FPV Video Adaptation for UAV Collision Avoidance

First person view (FPV) technology for unmanned aerial vehicles (UAVs) provides an immersive experience pilots and enables various personal commercial applications such as photography, drone racing, search rescue operations, agricultural surveillance, structural inspection. While real time video streaming from a UAV vision-based collision avoidance strategies have been studied in literature separate topics, this paper we tackle FPV scenarios, taking into account network delays parameters. We present theoretical model obstacle collisions that considers the current communication channel conditions, parameters, UAV’s position relative to closest obstacle. A adaptation algorithm is then designed, using metric, tune resolution, number of re-transmission attempts, modulation scheme maximize probability avoiding collisions. This also takes specific latency constraints application. was evaluated scenarios its ability respond both distances well conditions demonstrated. It found that, considered performance proposed adaptive was, on average, 58.63% higher than non-adaptive one terms maximizing collision. Such could be used make safer more reliable.