Vehicle Camera Lane-Marking False Positive Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

State-of-the-art camera image processing devices in vehicles are unreliable, particularly on poorly maintained roadways, leading to false detections of traffic lane markings, which can cause untimely vehicle trajectory corrections and reduce passenger comfort and trust in semi-autonomous or autonomous driving systems.

Innovation Solution

A method for detecting false positives in camera image processing by calculating initial and horizon discontinuities in marking line distances and comparing them to predetermined thresholds, along with an optional range threshold, and displaying visual alerts if false positives are detected.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the image processing device detects marking lines on poorly maintained roadways, then the device can provide trajectory guidance, but false positive detections occur leading to untimely trajectory corrections

Engineering Contradiction:
Improvedetection reliabilityVSAvoidmarking line detection precision
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action by calculating expected marking line positions using vehicle trajectory data and lane geometry models before actual detection. This predicted position serves as a reference to validate detected marking lines, filtering out false positives from poorly maintained roadways while maintaining reliable trajectory guidance.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If the image processing device increases detection sensitivity to capture faint marking lines, then detection coverage improves, but false positive detections increase

Engineering Contradiction:
Improvedetection coverageVSAvoiddetection accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent implements feedback by using vehicle trajectory information and lane geometry models to generate expected marking line positions, which then serve as feedback criteria to validate detected marking lines. This feedback mechanism allows the system to maintain high detection sensitivity for faint lines while filtering out false positives through consistency checks with predicted positions.

Inventive Principle:
Principle #23Feedback

3Measurement precision

If the system performs frequent trajectory corrections based on marking line detections, then lane keeping accuracy improves, but passenger comfort decreases due to untimely corrections

Engineering Contradiction:
Improvelane keeping accuracyVSAvoidpassenger comfort
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent applies preliminary action by predicting future marking line positions based on current vehicle trajectory and lane geometry. This allows the system to plan trajectory corrections in advance rather than reacting abruptly to detected markings, improving lane keeping accuracy while maintaining passenger comfort through smooth, timely corrections.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3847417B1Method for detecting false positives of an image-processing device of a camera
Publication Date: 2025.10.22 RENAULT SA
  • EP3847417B1 patent drawingFigure 1~2
  • EP3847417B1 patent drawingFigure 3~4
  • EP3847417B1 patent drawingFigure 5~6

AI summary

The invention relates to a method for detecting false positives of an image-processing device of a camera (2) located on-board a vehicle (1) and that delivers data for modelling a marking line (11, 12), the method for detecting false positives comprising the following steps: • - a first step (101) of determining a first distance (Yi) from the vehicle (1) to the marking line (11, 12), at a first instant (T1) in time, • - a second step (102) of determining a second distance (Y'i) from the vehicle (1) to the marking line (11, 12), at a second instant (T2) in time, • - a step (103) of computing an initial discontinuity, in which step an initial discontinuity equal to the absolute value of the difference between the first distance (Yi) and the second distance (Y'i) is computed, • - a step (104) of detecting a false initial-discontinuity positive, in which the initial discontinuity is compared to a predefined initial low threshold.