Gesture track recognition based on Kinect depth image information and its applications
Yi Zhang · Jisuanji yingyong yanjiu · 2012
In order to realize the gesture track recognition based on the depth image information got by the Kinect sensor,this paper presented a new method.First,it used Kinect sensor to obtain depth image information.Then it obtained the position of palm through OpenNI hand analysis module,and extracted trajectory feature.Finally,it adopted Hidden Markov model(HMM)trained effective track sample and achieved track recognition.Experiments results show that the presented method can effectively identify the gesture track,and apply to control intelligent wheelchair.