Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (11): 2609-2618.DOI: 10.3778/j.issn.1673-9418.2103082

• Graphics and Image • Previous Articles     Next Articles

Person Re-identification Based on Heterogeneous Branch Correlative Features Fusion

CHEN Fan, PENG Li+()   

  1. Engineering Research Center of Internet of Things Technology Applications of the Ministry of Education, School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China
  • Received:2021-03-24 Revised:2021-06-09 Online:2022-11-01 Published:2021-06-17
  • About author:CHEN Fan, born in 1996, M.S. candidate. Her research interests include deep learning and per-son re-identification.
    PENG Li, born in 1967, Ph.D., professor, Ph.D. supervisor, member of CAAI and CCF. His re-search interests include visual Internet of things, action recognition and deep learning.
  • Supported by:
    National Key Research and Development Program of China(2018YFD0400902);National Natural Science Foundation of China(61873112);Research Fund of Ministry of Education-China Mobile(MCM20170204);Project of Jiangsu Key Construction Laboratory of IoT Application Technology(190449);Project of Jiangsu Key Construction Laboratory of IoT Application Technology(190450)

异构分支关联特征融合的行人重识别

陈璠, 彭力+()   

  1. 物联网技术应用教育部工程研究中心(江南大学 物联网工程学院),江苏 无锡 214122
  • 通讯作者: + E-mail: penglimail2002@163.com
  • 作者简介:陈璠(1996—),女,辽宁兴城人,硕士研究生,主要研究方向为深度学习、行人重识别。
    彭力(1967—),男,河北唐山人,博士,教授,博士生导师,CAAI会员,CCF会员,主要研究方向为视觉物联网、行为识别、深度学习。
  • 基金资助:
    国家重点研发计划(2018YFD0400902);国家自然科学基金(61873112);教育部-中国移动科研基金(MCM20170204);江苏省物联网应用技术重点实验室项目(190449);江苏省物联网应用技术重点实验室项目(190450)

Abstract:

Most of the multi-branch network based person re-identification (Person Re-ID) methods face the pro-blem of lack of heterogeneous features in the procedure of extraction of pedestrian features. In this paper, a novel Person Re-ID algorithm based on heterogeneous branch correlative features fusion is proposed. In the training stage, the attention-based OSNet is designed as the backbone sharing network, which can extract more significant and distinguished key features. The pedestrian features from branch network are segmented equally in the vertical axis. The relevant stripe features are extracted to utilize the synthesis information between different stripes. The heterogeneous features extraction module is designed to increase the structural diversity of the model for learning difference features. In the inference stage, multiple feature vectors are fused into a new feature vector, and the similarity judgment is performed. The effectiveness of the proposed algorithm is verified by experiments on Market-1501 and DukeMTMC-reID datasets, and the experiment results are analyzed. The proposed algorithm can improve the accuracy of Person Re-ID, and the features extracted by the model have strong robustness and discriminability.

Key words: stripe feature correlation, heterogeneous branch, feature fusion, person re-identification, deep learning

摘要:

针对行人重识别(Person Re-ID)过程中,多分支结构的网络模型在提取行人特征时缺乏异构特征的问题,提出一种异构分支关联特征融合的行人重识别算法。训练阶段,将OSNet与注意力机制相结合作为主干共享网络,以学习到具有更强显著性和区分性的行人关键特征;将分支网络输出的行人特征进行水平均等分割,再提取关联条纹特征,从而全面利用位于条纹间的综合信息;设计异构特征提取模块,以增加模型学习差异特征所需的结构多样性。推理阶段,将多个特征向量融合成一个新的特征向量,再进行相似性判断。将该方法在Market-1501、DukeMTMC-reID数据集上进行有效性实验验证并对结果进行分析,所提算法能够提高行人重识别的准确率,模型所提取的特征具有较强的鲁棒性和判别力。

关键词: 条纹特征关联, 异构分支, 特征融合, 行人重识别, 深度学习

CLC Number: