Abstract
In this paper, we analyze data from Microsoft Kinect v2 camera using Kalman Tobit and Kalman filters so as to minimize noise. The data concern three-dimensional spatial coordinates recording movements of a persons’A joints, which are subject to measurement errors. The noise variances of the process and the measurements are estimated using the maximum likelihood function. In order to include into the model restrictive conditions based on anthropometric data (e.g. the distances between various joints) we apply the Tobit Kalman Filter. Additionally, restrictions for the joints displacements per fame based on real data can be used in order to get better results. Finally simulations of skeleton before and after using Kalman filtering are presented.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2019 Georgios Kontogiannis, Nikolaos Fountas, Panagiotis Georgiou, Georgios Tziatzios (Author)