1. NCCU Academic Hub
  2. Publications
  3. College of Informatics
  4. Periodical Articles
  5. Item

Publications-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 Real-Time Video-Based Posture Monitoring Measurement of Back Angles Using YOLOv8 and Edge Detection for Strength Training
作者 謝佩璇
Hsieh, Pei-Hsuan;Choi, Hyun Sub;Hsu, Hung-Yu
貢獻者 資訊系
關鍵詞 computer vision; YOLOv8; back angle measurement; strength training; sports injury prevention
日期 2026-03
上傳時間 1-Oct-2026 15:21:18 (UTC+8)
摘要 Workout-related lower back injuries are common during strength training and are often caused by improper posture, highlighting the need for real-time posture monitoring to support injury prevention and performance optimization. This study proposes a mobile-based computer vision approach for real-time quantification of back angles during workouts. The proposed method integrates YOLOv8 instance segmentation to isolate the trunk region and applies Canny edge detection for contour extraction. It then employs a geometric formulation to identify neck and back reference points for angle computation. This hybrid design enables robust trunk localization and stable angle estimation across dynamic exercise movements. The model is evaluated on six gym-recorded videos captured with a low-cost mobile camera, achieving a mean relative error of 6.49%, comparable to video-based biomechanical assessment methods. These findings indicate that the proposed approach provides an efficient and practical solution for real-time back-posture monitoring using mobile devices, supporting safer and higher-quality daily training.
關聯 International Journal of Engineering and Technology Innovation, Vol.16, No.2, pp.163-178
資料類型 article
DOI https://doi.org/10.46604/ijeti.2026.15942
dc.contributor 資訊系
dc.creator (作者) 謝佩璇
dc.creator (作者) Hsieh, Pei-Hsuan;Choi, Hyun Sub;Hsu, Hung-Yu
dc.date (日期) 2026-03
dc.date.accessioned 1-Oct-2026 15:21:18 (UTC+8)-
dc.date.available 1-Oct-2026 15:21:18 (UTC+8)-
dc.date.issued (上傳時間) 1-Oct-2026 15:21:18 (UTC+8)-
dc.identifier.uri (URI) https://ah.lib.nccu.edu.tw/item?item_id=185562-
dc.description.abstract (摘要) Workout-related lower back injuries are common during strength training and are often caused by improper posture, highlighting the need for real-time posture monitoring to support injury prevention and performance optimization. This study proposes a mobile-based computer vision approach for real-time quantification of back angles during workouts. The proposed method integrates YOLOv8 instance segmentation to isolate the trunk region and applies Canny edge detection for contour extraction. It then employs a geometric formulation to identify neck and back reference points for angle computation. This hybrid design enables robust trunk localization and stable angle estimation across dynamic exercise movements. The model is evaluated on six gym-recorded videos captured with a low-cost mobile camera, achieving a mean relative error of 6.49%, comparable to video-based biomechanical assessment methods. These findings indicate that the proposed approach provides an efficient and practical solution for real-time back-posture monitoring using mobile devices, supporting safer and higher-quality daily training.
dc.format.extent 105 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) International Journal of Engineering and Technology Innovation, Vol.16, No.2, pp.163-178
dc.subject (關鍵詞) computer vision; YOLOv8; back angle measurement; strength training; sports injury prevention
dc.title (題名) Real-Time Video-Based Posture Monitoring Measurement of Back Angles Using YOLOv8 and Edge Detection for Strength Training
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.46604/ijeti.2026.15942
dc.doi.uri (DOI) https://doi.org/10.46604/ijeti.2026.15942