A new method of object tracing based on similarity measure

This paper deals with object tracking in the video sequences. The goal is to determine in successive frames the object which best matches. Relying on the same principle of Chebyshev distance first, it can be distinguished by using the similar measure between reference object and candidate object in tracking. Hypothesis testing has been used to determine the follow-up strategies and tracking accuracy. The experiment results indicate that this method can avoid probability distribution of the estimated density function, reduce computing time as well as increase scientific property of the algorithm through statistical testing.