Kinematic and Kinetic Validation of an Improved Depth Camera Motion Assessment System Using Rigid Bodies

Abstract

The study of joint kinematics and dynamics has broad clinical applications including the identification of pathological motions or compensation strategies and the analysis of dynamic stability. High-end motion capture systems, however, are expensive and require dedicated camera spaces with lengthy setup and data processing commitments. Depth cameras, such as the Microsoft Kinect, provide an inexpensive, marker-free alternative at the sacrifice of joint-position accuracy. In this work, we present a fast framework for adding biomechanical constraints to the joint estimates provided by a depth camera system. We also present a new model for the lower lumbar joint angle. We validate key joint position, angle, and velocity measurements against a gold standard active motion-capture system on ten healthy subjects performing sit-to-stand (STS). Our method showed significant improvement in Mean Absolute Error and Intraclass Correlation Coefficients for the recovered joint angles and position-based metrics. These improvements suggest that depth cameras can provide an accurate and clinically viable method of rapidly assessing the kinematics and kinetics of the STS action, providing data for further analysis using biomechanical or machine learning methods.

Real-Time Detection of Compensatory Patterns in Patients With Stroke to Reduce Compensation During Robotic Rehabilitation Therapy

“…Finding an unobtrusive and easy-to-use solution is quite difficult. Camera-based detection systems, which include marker-based and markerless human motion capture technologies [13], [14]. Marker-based motion tracking systems can achieve accurate and robust results, This work is licensed under a Creative Commons Attribution 4.0 License.…”

Estimating Sit-to-Stand Dynamics Using a Single Depth Camera

“…This paper introduces a fast method for performing fullbody contactless dynamic analysis of the STS action using a single depth camera. Building on the author's prior results in improving the accuracy of the Kinect for STS actions by imposing rigid-body constraints [45], this work adds reducedcomplexity allometrically-scaled dynamic and musculoskeletal models. This provides estimates of torso momenta and joint torques of the low back, and lower limbs, key metrics that have been shown to act as correlates of disability in patient populations.…”

“…This method was chosen for the fast computation rate (524 fps) and the availability of commercial depth camera systems which can estimate the location of joint centres from a RGB-Depth image. The full kinematic recovery process is presented in the associated kinematic validation paper [45]. A brief overview is given below for completeness.…”

Simple benchmarking method for determining the accuracy of depth cameras in body landmark location estimation: Static upright posture as a measurement example

“…Most similar studies typically reported the validity of using the proprietary Kinect-specific skeletal model to obtain human motion data. However, for certain applications, the Kinectspecific skeletal model may not be adequate for some rigorous ergonomics assessments because it lacks clear anatomical definitions for some joints [5,15] and has insufficient anatomical landmarks [12]. In addition, as this technology evolves quickly, analyses directly derived from the Kinect-specific skeletal model may eventually be superseded [6].…”