Cross-Mode Image Correlation Surface for Infrared Vehicle Positioning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems face challenges in accurately determining vehicle location using cross-modal images, particularly when infrared and visible spectrum images are compared due to visual dissimilarities, leading to inaccurate location determinations.

Innovation Solution

A cross-mode image correlation surface location system that utilizes an infrared camera, a database of visible spectrum images, and a controller to convert infrared images to grayscale, determine an absolute correlation surface, and identify a maximum peak value for navigation system updates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If infrared and visible spectrum images are compared for location determination, then navigation capability is improved, but measurement precision deteriorates due to visual dissimilarities between the two image types

Engineering Contradiction:
Improvenavigation capabilityVSAvoidlocation determination accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent transforms the infrared image from thermal radiation data into a visible spectrum-like representation by adjusting temperature parameters and mapping them to visible light intensity values. This parameter transformation allows direct comparison with visible spectrum database images, resolving the visual dissimilarity issue while maintaining the ability to use infrared data for location determination

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediate conversion process that acts as a mediator between infrared and visible spectrum images. By converting infrared thermal data into a visible spectrum representation, this intermediary transformation enables accurate correlation between the two different image types without direct comparison of dissimilar data formats

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If infrared images are converted to grayscale for comparison with visible spectrum images, then image correlation accuracy is improved, but information loss occurs during the conversion process

Engineering Contradiction:
Improveimage correlation accuracyVSAvoidthermal data loss
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent applies parameter transformation that maps thermal radiation intensity values to visible light intensity values while preserving the relative relationships between different temperature regions. This parameter change enables grayscale conversion for accurate visual correlation while maintaining the essential thermal information through the transformed intensity values

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If phase correlation is used to compare cross-modal images, then location determination accuracy is improved, but computational complexity increases

Engineering Contradiction:
Improvelocation determination accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary transformation of the infrared image into a visible spectrum representation before applying phase correlation. This preliminary action prepares the images in compatible formats, enabling the phase correlation algorithm to work efficiently with transformed data that has already been optimized for comparison, thereby reducing the overall computational complexity

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4653815A1Cross-mode image correlation surface location system
Publication Date: 2025.11.26 HONEYWELL INTERNATIONAL INC
  • EP4653815A1 patent drawingFigure 1
  • EP4653815A1 patent drawingFigure 2A~2B
  • EP4653815A1 patent drawingFigure 3A

AI summary

A cross-mode image correlation surface location system is provided that includes an infrared camera to capture an infrared image. A database stores images in a visible spectrum and location information associated with each stored image. A controller selects a stored image of the stored images in the database when the infrared camera captures the infrared image. Selection of the stored image of the stored images is based on an estimated location of a vehicle that includes the infrared camera. The controller converts the selected stored image into a grayscale image. The controller determines an absolute correlation surface between the captured infrared image and the grayscale image. The controller determines a maximum first peak value in the determined absolute correlation surface. The controller updates a navigation system of the vehicle based on a peak correlation location associated with the determined maximum first peak value.