The study on the method of vehicle detection and tracking based on Gaussian Mixture Model and Kalman Filter

摘要

In the vehicle detection stage, in order to solve the problem of Gaussian Mixture Model having poor adapting capacity on the sudden changes of the illumination, this paper designs a illumination judgement factor. When the factor is greater than a certain threshold, this paper uses three frame difference method for target extraction, otherwise uses the Gaussian Mixture Model. In the vehicle tracking stage, the Kalman Filter is introduced to improve tarcking accuracy and tracking efficiency, at the same time, a tracking list is designed for single and multi objectives tracking. The results show that the method can adapte the sudden changes of the illumination and can achieve a better effect of vehicle detection and tracking.