Normalized distance aggregation of discriminative features for person reidentification

Hou, Li, Han, Kang, Wan, Wanggen, Hwang, Jenq Neng, and Yao, Haiyan (2018) Normalized distance aggregation of discriminative features for person reidentification. Journal of Electronic Imaging, 27 (2). 023006.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1117/1.JEI.27.2.02300...
 
3
1


Abstract

We propose an effective person reidentification method based on normalized distance aggregation of discriminative features. Our framework is built on the integration of three high-performance discriminative feature extraction models, including local maximal occurrence (LOMO), feature fusion net (FFN), and a concatenation of LOMO and FFN called LOMO-FFN, through two fast and discriminant metric learning models, i.e., cross-view quadratic discriminant analysis (XQDA) and large-scale similarity learning (LSSL). More specifically, we first represent all the cross-view person images using LOMO, FFN, and LOMO-FFN, respectively, and then apply each extracted feature representation to train XQDA and LSSL, respectively, to obtain the optimized individual cross-view distance metric. Finally, the cross-view person matching is computed as the sum of the optimized individual cross-view distance metric through the min-max normalization. Experimental results have shown the effectiveness of the proposed algorithm on three challenging datasets (VIPeR, PRID450s, and CUHK01).

Item ID: 58624
Item Type: Article (Research - C1)
ISSN: 1560-229X
Keywords: Discriminant distance metric learning, Discriminative features, Distance aggregation, Min-max normalization, Person reidentification
Funders: National Natural Science Foundation of China (NNSFC), Shanghai Science and Technology Commission Key Project (SSTC)
Projects and Grants: NNSFC No. 61373084, NNSFC No. 61704161, SSTC No. 17511106802
Date Deposited: 16 Jun 2019 23:05
FoR Codes: 40 ENGINEERING > 4009 Electronics, sensors and digital hardware > 400999 Electronics, sensors and digital hardware not elsewhere classified @ 100%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page