钱亚萍,王凤随,熊 磊.基于局部细化多分支与全局特征共享的
无监督行人重识别方法[J].电子测量与仪器学报,2023,37(1):106-115 |
基于局部细化多分支与全局特征共享的
无监督行人重识别方法 |
Unsupervised person re-identification method based on local refinementmulti-branch and global feature sharing |
|
DOI:10.13382/j.issn.1000-7105.2023.01.012 |
中文关键词: 行人重识别 无监督 多分支 局部细化 全局和局部特征 平均精度 |
英文关键词:person re-identification unsupervised multi-branch local refinement global and local characteristics mAP |
基金项目:安徽省自然科学基金(2108085MF197、1708085MF154)、安徽高校省级自然科学研究重点项目(KJ2019A0162)、检测技术与节能装置安徽省重点实验室开放基金(DTESD2020B02)、安徽工程大学国家自然科学基金预研项目(Xjky2022040)、安徽高校研究生科学研究项目(YJS20210448、YJS20210449)资助 |
|
Author | Institution |
Qian Yaping | 1. School of Electrical Engineering, Anhui Polytechnic University,2. Anhui Key Laboratory of Detection Technology and Energy Saving Devices,3. Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education |
Wang Fengsui | 1. School of Electrical Engineering, Anhui Polytechnic University,2. Anhui Key Laboratory of Detection Technology and Energy Saving Devices,4. Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education |
Xiong Lei | 1. School of Electrical Engineering, Anhui Polytechnic University,2. Anhui Key Laboratory of Detection Technology and Energy Saving Devices,5. Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education |
|
摘要点击次数: 423 |
全文下载次数: 874 |
中文摘要: |
无监督行人重识别因其在真实监控场景中具备良好的可扩展性而备受关注。 现有的无监督行人重识别方法主要通过
基础骨干网络获取粗略的全局特征来训练网络,很少利用局部细化分支与全局特征共享来形成更具有鉴别性的特征描述符。
本文提出一种基于局部细化多分支与全局特征共享的特征提取网络,该网络融合了粗略的全局特征和局部细化分支中的细腻
特征来获取行人多样化的特征表达。 另外,为了提升分支网络对潜在关键区域信息的捕获能力,在分支操作前放置通道细化信
息融合的注意力块来增强网络对行人特征的关注力度,执行细化特征的专注学习。 通过在 Market-1501、DukeMTMC-reID 和
MSMT17 数据集上的实验结果验证了所提方法的有效性,平均精度(mAP)分别提升了 4. 4%、3. 2%、6. 4%,其中在 Market-1501
数据集上的平均精度达到了 83. 3%。 |
英文摘要: |
Unsupervised person re-identification was attracted much attention due to its good scalability in real surveillance scenarios.
The existing unsupervised person re-identification methods mainly trained the network by obtaining rough global features through the basic
backbone network, and rarely used local refinement branches and global feature sharing to form more discriminative feature descriptors.
This paper proposed a feature extraction network based on local refinement multi-branch and global feature sharing. The network
combined rough global features and fine features in local refinement branches to obtain diverse feature expressions of person. In addition,
in order to improve the ability of the branch network to capture information of potential key areas, an attention block of channel
refinement information fusion was placed before the branch operation to enhance the network’ s attention to person features and perform
dedicated learning of refined features. The experimental results on Market-1501, DukeMTMC-reID and MSMT17 datasets verified the
effectiveness of the proposed method. The average accuracy (mAP) was improved by 4. 4%, 3. 2% and 6. 4% respectively, and the
average accuracy on Market-1501 dataset reached 83. 3%. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|