Automatic Geo-Spatial Alignment of Aerial Imagery

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Aerial and satellite imagery often suffers from geo-spatial misalignment due to errors in the image acquisition and stitching processes, requiring manual correction by human experts, which is time-consuming and prone to errors, especially when dealing with large datasets.

Innovation Solution

A computerized system employing a unique combination of image processing algorithms for automatic correction of geo-spatial locations in acquired image data, using segmentation, matching, and adjustment techniques to align features with ground truth data, and subsequently analyzing the corrected images to determine environmental conditions and generate control output for external mechanisms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual correction is used to align images with ground features, then alignment accuracy can be improved, but the processing time and labor cost increase significantly

Engineering Contradiction:

Improvealignment accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables automatic self-alignment of aerial images with ground features through computer-executable instructions that perform segmentation, matching, and adjustment operations without human intervention, allowing the system to correct its own geo-spatial errors autonomously

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of expert alignment with an automated computational system using image processing algorithms, including segmentation logic to identify features, matching logic to compare with ground truth data, and adjustment logic to correct geo-spatial coordinates

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If manual alignment process is used, then flexibility in handling different images can be maintained, but error rate increases due to human subjectivity

Engineering Contradiction:

Improveflexibility in handling imagesVSAvoidalignment consistency

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The automated system performs multiple functions including segmentation of image features, matching with ground truth data, estimation of adjustment parameters, and application of corrections across diverse image types and scales, making it universally applicable to various aerial and satellite imagery

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses feedback from comparing extracted image features with ground truth data to iteratively estimate and apply adjustment parameters, continuously refining the alignment until optimal geo-spatial accuracy is achieved

Inventive Principle:

Principle #23Feedback

3Quantity of substance

If large numbers of images are processed manually, then comprehensive coverage can be achieved, but the workload and time required become unmanageable

Engineering Contradiction:

Improvenumber of images processedVSAvoidprocessing efficiency

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The system performs preliminary segmentation of image features and extraction of boundary data before matching with ground truth data, preparing the images in advance for efficient batch processing and alignment operations across large datasets

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent segments the complex alignment task into distinct computational stages: feature segmentation in images, matching with ground features, parameter estimation, and adjustment application, allowing each stage to be optimized and processed efficiently

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10089712B2System and method providing automatic alignment of aerial/satellite imagery to known ground features

Publication Date: 2018.10.02 ORACLE INT CORP

AI summary

Systems, methods, and other embodiments are disclosed for correcting errors in the geo-spatial locations of acquired image data. In one embodiment, acquired aerial or satellite image data is segmented to generate extracted boundary data. The extracted boundary data represents boundaries of features of a portion of the Earth's surface, but at incorrect geo-spatial coordinates. The extracted boundary data is matched to expected boundary data derived from ground truth data. The expected boundary data represents boundaries of the features at correct geo-spatial coordinates. Adjustment parameters are generated that represent a geo-spatial misalignment between the extracted boundary data and the expected boundary data. Metadata in a header of the acquired image data is modified to include the adjustment parameters. The adjustment parameters may be applied to the acquired image data to generate corrected image data at correct geo-spatial coordinates.