Two-dimensional video-based analysis of human gait using pose estimation.
Human gait analysis is often conducted in clinical and basic research, but many common approaches (e.g., three-dimensional motion capture, wearables) are expensive, immobile, data-limited, and require expertise. Recent advances in video-based pose estimation suggest potential for gait analysis using...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-04-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1008935 |
| _version_ | 1818348916937064448 |
|---|---|
| author | Jan Stenum Cristina Rossi Ryan T Roemmich |
| author_facet | Jan Stenum Cristina Rossi Ryan T Roemmich |
| author_sort | Jan Stenum |
| collection | DOAJ |
| description | Human gait analysis is often conducted in clinical and basic research, but many common approaches (e.g., three-dimensional motion capture, wearables) are expensive, immobile, data-limited, and require expertise. Recent advances in video-based pose estimation suggest potential for gait analysis using two-dimensional video collected from readily accessible devices (e.g., smartphones). To date, several studies have extracted features of human gait using markerless pose estimation. However, we currently lack evaluation of video-based approaches using a dataset of human gait for a wide range of gait parameters on a stride-by-stride basis and a workflow for performing gait analysis from video. Here, we compared spatiotemporal and sagittal kinematic gait parameters measured with OpenPose (open-source video-based human pose estimation) against simultaneously recorded three-dimensional motion capture from overground walking of healthy adults. When assessing all individual steps in the walking bouts, we observed mean absolute errors between motion capture and OpenPose of 0.02 s for temporal gait parameters (i.e., step time, stance time, swing time and double support time) and 0.049 m for step lengths. Accuracy improved when spatiotemporal gait parameters were calculated as individual participant mean values: mean absolute error was 0.01 s for temporal gait parameters and 0.018 m for step lengths. The greatest difference in gait speed between motion capture and OpenPose was less than 0.10 m s-1. Mean absolute error of sagittal plane hip, knee and ankle angles between motion capture and OpenPose were 4.0°, 5.6° and 7.4°. Our analysis workflow is freely available, involves minimal user input, and does not require prior gait analysis expertise. Finally, we offer suggestions and considerations for future applications of pose estimation for human gait analysis. |
| first_indexed | 2024-12-13T17:57:40Z |
| format | Article |
| id | doaj.art-9dedf2adcdc34bd1b410d95000e23c95 |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-12-13T17:57:40Z |
| publishDate | 2021-04-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-9dedf2adcdc34bd1b410d95000e23c952022-12-21T23:36:20ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582021-04-01174e100893510.1371/journal.pcbi.1008935Two-dimensional video-based analysis of human gait using pose estimation.Jan StenumCristina RossiRyan T RoemmichHuman gait analysis is often conducted in clinical and basic research, but many common approaches (e.g., three-dimensional motion capture, wearables) are expensive, immobile, data-limited, and require expertise. Recent advances in video-based pose estimation suggest potential for gait analysis using two-dimensional video collected from readily accessible devices (e.g., smartphones). To date, several studies have extracted features of human gait using markerless pose estimation. However, we currently lack evaluation of video-based approaches using a dataset of human gait for a wide range of gait parameters on a stride-by-stride basis and a workflow for performing gait analysis from video. Here, we compared spatiotemporal and sagittal kinematic gait parameters measured with OpenPose (open-source video-based human pose estimation) against simultaneously recorded three-dimensional motion capture from overground walking of healthy adults. When assessing all individual steps in the walking bouts, we observed mean absolute errors between motion capture and OpenPose of 0.02 s for temporal gait parameters (i.e., step time, stance time, swing time and double support time) and 0.049 m for step lengths. Accuracy improved when spatiotemporal gait parameters were calculated as individual participant mean values: mean absolute error was 0.01 s for temporal gait parameters and 0.018 m for step lengths. The greatest difference in gait speed between motion capture and OpenPose was less than 0.10 m s-1. Mean absolute error of sagittal plane hip, knee and ankle angles between motion capture and OpenPose were 4.0°, 5.6° and 7.4°. Our analysis workflow is freely available, involves minimal user input, and does not require prior gait analysis expertise. Finally, we offer suggestions and considerations for future applications of pose estimation for human gait analysis.https://doi.org/10.1371/journal.pcbi.1008935 |
| spellingShingle | Jan Stenum Cristina Rossi Ryan T Roemmich Two-dimensional video-based analysis of human gait using pose estimation. PLoS Computational Biology |
| title | Two-dimensional video-based analysis of human gait using pose estimation. |
| title_full | Two-dimensional video-based analysis of human gait using pose estimation. |
| title_fullStr | Two-dimensional video-based analysis of human gait using pose estimation. |
| title_full_unstemmed | Two-dimensional video-based analysis of human gait using pose estimation. |
| title_short | Two-dimensional video-based analysis of human gait using pose estimation. |
| title_sort | two dimensional video based analysis of human gait using pose estimation |
| url | https://doi.org/10.1371/journal.pcbi.1008935 |
| work_keys_str_mv | AT janstenum twodimensionalvideobasedanalysisofhumangaitusingposeestimation AT cristinarossi twodimensionalvideobasedanalysisofhumangaitusingposeestimation AT ryantroemmich twodimensionalvideobasedanalysisofhumangaitusingposeestimation |