SAR Neural Network Object Measurement Through Cloud Obstruction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for monitoring facility states, such as floating roof container levels, are inefficient due to the need for physical observation and are hindered by obstructions like clouds and smoke, leading to inaccurate reports and inability to quickly measure multiple facilities.

Innovation Solution

A system using synthetic aperture radar (SAR) devices to capture backscatter signatures, which are analyzed using deep learning to determine object measurements, allowing for regular and accurate assessments regardless of weather conditions, without the need for direct visual imaging.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If optical imagery is used to observe facilities, then visual measurements can be obtained, but measurements cannot be taken when cloud cover or other obstructions are present

Engineering Contradiction:
Improvemeasurement availabilityVSAvoidcloud cover obstruction
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent introduces SAR technology as an intermediary measurement method that operates independently of optical conditions. Instead of relying on visible light that can be blocked by clouds, the system uses radar waves that can penetrate cloud cover, smoke, and other obstructions to obtain measurements of facility features such as floating roof heights

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the optical imaging system with a radar-based SAR system. This substitution transitions from using electromagnetic waves in the visible spectrum (which are easily blocked) to using radar waves (which can penetrate obstructions), thereby eliminating the harmful effect of cloud cover on measurement availability

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If physical observers are deployed to visit each facility, then direct measurements can be obtained, but the process is inefficient and time-consuming

Engineering Contradiction:
Improvedirect observation accuracyVSAvoidfacility monitoring efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The SAR system serves multiple facilities simultaneously through a single remote sensing platform. Instead of deploying individual observers to each facility, one SAR system can capture images of multiple facilities in sequence or parallel, providing universal measurement capability across numerous locations

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

Solution Approach 2:

The patent creates remote copies of facility measurements through SAR imaging. Physical observers are replaced by virtual observers using SAR technology to capture images and extract measurements from distant locations, eliminating the need for physical presence while maintaining measurement capability

Inventive Principle:
Principle #26Copying

3Loss of information

If optical sensors are used to image facilities, then visual data can be captured, but measurements cannot be obtained quickly for multiple facilities

Engineering Contradiction:
Improvevisual data qualityVSAvoidmeasurement time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The SAR system enables continuous measurement operations regardless of weather conditions. While optical sensors must stop operation during cloudy periods, the SAR system maintains continuous useful action by penetrating cloud cover, ensuring uninterrupted data collection across multiple facilities over time

Inventive Principle:
Principle #20Continuity of useful action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables regular and accurate measurements of facility states, such as container levels, over a larger area and through adverse weather, reducing human error and increasing efficiency in monitoring multiple facilities.

Implementation Method 1

a synthetic aperture radar (SAR) device to capture SAR backscatter signatures

Methodology Applied
Scientific EffectRadar: Radar

Data Source

PatentEP3805794B1Analysis of SAR data using neural networks
Publication Date: 2024.08.21 ORBITAL INSIGHT INC
  • EP3805794B1 patent drawingFigure 1
  • EP3805794B1 patent drawingFigure 2
  • EP3805794B1 patent drawingFigure 3

AI summary

A system is configured to receive synthetic aperture radar (SAR) backscatter signatures of a geographical area including the object of interest from a SAR device. The system also extracts feature vectors from the SAR backscatter signature based on the intensity values of the SAR backscatter signature. The system inputs the one or more feature vectors into a neural network model. The system receives, as output from the neural network model, coordinate values indicating one or more visual features of the object of interest. Using these coordinate values, the system determines one or more measurements of the object of interest.