Tran-GCN: A Transformer-Enhanced Graph Convolutional Network for Person Re-Identification in Monitoring Videos

TL;DR

This paper introduces Tran-GCN, a novel model combining transformer, graph convolution, and pose estimation to enhance person re-identification accuracy in monitoring videos by effectively capturing local and global features.

Contribution

The paper presents a Transformer-enhanced Graph Convolutional Network that integrates pose estimation, global dependency learning, and local feature extraction for improved person Re-ID.

Findings

Significantly improves identification accuracy on multiple datasets.

Effectively captures pose and local feature relationships.

Outperforms existing methods in challenging scenarios.

Abstract

Person Re-Identification (Re-ID) has gained popularity in computer vision, enabling cross-camera pedestrian recognition. Although the development of deep learning has provided a robust technical foundation for person Re-ID research, most existing person Re-ID methods overlook the potential relationships among local person features, failing to adequately address the impact of pedestrian pose variations and local body parts occlusion. Therefore, we propose a Transformer-enhanced Graph Convolutional Network (Tran-GCN) model to improve Person Re-Identification performance in monitoring videos. The model comprises four key components: (1) A Pose Estimation Learning branch is utilized to estimate pedestrian pose information and inherent skeletal structure data, extracting pedestrian key point information; (2) A Transformer learning branch learns the global dependencies between fine-grained and semantically meaningful local person features; (3) A Convolution learning branch uses the basic ResNet architecture to extract the person's fine-grained local features; (4) A Graph Convolutional Module (GCM) integrates local feature information, global feature information, and body information for more effective person identification after fusion. Quantitative and qualitative analysis experiments conducted on three different datasets (Market-1501, DukeMTMC-ReID, and MSMT17) demonstrate that the Tran-GCN model can more accurately capture discriminative person features in monitoring videos, significantly improving identification accuracy.