Sparse Matching of Random Patches for Person Re-Identification

Most of the open challenges in person re-identification are introduced by the large variations of human appearance and from the different camera views deployed to monitor the environment. To tackle these challenges, almost all state-of-the-art methods assume that all image pixels are equally relevant to the task, hence they are used in the feature extraction procedure. However, it is not guaranteed the a pixel sensed by one camera is viewed by a different one, so computing the person signature using such pixel might bring uninformative data in the feature matching phase. We believe that only some portions of the image are relevant to the re-identification task. Inspired by this, we introduce a novel algorithm that: (i) randomly samples a set of image patches to compute the person signature; (ii) uses the correlation matrix computed between such patches as a weighing tool in the signature matching process; (iii) brings sparsity in the correlation matrix so as only relevant patches are used in the matching phase. To validate the proposed approach, we have compared our performance to state-of-the-art methods using two publicly available benchmark datasets. Results show that superior performance to existing approaches are achieved.