Evaluating the Accuracy of the Azure Kinect and Kinect v2

Abstract

The Azure Kinect represents the latest generation of Microsoft Kinect depth cameras. Of interest in this article is the depth and spatial accuracy of the Azure Kinect and how it compares to its predecessor, the Kinect v2. In one experiment, the two sensors are used to capture a planar whiteboard at 15 locations in a grid pattern with laser scanner data serving as ground truth. A set of histograms reveals the temporal-based random depth error inherent in each Kinect. Additionally, a two-dimensional cone of accuracy illustrates the systematic spatial error. At distances greater than 2.5 m, we find the Azure Kinect to have improved accuracy in both spatial and temporal domains as compared to the Kinect v2, while for distances less than 2.5 m, the spatial and temporal accuracies were found to be comparable. In another experiment, we compare the distribution of random depth error between each Kinect sensor by capturing a flat wall across the field of view in horizontal and vertical directions. We find the Azure Kinect to have improved temporal accuracy over the Kinect v2 in the range of 2.5 to 3.5 m for measurements close to the optical axis. The results indicate that the Azure Kinect is a suitable substitute for Kinect v2 in 3D scanning applications.

Keywords

• 3D sensing
• Azure Kinect
• depth accuracy
• Kinect v2