Method and device for classifying road intersections

By converting GPS data into 2D contours encoded with EFDs and using a DNN, the method achieves precise classification of road intersections, enhancing navigation and autonomous driving applications.

DE102024211461A1Pending Publication Date: 2026-06-03ROBERT BOSCH GMBH
3 Cites 0 Cited by

Patent Information

Application Number
DE102024211461
Authority / Receiving Office
DE · DE
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-11-29
Publication Date
2026-06-03

AI Technical Summary

Technical Problem

Existing methods for classifying road intersections using GPS data are not precise enough to support accurate navigation and autonomous driving applications.

Method used

A method utilizing GPS data points to create a 2D contour of intersections, encoded with Elliptic Fourier Descriptors (EFDs) and processed by Fourier transformation, followed by classification using a trained deep neural network (DNN) to categorize intersections into types like T-junctions, X-junctions, and roundabouts.

Benefits of technology

Enables precise classification of intersections, improving navigation and autonomous driving by providing accurate intersection type identification and dynamic analysis in real time.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a computer-implemented method for classifying road intersections using GPS data, in particular from several vehicles of a vehicle fleet, comprising the following steps: using existing GPS data points (10, 11) of vehicle movements, which were recorded in particular by means of GPS sensors of the vehicles at at least one road intersection, Converting the recorded GPS data points into a 2D contour by determining a center point (13) of the road intersection and creating a polygon (12) which represents a 2D contour of the road intersection, Encoding the 2D contour of the road intersection using Elliptic Fourier Descriptors (EFDs) via a Fourier transformation procedure and classifying the encoded data into different intersection types.
Need to check novelty before this filing date? Find Prior Art