Sparse representation matching for person re-identification

The need for recognizing people across distributed surveillance cameras leads to the growth of recent research interest in person re-identification. Person re-identification aims at matching people in non-overlapping cameras at different time and locations. It is a difficult pattern matching task due to significant appearance variations in pose, illumination, or occlusion in different camera views. To address this multi-view matching problem, we first learn a subspace using canonical correlation analysis (CCA) in which the goal is to maximize the correlation between data from different cameras but corresponding to the same people. Given a probe from one camera view, we represent it using a sparse representation from a. jointly learned coupled dictionary in the CCA subspace. The l(1) induced sparse representation are regularized by an l(2) regularization term. The introduction of l(2) regularization allows learning a sparse representation while maintaining the stability of the sparse coefficients. To compute the matching scores between probe and gallery, their l(2) regularized sparse representations are matched using a modified cosine similarity measure. Experimental results with extensive comparisons on challenging datasets demonstrate that the proposed method outperforms the state-of-the-art methods and using l(2) regularized sparse representation (l(1) + l(2)) is more accurate compared to use a single l(1) or l(2) regularization term. (C) 2016 Elsevier Inc. All lights reserved.