Balance deficits can lead to injurious falls, early enrollment in long-term care facilities and hospitalization. Multiple clinical tools have been developed to identify balance deficits and direct treatment recommendations;​ however, they are often based on simple measures which might fail to sufficiently characterize an individual’s balance ability. Force plate systems can be used to evaluate balance in a laboratory setting;​ however, their non-portability renders them difficult for use in the clinic and in the field. Markerless motion capture is an emerging technology which could bridge the gap between clinical and laboratory assessments of balance by offering clinicians a relatively low-cost and versatile method of obtaining high resolution measurements of balance ability.

This work aims to validate the use of a deep neural network-, video-based markerless motion capture system, Theia3D, to measure aspects of balance which are commonly identified using force plate systems, as well as aspects of postural control which cannot be identified using standard clinical or laboratory tools. Three studies were carried out as part of this thesis:​ (1) an algorithm was developed to automatically identify distinct balance tasks within a functional assessment circuit, (2) measures of balance performance quantified using Theia3D were directly and indirectly compared with measures from a force plate system, and (3) the relationships between whole-body kinematics and participant age, BMI, and sex and measures from a force plate system during the maintenance of static balance poses were investigated.

Results from these studies demonstrate that Theia3D can be used (1) to automatically identify performances of distinct functional tasks, (2) to measure aspects of balance which are commonly identified using force plate systems, with similar levels of reliability, and (3) to measure whole-body motion to uncover age-, BMI-, and sex-specific mechanisms of balance which would otherwise be unobservable using clinical tools and force plate systems. Together, the studies in this thesis demonstrate how markerless motion capture technology, specifically Theia3D, can be used to augment clinical and laboratory tests of balance