Abstract
First person view (FPV) technology for unmanned aerial vehicles (UAVs) provides an immersive experience for pilots and enables various personal and commercial applications such as aerial photography, drone racing, search and rescue operations, agricultural surveillance, and structural inspection. While real time video streaming from a UAV and vision-based collision avoidance strategies have been studied in literature as separate topics, in this paper we tackle collision avoidance in FPV scenarios, taking into account network delays and real time video parameters. We present a theoretical model for obstacle collisions that considers the current communication channel conditions, the real time video parameters, and the UAV’s position relative to the closest obstacle. A video adaptation algorithm is then designed, using this metric, to tune the FPV video resolution, number of re-transmission attempts, and the modulation scheme to maximize the probability of avoiding collisions. This algorithm also takes into account specific latency constraints of the application. This video algorithm was evaluated in various scenarios and its ability to respond to both distances to the obstacle as well as the communication channel conditions was demonstrated. It was found that, for the considered scenarios, the performance of the proposed adaptive algorithm was, on an average, 58.63% higher than the closest non-adaptive one in terms of maximizing the probability of avoiding collision. Such collision avoidance strategies could be used to make UAV FPV applications safer and more reliable.
Highlights
First person view (FPV) technology provides the vantange point on an unmanned aerial vehicle (UAV) to a ground pilot, allowing the pilot to manoeuvre the unmanned aerial vehicles (UAVs) based on the video feed from the UAV’s camera
OJCOMS-00596-2021.R1 of UAV FPV applications safer, it is important to study the design of collision-avoidance video adaptation algorithms that take into account the complex interplay between the factors described above
We address this gap by presenting a dynamic video adaptation algorithm that tunes the parameters of a real-time FPV video stream with the goal of allowing a pilot to avoid obstacles
Summary
First person view (FPV) technology provides the vantange point on an unmanned aerial vehicle (UAV) to a ground pilot, allowing the pilot to manoeuvre the UAV based on the video feed from the UAV’s camera. OJCOMS-00596-2021.R1 of UAV FPV applications safer, it is important to study the design of collision-avoidance video adaptation algorithms that take into account the complex interplay between the factors described above We analyze this scenario and derive a collision avoidance metric that is a function of the UAV’s orientation with reference to the nearest obstacle, the real-time communication channel conditions, and the FPV feed parameters. This distinguishes our work from studies that focus on the problem of obstacle avoidance in conjunction with trajectory tracking [9], where the trajectory that the UAV has to navigate is known completely or partially, for example when the UAV is used to spray an agricultural field or survey infrastructure We evaluate this video adaptation algorithm for various latency constraints, and demonstrate its ability to respond to changes in channel conditions as well as distance to nearest obstacles.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
