Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway
New artificial intelligence- (AI) based marker-less motion capture models provide a basis for quantitative movement analysis within healthcare and eldercare institutions, increasing clinician access to quantitative movement data and improving decision making. This research modelled, simulated, desig...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Computation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-3197/9/12/130 |
| _version_ | 1797505737138634752 |
|---|---|
| author | Connor J. C. McGuirk Natalie Baddour Edward D. Lemaire |
| author_facet | Connor J. C. McGuirk Natalie Baddour Edward D. Lemaire |
| author_sort | Connor J. C. McGuirk |
| collection | DOAJ |
| description | New artificial intelligence- (AI) based marker-less motion capture models provide a basis for quantitative movement analysis within healthcare and eldercare institutions, increasing clinician access to quantitative movement data and improving decision making. This research modelled, simulated, designed, and implemented a novel marker-less AI motion-analysis approach for institutional hallways, a Smart Hallway. Computer simulations were used to develop a system configuration with four ceiling-mounted cameras. After implementing camera synchronization and calibration methods, OpenPose was used to generate body keypoints for each frame. OpenPose BODY25 generated 2D keypoints, and 3D keypoints were calculated and postprocessed to extract outcome measures. The system was validated by comparing ground-truth body-segment length measurements to calculated body-segment lengths and ground-truth foot events to foot events detected using the system. Body-segment length measurements were within 1.56 (SD = 2.77) cm and foot-event detection was within four frames (67 ms), with an absolute error of three frames (50 ms) from ground-truth foot event labels. This Smart Hallway delivers stride parameters, limb angles, and limb measurements to aid in clinical decision making, providing relevant information without user intervention for data extraction, thereby increasing access to high-quality gait analysis for healthcare and eldercare institutions. |
| first_indexed | 2024-03-10T04:22:29Z |
| format | Article |
| id | doaj.art-01b9a675537245a99c676769e87e0c50 |
| institution | Directory Open Access Journal |
| issn | 2079-3197 |
| language | English |
| last_indexed | 2024-03-10T04:22:29Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computation |
| spelling | doaj.art-01b9a675537245a99c676769e87e0c502023-11-23T07:46:20ZengMDPI AGComputation2079-31972021-12-0191213010.3390/computation9120130Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart HallwayConnor J. C. McGuirk0Natalie Baddour1Edward D. Lemaire2Department of Mechanical Engineering, University of Ottawa, Ottawa, ON K1N 6N5, CanadaDepartment of Mechanical Engineering, University of Ottawa, Ottawa, ON K1N 6N5, CanadaThe Ottawa Hospital Research Institute, Ottawa, ON K1H 8M2, CanadaNew artificial intelligence- (AI) based marker-less motion capture models provide a basis for quantitative movement analysis within healthcare and eldercare institutions, increasing clinician access to quantitative movement data and improving decision making. This research modelled, simulated, designed, and implemented a novel marker-less AI motion-analysis approach for institutional hallways, a Smart Hallway. Computer simulations were used to develop a system configuration with four ceiling-mounted cameras. After implementing camera synchronization and calibration methods, OpenPose was used to generate body keypoints for each frame. OpenPose BODY25 generated 2D keypoints, and 3D keypoints were calculated and postprocessed to extract outcome measures. The system was validated by comparing ground-truth body-segment length measurements to calculated body-segment lengths and ground-truth foot events to foot events detected using the system. Body-segment length measurements were within 1.56 (SD = 2.77) cm and foot-event detection was within four frames (67 ms), with an absolute error of three frames (50 ms) from ground-truth foot event labels. This Smart Hallway delivers stride parameters, limb angles, and limb measurements to aid in clinical decision making, providing relevant information without user intervention for data extraction, thereby increasing access to high-quality gait analysis for healthcare and eldercare institutions.https://www.mdpi.com/2079-3197/9/12/130Smart Hallwayartificial intelligencemotion analysismarker-lesscomputer vision3D reconstruction |
| spellingShingle | Connor J. C. McGuirk Natalie Baddour Edward D. Lemaire Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway Computation Smart Hallway artificial intelligence motion analysis marker-less computer vision 3D reconstruction |
| title | Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway |
| title_full | Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway |
| title_fullStr | Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway |
| title_full_unstemmed | Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway |
| title_short | Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway |
| title_sort | video based deep learning approach for 3d human movement analysis in institutional hallways a smart hallway |
| topic | Smart Hallway artificial intelligence motion analysis marker-less computer vision 3D reconstruction |
| url | https://www.mdpi.com/2079-3197/9/12/130 |
| work_keys_str_mv | AT connorjcmcguirk videobaseddeeplearningapproachfor3dhumanmovementanalysisininstitutionalhallwaysasmarthallway AT nataliebaddour videobaseddeeplearningapproachfor3dhumanmovementanalysisininstitutionalhallwaysasmarthallway AT edwarddlemaire videobaseddeeplearningapproachfor3dhumanmovementanalysisininstitutionalhallwaysasmarthallway |