期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 31, 期 -, 页码 4651-4662出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2022.3186759
关键词
Occluded person re-identification; transformer; graph; occlusion recovery
资金
- National Natural Science Foundation of China [U1836217]
- Beijing Nova Program [Z211100002121108]
This paper proposes a new approach called FRT to address the challenges of occluded person re-identification. It utilizes visibility graph matching and feature recovery transformer to reduce noise interference during feature matching and recover complete features based on graph similarity. Extensive experiments demonstrate the effectiveness of FRT, outperforming state-of-the-art results on challenging datasets.
One major issue that challenges person re-identification (Re-ID) is the ubiquitous occlusion over the captured persons. There are two main challenges for the occluded person Re-ID problem, i.e., the interference of noise during feature matching and the loss of pedestrian information brought by the occlusions. In this paper, we propose a new approach called Feature Recovery Transformer (FRT) to address the two challenges simultaneously, which mainly consists of visibility graph matching and feature recovery transformer. To reduce the interference of the noise during feature matching, we mainly focus on visible regions that appear in both images and develop a visibility graph to calculate the similarity. In terms of the second challenge, based on the developed graph similarity, for each query image, we propose a recovery transformer that exploits the feature sets of its k-nearest neighbors in the gallery to recover the complete features. Extensive experiments across different person Re-ID datasets, including occluded, partial and holistic datasets, demonstrate the effectiveness of FRT. Specifically, FRT significantly outperforms state-of-the-art results by at least 6.2% Rank- 1 accuracy and 7.2% mAP scores on the challenging Occluded-Duke dataset.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据