Autonomous person detection and tracking framework using unmanned aerial vehicles (UAVs)

Fradi, Hajer; Bracco, Lorenzo; Canino, Flavia; Dugelay, Jean-Luc
EUSIPCO 2018, 26th European Signal Processing Conference, 3-7 September 2018, Rome, Italy

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.

DOI
Type:
Conférence
City:
Rome
Date:
2018-09-03
Department:
Sécurité numérique
Eurecom Ref:
5666
Copyright:
© 2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/5666