We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于姿态估计和 Transformer 模型的遮挡行人重识别.
- Authors
陈禹; 刘慧; 梁东升; 张雷
- Abstract
Person re-identification ( ReID) is a technology that utilizes artificial intelligence to solve public safety application problems such as border inspection and personnel tracking. It has the ability to identify a specific person from images collected across devices. However, in person tracking and other issues, deliberate person occlusion and complex scene environment occlusion greatly increases the difficulty of person re-identification. An improved person re-identification network PT-Net based on ResNet50 network was proposed, which combined with pose estimation and Transformer models to improve the person re-identification ability under occlusion conditions. The existing pose estimation method was utilized to detect key-points in the input image, and combined the key-point information with the person feature maps to generate a pose based person feature representation. Then, the Transformer model was used to encode the pose-based person feature representation for feature alignment and fusion. Based on the internationally available dataset Occluded-Duke, the experimental validation was conducted. The results show that the PT-Net method improves its mean average precision(mAP) and similarity ranking Rank-1 increase by 1. 3, 1. 5 percentage points compared to the baseline model, respectively, verifying the effectiveness and superiority of the method.
- Publication
Science Technology & Engineering, 2024, Vol 24, Issue 12, p5051
- ISSN
1671-1815
- Publication type
Article
- DOI
10.12404/j.issn.1671-1815.2303944