Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Xiaobin Hong, Tarmizi Adam, Masitah Ghazali

TL;DR

Quantitative and qualitative analysis experiments conducted on three different datasets demonstrate that the Tran‐GCN model can more accurately capture discriminative person features in monitoring videos, significantly improving identification accuracy.

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.

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

TL;DR

Quantitative and qualitative analysis experiments conducted on three different datasets demonstrate that the Tran‐GCN model can more accurately capture discriminative person features in monitoring videos, significantly improving identification accuracy.

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.
Paper Structure (22 sections, 24 equations, 3 figures, 4 tables)

This paper contains 22 sections, 24 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Feature Representation-based Methods
  4. Metric Learning-based Methods
  5. Local Features-based Methods
  6. Proposed method
  7. Overview
  8. Multi-Branch Feature Extraction Backbone
  9. Pose Estimation Learning Module
  10. ResNet Learning branch
  11. Transformer Learning branch
  12. Graph Convolutional Module (GCM)
  13. Loss Function Design
  14. Experiments and Analysis
  15. Dataset
  16. ...and 7 more sections

Figures (3)

  • Figure 1: Illustration of our proposed framework includes two parts: (1) Multi-branch Feature Extraction Backbone which extracts pedestrian multi-scale features; (2) GCM branch which performs fusing the pedestrian features from above.
  • Figure 2: Experimental results of different partitioning methods for Transformer input.)
  • Figure 3: Visualization of top-5 retrieval results of our Tran-GCN method on three datasets.