Pulse Wave Calculation Using Multi-Frame Pixel Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pulse wave calculation methods suffer from increased noise due to rigid or non-rigid body motion of a living organism, leading to a decrease in the number of pixels used in the region of interest, which affects the signal-to-noise ratio and introduces noise in the calculated pulse wave signal.
Innovation Solution
An information processing device and method that specifies a region of interest in images, calculates representative pixel values across multiple frames, combines these values to reduce noise, and computes a pulse wave signal from temporal changes in these combined values, effectively stabilizing the signal by minimizing the impact of slight displacements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pixels in motion-affected portions of the region of interest are excluded from pulse wave calculation, then noise from rigid body motion or non-rigid body motion is reduced, but the number of usable pixels decreases, causing the signal-to-noise ratio to fall and noise to increase across the data set
Solution Approach 1:
The patent divides the region of interest into multiple subregions and processes each subregion separately. By segmenting the ROI, the system can identify and exclude only those specific subregions affected by motion while retaining pixels from subregions that remain stable, thus maintaining a higher number of usable pixels compared to excluding entire motion-affected portions.
Solution Approach 2:
The patent applies different processing treatments to different subregions based on their individual motion characteristics. Subregions with significant motion are excluded or weighted differently, while subregions with minimal motion are given full weight in the pulse wave calculation. This local quality approach ensures that only the necessary portions are filtered, preserving the overall signal-to-noise ratio.
2Object-affected harmful factors
If the number of pixels in the region of interest changes based on whether the living organism has moved, then motion-affected areas are excluded, but the calculated pulse wave signal includes noise due to this dynamic change in pixel count
Solution Approach 1:
The patent performs preliminary motion detection and subregion identification before the pulse wave calculation. By pre-identifying which subregions are affected by motion and assigning appropriate weights or exclusion flags, the system prepares the data in advance to prevent motion-induced noise from entering the pulse wave calculation, thereby maintaining signal accuracy.
Solution Approach 2:
The patent implements a feedback mechanism where motion detection results from analyzing temporal changes in pixel values are used to adjust the weighting or inclusion of subregions in subsequent pulse wave calculations. This feedback loop continuously refines the selection of usable pixels, ensuring that motion-affected areas are dynamically excluded while maintaining consistent signal quality across different motion states.
Data Source
AI summary
An information processing device including: a region of interest specifying unit configured to specify a location of a region of interest regarding an image of each frame of a moving image captured of a living organism; a pixel value calculation unit configured to calculate, in an image of a first frame of the moving image, a plurality of first representative values of pixel values of pixels in locations of a plurality of regions of interest specified regarding images of a plurality of second frames including the image of the first frame; a pixel value combining unit configured to calculate a second representative value regarding the first frame by combining the plurality of first representative values; and a pulse wave calculation unit configured to calculate a pulse wave signal from a temporal change in the second representative value.