PCD-ReID: Occluded Person Re-Identification for Base Station Inspection

TL;DR

This paper introduces PCD-ReID, a Transformer-based algorithm designed to improve occluded person re-identification in surveillance, achieving significant accuracy gains by extracting shared component features from real-world patrol images.

Contribution

The paper presents a novel Transformer-based PCD network for occlusion-aware person re-identification and introduces a new real-world dataset for training and evaluation.

Findings

Achieves 79.0% mAP and 82.7% Rank-1 accuracy on the new dataset.

Outperforms ResNet50-based methods with a 15.9% improvement in Rank-1 accuracy.

Effectively handles occlusions in surveillance scenarios for practical deployment.

Abstract

Occluded pedestrian re-identification (ReID) in base station environments is a critical task in computer vision, particularly for surveillance and security applications. This task faces numerous challenges, as occlusions often obscure key body features, increasing the complexity of identification. Traditional ResNet-based ReID algorithms often fail to address occlusions effectively, necessitating new ReID methods. We propose the PCD-ReID (Pedestrian Component Discrepancy) algorithm to address these issues. The contributions of this work are as follows: To tackle the occlusion problem, we design a Transformer-based PCD network capable of extracting shared component features, such as helmets and uniforms. To mitigate overfitting on public datasets, we collected new real-world patrol surveillance images for model training, covering six months, 10,000 individuals, and over 50,000 images. Comparative experiments with existing ReID algorithms demonstrate that our model achieves a mean Average Precision (mAP) of 79.0% and a Rank-1 accuracy of 82.7%, marking a 15.9% Rank-1 improvement over ResNet50-based methods. Experimental evaluations indicate that PCD-ReID effectively achieves occlusion-aware ReID performance for personnel in tower inspection scenarios, highlighting its potential for practical deployment in surveillance and security applications.