Localized multi-kernel discriminative canonical correlation analysis for video-based person re-identification

Guangyi Chen, Jiwen Lu, Jianjiang Feng, Jie Zhou

Abstract

This paper presents a localized multi-kernel discriminative canonical correlation analysis (LMKDCCA) approach for video-based person re-identification, which aims to match persons from pedestrian videos captured by non-overlapping cameras. Unlike conventional methods, our approach models each pedestrian video as a point on the Riemannian manifold and learns similarity over these points under the multiple kernel learning framework. For each given person video, we first represent it as a symmetric positive definite (SPD) matrix which lies on a Riemannian manifold and compute the similarity of multiple SPDs. Then, we develop an LMKDCCA algorithm to learn a nonlinear distance metric which effectively combines these SPDs to exploit complementary information for similarity measure. Experimental results on the iLIDS-VID and PRID 2011 datasets show that our approach achieves the state-of-the-arts.
BibTeX
@inproceedings{chen2017localized,
  author = {Guangyi Chen and Jiwen Lu and Jianjiang Feng and Jie Zhou},
  title = {{Localized multi-kernel discriminative canonical correlation analysis for video-based person re-identification}},
  booktitle = {ICIP},
  year = {2017},
  doi = {10.1109/icip.2017.8296253},
}

Loading related content...

Figure