Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification

TL;DR

This paper introduces a novel person re-identification method that combines multiple feature representations, spatial and background information, and ranking aggregation techniques to improve accuracy on standard datasets.

Contribution

It proposes a comprehensive framework integrating feature extraction, post-ranking, and ranking aggregation for enhanced person re-identification performance.

Findings

Achieved 67.21% top-1 accuracy on VIPeR dataset.

Achieved 75.64% top-1 accuracy on PRID450s dataset.

Demonstrated state-of-the-art results with a combined approach.

Abstract

Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view invariant features or cross-view robust metrics. In this work, we propose to exploit a post-ranking approach and combine different feature representations through ranking aggregation. Spatial information, which potentially benefits the person matching, is represented using a 2D body model, from which color and texture information are extracted and combined. We also consider background/foreground information, automatically extracted via Deep Decompositional Network, and the usage of Convolutional Neural Network (CNN) features. To describe the matching between images we use the polynomial feature map, also taking into account local and global information. The Discriminant Context Information Analysis based post-ranking approach is used to improve initial ranking lists. Finally, the Stuart ranking aggregation method is employed to combine complementary ranking lists obtained from different feature representations. Experimental results demonstrated that we improve the state-of-the-art on VIPeR and PRID450s datasets, achieving 67.21% and 75.64% on top-1 rank recognition rate, respectively, as well as obtaining competitive results on CUHK01 dataset.