Image processing-based extraction system for lane lines in parking space

Abstract

The invention discloses an image processing-based extraction system for lane lines in a parking space. A shot photography image is obtained from a first video camera to serve as a first photography image, and a photography image shot by a second video camera is a second photography image, wherein the first video camera is mounted in a vehicle head direction of a vehicle, and the second video camera is mounted in a parking space direction of the vehicle; Haar wavelet Haar_like features of a first region of interest and a second region of interest after filtration are obtained; the Haar_like features of the image regions are classified by adopting a preset classifier to obtain a first image region and a second image region which are the lane lines in type; and according to the first image region and the second image region, the lane lines on a color image are extracted. By applying the system, the lane line extraction efficiency can be improved.

Description

technical field [0001] The invention relates to the technical field of lane line extraction, in particular to a system for extracting lane lines in parking spaces based on image processing. Background technique [0002] With the rapid development of social economy, traveling by car has become the main way for people to travel. Motor vehicle travel has brought great convenience to people, but it also has great hidden dangers. According to incomplete statistics, the number of motor vehicle drivers has exceeded half, and hundreds of thousands of people die in traffic accidents every year. In order to reduce the occurrence of unfortunate accidents and improve the convenience and comfort of people's travel, it has become an inevitable trend to realize the automation of motor vehicles. Therefore, the detection of road lines, such as the detection of lane lines, is particularly important. The detection of lane lines can make automatic driving more intelligent and bring safer guar...

AI Technical Summary

Problems solved by technology

However, the lane line information contained in the ordinary road image is not comprehensive, and in the actual traffic road, the lane line is not always a straight line, and the lane line is extracted directly according to the straight line formed by the edge points of the lane line, which will cause the extracted lane line to be inaccurate , resulting in low lane line extraction accuracy. In addition, the edge detection of the ordinary road image requires a large amount of redundant image information to be processed, resulting in a slow edge detection speed, resulting in low lane line extraction efficiency.

Images