Kinect Sensor Based Gesture Recognition for Surveillance Application (1812.09595v1)

Abstract: Hand gesture recognition has been granted as one of the emerging fields in research today providing a natural way of communication between man and a machine. Gestures are some forms of body motions which a person expresses when doing a work or giving a reply. Human body tracking is a well studied topic in todays era of Human Computer Interaction and it can be formed by the virtue of human skeleton structures. These skeleton structures have been detected successfully due to the smart progress of some devices, used to measure depth. Human body movements have been viewed using these depth sensors which can provide sufficient accuracy while tracking full body in real time mode with low cost. In reality action and reaction activities are hardly periodic in a multi person perspective situation. Also recognizing their complex a-periodic gestures are highly challenging for detection in surveillance system.