TY  - CONF
AU  - M. Danelljan
AU  - Fahad Shahbaz Khan
AU  - Michael Felsberg
AU  - Joost Van de Weijer
A2  - CVPR
PY  - 2014//
TI  - Adaptive color attributes for real-time visual tracking
BT  - 27th IEEE Conference on Computer Vision and Pattern Recognition
SP  - 1090
EP  - 1097
N2  - Visual tracking is a challenging problem in computer vision. Most state-of-the-art visual trackers either rely on luminance information or use simple color representations for image description. Contrary to visual tracking, for objectrecognition and detection, sophisticated color features when combined with luminance have shown to provide excellent performance. Due to the complexity of the tracking problem, the desired color feature should be computationallyefficient, and possess a certain amount of photometric invariance while maintaining high discriminative power.This paper investigates the contribution of color in a tracking-by-detection framework. Our results suggest that color attributes provides superior performance for visual tracking. We further propose an adaptive low-dimensionalvariant of color attributes. Both quantitative and attributebased evaluations are performed on 41 challenging benchmark color sequences. The proposed approach improves the baseline intensity-based tracker by 24% in median distance precision. Furthermore, we show that our approach outperformsstate-of-the-art tracking methods while running at more than 100 frames per second.
L1  - http://refbase.cvc.uab.es/files/DKF2014.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2014.143
N1  - CIC; LAMP; 600.074; 600.079
ID  - M. Danelljan2014
ER  -