A new patch selection method based on parsing and saliency detection for person re-identification

Abstract

Person re-identification is an important technique towards automatic recognition of a person across non-overlapping cameras. In this paper, a novel patch selection method based on parsing and saliency detection is proposed. The algorithm is divided into two stages. The first stage, primary selection: Deep Decompositional Network (DNN) is adopted to parse a pedestrian image into semantic regions, then sliding window and color matching techniques are proposed to select pedestrian patches and remove background patches. The second stage, secondary selection: saliency detection is utilized to select reliable patches according to saliency map. Finally, PHOG, HSV and SIFT features are extracted from these patches and fused with the global feature LOMO to compensate for the inherent errors of saliency detection. By applying the proposed method on such datasets as VIPeR, PRID2011, CUHK01, CUHK03, PRID 450S and iLIDS-VID, it is found that the proposed descriptor can produce results superior to many state-of-the-art feature representation methods for person identification.