Adaptive Edge Extraction for Vehicle Landing Surface Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vision-based landing systems face challenges in accurately detecting edges and features of landing zones due to false positives from similar angled lines, limiting their effectiveness in navigation assistance for aerial vehicles.

Innovation Solution

An adaptive feature extraction method using onboard cameras, navigation databases, and vehicle sensors to estimate the slope and gradient of landing surface features, employing combined convolution kernels to filter out undesired edges and enhance detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If simple edge detection techniques are used to find landing zone features, then the system complexity is reduced, but false positives increase due to similar angled lines in the environment

Engineering Contradiction:
Improvesystem complexityVSAvoiddetection accuracy
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system performs preliminary actions by estimating the slope and gradient of the landing surface before conducting edge detection. This preliminary estimation allows the system to configure detection parameters in advance, making the detection process more targeted and less prone to false positives from unrelated edges in the environment.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The edge detection technique is made dynamic by adapting the detection parameters based on real-time estimation of landing surface characteristics. The system continuously adjusts detection sensitivity and orientation based on the estimated slope and gradient, allowing it to maintain high accuracy across varying landing zone configurations without requiring a fixed complex system.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If adaptive feature extraction with slope estimation is implemented, then edge detection accuracy is improved, but device complexity increases

Engineering Contradiction:
Improveedge detection accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system changes detection parameters dynamically based on estimated landing surface characteristics. By adjusting detection sensitivity, orientation, and threshold values according to the measured slope and gradient, the system achieves high measurement precision without requiring multiple fixed complex detection systems for different scenarios.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The adaptive feature extraction system serves multiple functions: it estimates slope, determines gradient, configures detection parameters, and performs edge detection all within a single integrated framework. This multi-functionality reduces the need for separate specialized systems while maintaining high detection accuracy across various landing zone types.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4239587B1Adaptive feature extraction to detect letters and edges on vehicle landing surfaces
Publication Date: 2025.09.03 HONEYWELL INTERNATIONAL INC
  • EP4239587B1 patent drawingFigure 1A
  • EP4239587B1 patent drawingFigure 1B
  • EP4239587B1 patent drawingFigure 2A~2C

AI summary

A vison-based landing system comprises a processor onboard an aerial vehicle, an onboard vision sensor, onboard aiding sensors, and a data storage unit. The processor hosts an adaptive feature extraction module operative to perform a method that comprises capturing an image of a landing area having a plurality of edge features; calculating an estimated slope of an expected edge feature; calculating an expected gradient direction of the expected edge feature; selecting a horizontal basis kernel for the expected edge feature along an expected horizontal gradient; selecting a vertical basis kernel for the expected edge feature along an expected vertical gradient; calculating a combined convolution kernel for the expected edge feature based on the horizontal and vertical basis kernels, the estimated slope, and the expected gradient direction; and performing a convolution operation on the image using the combined convolution kernel to obtain an edge feature image of the landing area.