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

Abstract

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.

Kinect V2-Based Gait Analysis for Children with Cerebral Palsy: Validity and Reliability of Spatial Margin of Stability and Spatiotemporal Variables

“…Thirdly, this study used ankle landmarks instead of foot landmarks to represent the BOS because the foot tracking is usually noisy and inaccurate in the Kinect V2. In contrast, the newest Azure Kinect sensor released in 2019 demonstrates significantly better foot tracking accuracy and more precise gait spatiotemporal parameter assessment, indicating improved image sensing strategies [ 74 ]. Therefore, in future investigations, it may be possible to use multiple Azure Kinect sensors to develop the precision of gait detection and skeleton tracking performance.…”

Embodiment in Virtual Reality Performance

“…We believed that the depth camera's signal is entirely relevant to represent the performer's body, as it is. In computing history, we have accustomed computers to immediately recognize human beings, whether through body detection [47] or facial analysis [48]. These mappings are sometimes not enough to describe the richness of detail in the subtle and artistic movement.…”

Adaptive Rehabilitation Bots in Serious Games

“…However, Kinect 2 sometimes falls short when it comes to (1) capturing subtle hand motions with high accuracy, (2) recognizing short-range motions, (3) functioning in bright sun light, and (4) immunity to interference caused by other nearby sensors [ 26 ]. A recent work [ 27 ] demonstrates a superiority in pose tracking performance of the Azure Kinect over the Kinect 2, in which the Azure Kinect more accurately measured the spatial gate parameters. Improving joint position estimation of Kinect using various types of filters can greatly enhance the rehabilitation experience [ 28 ].…”