With the increasing demand for the small unmanned aerial vehicles (UAVs), researches for target detection and tracking on a small UAV platform are of important significance. In this paper, a detection method based on the bionic visual attention is proposed. In this method, the bottom-up algorithm and up-bottom algorithm are combined. Intensity and color are the two main features to get the saliency map (SM). Regions of interest are obtained by adaptive threshold segmentation and the SM processing. The histogram of oriented gradients is used to derive a descriptor for a bounding box for each target. The support vector machine is used to obtain the classifier for exacting the targets by learning and training the descriptors. The target location is acquired via vision-based measurement. This method can effectively reduce the influence of illumination, motion blur, similar-color objects and complex background, and is successfully applied on a small UAV platform for tracking the ground targets.
Visual attention based target detection and tracking for UAVs
2016-08-01
937189 byte
Conference paper
Electronic Resource
English
DataCite | 2024
|Autonomous ground target tracking by multiple cooperative UAVs
Tema Archive | 2005
|Acoustic Detection and Tracking of UAVs and from UAVs
British Library Conference Proceedings | 2005
|Autonomous Ground Target Tracking by Multiple Cooperative UAVs
British Library Conference Proceedings | 2005
|