Pedestrian intrusion detection based on improved GMM and SVM

In recent years, the computer vision and intelligent video surveillance technology have been significantly developed, thanks to the development of computer science. The automated scenario pedestrian intrusion detection has been widely used in more and more fields, such as security. In this paper, we focus on the research work of dynamic pedestrian intrusion detection, improving some shortcomings in traditional methods. First, we take advantage of the GMM, based on gradient images, to finish the video motion foreground detection. In this stage, we promoted the traditional methods which could not deal with the light mutations, shadows and other interference. On the basis of this, SVM classifier based on HOG feature is used to detect the pedestrian in the moving area. On the other side, in order to significantly increase the performance of detection, we take advantage of the least squares fitting to optimize the motion area, making the detection rate has been greatly improved. In this experiment, the rate of highest accuracy of intrusion detection has reached 97.5% successfully, that is to say, our method in this paper has good accuracy and robustness in practical application.