Method and system for determining clustering parameters for generating map lane lines

Abstract

The invention relates to a method and system for determining clustering parameters for generating map lane lines, and the method comprises the steps: 1, setting the value minPts of the minimum numberof core points in a radius region, and determining a distance array from each line segment in the lane lines for clustering to the nearest kth line segment; setp 2, converting the distribution of thedistance array from each line segment to the nearest kth line segment into a cumulative probability curve; and step 3, determining the value eps of the radius parameter of the density cluster as the distance corresponding to the inflection point of the cumulative probability curve or the median of the distance array. According to the method, the density clustering radius parameter is determined according to the distance between the lane line center line segments used for clustering, the determination process can be automatically determined through the system, automatic parameter adjustment inthe map lane line clustering process is achieved, and a good result can be obtained without manual intervention.

Description

technical field [0001] The invention relates to the field of electronic maps, in particular to a method and system for determining clustering parameters for generating map lane lines. Background technique [0002] In order to generate lane line data in high-precision maps, it is necessary to cluster a large number of lane line vector data uploaded from the vehicle end. The current common clustering algorithm is the line segment-based density clustering algorithm DBSCAN (Density-BasedSpatial Clustering of Applications with Noise). DBSCAN is a relatively representative density-based clustering algorithm, which defines a cluster as the largest collection of density-connected points, can divide areas with sufficiently high density into clusters, and can find any cluster in a noisy spatial database. Clustering of shapes, but two clustering parameters, eps and minPts, need to be selected before clustering, eps is the radius of the core point, and minPts is the minimum number of c...

AI Technical Summary

Problems solved by technology

[0003] These two clustering parameters are often obtained through business experience. In different scenarios, they will h

Images