Lane Polygon Generation Using Road Shoulder and Marker Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods fail to accurately determine the lane of a road for vehicles due to the absence of center line data, limiting the generation of polygons representing lane regions and thus affecting the accuracy of lane congestion detection.

Innovation Solution

A generation device and method that processes road map data including longitude/latitude information on lane centers, shoulder lines, and markers to generate polygons based on intersections with vertical lines, enabling accurate lane region definition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If a polygon is generated using a center line and predetermined width, then the road region can be defined, but the lane region cannot be accurately generated due to absence of lane center line data

Engineering Contradiction:

Improvelane region definition accuracyVSAvoidlane center line data

Core Design Contradiction:

Manufacturing precisionVSLoss of information

Solution Approach 1:

The patent uses lane markers and road shoulder lines as intermediary elements to define lane regions. Instead of directly using the missing lane center line data, the invention employs detectable road features (lane markers, shoulder lines) as mediators to indirectly determine and define the lane polygon boundaries, thereby resolving the information loss problem.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments the lane region definition into multiple detectable components: lane markers (solid and broken), road shoulder lines, and intersection points. By dividing the continuous lane center line concept into discrete, observable road features, the system can reconstruct lane boundaries without requiring direct center line data.

Inventive Principle:

Principle #1Segmentation

2Manufacturing precision

If lane markers and road shoulder lines are used to define lane boundaries, then accurate lane polygons can be generated, but the complexity of processing road map data increases

Engineering Contradiction:

Improvelane polygon accuracyVSAvoiddata processing complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

Instead of trying to reconstruct the lane center line from scattered data points, the patent inverts the approach by using the detectable road features (lane markers, shoulder lines) as the primary definition of lane boundaries. The lane polygon is constructed by connecting intersections of vertical lines with these road features, reversing the traditional center-line-based methodology.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The patent creates a simplified geometric representation (polygon) that copies the essential spatial boundaries of the lane region. By using vertical lines from lane information points to intersect with lane markers and shoulder lines, the system creates an accurate geometric copy of the lane boundaries without needing to process complex raw road map data.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS12098933B2Generation device, generation method, and generation program

Publication Date: 2024.09.24 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

A generation device includes processing circuitry configured to receive a plurality of inputs of road map data including longitude/latitude data on lane information indicating a center line of a lane, longitude/latitude data on a road shoulder line, and longitude/latitude data on a lane marker, and refer to the road map data and generate a first polygon indicating a region of a lane based on a plurality of intersections on the lane marker or the road shoulder line crossed by a vertical line from the lane information.