A low-cost, AI-driven markerless motion capture system using 3 cameras demonstrated strong correlation to laboratory-standard measures and produced FGA reports similar to previous findings in older adults, demonstrating proof-of-principle for open-source markerless functional gait assessment.
The markerless motion capture system showed strong correlation with a traditional marker-based system for measuring step length.
The markerless system demonstrated strong correlation with the marker-based system for measuring step width.
The markerless system demonstrated strong correlation with the marker-based system for measuring head speed.
The markerless system's Functional Gait Assessment (FGA) reports demonstrated data similar to previous FGA findings in older adult subjects.
Supplemental standard biomechanical gait measures can be integrated into the system to augment existing FGA.
The system was built using recently-developed open-source tools at low cost using only 3 cameras.
This research suggests that a low-cost, camera-based system using artificial intelligence can automatically measure how people walk without requiring special reflective markers attached to the body. Using just three cameras and freely available software, the researchers built a system capable of analyzing a clinical test called the Functional Gait Assessment (FGA), which is commonly used to evaluate balance and fall risk in older adults. When compared to an expensive, laboratory-grade motion capture system, the new system produced very similar measurements of step length, step width, and head movement, with agreement scores (R²) of 0.98, 0.97, and 0.95 respectively. Currently, gait assessments in older adults must be performed in person by trained specialists, which limits how often they can be done and makes them harder to access widely. This research suggests that automating the process with affordable cameras and open-source AI tools could make these assessments easier to conduct in a variety of settings, such as clinics, community centers, or potentially homes. The system also automatically captures additional walking measures like step width, walking speed, and duration, which could provide richer information than the standard clinical test alone. This was a small feasibility study — only 3 subjects were used for the technical validation and 5 older adults completed the FGA — so the findings are considered proof-of-concept rather than definitive clinical validation. Nevertheless, the results indicate that markerless, automated gait analysis is technically feasible and may help broaden access to standardized gait assessments for older adults who are at risk of falls.
Upload your bloodwork. We'll cross-reference your results against this study and 4,700 others.
Upload Your LabsDarici O, Cabak C, Wong J. (2026). A low-cost markerless motion capture system to automate functional gait assessment: Feasibility study.. PloS one. https://doi.org/10.1371/journal.pone.0346606