Person Re-Identification by Unsupervised \(\ell _1\) Graph Learning
Most existing person re-identification (Re-ID) methods are based on supervised learning of a discriminative distance metric. They thus require a large amount of labelled training image pairs which severely limits their scalability. In this work, we propos
- PDF / 448,313 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 64 Downloads / 180 Views
Abstract. Most existing person re-identification (Re-ID) methods are based on supervised learning of a discriminative distance metric. They thus require a large amount of labelled training image pairs which severely limits their scalability. In this work, we propose a novel unsupervised Re-ID approach which requires no labelled training data yet is able to capture discriminative information for cross-view identity matching. Our model is based on a new graph regularised dictionary learning algorithm. By introducing a 1 -norm graph Laplacian term, instead of the conventional squared 2 -norm, our model is robust against outliers caused by dramatic changes in background, pose, and occlusion typical in a Re-ID scenario. Importantly we propose to learn jointly the graph and representation resulting in further alleviation of the effects of data outliers. Experiments on four benchmark datasets demonstrate that the proposed model significantly outperforms the state-of-the-art unsupervised learning based alternatives whilst being extremely efficient to compute.
Keywords: Unsupervised person Re-ID graph regularisation · Graph learning
1
· Dictionary learning · Robust
Introduction
The problem of matching people across non-overlapping cameras, known as person re-identification (Re-ID), has drawn a great deal of attention recently [20,53]. It remains an unsolved problem due to two reasons: (1) A person’s appearance often changes dramatically across cameras views due to occlusion, lighting, illumination and pose changes; (2) Many people in public spaces wear similar clothes (e.g. dark coats, jeans) thus having similar visual appearance. Most recent Re-ID methods are based on supervised learning. Given a set of labelled training data consisting of images of people paired across camera views according to identity, a distance metric is learned either using hand-crafted features [9,14,19,25,31,37,38,46,48,49,55,56,58,60], or end-to-end using deep Electronic supplementary material The online version of this chapter (doi:10. 1007/978-3-319-46448-0 11) contains supplementary material, which is available to authorized users. c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part I, LNCS 9905, pp. 178–195, 2016. DOI: 10.1007/978-3-319-46448-0 11
Person Re-Identification by Unsupervised 1 Graph Learning
(a)
179
(b)
Fig. 1. An illustration of graph learning for person re-id. (a) A graph constructed in the original low-level feature space; (b) A graph learned using the proposed model in this work. One graph node and its five connected neighbours are shown, with the neighbour capturing the same person highlighted in red. (Color figure online)
neural networks [2,36]. However, they require images of hundreds or more people to be paired across each pair of camera views which is both tedious and sometimes not possible – some people do not reappear in other camera views. This severely limits the scalability of the existing methods making them unsuitable for practical large scale Re-ID tasks. To overcome this pr
Data Loading...
