A comparative study of the clinical use of motion analysis from Kinect skeleton data

The analysis of human motion as a clinical tool can bring many benefits such as the early detection of disease and the monitoring of recovery, so in turn helping people to lead independent lives. However, it is currently under used. Developments in depth cameras, such as Kinect, have opened up the use of motion analysis in settings such as GP surgeries, care homes and private homes. To provide an insight into the use of Kinect in the healthcare domain, we present a review of the current state of the art. We then propose a method that can represent human motions from time-series data of arbitrary length, as a single vector. Finally, we demonstrate the utility of this method by extracting a set of clinically significant features and using them to detect the age related changes in the motions of a set of 54 individuals, with a high degree of certainty (F1-score between 0.9-1.0). Indicating its potential application in the detection of a range of age-related motion impairments.

I. Introduction

The analysis of human motion from video has a long history, beginning in the 1970s with the experiments of Johansson [1], which demonstrated people can recognise a wide range of human motions, even if only the joints of an actor are highlighted. This work led directly to the large multi camera, marker based, motion capture systems, still regarded by many as the gold standard for motion capture (mocap). The introduction of the Kinect depth camera, in 2011, heralded a new age of inexpensive markerless motion capture. Most importantly, thanks the work of Shotton et al. [2], Kinect reduces the depth image to a stick skeleton, who's joints while not strictly anatomically correct have been demonstrated to have a high correlation with its marker-based kinsman [3]. Originally conceived to rival the Wii, Kinect has now found applications in areas as diverse as facial analysis [4], surveillance, security and health.