An effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA) are proposed for person re-identification. The LOMO feature analyzes the horizontal occurrence of local features, and maximizes the occurrence to make a stable representation against viewpoint changes.
Besides, to handle illumination variations, we apply the Retinex transform and the Scale Invariant Local Ternary Pattern (SILTP). To learn a discriminant metric, we propose to learn a discriminant low dimensional subspace by cross-view quadratic discriminant analysis, and simultaneously, a QDA metric is learned on the derived subspace. We also present a practical computation method for XQDA, as well as its regularization. Experiments on four challenging person re-identification databases, VIPeR, QMUL GRID, CUHK Campus, and CUHK03, show that the proposed method improves the state-of-the-art rank-1 identification rates by 2.2\%, 4.88\%, 28.91\%, and 31.55\% on the four databases, respectively.
- Source code: LOMO_XQDA.zip
- Extracted features: lomo_viper+grid.zip cuhk01_lomo.mat cuhk03_labeled_lomo.mat cuhk03_detected_lomo.mat
Table 1. Summary of results (%) for the proposed LOMO+XQDA algorithm
|Database||Rank 1||Rank 5||Rank 10||Rank 15||Rank 20|
Note: the source code package contains the CMC curves for performance plot.
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences.
Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z. Li, “Person Re-identification by Local Maximal Occurrence Representation and Metric Learning.” In IEEE International Conference on Computer Vision and Pattern Recognition, June 7-12, Boston, Massachusetts, USA, 2015. [pdf]
Last updated: May 7, 2015