Breakfast Workshop B: Computer Vision for Motion Tracking in Osteoarthritis*

Chairperson: Thomas Hügle

Single Camera Motion Capture in Osteoarthritis 
Melissa Boswell, PhD

Laboratory-based motion capture by multiple camera systems is the gold standard for clinical motion capturing. Unfortunately, economic and time constraints inhibit the routine collection of this valuable, high-quality data. Also, motion data collected in a laboratory may fail to capture how individuals move in natural settings. Recent advances in machine learning, along with the ubiquity and low cost of wearable sensors and smartphones, show potential ways to overcome the limitations of laboratory-based motion analysis. Deep learning models trained from large databases can be applied to standard videos/cameras as a low-cost, easy-to-use alternative to monitor motion in osteoarthritis and to empower patients.