Regular Articles

Object tracking with hierarchical multiview learning

[+] Author Affiliations
Jun Yang

Systems Engineering Research Institute, No. 1 Fengxian East Road, Haidian District, Beijing 100094, China

Shunli Zhang

Beijing Jiaotong University, School of Software Engineering, No. 3 Shangyuancun, Haidian District, Beijing 100044, China

Li Zhang

Tsinghua University, Electronic Engineering Department, No. 1 Qinghuayuan, Haidian District, Beijing 100084, China

J. Electron. Imaging. 25(5), 053006 (Sep 08, 2016). doi:10.1117/1.JEI.25.5.053006
History: Received June 3, 2016; Accepted August 16, 2016
Text Size: A A A

Abstract.  Building a robust appearance model is useful to improve tracking performance. We propose a hierarchical multiview learning framework to construct the appearance model, which has two layers for tracking. On the top layer, two different views of features, grayscale value and histogram of oriented gradients, are adopted for representation under the cotraining framework. On the bottom layer, for each view of each feature, three different random subspaces are generated to represent the appearance from multiple views. For each random view submodel, the least squares support vector machine is employed to improve the discriminability for concrete and efficient realization. These two layers are combined to construct the final appearance model for tracking. The proposed hierarchical model assembles two types of multiview learning strategies, in which the appearance can be described more accurately and robustly. Experimental results in the benchmark dataset demonstrate that the proposed method can achieve better performance than many existing state-of-the-art algorithms.

Figures in this Article
© 2016 SPIE and IS&T

Citation

Jun Yang ; Shunli Zhang and Li Zhang
"Object tracking with hierarchical multiview learning", J. Electron. Imaging. 25(5), 053006 (Sep 08, 2016). ; http://dx.doi.org/10.1117/1.JEI.25.5.053006


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.