Mid-Point Stitching for Continuous PPG Signal Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for continuous cardiac pulse rate estimation from video data introduce artifacts due to endpoint stitching, which affects the accuracy and consistency of cardiac signal processing.
Innovation Solution
A system and method that processes time-series signals from video images by dividing them into batches with significant overlap, stitching together mid-points of each batch to generate a continuous cardiac signal, and using constrained source separation to remove artifacts and ensure accurate cardiac pulse rate estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of stationary object
If endpoint stitching is used to combine signal segments, then continuous cardiac signal can be obtained, but artifacts are introduced affecting signal accuracy
Solution Approach 1:
The patent divides the continuous video signal into multiple overlapping batches or segments for processing. Each batch is processed independently to extract PPG signals, and the overlapping regions provide redundancy that enables artifact-free continuous signal construction without traditional endpoint stitching.
Solution Approach 2:
The patent performs preliminary processing on each batch including signal extraction and artifact removal before combining results. By preparing each segment in advance with proper overlap, the system eliminates the need for post-processing stitching that introduces artifacts.
2Productivity
If video signal is divided into batches for processing, then computational efficiency is improved, but signal continuity may be compromised
Solution Approach 1:
The continuous video signal is segmented into discrete batches for parallel processing, improving computational efficiency. The segmentation is designed with overlapping regions that preserve signal continuity information across batch boundaries.
Solution Approach 2:
The patent introduces the dimension of temporal overlap between batches, transforming the simple sequential processing into a multi-dimensional approach where batches overlap in time. This allows independent batch processing while maintaining continuous signal integrity through the overlap regions.
3Measurement precision
If mid-point stitching is used instead of endpoint stitching, then artifacts are reduced, but processing complexity increases
Solution Approach 1:
Instead of stitching endpoints of consecutive segments (traditional approach), the patent inverts the approach by using mid-points of overlapping batches as the connection point. This reversal eliminates the discontinuity and artifact problems associated with endpoint stitching.
Solution Approach 2:
The overlapping batch regions serve as intermediaries that bridge consecutive processing segments. By selecting mid-points within these overlap regions for stitching, the method creates smooth transitions without artifacts while managing complexity through systematic selection criteria.
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 provides a computationally efficient and accurate method for continuous cardiac pulse rate estimation, reducing artifacts and improving measurement consistency, enabling reliable monitoring in non-contact remote sensing environments.
Implementation Method 1
a time-series signal generated from video captured of a subject being monitored for cardiac function... video images captured of a region of exposed skin where a PPG signal of a subject of interest can be registered
Data Source
AI summary
What is disclosed is a novel system and method for extracting photoplethysmographic (PPG) signals (i.e., cardiac signals) on a continuous basis from signals generated from video images captured of a subject being monitored for cardiac function in a non-contact remote sensing environment. In one embodiment, a time-series signal is received. The time-series signal is generated from video images captured of a region of exposed skin where a PPG signal of a subject of interest can be registered. The time-series signal is then divided into batches for processing, with successive batches having at least a 95% overlap with a previous batch. Each of the batches of time-series signals is processed to obtain a PPG signal from each batch. A mid-point of each of these PPG-signals is stitched together to obtain a continuous PPG signal for the subject. The continuous PPG signal for the subject can then viewed on a display device.