Person re-identification based on a novel mahalanobis distance feature dominated KISS metric learning

被引:4
|
作者
Zeng, Mingyong [1 ]
Wu, Zemin [1 ]
Tian, Chang [1 ]
Zhang, Lei [1 ]
Zhao, Xiaolong [2 ]
机构
[1] PLA Univ Sci & Technol, Coll Commun Engn, Nanjing 210007, Jiangsu, Peoples R China
[2] Unit 61541 PLA, Beijing 100094, Peoples R China
关键词
D O I
10.1049/el.2016.0290
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A novel and efficient method for person re-identification based on mahalabobis distance feature is proposed. This feature is built on the existing features but exhibits extraordinary discriminative power. With an additional lightweight PCA, it can be cascaded to greatly enhance the overall discrimination. Then Keep It Simple and Straightforward (KISS) metric learning is conducted on such enhanced features. The approach has been evaluated against current methods on a benchmark dataset and can reach outstanding performance.
引用
收藏
页码:1223 / 1224
页数:2
相关论文
共 50 条
  • [41] Regularized Bayesian Metric Learning for Person Re-identification
    Liong, Venice Erin
    Lu, Jiwen
    Ge, Yongxin
    [J]. COMPUTER VISION - ECCV 2014 WORKSHOPS, PT III, 2015, 8927 : 209 - 224
  • [42] Discriminative Regularized Metric Learning for Person Re-Identification
    Liong, Venice Erin
    Ge, Yongxin
    Lu, Jiwen
    [J]. 2015 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB), 2015, : 52 - 57
  • [43] Weighted Local Metric Learning for Person Re-identification
    Gu, Xinqian
    Ge, Yongxin
    [J]. BIOMETRIC RECOGNITION, 2016, 9967 : 686 - 694
  • [44] Relative Distance Metric Leaning Based on Clustering Centralization and Projection Vectors Learning for Person Re-Identification
    Ni, Tongguang
    Ding, Zongyuan
    Chen, Fuhua
    Wang, Hongyuan
    [J]. IEEE ACCESS, 2018, 6 : 11405 - 11411
  • [45] Relative Distance Metric Leaning Based on Clustering Centralization and Projection Vectors Learning for Person Re-identification
    Ni, Tongguang
    Ding, Zongyuan
    Chen, Fuhua
    Wang, Hongyuan
    [J]. COMPUTER VISION, PT I, 2017, 771 : 482 - 493
  • [46] Distance Metric Learning Using Privileged Information for Face Verification and Person Re-Identification
    Xu, Xinxing
    Li, Wen
    Xu, Dong
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (12) : 3150 - 3162
  • [47] Person Re-Identification Based on Feature Stitching
    Pan Tong
    Li Wenguo
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2019, 56 (16)
  • [48] Person Re-Identification Based on Distance Centralization and Projection Vectors Learning
    Ding, Zongyuan
    Wang, Hongyuan
    Chen, Fuhua
    Ni, Tongguang
    [J]. Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2017, 54 (08): : 1785 - 1794
  • [49] Part-based Fusion Feature Learning for Person Re-Identification
    Prakayaphun, Titipakorn
    Usanavasin, Sasiporn
    [J]. 2019 FIRST INTERNATIONAL CONFERENCE ON SMART TECHNOLOGY & URBAN DEVELOPMENT (STUD), 2019, : 83 - 87
  • [50] A GENERAL RE-RANKING METHOD BASED ON METRIC LEARNING FOR PERSON RE-IDENTIFICATION
    Xu, Tongkun
    Zhao, Xin
    Hou, Jiamin
    Zhang, Jiyong
    Hao, Xinhong
    Yin, Jian
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2020,