A lane marking method based on multi-feature fusion and multi-state mean

Abstract

The invention provides a lane line positioning method based on multi-feature fusion and a polymorphism mean value. According to the method, images of road conditions in front of vehicles are obtained through a camera; the gray level distribution information of lane lines and the color distribution information in an HSI space are fused according to weight to obtain a lane line suspected area according to the pavement gray scale normal distribution features and the HIS color space information; then, according to priori knowledge, the searching is carried out from the middle of a road to the two sides for excluding non-lane regions, and sub images which avoid the non-road feature interference and contain the lane lines are obtained; then, the sub images are subjected to margin determination; Hough transformation is adopted for detecting straight lines for determining the positions of the lane lines in the current frame; and finally, through fusing the multi-frame lane line states and utilizing the actual condition that the lane line positions cannot suddenly change, the mean value of detection results of continuous frames is worked out, and stable lane line positioning results are obtained.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, relates to the fields of computer vision and pattern recognition, and is applied to advanced driver assistance technology. [0002] technical background [0003] With the development of machine vision, driver-assisted driving technology has received more and more attention. Vehicles deviate from the lane are prone to vehicle collisions and cause traffic accidents. Lane line detection technology can help drivers grasp road condition information in a timely and accurate manner. Once there is a deviation When the lane situation occurs, the driver can be reminded of the deviation of the lane in time, and the steering wheel can be adjusted in time to avoid accidents. Of course, the lane line technology can also be applied to the automatic driving of cars. At present, many large companies including Google are vigorously developing the automatic driving technology of cars. However, the k...

AI Technical Summary

Problems solved by technology

[0007] 4. Combining Principle Component Analysis (PCA, principal component analysis) dimensionality reduction with k-means lane line detection and Mean-Shift tracking algorithm to realize lane line detection, but this method does not work well when lane markings are defaced

[0009] Due to changes in scene lighting, complex road conditions, and lane line pollution, the accurate positioning of lane lines has not been effectively solved.

Images