EPAN: Robust Pedestrian Re-Identification via Enhanced Alignment Network for IoT Surveillance

TL;DR

This paper presents EPAN, a novel deep learning architecture designed to improve pedestrian re-identification accuracy in IoT surveillance by effectively handling perspective and environmental variations.

Contribution

EPAN introduces a dual-branch network that enhances alignment and feature extraction for robust person re-identification in diverse IoT surveillance scenarios.

Findings

Achieved 90.09% Rank-1 accuracy on Inspection-Personnel dataset.

Attained 78.82% mean Average Precision (mAP).

Demonstrated strong real-world IoT application potential.

Abstract

Person re-identification (ReID) plays a pivotal role in computer vision, particularly in surveillance and security applications within IoT-enabled smart environments. This study introduces the Enhanced Pedestrian Alignment Network (EPAN), tailored for robust ReID across diverse IoT surveillance conditions. EPAN employs a dual-branch architecture to mitigate the impact of perspective and environmental changes, extracting alignment information under varying scales and viewpoints. Here, we demonstrate EPAN's strong feature extraction capabilities, achieving outstanding performance on the Inspection-Personnel dataset with a Rank-1 accuracy of 90.09% and a mean Average Precision (mAP) of 78.82%. This highlights EPAN's potential for real-world IoT applications, enabling effective and reliable person ReID across diverse cameras in surveillance and security systems. The code and data are available at: https://github.com/ggboy2580/EPAN