Real-time Obstacle Detection and Tracking Mechanism in UAVs

Obstacle detection and tracking is an important research area in computer vision with a number of practical applications. Though an ample amount of research has been done in this domain, implementing automatic obstacle detection and tracking in real-time is still a big challenge. To address this issue, we propose a fast and robust obstacle detection and tracking approach by integrating an adaptive obstacle detection strategy within a YOLO framework in this paper. A suitable salient object detection method auto initializes the tracker for this purpose. Moreover, an adaptive obstacle detection strategy is proposed to re�ne the location and boundary of the object when the con�dence value of the tracker drops below a prede�ned threshold. In addition, a reliable pre-processing technique is implemented to accurately localize the obstacle from a saliency map recovered from the search region. The experiments reveal that the proposed approach signi�cantly outperforms the state-of-the-art methods in terms of tracking speed and accuracy.