Airport Scene Perception with Logic-Based Feature Verification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing machine learning-based approaches for perceiving airport scenes are not optimal or robust in some situations, leading to inaccuracies and reduced reliability in identifying airport features.

Innovation Solution

A method combining machine learning algorithms with predetermined logical tests to refine initial estimates of airport features, using real-world coordinates and dimensions, to produce a reviewed estimate that filters out implausible categorizations and verifies correct categorizations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If machine learning algorithms are used to identify airport features, then the speed and automation of scene perception is improved, but the accuracy and reliability of feature categorization deteriorates due to implausible categorizations

Engineering Contradiction:

Improvespeed of scene perceptionVSAvoidaccuracy of feature categorization

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system applies predetermined logical tests to the initial machine learning estimates and uses the results to generate reviewed estimates. This feedback mechanism verifies and corrects categorizations, improving reliability while maintaining the automated processing speed of the machine learning approach.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary machine learning estimation followed by predetermined logical tests before finalizing the airport feature categorization. This preliminary action structure allows the system to quickly filter implausible categorizations while maintaining high processing speed and improved accuracy.

Inventive Principle:

Principle #10Preliminary action

2Extent of automation

If machine learning algorithms are used to identify airport features, then the automation level is improved, but the measurement precision of feature coordinates and dimensions deteriorates

Engineering Contradiction:

Improveautomation of feature identificationVSAvoidprecision of coordinates and dimensions

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The system uses predetermined logical tests to verify the precision of machine learning estimates for coordinates and dimensions. The feedback from these logical tests allows the system to maintain high automation while improving measurement precision by filtering out inaccurate estimates.

Inventive Principle:

Principle #23Feedback

3Reliability

If logical tests are applied to review machine learning estimates, then the accuracy of feature categorization is improved, but the device complexity increases

Engineering Contradiction:

Improveaccuracy of feature categorizationVSAvoidcomplexity of processing system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary machine learning estimation followed by predetermined logical tests. This structured approach improves accuracy by systematically verifying estimates without requiring complex real-time processing, thus managing device complexity effectively.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The predetermined logical tests act as an intermediary between the machine learning algorithm and the final output. This intermediary layer verifies and refines estimates, improving accuracy while keeping the overall system complexity manageable through modular design.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Reliability

If real-world coordinates and dimensions are determined for segments, then the reliability of feature identification is improved, but the loss of time in processing increases

Engineering Contradiction:

Improvereliability of feature identificationVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system determines real-world coordinates and dimensions as part of the preliminary estimation phase, before applying logical tests. This approach improves reliability by having ground truth data available for verification while minimizing additional processing time through efficient calculation methods.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250265837A1Aircraft scene perception

Publication Date: 2025.08.21 COLLINS AEROSPACE IRELAND LTD

AI summary

A method of perceiving an airport scene is disclosed. The method comprises receiving an image of at least part of an airport and processing (304) said image using a first machine learning algorithm to identify at least one segment (402) in said image and determine an initial estimate of a category of airport feature present in said segment. The method also comprises determining (310) one or more real-world coordinates or dimensions associated with the segment, applying (312) one or more predetermined logical tests to the initial estimate of the category of airport feature present in the segment and the real-world coordinates or dimensions of the segment to determine a reviewed estimate of the category of airport feature present in the segment, and outputting (320) said reviewed estimate.