Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mapping. (June 2017)

• Record Type: Journal Article
• Authors: Su, Chi; Zhang, Shiliang; Yang, Fan; Zhang, Guangxiao; Tian, Qi; Gao, Wen; Davis, Larry S.
• Is Part Of: Pattern recognition. Volume 66(2017:Jun.)
• Page Start: 4
• Page End: 15
• Publication Date: 2017-06
• Subjects: Tracklet-to-tracklet -- Person re-identification -- Attributes -- Latent prototypes space -- Attribute correlations; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.01.006
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Most of current person re-identification works identify a person by matching his/her probe image against a galley images set. One feasible way to improve the identification accuracy is the multi-shot re-identification, where the probe includes a small set of images rather than a single image. In this paper, we study the tracklet-to-tracklet identification, where both the probe and the target dataset are composed of small sets of sequential images, i.e., tracklets. To solve this problem and make our algorithm robust under multi-camera setting, we take full advantage of low-level features, attributes and inter-attribute correlations at the same time. Attributes are expected to offer semantic information complementary to low-level features. In order to discover the correlations among attributes, a novel discriminative model is proposed to exploit low-level features and map attributes to a discriminative latent prototypes space. An alternating optimization procedure is designed to perform the learning process. We also devise a number of voting schemes to total up matching scores from images to tracklets. Experiments on four public datasets show that our approach achieves a consistently better performance than existing person re-identification methods. Abstract : Highlights: Different from most of current person re-identification works, our work focus on tracklet-to- tracklet identification under multi-camera setting. We learn and consider the contextual relations among human attributes, and validate that such cues help person re-identification tasks. Our learning framework establishes a discriminative feature representation by leveraging the relations between attributes and low-level features within a latent space.