点击次数：

论文类型：期刊论文

发表时间：2015-12-01

发表刊物：IEEE TRANSACTIONS ON IMAGE PROCESSING

收录刊物：SCIE、EI、Scopus

卷号：24

期号：12

页面范围：5166-5176

ISSN号：1057-7149

关键字：Object tracking; linear representation; outlier handling; probability model

摘要：This paper presents a novel visual tracking method based on linear representation. First, we present a novel probability continuous outlier model (PCOM) to depict the continuous outliers within the linear representation model. In the proposed model, the element of the noisy observation sample can be either represented by a principle component analysis subspace with small Guassian noise or treated as an arbitrary value with a uniform prior, in which a simple Markov random field model is adopted to exploit the spatial consistency information among outliers (or inliners). Then, we derive the objective function of the PCOM method from the perspective of probability theory. The objective function can be solved iteratively by using the outlier-free least squares and standard max-flow/min-cut steps. Finally, for visual tracking, we develop an effective observation likelihood function based on the proposed PCOM method and background information, and design a simple update scheme. Both qualitative and quantitative evaluations demonstrate that our tracker achieves considerable performance in terms of both accuracy and speed.