Contactless Disease Detection System Using Multi-Sensor Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for detecting contagious diseases like COVID-19 are inefficient, relying on temperature checks and clinical examinations with low confidence levels, and lack the ability for rapid, contactless, and mass screening.

Innovation Solution

A system utilizing a combination of physiological measurement sensors, thermal cameras, and artificial intelligence for rapid diagnosis, enabling contactless data acquisition and processing to provide diagnostic information on the probability of infection, which can be displayed remotely and automatically, facilitating rapid diagnosis and mass screening.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional temperature checks and clinical examinations are used, then the detection process is simple, but the confidence level and accuracy of disease detection remain low

Engineering Contradiction:
Improvedetection accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple sensing modalities (thermal imaging, visible imaging, radar) into a single integrated detection system. This merging of different measurement techniques enables comprehensive disease detection with high confidence levels while maintaining a unified system architecture that processes all sensor data through a common AI diagnostic engine.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The detection system is designed to perform multiple functions: thermal imaging for temperature detection, visible imaging for facial and respiratory pattern analysis, radar for contactless physiological monitoring, and AI-based diagnostic processing. This multi-functionality allows a single system to replace multiple separate detection methods while improving overall detection accuracy.

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

2Object-affected harmful factors

If contactless measurements are implemented, then the risk of contamination is reduced, but the technical complexity of the acquisition device increases

Engineering Contradiction:
Improvecontamination riskVSAvoidacquisition device complexity
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The patent replaces direct physical contact with contactless sensing technologies. Thermal cameras detect body temperature without contact, radar sensors measure respiratory and cardiac rates remotely, and visible cameras monitor facial expressions and movements. This substitution eliminates mechanical contact while gathering comprehensive physiological data through electromagnetic field-based sensing.

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

Solution Approach 2:

The system uses electromagnetic fields (infrared for thermal imaging, radio waves for radar) as intermediaries to transmit physiological information from the patient to the sensors without direct contact. These intermediary fields enable remote measurement of temperature, respiration, and heart rate while maintaining safety and preventing contamination.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of time

If rapid diagnosis is achieved through automated processing, then the time required for detection is reduced, but the need for advanced AI processing increases system complexity

Engineering Contradiction:
Improvediagnosis timeVSAvoidprocessing system complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The system performs preliminary processing of sensor data in real-time as it is acquired. The AI diagnostic engine continuously analyzes incoming thermal, visible, and radar data streams, pre-processing and filtering information before final diagnostic rendering. This preliminary action enables rapid diagnosis by having the processing pipeline already prepared and active before complete data collection is finalized.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The AI diagnostic engine autonomously processes the sensor data without requiring manual intervention or interpretation by medical personnel. The system self-services by automatically integrating multi-sensor data, identifying patterns indicative of disease, and generating diagnostic outputs. This automation dramatically reduces diagnosis time while the AI system manages its own complex processing requirements internally.

Inventive Principle:
Principle #25Self-service

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 rapid, accurate, and contactless detection of contagious diseases, reducing the risk of contamination and facilitating the deployment of field hospitals, allowing for quicker return to work or lifting of lockdowns by providing diagnostic information within minutes.

Implementation Method 1

an acquisition device for acquiring examination data on the person, this acquisition device notably comprising at least one physiological measurement sensor such as a radar

Methodology Applied
Scientific EffectRadar: Radar

Implementation Method 2

a thermal camera for acquiring these examination data

Methodology Applied
Scientific EffectThermal radiation: Thermal Radiation

Data Source

PatentUS20230414114A1Disease detection system
Publication Date: 2023.12.28 VALEO SYST THERMIQUES SAS
  • US20230414114A1 patent drawing
  • US20230414114A1 patent drawing

AI summary

A system for detecting a disease in a person, having an acquisition device configured to acquire examination data on the person, and a data processing device arranged to receive the examination data and including a correction table with at least one corrective term corresponding to a measurement error or to variation of a physical characteristic between individuals; the data processing device being arranged to correct the examination data using the at least one corrective term and consequently generate a corrected value, the data processing device including a memory of reference values and being configured to compare the reference values against the corrected value.