Vehicle distance measurement method based on monocular vision and license plate recognition

Abstract

The invention belongs to the technical field of traffic information detection, and relates to a vehicle distance measurement method based on monocular vision and license plate recognition. A vehicle-mounted monocular camera photographs the front road condition of the lane in real time so as to obtain a video, frame extraction is performed on the video stream and thus a single target image is obtained; then image preprocessing is performed on the target image; and then a license plate image only including the license plate area is located and segmented out of the target image, the specific value of the number of the pixel points occupied by the lower edge of the license plate image to the number of the pixel points occupied by the lower edge of the target image is calculated, the function relation between the vehicle distance and the pixel specific value is obtained through fitting by using the corresponding relation between different vehicle distance and the pixel specific value through the least square method, and the calculated pixel specific value is substituted in the function so that the current vehicle distance can be obtained. The technology is simple and operation is convenient with no requirement for classification detection of the vehicle so that the algorithm can be simplified, the real-time performance can be enhanced, the measurement data are accurate and the environment is friendly.

Description

Technical field: [0001] The invention belongs to the technical field of traffic information detection and relates to a vehicle distance measurement method based on monocular vision and license plate recognition. Background technique: [0002] During the driving process of the car, the real-time distance between the vehicle and the vehicle in front is an important driving parameter. For the driver, obtaining the real-time distance can provide timely warning and advance operation for dangerous driving conditions, effectively reducing the occurrence of rear-end collision accidents . In the field of assisted driving, real-time vehicle distance is the basic parameter of adaptive cruise system. In the field of unmanned driving, the real-time vehicle distance is one of the important parameters acquired by the vehicle autonomous driving sensor system. [0003] Currently, there are lidar, millimeter-wave radar, machine vision and ultrasonic methods for detecting the distance betwee...

AI Technical Summary

Problems solved by technology

However, at present, there is no public use or report of vehicle distance detection and measurement based on monocular vision and license plate recognition.

Images