Visual tracking using sparse representation

Feghahati, A. H ; Sharif University of Technology | 2012

180 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ISSPIT.2012.6621305
  3. Publisher: 2012
  4. Abstract:
  5. In this work we present a sparse dictionary learning method, specifically tuned to solve the tracking problem. Recently, sparse representation has drawn much attention because of its genuineness and strong mathematical background. In this paper we present an online method for dictionary learning which is desirable for problems such as tracking. Online learning methods are preferable because the whole data are not available at the current time. The presented method tries to use the advantages of the generative and discriminative models to achieve better performance. The experimental results show our method can overcome many tracking challenges
  6. Keywords:
  7. Visual tracking ; Better performance ; Dictionary learning ; Discriminative models ; On-line learning methods ; Sparse coding ; Sparse dictionaries ; Sparse representation ; Learning systems ; Signal processing ; Tracking (position) ; Information technology
  8. Source: 2012 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2012, 12 December 2012 through 15 December 2012, Ho Chi Minh City ; 2012 , Pages 304-309 ; 9781467356060 (ISBN)
  9. URL: http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=6621305&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6621305