A posture evaluation system for fitness videos based on recurrent neural network

An Lun Liu, Wei Ta Chu

研究成果: Conference contribution

10 引文 斯高帕斯(Scopus)

摘要

We present a posture evaluation system especially for fitness. Given a fitness video where a user repetitively performs a movement for fitness, we first detect human posture at each video frame. The evolution of posture in consecutive frames is then characterized by a recurrent neural network (RNN). This RNN examines this movement and outputs the degree of goodness (badness). This examination is important for users because prompt inspection of bad movement avoids injury and improves effectiveness of fitness. We demonstrate that the proposed system can accurately detect bad postures when the users perform two movements called Dumbbell Lateral Raise and Biceps Curl. We believe this work is one of the very few studies of using deep neural networks for fitness evaluation.

原文English
主出版物標題Proceedings - 2020 International Symposium on Computer, Consumer and Control, IS3C 2020
發行者Institute of Electrical and Electronics Engineers Inc.
頁面185-188
頁數4
ISBN(電子)9781728193625
DOIs
出版狀態Published - 2020 11月
事件2020 International Symposium on Computer, Consumer and Control, IS3C 2020 - Taichung, Taiwan
持續時間: 2020 11月 132020 11月 16

出版系列

名字Proceedings - 2020 International Symposium on Computer, Consumer and Control, IS3C 2020

Conference

Conference2020 International Symposium on Computer, Consumer and Control, IS3C 2020
國家/地區Taiwan
城市Taichung
期間20-11-1320-11-16

All Science Journal Classification (ASJC) codes

  • 電氣與電子工程
  • 控制和優化
  • 儀器
  • 原子與分子物理與光學
  • 電腦科學應用
  • 能源工程與電力技術
  • 人工智慧

指紋

深入研究「A posture evaluation system for fitness videos based on recurrent neural network」主題。共同形成了獨特的指紋。

引用此