Virtual ERAS (V-ERAS) forms a salient part of European Mars Analog Station (ERAS) for Italian Mars Society (IMS).
The immersive VR Simulation of V-ERAS allows users to interact with a simulated Martian environment using Aldebran VSS Motivity, Oculus Rift and Microsoft Kinect. Motivity is a passive omnidirectional treadmill, so users’ steps are not in real dimensions. Therefore, the configuration needs to include an accurate and robust algorithm for estimating users’ steps, to be reproduced in the V-ERAS.
In the V-ERAS station simulation, the data used for the Step Recognition Algorithm with the Microsoft Kinect are the skeletal joints. They are recognized by means of the Skeletal Tracking implemented in Microsoft Kinect SDK (1.8).
However, there are two main issues with the current settings, and the goal of my project is to rectify and overcome them:
- Enhance the accuracy of the current step recognition algorithm.
- Improve the recognition of feet joints.