Vehicle Lane Centerline Estimation from Surrounding Object Clusters

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies struggle to accurately estimate the lane on which a vehicle is traveling when lane marking lines are unclear, obscured by other vehicles, or not detectable from a road surface image.

Innovation Solution

An information processing device and method that detects other mobile objects, calculates their relative positions and movements, clusters them, identifies lane areas, and estimates the center line of the lane based on these clusters, using vanishing points and lane markings even when actual lane markings are undetectable.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If lane marking lines are used to estimate the lane, then the lane estimation is straightforward and accurate under normal conditions, but the lane estimation fails when lane marking lines are unclear, obscured, or not detectable

Engineering Contradiction:

Improvelane estimation reliabilityVSAvoidadaptability to poor visibility conditions

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent uses other mobile objects (vehicles, pedestrians) as intermediary references to infer lane information when direct lane marking detection fails. By detecting the positions and movements of surrounding mobile objects and clustering them, the system indirectly determines the lane area and center line, replacing the direct lane marking detection method with an alternative reference system.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

Instead of directly detecting lane markings to determine the lane, the patent inverts the approach by detecting mobile objects and using their spatial distribution patterns to infer the lane structure. The lane center line is estimated as a line between clustered mobile object groups, reversing the traditional detection logic from 'lane markings → lane' to 'mobile objects → lane'.

Inventive Principle:

Principle #13The other way round (Inversion)

2Measurement precision

If candidate lines are extracted from road surface images to determine lane markings, then the process works well when markings are clear, but it cannot appropriately estimate the lane when markings are not clear or when multiple vehicles are present

Engineering Contradiction:

Improvelane marking detection accuracyVSAvoiddifficulty under occlusion and poor visibility

Core Design Contradiction:

Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent replaces the direct detection of lane markings with indirect detection through mobile objects. When lane markings become undetectable due to occlusion or poor visibility, the system uses the positions, movements, and clustering patterns of surrounding mobile objects as intermediary indicators to infer the underlying lane structure, maintaining measurement precision without direct marking detection.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system uses the mobile objects themselves (other vehicles, pedestrians) as the detection medium. These mobile objects naturally present themselves in the scene and their spatial distribution automatically reveals lane information, eliminating the need for direct lane marking detection and making the system self-sufficient in poor visibility conditions.

Inventive Principle:

Principle #25Self-service

3Loss of information

If the system relies on detecting lane marking lines from the road surface, then it provides accurate lane information when markings are visible, but it cannot determine the lane when markings are obscured by other vehicles or not clear

Engineering Contradiction:

Improvelane information availabilityVSAvoidocclusion by other vehicles

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent introduces mobile objects as intermediary elements that can be detected even when lane markings are obscured. By using the positions and movements of these mobile objects as proxies for lane information, the system recovers lane data that would otherwise be lost due to occlusion by other vehicles or poor marking visibility.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent converts the presence of other vehicles, which normally causes occlusion and loss of lane marking information, into a beneficial detection resource. The mobile objects that obscure the lane markings are themselves detected and used as reference points for inferring lane structure, transforming the harmful occlusion effect into a useful detection mechanism.

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Data Source

PatentUS20250336213A1Information processing device, information processing method, and storage medium

Publication Date: 2025.10.30 HONDA MOTOR CO LTD

AI summary

An information processing device includes a storage medium that stores computer-readable instructions, and a processor connected to the storage medium, and the processor executes the computer-readable instructions to detect one or more other mobile objects from image data obtained by imaging an area around a mobile object, calculate a relative position of the other mobile objects in a lateral direction of the mobile object and a relative movement amount of the other mobile objects in a longitudinal direction of the mobile object, with the mobile object as a reference, cluster the other mobile objects based on the relative position of the other mobile objects in the lateral direction and the relative movement amount of the other mobile objects in the longitudinal direction, identify a lane area based on a result of the clustering, and estimate a center line of a lane on which the mobile object is traveling, based on the lane area.