Saliency Weighted Features for Person Re-identification

Niki Martinel, Christian Micheloni, Gian Luca Foresti

Abstract: In this work we propose a novel person re-identification approach. The solution, inspired by human gazing capabilities, wants to identify the salient regions of a given person. Such regions are used as a weighting tool in the image feature extraction process. Then, such novel representation is combined with a set of other visual features in a pairwise-based multiple metric learning framework. Finally, the learned metrics are fused to get the distance between image pairs and to re-identify a person. The proposed method is evaluated on three different benchmark datasets and compared with best state-of-the-art approaches to show its overall superior performance.