Real-time hand tracking using integrated optical flow and CAMshift algorithm

Abstract

Hand gesture interfaces are more convenient, natural, intuitive, and user-friendly form of input for HumanComputer Interaction(HCI). Hand detection and tracking are the most vital stages for any kind of hand gesture based interface and the accuracy of the final gesture recognition algorithm depends substantially on the proper and correct segmentation of hand from incoming video frames in real time. This paper proposes a novel hand tracking algorithm, that combines Continuous Adaptive Mean Shift Algorithm(CAMshift), Shi-Tomasi points, and Lukas Kanade Optical flow to track hand with high accuracy in real time using only a single camera in non-limiting and unrestrained environment. Results obtained reflect that the algorithm can precisely track the hand of an operator in an input video sequence obtained from a web-cam at 30fps.