Time-Varying Signal Formation for Contactless Vital Sign Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for contactless imaging of vital signs, such as SpO2, face challenges in accurate outlier removal due to inadequate pixel alignment, particularly when differences between corresponding pixels are at or below the quantization error level.
Innovation Solution
A method that forms and processes time-varying signals by selecting groups of pixel values from multiple images, allowing for different sub-sets to be used across varying intervals, and fuses these signal segments to extract biometric information from skin reflectance variations, thereby improving alignment accuracy and reducing noise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional outlier removal methods are used with fixed alignment parameters, then the processing is simple, but the alignment accuracy deteriorates when pixel differences are at or below quantization error level
Solution Approach 1:
The patent segments the signal processing into multiple intervals and selects different sub-sets of pixel values for each interval. This allows the system to adapt to varying alignment conditions across different time periods without requiring complex global realignment, thereby improving alignment accuracy while keeping processing manageable through structured segmentation.
Solution Approach 2:
The patent dynamically adjusts the selection of pixel sub-sets based on the specific interval being analyzed. Instead of using a fixed alignment approach, the system adapts its pixel selection criteria for each interval, allowing it to handle varying degrees of alignment accuracy requirements and maintain optimal performance across different conditions.
2Measurement precision
If a single region of interest is tracked throughout the entire image sequence, then the method is simple, but the signal accuracy deteriorates due to motion artifacts and illumination changes
Solution Approach 1:
The patent divides the image sequence into multiple intervals and selects different pixel sub-sets for each interval rather than tracking a single region throughout. This segmentation approach allows the system to adapt to motion artifacts and illumination changes that occur between intervals, improving signal accuracy by selecting the most reliable pixel data for each time period.
Solution Approach 2:
The patent changes the parameters of pixel selection based on the specific interval being analyzed. By adjusting which pixel sub-sets are selected for each interval, the system can compensate for changes in lighting conditions, motion, and other environmental factors, thereby maintaining high signal accuracy without requiring complex continuous tracking.
3Measurement precision
If corresponding pixel sub-sets are selected from multiple images to form groups, then the signal represents accurate variations, but the processing time increases
Solution Approach 1:
The patent segments the processing into discrete intervals and selects pixel sub-sets for each interval independently. This segmentation allows the system to process data in manageable chunks rather than handling the entire sequence at once, improving signal representation accuracy while controlling processing time through structured, interval-based computation.
Solution Approach 2:
The patent selects and processes only the necessary pixel sub-sets for each interval rather than processing all pixels throughout the entire sequence. This partial action approach focuses computational resources on the most relevant data for each time period, improving signal accuracy while reducing overall processing time by avoiding unnecessary computations.
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
This approach enhances the accuracy of time-varying signals for spectral analysis, effectively determining heart rate or respiration rate by accounting for variations in color and intensity, while being robust against motion artifacts and illumination changes.
Implementation Method 1
Contactless Multiple Wavelength Photoplethysmographic Imaging: A First Step Toward SpO2 Camera Technology, Annals of Biomedical Engineering, vol. 33, no. 8, 1 August 2005, pages 1034-1041, relates to a system for contactless imaging of arterial oxygen saturation (SpO2) distribution within tissue, based upon detection of a 2-dimensional-matrix of spatially resolved optical plethysmographic signals
Data Source
AI summary
A method of forming a time- varying signal representative of at least variations in a value based on pixel values from a sequence of images, the signal corresponding in length to the sequence of images, includes obtaining the sequence of images. A plurality of groups (21) of sub-sets of pixel values are formed by selecting a sub-set of at least one pixel value from each of at least two images defining an interval to form a group (21) of associated sub-sets. For any pair of groups (21) with only sub-sets from the same images, the sub-sets from more than one image are different. Groups (21) of sub-sets are selected to form the signal in accordance with at least one selection criterion. The selected groups (21) of sub-sets cover different intervals, shorter than a length of the sequence