Learning pairwise feature dissimilarities for person re-identification

This paper deals with person re-identification in a multi-camera scenario with non-overlapping fields of view. Signature based matching has been the dominant choice for state-of-the-art person re-identification across multiple non-overlapping cameras. In contrast we propose a novel approach that exploits pairwise dissimilarities between feature vectors to perform the re-identification in a supervised learning framework. To achieve the proposed objective we address the person re-identification problem as follows: i) we extract multiple features from two persons images and compare them using standard distance metrics. This gives rise to what we called distance feature vector; ii) we learn the set of positive and negative distance feature vectors and perform the re-identification by classifying the test distance feature vectors. We evaluate our approach on two publicly available benchmark datasets and we compare it with state-of-the-art methods for person re-identification.