Frontal plane spatial and temporal gait assessment using MediaPipe pose
Gait analysis is a vital field in biomechanics, focusing on studying human walking patterns and movement. Traditional methods relied on visual observation, lacking accuracy and objectivity. Instrumented gait analysis improved measurements using specialized equipment like motion capture systems and w...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2024
|
| Online Access: | http://journalarticle.ukm.my/25562/ http://journalarticle.ukm.my/25562/1/kejut_22.pdf |
| _version_ | 1848816390995181568 |
|---|---|
| author | Hii, Chang Soon Tony Gan, Kok Beng You, Huay Woon Nasharuddin Zainal, Norlinah Mohamed Ibrahim, Shahrul Azmin, |
| author_facet | Hii, Chang Soon Tony Gan, Kok Beng You, Huay Woon Nasharuddin Zainal, Norlinah Mohamed Ibrahim, Shahrul Azmin, |
| author_sort | Hii, Chang Soon Tony |
| building | UKM Institutional Repository |
| collection | Online Access |
| description | Gait analysis is a vital field in biomechanics, focusing on studying human walking patterns and movement. Traditional methods relied on visual observation, lacking accuracy and objectivity. Instrumented gait analysis improved measurements using specialized equipment like motion capture systems and wearable sensors, but had limitations due to cost, and markers or sensors interfering with natural movement. The field underwent a significant transformation with the advent of markerless pose estimation-based gait analysis, which harnessed computer vision methodologies to monitor human movement without the requirement for specialized equipment, delivering a cost-effective and easily accessible analysis in real-world environments. However, it still faces challenges, including limitations in the sagittal plane and reliance on computationally demanding models like OpenPose. This study introduced a novel frontal plane gait analysis approach using the lightweight MediaPipe Pose model and a single camera setup. The objective is to evaluate the feasibility, and accuracy of MediaPipe Pose by comparing it to the established 3D Vicon motion capture system. The proposed approach tracked body keypoints during gait, detected gait events based on ankle depth changes and vertical difference between left and right ankles, and calculated gait parameters. The findings demonstrated that MediaPipe Pose-based gait analysis showed promise for accurately analyzing gait parameters in the frontal plane with low mean absolute error (0.00–0.30). Combining this method with satellite technology enhances e-health by facilitating teleconsultations, remote diagnostics, and extending healthcare services to disaster-stricken or remote areas. |
| first_indexed | 2025-11-15T01:05:07Z |
| format | Article |
| id | oai:generic.eprints.org:25562 |
| institution | Universiti Kebangasaan Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T01:05:07Z |
| publishDate | 2024 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | oai:generic.eprints.org:255622025-07-14T08:27:59Z http://journalarticle.ukm.my/25562/ Frontal plane spatial and temporal gait assessment using MediaPipe pose Hii, Chang Soon Tony Gan, Kok Beng You, Huay Woon Nasharuddin Zainal, Norlinah Mohamed Ibrahim, Shahrul Azmin, Gait analysis is a vital field in biomechanics, focusing on studying human walking patterns and movement. Traditional methods relied on visual observation, lacking accuracy and objectivity. Instrumented gait analysis improved measurements using specialized equipment like motion capture systems and wearable sensors, but had limitations due to cost, and markers or sensors interfering with natural movement. The field underwent a significant transformation with the advent of markerless pose estimation-based gait analysis, which harnessed computer vision methodologies to monitor human movement without the requirement for specialized equipment, delivering a cost-effective and easily accessible analysis in real-world environments. However, it still faces challenges, including limitations in the sagittal plane and reliance on computationally demanding models like OpenPose. This study introduced a novel frontal plane gait analysis approach using the lightweight MediaPipe Pose model and a single camera setup. The objective is to evaluate the feasibility, and accuracy of MediaPipe Pose by comparing it to the established 3D Vicon motion capture system. The proposed approach tracked body keypoints during gait, detected gait events based on ankle depth changes and vertical difference between left and right ankles, and calculated gait parameters. The findings demonstrated that MediaPipe Pose-based gait analysis showed promise for accurately analyzing gait parameters in the frontal plane with low mean absolute error (0.00–0.30). Combining this method with satellite technology enhances e-health by facilitating teleconsultations, remote diagnostics, and extending healthcare services to disaster-stricken or remote areas. Penerbit Universiti Kebangsaan Malaysia 2024-07 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/25562/1/kejut_22.pdf Hii, Chang Soon Tony and Gan, Kok Beng and You, Huay Woon and Nasharuddin Zainal, and Norlinah Mohamed Ibrahim, and Shahrul Azmin, (2024) Frontal plane spatial and temporal gait assessment using MediaPipe pose. Jurnal Kejuruteraan, 36 (4). pp. 1561-1574. ISSN 0128-0198 https://www.ukm.my/jkukm/volume-3604-2024/ |
| spellingShingle | Hii, Chang Soon Tony Gan, Kok Beng You, Huay Woon Nasharuddin Zainal, Norlinah Mohamed Ibrahim, Shahrul Azmin, Frontal plane spatial and temporal gait assessment using MediaPipe pose |
| title | Frontal plane spatial and temporal gait assessment using MediaPipe pose |
| title_full | Frontal plane spatial and temporal gait assessment using MediaPipe pose |
| title_fullStr | Frontal plane spatial and temporal gait assessment using MediaPipe pose |
| title_full_unstemmed | Frontal plane spatial and temporal gait assessment using MediaPipe pose |
| title_short | Frontal plane spatial and temporal gait assessment using MediaPipe pose |
| title_sort | frontal plane spatial and temporal gait assessment using mediapipe pose |
| url | http://journalarticle.ukm.my/25562/ http://journalarticle.ukm.my/25562/ http://journalarticle.ukm.my/25562/1/kejut_22.pdf |