Adaptive Color Attributes for Real-Time Visual Tracking

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 1090 - 1097
• Main Authors: Danelljan, Martin, Khan, Fahad Shahbaz, Felsberg, Michael, Van De Weijer, Joost
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Adaptive Dimensionality Reduction; Appearance Model; Color; Color Features; Computational modeling; Computer vision; Covariance matrices; Image color analysis; Kernel; Luminance; Object recognition; Pattern recognition; Photometry; State of the art; Target tracking; Tracking; Visual; Visual Tracking; Visualization
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2014.143

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 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-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.