Aviation Document Target Area Extraction with Polygon Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual identification of target areas of interest in aviation documents is labor-intensive, time-consuming, and prone to inconsistencies, making it inefficient and impractical for large volumes of documents.

Innovation Solution

An automated system using an image segmentation model and edge/contour detection algorithm to accurately determine the pixel coordinates of target areas within aviation documents, enhancing precision and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual review and selection of intersection points is used to identify to-scale areas, then the operator can flexibly review documents, but the process becomes labor-intensive, time-consuming, and prone to inconsistencies

Engineering Contradiction:

Improveflexibility in reviewing documentsVSAvoidprocessing speed and efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The patent replaces the manual mechanical process of reviewing documents and selecting intersection points with an automated image processing system. The system uses image segmentation models and edge/contour detection algorithms to automatically identify to-scale areas and their boundary intersection points, eliminating the need for manual operation while maintaining accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically analyzing aviation documents without requiring operator intervention. The image segmentation model and edge detection algorithm independently identify target areas and intersection points, with the system generating outputs that define the to-scale areas without human assistance.

Inventive Principle:

Principle #25Self-service

2Reliability

If manual selection of intersection points is used, then the operator can identify target areas, but human operators introduce inconsistencies and errors in selection

Engineering Contradiction:

Improveconsistency in identificationVSAvoidaccuracy of intersection point selection

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent replaces manual intersection point selection with automated computer vision algorithms. The edge detection algorithm objectively identifies intersection points by analyzing image data, eliminating human subjectivity and ensuring consistent, accurate results across all documents.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system uses feedback mechanisms where the image segmentation model generates predicted locations of to-scale areas, which are then verified and refined by the edge detection algorithm. This feedback loop ensures high accuracy in intersection point identification by cross-validating results from multiple processing stages.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If manual process is used to process aviation documents, then detailed review is possible, but the process is inefficient and impractical for large amounts of documents

Engineering Contradiction:

Improvedetail accuracy in target area identificationVSAvoidvolume of documents that can be processed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent substitutes manual detailed review with automated image processing systems that maintain high measurement precision while enabling processing of large document volumes. The image segmentation model and edge detection algorithm analyze documents with the same level of detail as manual review but at automated speed, making processing of large datasets practical.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250272869A1Aviation document target area extraction system and method

Publication Date: 2025.08.28 THE BOEING CO

AI summary

A system and a method are described for extracting a target area of an aviation document. The system and method include inputting the aviation document to an image segmentation model. The aviation document includes a target area of interest that is shown to scale. The image segmentation model generates a first output that provides a predicted location of the target AOI relative to the aviation document. The aviation document is input to an edge/contour detection algorithm that generates a second output which identifies a plurality of candidate polygons based on content in the aviation document. The first output is analyzed with the second output to determine a selected polygon of the candidate polygons in the second output that corresponds with the predicted location of the target AOI in the first output. Pixel coordinate values of the selected polygon in the aviation document are determined.