LED Traffic Sign Reconstruction for Camera Flicker Removal

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing traffic sign recognition systems fail to accurately detect and classify LED traffic signs due to flickering caused by asynchronous capture rates between cameras and LED lights, leading to incomplete or incorrect shape recognition.

Innovation Solution

A device and method for flicker removal by image analysis, comprising a LED-region identifier, shape constructor, color verifier, tracker, and frame reconstructor, which identifies, tracks, and reconstructs LED signs across frames using affine transformation and color checks to align and register cutouts for accurate classification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If LED traffic signs are captured by camera at 30 Hz, then the camera can capture images at a reasonable refreshing rate, but the LED lights appear to flicker due to lack of time synchronization with 50 Hz LED frequency

Engineering Contradiction:
Improvecamera refreshing rateVSAvoidshape recognition accuracy
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system performs preliminary actions by detecting and identifying the LED traffic sign in the current frame before the flicker occurs, then uses tracker modules to predict and locate the sign in subsequent frames where it may be partially or fully visible, allowing reconstruction of the complete sign shape

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a copy or model of the complete LED traffic sign shape by combining detected portions from multiple frames. The shape constructor module generates a complete shape model based on detected LED regions from different time points, effectively copying the full sign appearance despite temporal fragmentation

Inventive Principle:
Principle #26Copying

2Reliability

If the camera refreshing rate is increased to synchronize with LED frequency, then flicker can be eliminated, but the device complexity and energy consumption increase

Engineering Contradiction:
Improveflicker eliminationVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system dynamically adapts to the flickering condition rather than attempting to eliminate it through hardware changes. The tracker and shape constructor modules dynamically adjust to capture and reconstruct the sign shape from varying visibility conditions across frames, making the system flexible and adaptable without increasing hardware complexity

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The shape constructor module acts as an intermediary that processes and integrates information from multiple frames to produce a complete sign shape. This software-based intermediary enables flicker compensation without requiring hardware synchronization, maintaining system simplicity while achieving reliable recognition

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If LED traffic signs are partially depicted due to flicker, then the capture system can operate at lower refreshing rates, but the shape recognition fails due to wrong shape information

Engineering Contradiction:
Improvecapture efficiencyVSAvoidshape detection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system merges detected LED regions from multiple frames to reconstruct the complete sign shape. The memory module accumulates detected portions across frames, and the shape constructor combines these fragmented detections into a complete, accurate shape representation, enabling precise recognition despite partial visibility in individual frames

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The tracking and shape construction process continues across multiple frames to accumulate sufficient information for accurate shape detection. Rather than requiring complete information in a single frame, the system continuously gathers useful data across the flicker cycle, ensuring accurate shape measurement through persistent detection and integration

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP3355238B1Device and method for flicker removal by image analysis
Publication Date: 2026.03.11 CONTINENTAL AUTONOMOUS MOBILITY GERMANY GMBH
  • EP3355238B1 patent drawingFigure 1~2
  • EP3355238B1 patent drawingFigure 3
  • EP3355238B1 patent drawingFigure 4

AI summary

The present invention relates to a device (100) for flicker removal by image analysis, the device (100) comprising: a LED-region identifier (10), which is configured to identify a portion of a LED traffic sign in at least one starting frame provided by an image sensor; a shape constructor (20), which is configured to calculate a shape for a reconstructed LED sign based on the identified portion; a color verifier (30), which is configured to perform a color check of the reconstructed LED sign; and a frame reconstructor (40), which is configured to reconstruct the verified reconstructed LED sign of the at least one starting frame in at least one another frame provided by the image sensor.