EfficientPose: Scalable single-person pose estimation

被引:45
|
作者
Groos, Daniel [1 ]
Ramampiaro, Heri [2 ]
Ihlen, Espen A. F. [1 ]
机构
[1] Norwegian Univ Sci & Technol, Dept Neuromed & Movement Sci, Trondheim, Norway
[2] Norwegian Univ Sci & Technol, Dept Comp Sci, Trondheim, Norway
关键词
Human pose estimation; Model scalability; High precision; Computational efficiency; Openly available;
D O I
10.1007/s10489-020-01918-7
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Single-person human pose estimation facilitates markerless movement analysis in sports, as well as in clinical applications. Still, state-of-the-art models for human pose estimation generally do not meet the requirements of real-life applications. The proliferation of deep learning techniques has resulted in the development of many advanced approaches. However, with the progresses in the field, more complex and inefficient models have also been introduced, which have caused tremendous increases in computational demands. To cope with these complexity and inefficiency challenges, we propose a novel convolutional neural network architecture, called EfficientPose, which exploits recently proposed EfficientNets in order to deliver efficient and scalable single-person pose estimation. EfficientPose is a family of models harnessing an effective multi-scale feature extractor and computationally efficient detection blocks using mobile inverted bottleneck convolutions, while at the same time ensuring that the precision of the pose configurations is still improved. Due to its low complexity and efficiency, EfficientPose enables real-world applications on edge devices by limiting the memory footprint and computational cost. The results from our experiments, using the challenging MPII single-person benchmark, show that the proposed EfficientPose models substantially outperform the widely-used OpenPose model both in terms of accuracy and computational efficiency. In particular, our top-performing model achieves state-of-the-art accuracy on single-person MPII, with low-complexity ConvNets.
引用
收藏
页码:2518 / 2533
页数:16
相关论文
共 50 条
  • [1] EfficientPose: Scalable single-person pose estimation
    Daniel Groos
    Heri Ramampiaro
    Espen AF Ihlen
    Applied Intelligence, 2021, 51 : 2518 - 2533
  • [2] A Comprehensive Survey on Single-Person Pose Estimation in Social Robotics
    Zhang, Feng
    Zhu, Xiatian
    Wang, Chen
    INTERNATIONAL JOURNAL OF SOCIAL ROBOTICS, 2022, 14 (09) : 1995 - 2008
  • [3] A Comprehensive Survey on Single-Person Pose Estimation in Social Robotics
    Feng Zhang
    Xiatian Zhu
    Chen Wang
    International Journal of Social Robotics, 2022, 14 : 1995 - 2008
  • [4] Knowledge Distillation for Lightweight 2D Single-Person Pose Estimation
    Zhang, Shihao
    Qiang, Baohua
    Yang, Xianyi
    Zhou, Mingliang
    Chen, Ruidong
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2023, 32 (03)
  • [5] Review on Deep Learning-Based 2D Single-Person Pose Estimation
    Su, Yanyan
    Qiu, Zhiliang
    Li, Guo
    Lu, Shenglian
    Chen, Ming
    Computer Engineering and Applications, 2024, 60 (21) : 18 - 37
  • [6] Simple Single-Person Fall Detection Model Using 3D Pose Estimation Mechanisms
    Yang, Jinmo
    Kim, R. Young Chul
    IEEE Access, 2024, 12 : 174640 - 174653
  • [7] Fast CNN-Based Single-Person 2D Human Pose Estimation for Autonomous Systems
    Papaioannidis, Christos
    Mademlis, Ioannis
    Pitas, Ioannis
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 33 (03) : 1262 - 1275
  • [8] More single-person firms
    不详
    MANUFACTURING ENGINEERING, 2007, 139 (03): : 28 - 28
  • [9] Single-person groups and globalisation
    Csanyi, V
    HUNGARIAN QUARTERLY, 2002, 43 (167): : 3 - 18
  • [10] The environment and the single-person household
    Schollmeyer, Josh
    BULLETIN OF THE ATOMIC SCIENTISTS, 2006, 62 (06) : 12 - 12