Share Email Print
cover

Proceedings Paper

Multi-patch matching for person re-identification
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Recognizing a target object across non-overlapping distributed cameras is known in the computer vision community as the problem of person re-identification. In this paper, a multi-patch matching method for person reidentification is presented. Starting from the assumption that: the appearance (clothes) of a person does not change during the time of passing in different cameras field of view , which means the regions with the same color in target image will be identical while crossing cameras. First, we extract distinctive features in the training procedure, where each image target is devised into small patches, the SIFT features and LAB color histograms are computed for each patch. Then we use the KNN approach to detect group of patches with high similarity in the target image and then we use a bi-directional weighted group matching mechanism for the re-identification. Experiments on a challenging VIPeR dataset show that the performances of the proposed method outperform several baselines and state of the art approaches.

Paper Details

Date Published: 5 August 2015
PDF: 7 pages
Proc. SPIE 9622, 2015 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology, 96220F (5 August 2015); doi: 10.1117/12.2193303
Show Author Affiliations
Hocine Labidi, Beijing Institute of Technology (China)
Sen-Lin Luo, Beijing Institute of Technology (China)
Mohamed Bachir Boubekeur, Beijing Institute of Technology (China)
Tarek Benlefki, Beihang Univ. (China)


Published in SPIE Proceedings Vol. 9622:
2015 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology
Guangming Shi; Xuelong Li; Bormin Huang, Editor(s)

© SPIE. Terms of Use
Back to Top