Pose and Optical Flow Fusion (POFF) for accurate tremor detection and quantification

Abstract Limb tremor measurements are one factor used to characterize and quantify the severity of neurodegenerative disorders. These tremor measurements can also provide dosage-response feedback to guide medication treatments. Here, we propose a system to automatically measure limb tremors in home or clinic settings. The key feature of proposed method is that it is contactless; not requiring a user to wear or hold a device or marker. Our sensor is a Kinect 2, which measures color and depth and estimates rough limb motion. We show that its pose accuracy is poor for small limb tremors below 10 mm amplitude, and so we propose an additional level of tremor tracking that recovers limb motion at a higher precision. Our method upgrades the sensitivity to achieve detection and analysis for tremors down to 2 mm amplitude. We include empirical experiments and measurements showing improved tremor amplitude and frequency estimation using our proposed Pose and Optical Flow Fusion (POFF) algorithm.