Improving Person Re-Identification with Temporal Constraints

TL;DR

This paper introduces a new anonymized dataset with timestamp data for person re-identification in airports, demonstrating that temporal information significantly improves identification accuracy and proposing a Bayesian re-ranking method for further gains.

Contribution

The paper presents a novel dataset with timestamp information and a Bayesian temporal re-ranking method, enabling improved person re-identification performance in real-world scenarios.

Findings

Leveraging timestamp data improves mAP by 37.43% and Rank1 by 30.22%.

Bayesian re-ranking adds an additional 10.03% mAP gain.

Dataset facilitates research combining visual and temporal cues in person re-identification.

Abstract

In this paper we introduce an image-based person re-identification dataset collected across five non-overlapping camera views in the large and busy airport in Dublin, Ireland. Unlike all publicly available image-based datasets, our dataset contains timestamp information in addition to frame number, and camera and person IDs. Also our dataset has been fully anonymized to comply with modern data privacy regulations. We apply state-of-the-art person re-identification models to our dataset and show that by leveraging the available timestamp information we are able to achieve a significant gain of 37.43% in mAP and a gain of 30.22% in Rank1 accuracy. We also propose a Bayesian temporal re-ranking post-processing step, which further adds a 10.03% gain in mAP and 9.95% gain in Rank1 accuracy metrics. This work on combining visual and temporal information is not possible on other image-based person re-identification datasets. We believe that the proposed new dataset will enable further development of person re-identification research for challenging real-world applications. DAA dataset can be downloaded from https://bit.ly/3AtXTd6