Distance measurement method of multiple lanes

Abstract

The invention discloses a distance measurement method of multiple lanes. The method comprises the following steps: 1, performing lane feature extraction; 2, obtaining a maximum confidence lane and correlation information thereof; 3, obtaining disappearance line correlation information; 4, obtaining disappearance point correlation information; 5, obtaining other lanes and correlation information thereof; and 6, performing curve type lane parameter searching optimization and performing distance measurement work. According to the invention, the multiple lanes can be rapidly and accurately identified, accurate distance measurement is performed, and the method can help an intelligent auxiliary driving system in its control over vehicles.

Description

technical field [0001] The invention belongs to the field of automobile intelligent driving assistance systems, and in particular relates to a multi-lane line detection and ranging method based on improved feature extraction. Background technique [0002] In recent years, my country's automobile industry has maintained a steady development trend. However, while automobiles bring people convenient travel, various traffic accidents remain high. The intelligentization of automobiles has become a research hotspot for researchers. [0003] In the intelligent vehicle driving assistance system, fast and accurate identification of lane lines and accurate distance measurement for lane lines are very important. The current feature-based lane line recognition mainly performs image segmentation on the road image by analyzing the low-level features of the image. On the actual road, due to factors such as vehicles, shadows, and water marks, the feature-based method interferes with noise ...

AI Technical Summary

Problems solved by technology

The current feature-based lane line recognition mainly performs image segmentation on the road image by analyzing the low-level features of the image. On the actual road, due to factors such as vehicles, shadows, and water marks, the feature-based method interferes with noise such as vehicle occlusion. Insufficient, which makes the identification of lane lines in images with more interference inaccurate

The current model-based lane recognition mainly uses model parameters to describe lane lines, which is more robust than feature-based methods, but there are still problems with too many parameters leading to poor real-time performance.

Images