3D PostureNet: A unified framework for skeleton-based posture recognition

被引:24
作者
Liu, Jianbo [1 ,2 ]
Wang, Ying [1 ]
Liu, Yongcheng [1 ,2 ]
Xiang, Shiming [1 ]
Pan, Chunhong [1 ]
机构
[1] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
[2] Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
基金
中国国家自然科学基金;
关键词
Human posture recognition; Static hand gesture recognition; Skeleton-based; 3D convolutional neural network; SYSTEM;
D O I
10.1016/j.patrec.2020.09.029
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Image-based posture recognition is a very challenging problem as it is difficult to acquire rich 3D information from postures in 2D images. Existing methods founded on 3D skeleton cues could alleviate this issue, but they are not particularly efficient due to the application of handcrafted features and traditional classifiers. This paper presents a novel and unified framework for skeleton-based posture recognition, applying powerful 3D Convolutional Neural Network (CNN) to this issue. Technically, bounding-box-based normalization for the raw skeleton data is proposed to eliminate the coordinate differences caused by diverse recording environments and posture displacements. Moreover, Gaussian voxelization for the skeleton is employed to expressively represent the posture configuration. Thereby, an end-to-end framework based on 3D CNN, called 3D PostureNet, is developed for robust posture recognition. To verify its effectiveness, a large-scale writing posture dataset is created and released in this work, including 113,400 samples of 30 subjects with 15 postures. Extensive experiments on the public MSRA hand gesture dataset, body pose dataset and the proposed writing posture dataset demonstrate that 3D PostureNet achieves significantly superior performance on both skeleton-based human posture and hand posture recognition tasks. (C) 2020 Elsevier B.V. All rights reserved.
引用
收藏
页码:143 / 149
页数:7
相关论文
共 50 条
[31]   Dynamic Semantic-Based Spatial-Temporal Graph Convolution Network for Skeleton-Based Human Action Recognition [J].
Xie, Jianyang ;
Meng, Yanda ;
Zhao, Yitian ;
Nguyen, Anh ;
Yang, Xiaoyun ;
Zheng, Yalin .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 :6691-6704
[32]   3D Fingerprint Recognition based on Ridge-Valley-Guided 3D Reconstruction and 3D Topology Polymer Feature Extraction [J].
Yin, Xuefei ;
Zhu, Yanming ;
Hu, Jiankun .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (03) :1085-1091
[33]   A Discriminative Dual-Stream Model With a Novel Sustained Attention Mechanism for Skeleton-Based Human Action Recognition [J].
Liang, Zhihong ;
Shi, Xiaoshan ;
Zhang, Yanxin ;
Liu, Bo .
IEEE ACCESS, 2020, 8 (08) :208395-208406
[34]   Multi-stream P&U adaptive graph convolutional networks for skeleton-based action recognition [J].
Chen, Minglong ;
Liang, Jiuzhen ;
Liu, Hao .
JOURNAL OF SUPERCOMPUTING, 2024, 80 (08) :11614-11639
[35]   Multi-stream P&U adaptive graph convolutional networks for skeleton-based action recognition [J].
Minglong Chen ;
Jiuzhen Liang ;
Hao Liu .
The Journal of Supercomputing, 2024, 80 :11614-11639
[36]   Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR) [J].
Mehmood, Faisal ;
Guo, Xin ;
Chen, Enqing ;
Akbar, Muhammad Azeem ;
Khan, Arif Ali ;
Ullah, Sami .
COMPUTERS IN HUMAN BEHAVIOR, 2025, 163
[37]   Ergonomic posture recognition using 3D view-invariant features from single ordinary camera [J].
Zhang, Hong ;
Yan, Xuzhong ;
Li, Heng .
AUTOMATION IN CONSTRUCTION, 2018, 94 :1-10
[38]   Skeleton-Based Violation Action Recognition Method for Safety Supervision in Operation Field of Distribution Network Based on Graph Convolutional Network [J].
Wang, Bo ;
Ma, Fuqi ;
Jia, Rong ;
Luo, Peng ;
Dong, Xuzhu .
CSEE JOURNAL OF POWER AND ENERGY SYSTEMS, 2023, 9 (06) :2179-2187
[39]   Building a Gait Analysis Framework for Parkinson's Disease Patients: Motion Capture and Skeleton 3D Representation [J].
Pachoulakis, Ioannis ;
Kourmoulis, Konstantinos .
2014 INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND MULTIMEDIA (TEMU), 2014, :220-225
[40]   Stereo-based palmprint recognition in various 3D postures [J].
Bingol, Ozkan ;
Ekinci, Murat .
EXPERT SYSTEMS WITH APPLICATIONS, 2017, 78 :74-88