A road marking line automatic extracting method based on laser scanning discrete point strength gradients

Abstract

A road marking line automatic extracting method based on laser scanning discrete point strength gradients is disclosed. The method includes steps of 1) extracting a road surface point set from a laser point cloud by utilizing height information and an RANSAC process, 2) filtering road surface points in the road surface point set by adopting a median filter, 3) separately calculating the strength gradient of each road surface point in the road surface point set, 4) according to the strength gradients of the road surface points, clustering the road surface points in the road surface point set into road surface points with high strength gradients and road surface points with low strength gradients by adopting a global clustering process, and adopting the road surface points with high strength gradients as seed points, and 5) performing marking line point searching according to the seed points. Strength gradient information of discrete points and geometrical morphology information of a marking line are comprehensively utilized in the method. The road marking line extraction accuracy and efficiency are increased. Automatic extraction can still be achieved for laser point cloud data with poor quality. The method is suitable for most mobile laser scanning data.

Description

technical field [0001] The invention belongs to the intersecting field of computer vision and laser scanning data processing, and in particular relates to an automatic extraction method of road markings based on intensity gradients of discrete points of laser scanning. Background technique [0002] The mobile laser scanning system can automatically obtain high-precision three-dimensional coordinate information around the road environment. It has become a fast means of spatial data acquisition and is widely used in basic surveying and mapping, digital city construction, transportation planning and other fields. At the same time, mobile laser scanning data has the characteristics of large data volume, uneven density distribution, diverse scene objects (buildings, roads, trees, vehicles, traffic signs, traffic lights, etc.), and rich detail structures. As an important part of the 3D road model, road markings have rich semantic information, which provides rich road information f...

AI Technical Summary

Problems solved by technology

Therefore, the global threshold method is easy to fail when the intensity is greatly affected by distance interference

The difficulty of the local threshold method is to determine a local size that can use a single threshold

The above methods give some methods to determine the locality, but these methods are prone to failure under the influence of noise and are not robust

The relationship between distance and threshold is not a simple inverse distance weighted or linear relationship. Therefore, the distance threshold models of the above methods are relatively simple and cannot solve general problems.

The image conversion method uses the image processing method to ext

Images