Tire Surface Relief Analysis Using Gradient Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current automatic tire inspection methods using image processing techniques for detecting anomalies on tire surfaces are computationally intensive, requiring significant calculation time, which hinders rapid identification of potential anomalies.

Innovation Solution

A rapid relief feature analysis method that transforms the three-dimensional tire surface image into an orthogonal coordinate system, assigns altitude gradient values using a reduced number of discrete points, and extracts a reduced circumferential profile to quickly identify anomalies, followed by demodulation using low-pass filters to highlight significant features.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If morphological analysis and image processing techniques are used to detect anomalies on tire surfaces, then measurement precision and reliability are improved, but calculation time increases significantly

Engineering Contradiction:
Improveanomaly detection precisionVSAvoidcalculation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the tire surface image into multiple zones based on relief height thresholds. By dividing the image into different regions (first zone with relief > first threshold, second zone with relief between first and second thresholds, third zone with relief < second threshold), the method enables selective processing of different areas with varying levels of detail, reducing overall calculation time while maintaining detection precision for critical anomalies

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by using different analysis depths for different zones of the tire surface. The first zone (higher relief) receives more intensive morphological analysis, while the second and third zones receive progressively less intensive processing. This localized adaptation of processing quality maintains anomaly detection precision in critical areas while reducing calculation time in less critical areas

Inventive Principle:
Principle #3Local quality

2Reliability

If comprehensive image processing is performed on the entire tire surface, then anomaly detection coverage is improved, but processing speed decreases

Engineering Contradiction:
Improveanomaly detection coverageVSAvoidinspection speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments the tire surface into multiple zones based on relief characteristics, enabling differentiated processing strategies. This segmentation allows the system to maintain comprehensive coverage of the entire surface while applying computationally intensive methods only where necessary, thus preserving detection reliability while improving overall inspection speed

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements partial action by applying full morphological analysis only to the first zone (areas with relief exceeding the first threshold), while using simplified or no processing for the second and third zones. This selective application of processing intensity maintains reliability for detecting significant anomalies while significantly improving processing speed by avoiding unnecessary computation in areas less likely to contain critical defects

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP2761588B1Fast analysis method for relief parts showing on the interior surface of a tyre
Publication Date: 2017.11.15 MICHELIN & CO (CIE GEN DES ESTAB MICHELIN)
  • EP2761588B1 patent drawingFigure 1~4
  • EP2761588B1 patent drawingFigure 5~8
  • EP2761588B1 patent drawing

AI summary

Method of fast analysis of the relief elements featuring on the interior surface of a tyre, said method comprising the steps in the course of which: A- the three dimensional image of said surface is captured by assigning each pixel of the image a grey level value proportional to the topographical elevation of this point, so as to obtain a starting image, B- the image of the surface captured is transformed into an orthogonal reference frame (OXY) in which the abscissa axis (OX) represents the circumferential values, and the ordinate axis (OY) represents the radial values, C- each pixel of the surface is assigned a value of altitude gradient (f(p)) by comparing its elevation with the elevation of a discrete and reduced number of points disposed on a straight line passing through the relevant pixel (p) and oriented in the circumferential direction.