Sensor Image Geo-Referencing With 3D Model Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for geo-referencing sensor images lack accuracy and reliability, necessitating improved measures to ensure precise geographical positioning and uncertainty assessment.

Innovation Solution

A method involving matching sensor images with 3D models, using geo-coded coordinate data, and determining uncertainty measures through feature matching and similarity comparisons to enhance geo-referencing accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional geo-referencing methods are used, then the process is simple, but the accuracy and reliability of geographical positioning is insufficient

Engineering Contradiction:
Improvegeo-referencing accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary uncertainty measure that bridges the gap between simple geo-referencing methods and accurate positioning. This uncertainty measure acts as a mediator that quantifies the reliability of geo-referenced coordinates without requiring completely complex alternative systems, thus improving measurement precision while managing system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional mechanical/geometric matching approaches with image processing and pattern recognition techniques. By using image matching between sensor images and reference images, the system achieves higher geo-referencing accuracy while the computational approach substitutes complex mechanical alignment systems.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If advanced matching techniques are used to improve accuracy, then geo-referencing precision increases, but the computational complexity and processing time increase

Engineering Contradiction:
Improvematching accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-establishing the uncertainty measure calculation framework and pre-processing reference images. By preparing uncertainty calculation methodologies and reference data structures in advance, the system reduces real-time processing time while maintaining high matching accuracy through pre-computed reference frameworks.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements self-service through automated uncertainty calculation and self-validation mechanisms. The uncertainty measure is automatically computed as part of the matching process itself, eliminating the need for separate validation steps and reducing overall processing time while maintaining accuracy.

Inventive Principle:
Principle #25Self-service

3Reliability

If uncertainty measures are calculated for all points in the sensor image, then the reliability assessment is comprehensive, but the computational load increases

Engineering Contradiction:
Improvereliability assessment completenessVSAvoidcomputational energy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies local quality by calculating uncertainty measures selectively at key locations rather than uniformly across the entire image. The system focuses computational resources on critical regions where uncertainty assessment is most valuable, providing comprehensive reliability assessment where needed while reducing energy consumption in less critical areas.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system implements partial action by calculating uncertainty measures for a representative subset of points rather than all points in the sensor image. This partial sampling approach provides sufficient reliability assessment for practical purposes while significantly reducing computational energy consumption compared to complete coverage.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP2946366B1Method and system for geo-referencing at least one sensor image
Publication Date: 2025.09.24 MAXAR INT SWEDEN AB
  • EP2946366B1 patent drawingFigure 1~3
  • EP2946366B1 patent drawingFigure 4~5
  • EP2946366B1 patent drawingFigure 6~7

AI summary

The present invention relates to a method (700) and system for geo-referencing at least one sensor image. The method comprises the steps of -generating (701 )said at least one sensor image of a first scene with at least one sensor, -accessing (702) a 3D model of the environment comprising geo-coded 3D coordinate data and related to at least one second scene, said second scene encompassing said first scene, -matching (703) the sensor image with the 3D model find a section of the 3D model where there is a match between the first and the second scenes, -geo-referencing (704 )the sensor image based on the geo-coded 3D coordinate data of the found section of the 3D model, and -determining (705) a measure related to an uncertainty in the matching between the sensor image and the 3D model.