Infrared Thermal Image Segmentation for Temperature Gradient Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Infrared thermal imaging struggles to accurately distinguish between sound and damaged parts of a structure due to temperature gradients caused by varying surface inclinations, colors, roughness, thermal conductivity, and emissivity, leading to erroneous detection of boundaries and incorrect reduction of temperature gradients.

Innovation Solution

An infrared thermal image analysis device and method that acquires region information from visible images and infrared thermal images, estimates temperature gradients within these regions, and reduces the influence of temperature gradients using preferential smoothing and thermal simulation to correct temperature gradient estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If simple smoothing is applied to the entire infrared thermal image, then processing is simple and fast, but temperature gradients cannot be correctly reduced and boundaries between different surfaces are erroneously detected as damaged parts

Engineering Contradiction:

Improveprocessing simplicityVSAvoidtemperature gradient reduction accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The infrared thermal image is divided into multiple regions based on surface inclination and discontinuity information. Each region is processed separately with appropriate smoothing parameters, allowing correct temperature gradient reduction while preserving boundaries between different surfaces. This segmentation prevents erroneous detection of surface boundaries as damaged parts.

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If region-based processing with multiple parameters is implemented, then temperature gradient reduction accuracy is improved, but device complexity and processing time increase

Engineering Contradiction:

Improvetemperature gradient reduction accuracyVSAvoidprocessing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

Surface inclination and discontinuity information is acquired and processed in advance to determine region boundaries before temperature gradient reduction. This preliminary segmentation allows subsequent processing to focus only on relevant regions with appropriate parameters, improving accuracy without proportionally increasing overall system complexity.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Different smoothing parameters and processing methods are applied to different regions based on their specific characteristics (surface inclination, discontinuities). This local adaptation optimizes temperature gradient reduction for each region while avoiding unnecessary complex processing in uniform areas, balancing accuracy and complexity.

Inventive Principle:

Principle #3Local quality

3Quantity of substance

If other surfaces are included in the pixel range for smoothing, then more data is available for processing, but the temperature gradient cannot be reduced correctly due to contamination from different temperature zones

Engineering Contradiction:

Improvedata volume for processingVSAvoidtemperature gradient estimation accuracy

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The image is segmented into distinct regions based on surface geometry information, creating clear boundaries between different surfaces. This segmentation ensures that smoothing operations only include pixels from the same surface, preventing contamination from other surfaces with different temperature gradients while maintaining sufficient data volume for accurate processing.

Inventive Principle:

Principle #1Segmentation

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Accurately reduces temperature gradients by distinguishing surface regions, improving the accuracy of infrared thermal image analysis and correctly identifying damaged parts in structures.

Implementation Method 1

an infrared thermal image acquired in a case where a structure such as concrete is imaged with an infrared camera

Methodology Applied

Scientific EffectInfrared radiation detection: Infrared Radiation

Implementation Method 2

smoothing processing on the second infrared thermal image with different weights for the region and the other region

Methodology Applied

Scientific EffectThermal diffusion: Conduction (thermal)

Data Source

PatentUS12618789B2Infrared thermal image analysis device, infrared thermal image analysis method, and program

Publication Date: 2026.05.05 FUJIFILM CORP

AI summary

Provided are an infrared image analysis device, an infrared image analysis method, and a program capable of correctly reducing a temperature gradient. An infrared thermal image analysis device (10) includes a processor. The processor acquires a first infrared thermal image of a structure surface, which is obtained by capturing a structure (36) to be inspected, acquires region information (105) that distinguishes a region of the structure surface corresponding to the first infrared thermal image for at least one region, estimates a temperature gradient in the at least one region based on the region information (105) and a second infrared thermal image, and reduces an influence of the temperature gradient from the first infrared thermal image.