Electro-Optic Protection via Machine Learning Video Metrics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems for protecting electro-optic systems against degradation and disruption lack real-time, reliable, and non-destructive capabilities, relying heavily on subjective human analysis and binary engagement approaches, which are inefficient and unreliable.

Innovation Solution

An artificial learning counter surveillance system using machine learning algorithms and video metrics analysis to automate the assessment of directed energy effects on electro-optic systems, enabling quantifiable results and varying levels of disruption or degradation engagement, from minor to complete, without causing permanent damage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If laser countermeasures are used to disrupt electro-optic systems, then disruption effectiveness is improved, but permanent damage to the system occurs

Engineering Contradiction:

Improvedisruption effectivenessVSAvoidpermanent damage

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system changes the parameters of laser energy application by using multiple metrics (structural similarity, power spectral density, radius of saturated pixels) to precisely control and measure the level of disruption, enabling adjustment between minor degradation and complete disruption without permanent damage

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces subjective human visual analysis with automated machine learning algorithms and video metrics analysis, substituting mechanical/manual assessment with systematic computational analysis to determine disruption levels

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If human visual analysis is used to assess disruption effectiveness, then system complexity is reduced, but analysis reliability and objectivity deteriorate

Engineering Contradiction:

Improvesystem simplicityVSAvoidanalysis reliability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system replaces the human visual system (HVS) with automated machine learning algorithms and video metrics analysis, substituting subjective human analysis with objective computational methods that systematically evaluate disruption effectiveness

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automating the analysis process through machine learning algorithms that independently assess video metrics and determine disruption levels without requiring constant human intervention or subjective judgment

Inventive Principle:

Principle #25Self-service

3Speed

If binary engagement approach is used (engaged/not engaged), then decision-making speed is improved, but measurement precision of disruption levels deteriorates

Engineering Contradiction:

Improvedecision-making speedVSAvoiddisruption level precision

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The system transitions from binary engagement states to a multi-level disruption scale by introducing multiple video metrics (structural similarity index, power spectral density, radius of saturated pixels) that enable precise measurement of disruption intensity ranging from minor degradation to complete disruption

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent segments the disruption assessment into multiple measurable components using different video metrics, dividing the continuous disruption spectrum into quantifiable levels that can be systematically analyzed and reported

Inventive Principle:

Principle #1Segmentation

4Adaptability or versatility

If constant human interaction is used for video analysis, then analysis adaptability is improved, but productivity and efficiency deteriorate

Engineering Contradiction:

Improveanalysis adaptabilityVSAvoidanalysis efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system implements self-service by using machine learning algorithms that automatically perform video analysis without requiring constant human interaction, enabling the system to independently process and interpret video metrics for disruption assessment

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system incorporates feedback mechanisms where machine learning algorithms continuously analyze video metrics and adjust their assessment based on the measured disruption levels, providing systematic feedback loops that improve analysis accuracy without human intervention

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10579911B2Systems and related methods employing directed energy and machine learning operable for enabling or protecting from non-destructive degradation or disruption of electro-optic(s) or sensors

Publication Date: 2020.03.03 THE UNITED STATES OF AMERICA AS REPRESENTED BY THE SECRETARY OF THE NAVY

AI summary

Various embodiments can include artificial learning counter surveillance (ALCS) or self-protection surveillance systems (SPSS) and related methods. Apparatuses and methods can include non-destructive electro-optic interference or protection systems as well non-destructive directed energy systems, a control system, and an analysis system for determining an optical system of interest and generating degradation or disruption effects using various equipment items and machine learning systems. Additionally, methods are also provided for determining degree of severity of degradation or disruption based on threshold definitions related to ability to use the optical system of interest for one or more specified applications.