Static Human Gesture grading based on Kinect

We presented a static human gesture grading system based on the skeletal tracking module of Kinect sensor. We captured the 2-D skeleton wireframe of a poser´s body and represented the data as limb vectors. The distance metric is defined as the included angle array computed between the real-time and the standard gesture. We proposed a grading formula to simulate the gesture judging scenario, of which the parameters can be adaptively computed or manually set. The system worked efficiently under the low computational complexity and was robust to input noise.