Condliffe, Elizabeth G.Rande, Amanda2024-09-132024-09-132024-09-12Rande, A. (2024). Usability of markerless motion capture for conducting 3D instrumented gait analysis with children (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.https://hdl.handle.net/1880/119716Three-dimensional gait analysis (3DGA) provides important data for informing clinical decisions for children living with cerebral palsy and other mobility impairments. However, marker-based motion capture —the current clinical standard for conducting 3DGA— may be uncomfortable or even intolerable for many children. Marker-based assessments require the accurate placement of reflective markers on bony landmarks, which requires participants to wear tight clothing or clothing with a waistband that can be rolled down enabling markers to be placed on the pelvis. Marker placement can be time-consuming, especially for participants with non-typical anatomical development, increasing their fatigue level throughout the assessment. Markerless motion capture technologies that utilize computer vision to identify key landmarks may increase the patient-friendliness of 3DGA. The purposes of this research were to a) compare markerless technologies with marker-based technologies for 3DGA with pediatric populations including those with mobility impairments, and b) to determine the factors that impact the usability of markerless motion capture for clinical gait assessments. The first study concurrently compared a markerless motion capture system to a marker-based system. Our results indicated that markerless and marker-based motion capture had good agreement in the sagittal plane for pediatric populations with and without mobility impairments. The second study investigated the impact of clothing on kinematic data when markerless systems are used, explored participant and caregiver perceptions of 3DGA, and assessed the time required to complete a markerless assessment. We found that many clothing styles had minimal impact on the kinematic data; however, clothing that was baggy or obstructed the joints reduced data quality. Our participants preferred completing markerless assessments as they could wear their own clothing, did not have to have markers placed, and appreciated the brevity of the assessment. This study combined with the literature, provides good evidence that markerless motion capture is an accurate method of assessing joint angles in the sagittal plane of children with and without mobility impairments that enables a more participant-friendly assessment.enUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.Clinical Gait AnalysisMotion CapturePediatricsMovement ImpairmentsCerebral PalsyNeuroscienceArtificial Intelligencemaster thesis