Technique of Measuring Leading Vehicle Distance Based on Digital Image Processing Theory

摘要

Based on the digital image processing theory, a new method of measuring the leading vehicle distance was proposed. The input image using the method of edge enhancement and morphological transformation was established, so the edges of objects were enhanced to identify. The target vehicle was identified and calibrated in the image by using the method of the obstacle detection by segmentation and decision tree. The relationship between coordinates value in image space and the data of the real space plane was established by applying the ray angles. Thus, through accessing to image pixel coordinates of the vehicle, the vehicle's actual position in the plane can be calculated. At last, the leading vehicle distance based on the calculating model of inverse perspective mapping was measured. By using software VC++, an experiment program was made. The experiment results prove that the method of measuring the leading vehicle distance is simple and effective. It can meet the requirement of intelligent vehicle technologies. It is an more available and more advanced method to calculate the leading vehicle distance.