How the Processing Mode Influences Azure Kinect Body Tracking Results

Abstract

The Azure Kinect DK is an RGB-D-camera popular in research and studies with humans. For good scientific practice, it is relevant that Azure Kinect yields consistent and reproducible results. We noticed the yielded results were inconsistent. Therefore, we examined 100 body tracking runs per processing mode provided by the Azure Kinect Body Tracking SDK on two different computers using a prerecorded video. We compared those runs with respect to spatiotemporal progression (spatial distribution of joint positions per processing mode and run), derived parameters (bone length), and differences between the computers. We found a previously undocumented converging behavior of joint positions at the start of the body tracking. Euclidean distances of joint positions varied clinically relevantly with up to 87 mm between runs for CUDA and TensorRT; CPU and DirectML had no differences on the same computer. Additionally, we found noticeable differences between two computers. Therefore, we recommend choosing the processing mode carefully, reporting the processing mode, and performing all analyses on the same computer to ensure reproducible results when using Azure Kinect and its body tracking in research. Consequently, results from previous studies with Azure Kinect should be reevaluated, and until then, their findings should be interpreted with caution.

Remote, Touchless Interaction with Medical Images and Telementoring in the Operating Room Using a Kinect-Based Application—A Usability Study

“…This device can be considered an extended version on which the next updated application version can be based. Several medical applications are continuing on Kinect Azure [35][36][37]. The solution described can be considered valuable and worth continuing.…”

“…The Kinect is no longer produced in its former form. In 2020, Microsoft released a continuation of the technology as Azure Kinect by integrating with the Microsoft Azure cloud computing platform, enabling the compatibility of the solution [35][36][37].…”

Evaluating Desk-Assisted Standing Techniques for Simulated Pregnant Conditions: An Experimental Study Using a Maternity-Simulation Jacket

“…The sEMG sensors (BioSignalsPlux) were attached 4 cm from the third and fourth lumbar vertebrae to measure the muscle activities during standing up (Figure 1b). Joint coordinates were estimated using Azure Kinect and Azure Kinect Body Tracking [20][21][22]. In addition, the subjects' age, height, weight, and exercise habits were obtained through a questionnaire.…”

A Model-Based Markerless Protocol for Clinical Gait Analysis Based on a Single RGB-Depth Camera: Concurrent Validation on Patients With Cerebral Palsy

“…Generally, black-box methods are conceived especially for animation or gaming purposes and are not compliant with clinical standards and terminology [27]. The major limitation of this category is related to its 'black box' functioning resulting in the inability of fine-tuning some model parameters for pathological data at the expense of external validity and performance [28]. In addition, body tracking SDKs are developed for specific hardware solutions and therefore difficult to generalize.…”