An obstacle recognition method based on binary tree support vector machine for vehicle side blind area

Due to the problems of low recognition accuracy and long recognition time in the traditional vehicle side blind area obstacle recognition methods, a vehicle side blind area obstacle recognition method based on binary tree support vector machine is proposed. First, build the camera pinhole model, collect the vehicle side blind area image, after correcting the image distortion, preprocess the collected vehicle side blind area image through three steps of image denoising, graying and enhancement, then use Roberts operator to detect the edge of the processed image, screen the obstacle area in the vehicle side blind area, and finally use the binary tree support vector machine to filter the obstacle area according to the selected obstacle area, The obstacles in the lateral blind area of the vehicle are classified to identify the obstacles. The simulation results show that the proposed method has higher accuracy and shorter recognition time for vehicle side blind zone obstacle recognition.