Optical Depth Sensor Cardiac Pulse Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing non-contact optical methods for heart rate monitoring face challenges in accurately extracting cardiac pulses due to interference from unwanted motions such as breathing and involuntary body movements.
Innovation Solution
The use of optical depth sensors, such as depth cameras employing time-of-flight technology, to extract ballistocardiography (BCG) signals and estimate heart rate by processing optical depth video data through methods involving region of interest identification, signal decomposition, and pulsatile direction projection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If non-contact optical methods are used for heart rate monitoring, then physical contact discomfort is eliminated, but measurement precision deteriorates due to motion interference from breathing and involuntary body movements
Solution Approach 1:
The patent segments the depth video signal into multiple spatial channels by dividing the region of interest into multiple areas, then processes each channel separately through eigendecomposition to extract cardiac pulse information while suppressing motion interference
Solution Approach 2:
The patent transforms the depth video data into the eigen-space domain by performing eigendecomposition on the spatial-temporal data matrix, changing the parameter representation from raw pixel depth values to eigen-coefficients that separate cardiac pulse signals from motion artifacts
2Device complexity
If traditional signal processing methods are used on depth video data, then processing complexity is reduced, but measurement precision deteriorates due to inability to effectively separate cardiac pulses from motion artifacts
Solution Approach 1:
The patent extends the signal processing from traditional single-channel or color-space domain to a multi-dimensional eigen-space domain by performing eigendecomposition on the spatial-temporal data matrix, enabling separation of cardiac pulses from motion artifacts through dimensional transformation
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 enables accurate and noise-reduced heart rate monitoring without physical contact, effectively overcoming motion interference and providing reliable cardiac pulse signals.
Implementation Method 1
depth cameras that derive depth images based on time-of-flight (ToF) technology
Data Source
AI summary
A system and method utilizes optical depth sensors to estimate heart rate of one or more subjects. A method includes obtaining optical depth video data of at least one subject; identifying a region of interest of the subject(s) from optical depth video data; segmenting the region of interest into multiple areas; identifying pixel intensity with respect to time in the areas to produce a depth signal data matrix including multiple spatial channels; decomposing the depth signal data matrix into a low-rank spatial-temporal eigenvector matrix to produce refined depth signal data streams; and projecting the refined depth signal data streams onto a selected pulsatile direction and producing a cardiac pulse signal for the subject(s).