A bare-hand gesture location and tracking system with single camera in real-time was introduced.By employing improved difference method

restrictions of hand are used to location region of Interesting（ROI）.Then on the basis of relatively satisfied segment result the thesis analyzed and extracted the hand features combined with the improved vector coherence mapping（VCM） whose constraint was enhanced to overcome the illegibility for robust results.Furthermore

a time-correlation forecasting model proved the demand of real-time and the consistency of the results now and before.The experiment results show the system has a high recognition rate up to 99% in different illuminations and backgrounds and has more efficient performance compared with existing other systems.