Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard: A Pilot Study

Gait analysis is an important tool for the early detection of neurological diseases and for the assessment of risk of falling in elderly people. The availability of low-cost camera hardware on the market today and recent advances in Machine Learning enable a wide range of clinical and health-related applications, such as patient monitoring or exercise recognition at home. In this study, we evaluated the motion tracking performance of the latest generation of the Microsoft Kinect camera, Azure Kinect, compared to its predecessor Kinect v2 in terms of treadmill walking using a gold standard Vicon multi-camera motion capturing system and the 39 marker Plug-in Gait model. Five young and healthy subjects walked on a treadmill at three different velocities while data were recorded simultaneously with all three camera systems. An easy-to-administer camera calibration method developed here was used to spatially align the 3D skeleton data from both Kinect cameras and the Vicon system. With this calibration, the spatial agreement of joint positions between the two Kinect cameras and the reference system was evaluated. In addition, we compared the accuracy of certain spatio-temporal gait parameters, i.e., step length, step time, step width, and stride time calculated from the Kinect data, with the gold standard system. Our results showed that the improved hardware and the motion tracking algorithm of the Azure Kinect camera led to a significantly higher accuracy of the spatial gait parameters than the predecessor Kinect v2, while no significant differences were found between the temporal parameters. Furthermore, we explain in detail how this experimental setup could be used to continuously monitor the progress during gait rehabilitation in older people.

[1]  Yaser Sheikh,et al.  OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Nira Herrmann,et al.  Accuracy, reliability, and validity of a spatiotemporal gait analysis system. , 2006, Medical engineering & physics.

[3]  P. Olivier,et al.  Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease. , 2014, Gait & posture.

[4]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[5]  Lucas Sabalka,et al.  Automated Depth Video Monitoring For Fall Reduction : A Case Study , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  KolbAndreas,et al.  Kinect range sensing , 2015 .

[7]  John Hansen,et al.  Investigating the impact of a motion capture system on Microsoft Kinect v2 recordings: A caution for using the technologies together , 2018, PloS one.

[8]  S. Fritz,et al.  White paper: "walking speed: the sixth vital sign". , 2009, Journal of geriatric physical therapy.

[9]  Eduardo Palermo,et al.  A markerless system for gait analysis based on OpenPose library , 2020, 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC).

[10]  Hans-Peter Seidel,et al.  VNect , 2017, ACM Trans. Graph..

[11]  V. L. Nickel,et al.  Gait parameters following stroke: a practical assessment. , 1995, Journal of rehabilitation research and development.

[12]  Alessandro Scano,et al.  A Kinect-Based Biomechanical Assessment of Neurological Patients' Motor Performances for Domestic Rehabilitation , 2016 .

[13]  Min-Ho Song,et al.  How Fast Is Your Body Motion? Determining a Sufficient Frame Rate for an Optical Motion Tracking System Using Passive Markers , 2016, PloS one.

[14]  I. Jonkers,et al.  Quantitative gait analysis in Parkinson's disease: comparison with a healthy control group. , 2005, Archives of physical medicine and rehabilitation.

[15]  Luca Romeo,et al.  Accuracy evaluation of the Kinect v2 sensor during dynamic movements in a rehabilitation scenario , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[16]  Ruzena Bajcsy,et al.  Evaluation of Pose Tracking Accuracy in the First and Second Generations of Microsoft Kinect , 2015, 2015 International Conference on Healthcare Informatics.

[17]  Tung-Wu Lu,et al.  Quantification of three-dimensional soft tissue artifacts in the canine hindlimb during passive stifle motion , 2018, BMC Veterinary Research.

[18]  Ciara M O'Connor,et al.  Automatic detection of gait events using kinematic data. , 2007, Gait & posture.

[19]  Melvyn Roerdink,et al.  Kinematic Validation of a Multi-Kinect v2 Instrumented 10-Meter Walkway for Quantitative Gait Assessments , 2015, PloS one.

[20]  Moataz Eltoukhy,et al.  Improved kinect-based spatiotemporal and kinematic treadmill gait assessment. , 2017, Gait & posture.

[21]  Begonya Garcia-Zapirain,et al.  Gait Analysis Methods: An Overview of Wearable and Non-Wearable Systems, Highlighting Clinical Applications , 2014, Sensors.

[22]  Leslie G. Portney Dpt PhD Fapta,et al.  Foundations of Clinical Research: Applications to Practice , 2015 .

[23]  M. Morris,et al.  Constraints on the kinetic, kinematic and spatiotemporal parameters of gait in Parkinson's disease , 1999 .

[24]  Linda Denehy,et al.  Validity of the Microsoft Kinect for assessment of postural control. , 2012, Gait & posture.

[25]  Julius Verrel,et al.  Accuracy and Reliability of the Kinect Version 2 for Clinical Measurement of Motor Function , 2016, PloS one.

[26]  Christian Szegedy,et al.  DeepPose: Human Pose Estimation via Deep Neural Networks , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Xu Xu,et al.  Accuracy of the Microsoft Kinect for measuring gait parameters during treadmill walking. , 2015, Gait & posture.

[28]  Andreas Kolb,et al.  Kinect range sensing: Structured-light versus Time-of-Flight Kinect , 2015, Comput. Vis. Image Underst..

[29]  Jennifer McGinley,et al.  Test-retest reliability and inter-tester reliability of kinematic data from a three-dimensional gait analysis system. , 2003, Journal of the Japanese Physical Therapy Association = Rigaku ryoho.

[30]  Tom W Macpherson,et al.  Real-time measurement of pelvis and trunk kinematics during treadmill locomotion using a low-cost depth-sensing camera: A concurrent validity study. , 2016, Journal of biomechanics.

[31]  J S Higginson,et al.  Two simple methods for determining gait events during treadmill and overground walking using kinematic data. , 2008, Gait & posture.

[32]  Ross A Clark,et al.  Three-dimensional cameras and skeleton pose tracking for physical function assessment: A review of uses, validity, current developments and Kinect alternatives. , 2019, Gait & posture.

[33]  Elise Lachat,et al.  Assessment and Calibration of a RGB-D Camera (Kinect v2 Sensor) Towards a Potential Use for Close-Range 3D Modeling , 2015, Remote. Sens..

[34]  Nasser Kehtarnavaz,et al.  Fusion of depth, skeleton, and inertial data for human action recognition , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[35]  Yohan Dupuis,et al.  A Study of Vicon System Positioning Performance , 2017, Sensors.

[36]  Ross A Clark,et al.  Gait assessment using the Microsoft Xbox One Kinect: Concurrent validity and inter-day reliability of spatiotemporal and kinematic variables. , 2015, Journal of biomechanics.

[37]  Naoto Fujita,et al.  Validity of motion analysis using the Kinect system to evaluate single leg stance in patients with hip disorders. , 2018, Gait & posture.

[38]  G Atkinson,et al.  Statistical Methods For Assessing Measurement Error (Reliability) in Variables Relevant to Sports Medicine , 1998, Sports medicine.