UAV Surface Inspection Flight Path Using Targeted Non-Visible Imaging

Solution Overview

Problem

Existing drone systems that capture images using infrared or ultraviolet light for damage diagnosis face excessive power consumption and reduced flight time due to continuous irradiation, even when no damage is present, and require re-capturing images with different wavelengths for analysis.

Innovation Solution

A computer system and method that acquires images from a drone, performs image analysis to extract points with significant edge variations or low resolution, and controls the drone to fly towards these points for re-capturing using non-visible light, reducing power consumption and enabling efficient data collection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If continuous irradiation with non-visible light is used for damage diagnosis, then measurement precision is improved, but use of energy increases excessively

Engineering Contradiction:

Improvedamage diagnosis accuracyVSAvoidpower consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs periodic image capture with non-visible light only at intervals or when specific conditions are met, rather than continuous irradiation. The drone captures images using non-visible light periodically during flight, reducing energy consumption while still achieving effective damage diagnosis through targeted periodic measurement.

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

The system applies non-visible light irradiation locally only to specific regions of interest identified in visible light images, rather than irradiating the entire area. By extracting interest points from visible light images and targeting only those locations for non-visible light capture, the system reduces overall energy consumption while maintaining diagnostic precision where needed.

Inventive Principle:

Principle #3Local quality

2Measurement precision

If continuous irradiation with non-visible light is used for damage diagnosis, then measurement precision is improved, but duration of action decreases

Engineering Contradiction:

Improvedamage diagnosis accuracyVSAvoidflight time

Core Design Contradiction:

Measurement precisionVSDuration of action of moving object

Solution Approach 1:

The system performs periodic image capture with non-visible light only at intervals or when specific conditions are met, rather than continuous irradiation. The drone captures images using non-visible light periodically during flight, reducing energy consumption while still achieving effective damage diagnosis through targeted periodic measurement.

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

The system applies non-visible light irradiation locally only to specific regions of interest identified in visible light images, rather than irradiating the entire area. By extracting interest points from visible light images and targeting only those locations for non-visible light capture, the system reduces overall energy consumption while maintaining diagnostic precision where needed.

Inventive Principle:

Principle #3Local quality

3Measurement precision

If non-visible light is used for all image capture, then measurement precision is improved, but use of energy increases

Engineering Contradiction:

Improveimage analysis accuracyVSAvoidpower consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system segments the image capture process into two stages: initial capture with visible light for general survey, followed by targeted re-capture with non-visible light only for specific interest points. This segmentation allows the system to use energy-intensive non-visible light only when necessary, reducing overall power consumption while maintaining analytical accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies non-visible light irradiation locally only to specific regions of interest identified in visible light images, rather than irradiating the entire area. By extracting interest points from visible light images and targeting only those locations for non-visible light capture, the system reduces overall energy consumption while maintaining diagnostic precision where needed.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS11774969B2System and method using image analysis for controlling a flight path of a surface inspection unmanned aerial vehicle

Publication Date: 2023.10.03 OPTIM

AI summary

Provided are a computer system and method using image analysis for controlling a flight path of a surface inspection unmanned aerial vehicle, wherein the computer system is configured to: acquire an image captured by a drone; perform image analysis on the acquired image; extract, in a result of the image analysis, a point whose an edge variation amount is equal to or greater than a predetermined threshold; acquire a position coordinate of the extracted point; in a case where there are a plurality of points, set a flight path of the drone in a manner of flying in an order of edge variation amounts of the plurality of points from large to small; and control the drone to fly towards the acquired position coordinate and perform capturing with a camera using light other than visible light.