We introduce a vision-based arm gesture recognition (AGR) system using Kinect. The AGR system learns the discrete Hidden\nMarkov Model (HMM), an effective probabilistic graph model for gesture recognition, from the dynamic pose of the arm joints\nprovided by the Kinect API. Because Kinect�s viewpoint and the subject�s arm length can substantially affect the estimated 3Dpose of\neach joint, it is difficult to recognize gestures reliably with these features. The proposed system performs the feature transformation\nthat changes the 3D Cartesian coordinates of each joint into the 2D spherical angles of the corresponding arm part to obtain view invariant\nand more discriminative features. We confirmed high recognition performance of the proposed AGR system through\nexperiments with two different datasets.
Loading....