LiU startsida
Adaptive Color Attributes for Real-Time Visual Tracking
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 object recognition 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 computationally efficient, and possess a certain amount of photometric invariance while maintaining high discriminative power.
This work 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-dimensional variant of color attributes.
Both quantitative and attribute-based 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 outperforms
state-of-the-art tracking methods while running at more than 100 frames
per second.
Publication
Martin Danelljan, Fahad Shahbaz Khan,
Michael Felsberg and Joost van de Weijer.
Adaptive Color Attributes for Real-Time
Visual Tracking.
In Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition (CVPR), 2014 (Oral).
Supplementary material
Poster
Code
Matlab code can be found here.
Dataset
The 35 color sequences in the visual tracking benchmark by Wu et al. used in our paper are found at:https://sites.google.com/site/trackerbenchmark/benchmarks/v10
All six additional color sequences can be downloaded here.
Board, Stone and Panda was obtained from:
http://faculty.ucmerced.edu/mhyang/project/cvpr12_scm.htm
Kitesurf was obtained from:
http://www4.comp.polyu.edu.hk/~cslzhang/CT/CT.htm
Shirt was obtained from:
http://www.eng.tau.ac.il/~oron/LOT/LOT.html
Surfer was obtained from:
http://vision.ucsd.edu/~bbabenko/project_miltrack.shtml
Raw Results
Raw results for the OTB-2015 and TempleColor datasets.
Video
Last updated: 2017-06-27
