Exploring hard joints mining via hourglass-based generative adversarial network for human pose estimation

被引:4
|
作者
Zhu, Aichun [1 ]
Zhang, Sai [2 ]
Huang, Yaoying [1 ]
Hu, Fangqiang [1 ]
Cui, Ran [2 ]
Hua, Gang [2 ]
机构
[1] Nanjing Tech Univ, Sch Comp Sci & Technol, Nanjing 210000, Jiangsu, Peoples R China
[2] China Univ Min & Technol, Sch Informat & Control Engn, Xuzhou 221000, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
Behavioral research - Mining - Backpropagation - Human computer interaction;
D O I
10.1063/1.5080207
中图分类号
TB3 [工程材料学];
学科分类号
0805 ; 080502 ;
摘要
Human pose estimation has broad application prospects in the fields of human behavior recognition and human-computer interaction. Although the current human pose estimation methods have made tremendous progress, the partial occlusion of human bodies still remains a challenging problem. In this paper, we address the challenging joints in human bodies by the hard joints mining technique. The proposed hard joints mining method is based on the generative adversarial network, which consists of two stacked hourglasses with a similar architecture: the generator and the discriminator. During the training period, the discriminator distinguishes the generated heatmaps from the ground-truth heatmaps and introduces the adversarial loss to the generator through back-propagation to induce generator generates a more reasonable prediction. Moreover, the hard joints mining technique is used to focus the training attention on the difficult joint points in the generator. Finally, the experimental results demonstrate the effectiveness of the proposed approach for human pose estimation on Leeds Sports Pose (LSP) Dataset, LSP-extended datasets and MPII Human Pose Datasets. (C) 2019 Author(s).
引用
收藏
页数:8
相关论文
共 50 条
  • [21] An adversarial human pose estimation network injected with graph structure
    Tian, Lei
    Wang, Peng
    Liang, Guoqiang
    Shen, Chunhua
    PATTERN RECOGNITION, 2021, 115
  • [22] Human Pose Estimation of Diver Based on Improved Stacked Hourglass Model
    Lei, Fei
    Yan, Junyou
    Wang, Xueli
    ICVIP 2019: PROCEEDINGS OF 2019 3RD INTERNATIONAL CONFERENCE ON VIDEO AND IMAGE PROCESSING, 2019, : 178 - 182
  • [23] Combining fractal hourglass network and skeleton joints pairwise affinity for multi-person pose estimation
    Yanmin Luo
    Zhitong Xu
    Peizhong Liu
    Yongzhao Du
    Jingming Guo
    Multimedia Tools and Applications, 2019, 78 : 7341 - 7363
  • [24] Combining fractal hourglass network and skeleton joints pairwise affinity for multi-person pose estimation
    Luo, Yanmin
    Xu, Zhitong
    Liu, Peizhong
    Du, Yongzhao
    Guo, Jingming
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (06) : 7341 - 7363
  • [25] Multi-Pose Facial Expression Recognition Based on Generative Adversarial Network
    Li, Dejian
    Li, Zejian
    Luo, Ruiming
    Deng, Jia
    Sun, Shouqian
    IEEE ACCESS, 2019, 7 : 143980 - 143989
  • [26] PFA-GAN: Pose Face Augmentation Based on Generative Adversarial Network
    Zeno, Bassel
    Kalinovskiy, Ilya
    Matveev, Yuri
    INFORMATICA, 2021, 32 (02) : 425 - 440
  • [27] 3D Human Pose Dataset Augmentation Using Generative Adversarial Network
    Shangguan, Huyuan
    Mukundan, Ramakrishnan
    ICGSP '19 - PROCEEDINGS OF THE 2019 3RD INTERNATIONAL CONFERENCE ON GRAPHICS AND SIGNAL PROCESSING, 2019, : 53 - 57
  • [28] Graph Convolutional Adversarial Network for Human Body Pose and Mesh Estimation
    Huang, Yuancheng
    Xiao, Nanfeng
    IEEE ACCESS, 2020, 8 : 215419 - 215425
  • [29] Multi-scale information transport generative adversarial network for human pose transfer ☆
    Zhang, Jinsong
    Lai, Yu-Kun
    Ma, Jian
    Li, Kun
    DISPLAYS, 2024, 84
  • [30] Smart Multimodal In-Bed Pose Estimation Framework Incorporating Generative Adversarial Neural Network
    Singh, Sumit
    Anisi, Mohammad Hossein
    Jindal, Anish
    Jarchi, Delaram
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (06) : 3379 - 3388