Hand-tremor frequency estimation in videos

TL;DR

This paper introduces two video-based methods for estimating human hand-tremor frequency, leveraging Lagrangian and Eulerian approaches, and validates them on a new dataset with synchronized video and accelerometer data.

Contribution

It presents novel video-based tremor frequency estimation techniques and introduces the TIM-Tremor dataset with synchronized video and accelerometer data for validation.

Findings

Effective tremor frequency estimation from video data.

Comparison of Lagrangian and Eulerian approaches.

Validation on a new comprehensive dataset.

Abstract

We focus on the problem of estimating human hand-tremor frequency from input RGB video data. Estimating tremors from video is important for non-invasive monitoring, analyzing and diagnosing patients suffering from motor-disorders such as Parkinson's disease. We consider two approaches for hand-tremor frequency estimation: (a) a Lagrangian approach where we detect the hand at every frame in the video, and estimate the tremor frequency along the trajectory; and (b) an Eulerian approach where we first localize the hand, we subsequently remove the large motion along the movement trajectory of the hand, and we use the video information over time encoded as intensity values or phase information to estimate the tremor frequency. We estimate hand tremors on a new human tremor dataset, TIM-Tremor, containing static tasks as well as a multitude of more dynamic tasks, involving larger motion of the hands. The dataset has 55 tremor patient recordings together with: associated ground truth accelerometer data from the most affected hand, RGB video data, and aligned depth data.