Adaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters

• Published in: International journal of computer vision Vol. 129; no. 5; pp. 1359 - 1375
• Main Authors: Xu, Tianyang, Feng, Zhenhua, Wu, Xiao-Jun, Kittler, Josef
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2021; Springer; Springer Nature B.V
• Subjects: Adaptive filters; Artificial Intelligence; Computer Imaging; Computer Science; Image Processing and Computer Vision; Model accuracy; Optical tracking; Pattern Recognition; Pattern Recognition and Graphics; Performance enhancement; Regularization; Robustness (mathematics); Smoothness; Special Issue on Computer Vision in the Wild; Stability; Vision; Visual discrimination; Adaptive Channel Selection; Discriminative Correlation Filters; Adaptive Elastic Net; Visual Object Tracking

Discriminative Correlation Filters (DCF) have been shown to achieve impressive performance in visual object tracking. However, existing DCF-based trackers rely heavily on learning regularised appearance models from invariant image feature representations. To further improve the performance of DCF in...