Please login first

  • Open Access
  • 5 Reads
  • 0 Citations
  • 0 Recommendations

Person Re-identification by Null Space Marginal Fisher Analysis
Husheng Dong 1 , Shengrong Gong 2 , Chunping Liu 3 , Yi Ji 4 , Mengfei Li 4

1  1.School of Computer Science and Technology, Soochow University;2.Suzhou Institute of Trade and Commerce
2  1.Changshu Institute of Science and Technology;2.School of Computer Science and Technology, Soochow University
3  1.School of Computer Science and Technology, Soochow University;2.Collaborative Innovation Center of Novel Software Technology and Industrialization;3.Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin Univers
4  School of Computer Science and Technology, Soochow University

Published: 01 January 2017 by MDPI AG in Proceedings of MOL2NET 2016, International Conference on Multidisciplinary Sciences, 2nd edition in MOL2NET 2016, International Conference on Multidisciplinary Sciences, 2nd edition
MDPI AG, 10.3390/mol2net-02-03856
Abstract:

For better describing pedestrian’s appearance, the feature representations used in person re-identification are usually of high dimension - typically amounting to thousands or even higher. However, this incurs the typical Small Sample Size (SSS) problem, i.e., the number of training samples in most re-identification datasets is much smaller than the feature dimension. Although some dimension reduction techniques or metric regularization could be applied to alleviate this problem, they may result in the loss of discriminative power.

In this work, we propose to overcome SSS problem by embedding training samples into a discriminative null space based on Marginal Fisher Analysis (MFA). In such a null space, the within-class distribution of the images of the same pedestrian will shrink to a single point, resulting the extreme fisher analysis criterion. We theoretically analyze the subspace where the discriminant vectors lie on and derive a closed-form solution. Furthermore, we also extend the proposed method to nonlinear domain via the kernel trick. Experiments on VIPeR, PRID450S and 3DPes benchmark datasets show that our method achieves 56.30%, 76.80% and 66.88% rank-1 matching rates respectively, outperforming the state-of-the-art results by 2.74%, 15.38% and 9.59%.


Comments on this paper Get comment updates
Currently there are no comments available.