Polarimetric Sensor Array with AI Subsystem for Machine Vision

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current machine vision systems lack polarimetric functionalities, which are essential for navigation and authentic image processing, and are often bulky, energy-intensive, and inefficient due to discrete computation hierarchies.

Innovation Solution

An optically-controlled polarimetry memtransistor (OCPM) based on a van der Waals heterostructure (ReS2/GeSe2) is integrated into a polarimetric sensor array, coupled with an artificial intelligence subsystem to process polarization signals for machine vision functions, enabling real-time navigation and anti-glare pattern recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional machine vision systems are used, then basic image capture is achieved, but polarimetric functionality is missing and system becomes bulky

Engineering Contradiction:

Improvepolarimetric functionalityVSAvoidsystem structure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges polarimetric sensing and machine vision processing into a single integrated system. The polarimetric sensor array captures polarization information directly at the sensor level, while the AI subsystem processes this data for machine vision functions, eliminating the need for separate bulky polarimetric devices and traditional image processing pipelines.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The integrated system performs multiple functions simultaneously: capturing visible light images, detecting polarization patterns, and executing machine vision algorithms. The polarimetric sensor array serves both as an image sensor and a polarization detector, while the AI subsystem handles both navigation and pattern recognition tasks.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Productivity

If discrete computation hierarchies are used, then processing is achieved, but energy consumption increases

Engineering Contradiction:

Improveprocessing capabilityVSAvoidenergy consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent replaces traditional discrete computational hierarchies with a neuromorphic computing approach that mimics biological neural networks. The system uses spiking neural networks with event-driven processing, where computational operations occur only when necessary (when events are detected), significantly reducing energy consumption compared to continuous processing in traditional systems.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The neuromorphic computing system employs event-driven, periodic processing rather than continuous computation. The AI subsystem activates and processes polarization signals only when changes are detected in the field of view, creating an efficient periodic action pattern that reduces overall energy consumption while maintaining processing capability.

Inventive Principle:

Principle #19Periodic action

3Adaptability or versatility

If polarimetric sensors are added to machine vision systems, then navigation capability is improved, but device complexity increases

Engineering Contradiction:

Improvenavigation capabilityVSAvoidsensor array integration

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent integrates polarimetric sensing elements directly into the machine vision sensor array, creating a unified sensor structure. This merging approach allows the system to capture both intensity and polarization information simultaneously using a single sensor array, avoiding the complexity of adding separate polarimetric devices.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The sensor array is designed to perform multiple functions: capturing visible light for image processing and detecting polarization patterns for navigation. Each sensor element in the array contributes to both image formation and polarization measurement, eliminating the need for additional dedicated navigation sensors.

Inventive Principle:

Principle #6Universality (Multi-functionality)

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

The system achieves efficient real-time navigation and significantly reduces energy consumption by integrating polarimetric and cognitive recognition functions, improving pattern recognition accuracy and reducing training epochs by an order of magnitude compared to traditional neuromorphic machine vision systems.

Implementation Method 1

detect incoming light representing a field of view of the polarimetric sensor array; and generate a polarization signal representing a polarization of the incoming light

Methodology Applied

Scientific EffectPolarization: Polarisation

Data Source

PatentUS20250130108A1Polarimetric sensor array for machine vision systems

Publication Date: 2025.04.24 WU YIMIN A

AI summary

An example device includes a polarimetric sensor array comprising an optically controlled polarimetry memtransistor, the polarimetric sensor array configured to: detect incoming light representing a field of view of the polarimetric sensor array; and generate a polarization signal representing a polarization of the incoming light; and an artificial intelligence subsystem interconnected with the polarimetric sensor array, the artificial intelligence subsystem configured to: process the polarization signal for a machine vision function on the field of view.