Deep Learning Pose Estimation for Kinematics Measurement in Archery

被引：1
作者：
Phang, Jonathan Then Sien [1 ]
Lim, King Hann [1 ]
Lease, Basil Andy [1 ]
Chiam, Dar Hung [1 ]
机构：
[1] Curtin Univ Malaysia, Curtin Malaysia Res Inst, CDT 250, Miri Sarawak, Malaysia
来源：
2022 INTERNATIONAL CONFERENCE ON GREEN ENERGY, COMPUTING AND SUSTAINABLE TECHNOLOGY (GECOST) | 2022年
关键词：
Kinematic; Archery; Sport Science; Joint Information; Pose Estimation; Deep Learning;
D O I：
10.1109/GECOST55694.2022.10010619
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
Posture control is crucial in archery to achieve consistent and accurate arrow release on target shooting. Application of correct posture and joint motion can prevent undesired injuries and effectively reduces rapid fatigue in muscles. By using a markerless motion capture system, it can identify the posture and joint motion of archers between shooting performances and physical capacities with minimal interference on the archer. In this paper, a deep learning pose estimation approach is applied to retrieve joint information of an archer for in-depth posture and motion analysis. The posture of professional archers with average age of 17.3 are recorded as the samples of this study. Important parameters and joints, particularly the angles and its consistencies are analyzed to study archers shooting performances. In addition, an algorithm is proposed in this study to automate the determination of archer's anchoring and release sequence. Several qualitative results of joint kinematics and parameters and visualization are presented to further understand the bio-mechanical aspect of archery.
引用
收藏
页码：298 / 302
页数：5
相关论文
共 50 条
  • [31] Deep 1D Landmark Representation Learning for Space Target Pose Estimation
    Liu, Shengli
    Zhu, Xiaowen
    Cao, Zewei
    Wang, Gang
    REMOTE SENSING, 2022, 14 (16)
  • [32] Across-Species Pose Estimation in Poultry Based on Images Using Deep Learning
    Doornweerd, Jan Erik
    Kootstra, Gert
    Veerkamp, Roel F.
    Ellen, Esther D.
    van der Eijk, Jerine A. J.
    van de Straat, Thijs
    Bouwman, Aniek C.
    FRONTIERS IN ANIMAL SCIENCE, 2021, 2
  • [33] Human Pose Estimation Using Deep Learning: A Systematic Literature Review
    Samkari, Esraa
    Arif, Muhammad
    Alghamdi, Manal
    Al Ghamdi, Mohammed A.
    MACHINE LEARNING AND KNOWLEDGE EXTRACTION, 2023, 5 (04): : 1612 - 1659
  • [34] Human pose, hand and mesh estimation using deep learning: a survey
    Toshpulatov, Mukhiddin
    Lee, Wookey
    Lee, Suan
    Roudsari, Arousha Haghighian
    JOURNAL OF SUPERCOMPUTING, 2022, 78 (06) : 7616 - 7654
  • [35] Pose Estimation for Non-cooperative Spacecraft based on Deep Learning
    Huan, Wenxiu
    Liu, Mingmin
    Hu, Qinglei
    PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE, 2020, : 3339 - 3343
  • [36] NEMA: 6-DoF Pose Estimation Dataset for Deep Learning
    Roman, Philippe Perez de San
    Desbarats, Pascal
    Domenger, Jean-Philippe
    Buendia, Axel
    PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 4, 2022, : 682 - 690
  • [37] 3D Pose Estimation of Markerless Fish on Deep Learning
    Wang, Yuanchang
    Cao, Jianrong
    Wang, Ming
    Zhao, Qianchuan
    Gao, He
    NEURAL COMPUTING FOR ADVANCED APPLICATIONS, NCAA 2024, PT I, 2025, 2181 : 261 - 274
  • [38] Deep Learning-based Pose Estimation for Mobile Manipulator Tasks
    Kim, Hae-Chang
    Yoon, In-Hwan
    Song, Jae-Bok
    TRANSACTIONS OF THE KOREAN SOCIETY OF MECHANICAL ENGINEERS A, 2021, 45 (12) : 1161 - 1166
  • [39] Crane pose estimation using deep learning models and synthetic images
    Park G.
    Hong H.
    Jeong H.
    Kang H.
    Won M.
    Journal of Institute of Control, Robotics and Systems, 2021, 27 (04) : 312 - 319
  • [40] A deep learning approach for pose estimation from volumetric OCT data
    Gessert, Nils
    Schlueter, Matthias
    Schlaefer, Alexander
    MEDICAL IMAGE ANALYSIS, 2018, 46 : 162 - 179
12345