Robust visual tracking via speedup multiple kernel ridge regression

Qian, Cheng; Breckon, Toby P.; Li, Hui

Abstract

Most of the tracking methods attempt to build up feature spaces to represent the appearance of a target. However, limited by the complex structure of the distribution of features, the feature spaces constructed in a linear manner cannot characterize the nonlinear structure well. We propose an appearance model based on kernel ridge regression for visual tracking. Dense sampling is fulfilled around the target image patches to collect the training samples. In order to obtain a kernel space in favor of describing the target appearance, multiple kernel learning is introduced into the selection of kernels. Under the framework, instead of a single kernel, a linear combination of kernels is learned from the training samples to create a kernel space. Resorting to the circulant property of a kernel matrix, a fast interpolate iterative algorithm is developed to seek coefficients that are assigned to these kernels so as to give an optimal combination. After the regression function is learned, all candidate image patches gathered are taken as the input of the function, and the candidate with the maximal response is regarded as the object image patch. Extensive experimental results demonstrate that the proposed method outperforms other state-of-the-art tracking methods.

Citation

Qian, C., Breckon, T. P., & Li, H. (2015). Robust visual tracking via speedup multiple kernel ridge regression. Journal of Electronic Imaging, 24(5), Article 053016. https://doi.org/10.1117/1.jei.24.5.053016

• Journal Article Type: Article
• Acceptance Date: Aug 20, 2015
• Online Publication Date: Sep 21, 2015
• Publication Date: Sep 21, 2015
• Deposit Date: Sep 20, 2015
• Publicly Available Date: Oct 5, 2015
• Journal: Journal of Electronic Imaging
• Print ISSN: 1017-9909
• Electronic ISSN: 1560-229X
• Publisher: Society of Photo-optical Instrumentation Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 24
• Issue: 5
• Article Number: 053016
• DOI: https://doi.org/10.1117/1.jei.24.5.053016
• Public URL: https://durham-repository.worktribe.com/output/1402500