Road Marking Detection via Grid Histograms Under Adverse Conditions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for real-time detection of road markings struggle to accurately distinguish lane markings from the road surface, especially under adverse conditions such as moisture, darkness, and fog, leading to functional disorders in driving assistance systems.

Innovation Solution

A procedure involving sensors and pattern recognition for real-time detection of road markings, which includes recording a color image, transforming it into a color model, segmenting the image, overlaying a grid, creating histograms, and classifying pixel fields to identify lane markings, regardless of environmental conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional image recognition methods are used to detect road markings, then the system is simple to implement, but the detection accuracy deteriorates under adverse conditions such as wetness, darkness, and fog

Engineering Contradiction:
Improveroad marking detection accuracyVSAvoidadverse environmental conditions
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent divides the road surface image into multiple pixel fields arranged in a grid pattern, and creates separate histograms for each pixel field. This segmentation allows the system to analyze local color distributions independently, improving the ability to detect road markings even when parts of the image are affected by adverse conditions like wetness or darkness.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms the problem from direct image analysis to histogram analysis of color value distributions. By creating histograms that represent frequency distributions of color values across pixel fields, the system adds a statistical dimension to the detection process, enabling more robust identification of road markings under varying environmental conditions.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If multiple color channels are analyzed to improve detection accuracy, then the detection reliability improves, but the computational complexity increases

Engineering Contradiction:
Improvedetection reliabilityVSAvoidprocessing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent analyzes all color channels (RGB or YCbCr) to ensure complete information is captured, but applies histogram creation and classification only to pixel fields where road markings are likely to be present. This partial application of complex processing reduces overall computational burden while maintaining detection reliability.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent transforms color image data into histogram representations, changing the parameter space from raw pixel values to frequency distributions. This parameter transformation simplifies the comparison between different color channels and makes the detection process more computationally efficient while maintaining reliability.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4538988A1Method for real-time detection of road markings
Publication Date: 2025.04.16 ZKW GRP GMBH
  • EP4538988A1 patent drawingFigure 1
  • EP4538988A1 patent drawingFigure 2~4
  • EP4538988A1 patent drawing

AI summary

Method for real-time detection of road markings (2, 4) on a roadway (1), comprising the following steps: capturing a color image of a vehicle environment of a motor vehicle, transforming the color image into a color model with at least three color channels, segmenting a color channel image into a roadway image section and an environment image section, overlaying the roadway image section of a color channel image with a grid of pixel fields (3), creating histograms (5) for the pixel fields (3), classifying the histograms (5) of the pixel fields as pixels of a road marking (2, 4) or a roadway (1).