Infrared Thermal Image Contour Extraction via Histogram Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for infrared thermal image contour extraction are complex and difficult to operate, necessitating a simple and precise approach.

Innovation Solution

A method involving the calculation of average multiple frames of static infrared thermal video, using histogram statistics to determine temperature thresholds, and applying threshold segmentation and window extraction with red, green, and blue components to extract human body contours.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If complex existing methods for infrared thermal image contour extraction are used, then extraction capability is achieved, but device complexity and operational difficulty increase

Engineering Contradiction:
Improvecontour extraction precisionVSAvoidextraction method complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the infrared thermal image processing into distinct stages: frame averaging to reduce noise, histogram calculation to determine temperature distribution, threshold segmentation to separate target from background, and window extraction to isolate contours. This stepwise segmentation simplifies the overall complex extraction process while maintaining precision.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions before contour extraction by first averaging multiple frames to reduce thermal noise and calculate histograms to determine optimal thresholds. These preliminary processing steps prepare the image data in advance, making the subsequent contour extraction simpler and more accurate without requiring complex real-time processing.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If complex existing methods for infrared thermal image contour extraction are used, then extraction capability is achieved, but ease of operation deteriorates

Engineering Contradiction:
Improvecontour extraction precisionVSAvoidextraction method ease of operation
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent implements self-service through automatic threshold determination using histogram analysis. The system automatically calculates the temperature histogram from the thermal image and derives optimal segmentation thresholds without requiring manual intervention or complex parameter tuning by the operator. This automation maintains high extraction precision while significantly improving ease of operation.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent changes parameters dynamically based on the specific thermal image characteristics. By calculating histograms for each image and deriving thresholds from the actual temperature distribution, the method adapts to different scenes and targets automatically, making the operation simple while maintaining precision across varying conditions.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If multiple frames are averaged to reduce error, then measurement precision improves, but loss of time increases

Engineering Contradiction:
Improveimage precisionVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial averaging by processing a limited number of frames (typically 3-10 frames) rather than continuously averaging all available frames. This partial action provides sufficient noise reduction and precision improvement while limiting the time cost, achieving an optimal balance between measurement precision and processing time.

Inventive Principle:
Principle #16Partial or excessive action

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

This method reduces errors and provides a more precise image for subsequent contour extraction, effectively highlighting effective information and obtaining accurate human body contours.

Implementation Method 1

obtainment of an infrared (IR) thermal image

Methodology Applied
Scientific EffectThermal radiation: Thermal Radiation

Data Source

PatentEP3414706B1Method and apparatus for infrared thermal image contour extraction
Publication Date: 2020.10.28 BOE TECHNOLOGY GROUP CO LTD
  • EP3414706B1 patent drawingFigure 1
  • EP3414706B1 patent drawingFigure 2
  • EP3414706B1 patent drawingFigure 3

AI summary

The present disclosure provides a method and apparatus for infrared thermal image contour extraction. The method includes: obtaining an infrared thermal image; and determining histograms based on grayscale image of the infrared thermal image, determining segmentation thresholds of the infrared image based on the histograms, and extracting a contour based on the segmentation thresholds. The apparatus includes an image acquisition circuit, configured to capture an infrared thermal image; and a processing circuit, configured to determine histograms based on greyscale images of the infrared thermal image, to determine segmentation thresholds of the infrared thermal image based on the histograms, and to extract a contour based on segmentation thresholds.