Mobile Device Biometric Detection via Motion-Compensated Image Amplification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing mobile device technologies face challenges in accurately measuring biometric characteristics like heart rate and breathing rate due to device motion and positioning issues, which affect the reliability of image-based vital signs monitoring.

Innovation Solution

The method involves capturing images of a target object using a mobile device, determining the device's motion by tracking a stationary reference object or using onboard sensors, and applying Eulerian motion amplification processes to extract and amplify variations in the target object's features, such as skin color changes, independent of the object's position, to derive biometric characteristics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a mobile device is used to capture images for biometric measurement, then the ease of operation and accessibility are improved, but the measurement precision and reliability deteriorate due to device motion and positioning issues

Engineering Contradiction:
Improveease of operationVSAvoidmeasurement precision
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces a stationary reference object as an intermediary element between the mobile device and the target object. This reference object serves as a stable mediator that allows the system to compensate for device motion. By tracking the reference object's position across multiple frames, the system can calculate motion vectors and apply corrective transformations to maintain accurate measurement of the target object's biometric features despite handheld device movement

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent dynamically adjusts measurement parameters based on detected device motion. The system changes the frame of reference for image analysis by applying motion compensation transformations derived from reference object tracking. This parameter change approach allows the measurement system to adapt to varying device positions and orientations, maintaining measurement precision across different operating conditions

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If the device moves during image capture, then the ease of operation is maintained, but the reliability of the measurement deteriorates due to position-dependent variations

Engineering Contradiction:
Improveease of operationVSAvoidreliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The stationary reference object acts as a mediator that enables the system to distinguish between device-induced motion and actual target object variations. By providing a stable reference frame, it allows reliable separation of motion artifacts from genuine biometric signals, maintaining measurement reliability during handheld operation

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary motion compensation by tracking the reference object and calculating motion vectors before conducting the actual biometric measurement. This preliminary action of establishing a corrected frame of reference ensures that subsequent measurements are not affected by device motion, maintaining reliability throughout the capture sequence

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If motion amplification is applied to extract varying features, then the measurement precision is improved, but the device complexity increases due to additional processing steps

Engineering Contradiction:
Improvemeasurement precisionVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts and isolates the motion component from the image sequence by using the stationary reference object as a basis for separation. By taking out the device-induced motion as a distinct element that can be measured and compensated, the system simplifies the subsequent extraction of actual biometric variations, achieving high precision without requiring complex multi-step processing of the entire image

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3072106B1Detection of an object's varying features with a non-stationary device
Publication Date: 2018.01.03 QUALCOMM INC
  • EP3072106B1 patent drawingFigure 1
  • EP3072106B1 patent drawingFigure 2
  • EP3072106B1 patent drawingFigure 3

AI summary

Disclosed are systems, apparatus, devices, method, computer program products, media and other implementations, including a method that includes capturing by an image capturing unit of a mobile device images of a scene including a target object, determining motion of the mobile device, and detecting from the captured images variations in one or more varying features of the target object based, at least in part, on the determined motion of the mobile device, the variations in the one or more varying features being independent of the target object's position in the scene.