Autonomous Person Detection and Tracking Framework Using Unmanned Aerial Vehicles (UAVs)
Hajer Fradi, L. Bracco, Flavia Canino, Jean‐Luc Dugelay · 2018
While person tracking has made significant progress over the last few years, most of the existing approaches are of limited success in real-time applications using moving sensors. In particular, we emphasize in this paper the need for a visual tracker that enables autonomous navigation functionality to drones (UAVs), mainly to follow a specific target. To achieve this goal, a color-based detection framework is proposed. The approach includes as well the execution of control commands, which are essential to switch from the detection to automatically follow the detected target. Our proposed approach is evaluated on videos recorded by drones. The obtained results demonstrate the effectiveness of the proposed approach to accurately follow a target in real-time, and despite different challenges such as lighting changes, speed, and occlusions.