Embedding Deep Metric for Person Re-identification: A Study Against Large Variations
Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the current convol
- PDF / 4,574,960 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 108 Downloads / 163 Views
3
National Laboratory of Pattern Recognition and Center for Biometrics and Security Research, Institute of Automation, Chinese Academy of Sciences, Beijing, China {hailin.shi,yang.yang,xiangyu.zhu,scliao,zlei,szli}@nlpr.ia.ac.cn 2 University of Chinese Academy of Sciences, Beijing, China School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China
Abstract. Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the current convolutional neural networks (CNN)’s capability of feature extraction. However, the distribution is unknown, so it is difficult to use the geodesic distance when comparing two samples. In practice, the current deep embedding methods use the Euclidean distance for the training and test. On the other hand, the manifold learning methods suggest to use the Euclidean distance in the local range, combining with the graphical relationship between samples, for approximating the geodesic distance. From this point of view, selecting suitable positive (i.e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations. In this paper, we propose a novel moderate positive sample mining method to train robust CNN for person re-identification, dealing with the problem of large variation. In addition, we improve the learning by a metric weight constraint, so that the learned metric has a better generalization ability. Experiments show that these two strategies are effective in learning robust deep metrics for person re-identification, and accordingly our deep model significantly outperforms the state-of-the-art methods on several benchmarks of person re-identification. Therefore, the study presented in this paper may be useful in inspiring new designs of deep models for person re-identification. Keywords: Person re-identification
1
· Deep learning · CNN
Introduction
Given a set of pedestrian images, person re-identification aims to identify the probe image that generally captured by different cameras. Nowadays, person re-identification becomes increasingly important for surveillance and security c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part I, LNCS 9905, pp. 732–748, 2016. DOI: 10.1007/978-3-319-46448-0 44
Embedding Deep Metric for Person Re-identification
733
system, e.g. replacing manual video screening and other heavy loads. Person reidentification is a challenging task due to large variations of body pose, lighting, view angles, scenarios across time and cameras. The framework of existing methods usually consists of two parts: (1) extracting discriminative features from pedestrian images; (2) computing the distance of samples by feature comparison. There are many works focus on these two aspects. The traditional methods work at improving suitable hand-crafted features [34,41], or good met
Data Loading...
