The improvement and application of evidence theory in recognition of Car

In this paper, a new recognition method of car is presented. Firstly, it gets the Basic Probability Assignment Function (BPAF) of evidence with fuzzy mathematics method. Then, based on evidence theory, a second-level fusion algorithm is presented, which includes the time domain fusion of single sensor evidence of mutli-measuring period and the space domain fusion of mutli-sensors. Finally, a decision-making method based on the basic probability number is used as the recognition of car. The theory analysis and simulation result prove that it is a valid and feasible method for the recognition of car, and has better recognition result than traditional evidence theory.