Human posture identification for motion controlling applications is becoming more of a challenge. We present a posture classification system using skeletal-tracking feature of Microsoft Kinect sensor. Posture recovery is carried out by detecting the human body joints, its position, and orientation at the same time. Angular representation of the skeleton data makes the system very robust and avoids problems related to human body occlusions and motion ambiguities. The implemented system is tested on a class of relatively common postures comprising hundreds of human pose instances by different people, where our classifier shows an average accuracy of 94.9%, 96.7% and 96.9% for linear, exponential and priority based matching systems respectively.

The Microsoft Kinect sensor has brought a new era of Natural User Interface (NUI) based gaming and the associated SDK has provided access to its powerful sensors, which can be utilized in many ways, especially in research purposes. We have already seen its use in robotics, developing assistive technologies, and augmented reality, aside from gaming. Thousands of people around the world are playing with its built-in multimodal sensors, but still a complete emulator for the Kinect sensor device is lacking, thus requiring a physical device to do any experiments with it. In this work, we have come forward with a novel design of an emulator for the Kinect sensor and its implementation in the .NET platform using the Microsoft Kinect SDK. We have demonstrated the applicability of our system through detailed software design, code descriptions to incorporate this emulator in user's own code, and video demonstration of our proposed system.