Cross-Domain Person Re-Identification Based on Feature Fusion

Abstract

Person re-identification (ReID) is one of the commonly used criminal investigation methods in reconnaissance. Although the current ReID has achieved robust results on single domains, the focus of researches has shifted to cross-domain in recent years, which is caused by domain bias between different datasets. Generative Adversarial Networks (GAN) is used to realize the image style transfer of different datasets to alleviate the effect of cross-domain [9], [13]. However, the existing GAN-based models ignore complete expressions and occlusion of pedestrian characteristics, resulting in low accuracy in feature extraction [12], [22]. To address these issues, we introduce a cross domain model based on feature fusion (FFGAN) to fuse global, local and semantic features to extract more delicate pedestrian features. Before extracting pedestrian features, we preprocess feature maps with a feature erasure block to solve an occlusion issue. Finally, FFGAN enables a more complete visual description of pedestrian characteristics, thereby improving the accuracy of FFGAN in identifying pedestrians. Experimental results show that the effect of FFGAN is significantly improved compared with some advanced cross-domain ReID algorithms.

QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification

“…Person re-identification (re-ID) aims to retrieve the same person across a group of networking cameras, which has been widely applied in video surveillance and criminal investigation (Wang et al 2020;Luo et al 2021;Zahra et al 2023). The existing re-ID research mainly focuses on designing a single algorithm by improving the feature extraction (Ge et al 2020;Cho et al 2022), or metric learning (Yuan et al 2020;Liu et al 2022) or re-ranking (Mansouri, Ammar, and Kessentini 2021; Zhang et al 2022).…”