Camera-Based SpO2 Estimation Using Multi-Channel Color Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional contact-based SpO2 measurement methods cause discomfort, skin irritation, and are not accessible to the public, necessitating a contactless technique for SpO2 estimation.
Innovation Solution
A method utilizing a camera to capture images or videos, perform feature extraction, and estimate blood oxygen saturation through spatial and temporal data analysis of multiple color channels, incorporating spatial averaging, color channel mixing, and temporal trend analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contact-based pulse oximetry is used, then SpO2 measurement can be obtained, but skin irritation and discomfort occur
Solution Approach 1:
The patent replaces the mechanical contact-based optical sensing system with a contactless video-based system. Instead of placing an optical sensor in direct contact with the fingertip to detect light absorption, the system uses a camera to capture video of the fingertip and analyzes color changes in the RGB channels to estimate SpO2, thereby eliminating skin irritation while maintaining measurement capability
Solution Approach 2:
The patent introduces video capture and color space transformation as an intermediary between the light-tissue interaction and the SpO2 measurement. By capturing reflected light through a camera and processing it through RGB to YCbCr color space transformation, the system indirectly measures SpO2 without requiring direct contact between sensor and tissue
2Measurement precision
If conventional pulse oximeter is used, then SpO2 reading is obtained, but measurement deviation of ±2% exists
Solution Approach 1:
The patent transitions from the traditional two-wavelength (red and infrared) measurement approach to a multi-dimensional color space analysis using YCbCr channels. By utilizing the Cr channel which captures red color information and combining it with temporal analysis of color variations, the system achieves improved measurement precision with mean absolute error of 1.26%, outperforming conventional ±2% deviation
Solution Approach 2:
The patent employs dynamic temporal analysis of color channel variations over time to extract SpO2 information. By analyzing the temporal trends and pulsatile variations in the Cr channel and other color channels, the system dynamically adapts to changing physiological conditions and achieves more reliable and accurate SpO2 measurements
3Object-affected harmful factors
If contactless video-based method is used, then skin irritation is eliminated, but measurement accuracy must be maintained
Solution Approach 1:
The patent transforms the input video data from RGB color space to YCbCr color space and utilizes specific channel combinations (particularly the Cr channel) to optimize the measurement. By changing the parameter representation of color information and applying temporal filtering and pulsatile component extraction, the system maintains high measurement accuracy (1.26% mean absolute error) while achieving contactless operation
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
Achieves accurate SpO2 estimation with a mean absolute error of 1.26%, outperforming traditional methods by 25%, and is tolerant to different skin tones and ambient lighting conditions.
Implementation Method 1
The RoR principle is based on the different optical absorption rates of the oxygenated hemoglobin (HbO2) and deoxygenated hemoglobin (Hb) at 660 nm (red) and 940 nm (infrared) wavelengths
Data Source
AI summary
Systems, methods, apparatuses, and computer program products for contactless image-based blood oxygen estimation. A method may include receiving an image or video of a part of a subject captured by a camera of a computing device. The method may also include extracting a region of interest of the part of the subject from the image or video. The method may further include performing feature extraction of the region of interest. In addition, the method may include estimating a blood oxygen saturation level of the subject based on a spatial and temporal data analysis of more than two color channels. Feature extraction and estimation of the blood oxygen saturation level may include implementing a combination of spatial averaging, color channel mixing, and temporal trend analysis.