A Person Re-Identification System For Mobile Devices

TL;DR

This paper introduces a practical person re-identification system designed for mobile devices that uses high-level semantic features from RGB and depth data to improve robustness and adaptability in dynamic environments.

Contribution

It presents a novel mobile framework combining RGB and depth cues for person re-identification, addressing computational efficiency and robustness issues of prior methods.

Findings

Preliminary results on BIWI dataset are promising.

The system demonstrates robustness to noise and illumination variations.

Potential for deployment in areas lacking fixed sensor infrastructure.

Abstract

Person re-identification is a critical security task for recognizing a person across spatially disjoint sensors. Previous work can be computationally intensive and is mainly based on low-level cues extracted from RGB data and implemented on a PC for a fixed sensor network (such as traditional CCTV). We present a practical and efficient framework for mobile devices (such as smart phones and robots) where high-level semantic soft biometrics are extracted from RGB and depth data. By combining these cues, our approach attempts to provide robustness to noise, illumination, and minor variations in clothing. This mobile approach may be particularly useful for the identification of persons in areas ill-served by fixed sensors or for tasks where the sensor position and direction need to dynamically adapt to a target. Results on the BIWI dataset are preliminary but encouraging. Further evaluation and demonstration of the system will be available on our website.