Multi Channel-Kernel Canonical Correlation Analysis for Cross-View Person Re-Identification
This addresses the problem of identifying persons across different camera views in surveillance systems, but it is incremental as it builds on existing methods with feature and kernel variations.
The paper tackles cross-view appearance changes in person re-identification by using multiple feature representations with Kernel Canonical Correlation Analysis and iterative logistic regression, achieving comparable performance on VIPeR and PRID 450s datasets and improvements on PRID and CUHK01 datasets.
In this paper we introduce a method to overcome one of the main challenges of person re-identification in multi-camera networks, namely cross-view appearance changes. The proposed solution addresses the extreme variability of person appearance in different camera views by exploiting multiple feature representations. For each feature, Kernel Canonical Correlation Analysis (KCCA) with different kernels is exploited to learn several projection spaces in which the appearance correlation between samples of the same person observed from different cameras is maximized. An iterative logistic regression is finally used to select and weigh the contributions of each feature projections and perform the matching between the two views. Experimental evaluation shows that the proposed solution obtains comparable performance on VIPeR and PRID 450s datasets and improves on PRID and CUHK01 datasets with respect to the state of the art.