proposed image analysis combination was effective even under elevated ambient temperatures. The prototype was able to capture and analyze an image every three seconds allowing travel at a speed close to 2 m/sec. An area of 10,000 m2 can be scanned from an altitude of 10 m without the need for recharging.