Thermal Camera Image Contrast Enhancement via Pixel Intensity Redistribution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Thermal cameras have lower resolution compared to visual light cameras, making it difficult to detect small or distant objects in thermal image sequences, as these objects may be mistaken for noise rather than moving objects due to limited pixel coverage, and most motion detection engines are optimized for visual camera images rather than thermal camera images.

Innovation Solution

A method that enhances changes in thermal image sequences by identifying pixels that have changed since the previous image, determining a redistribution function based on intensity values, and applying this function to redistribute intensity values, thereby emphasizing changed pixels and suppressing non-changed pixels, increasing contrast and improving object detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If thermal cameras are used for surveillance, then detection capability at long distances and under difficult circumstances is improved, but resolution is reduced making small or distant objects difficult to detect

Engineering Contradiction:
Improvedetection capabilityVSAvoidresolution
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent applies parameter changes by modifying the intensity values of pixels through a redistribution function. The function has a maximum for a first intensity value in a range of intensity values of identified pixels and decays with increasing distance from the first intensity value, thereby enhancing the contrast between changed and non-changed pixels without altering the physical resolution of the thermal camera

Inventive Principle:
Principle #35Parameter changes

2Reliability

If simple pixel enhancement is applied by adding offset to pixel values, then detection of small moving objects is improved, but contrast enhancement is insufficient and further improvement is needed

Engineering Contradiction:
Improveobject detection accuracyVSAvoidcontrast enhancement
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

Instead of simple offset addition, the patent uses a decay function that redistributes intensity values based on their distance from a reference intensity value (the maximum of the function). This non-linear transformation provides superior contrast enhancement by assigning lower values to intensity values outside the range than to the first intensity value, thereby amplifying the visual difference between changed and non-changed pixels

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces dynamic adaptation by determining the redistribution function based on the actual intensity values of identified pixels in each image. The function adapts to the specific characteristics of each image sequence, making the enhancement process dynamic rather than static, which improves detection accuracy across varying thermal conditions

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3671625B1Method, device, and system for enhancing changes in an image captured by a thermal camera
Publication Date: 2020.11.25 AXIS
  • EP3671625B1 patent drawingFigure 1~2
  • EP3671625B1 patent drawingFigure 3
  • EP3671625B1 patent drawingFigure 4~5c

AI summary

There is provided a method, a device (104), and a system (100) for enhancing changes in an image (103a) of an image sequence (103) captured by a thermal camera (102). An image (103a) which is part of the image sequence (103) is received (S02) and pixels (408) in the image that have changed in relation to another image (103b) in the sequence are identified (S04). Based on the intensity values of the identified pixels, a function (212, 212a, 212b, 212c, 212d, 212e) which is used to redistribute intensity values of changed as well as non-changed pixels in the image is determined (S06). The function has a maximum (601) for a first intensity value (602) in a range (514) of the intensity values of the identified pixels, and decays with increasing distance from the first intensity value.