Respiratory Function Estimation from 2D Monocular Video
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current respiratory function monitoring technologies require expensive 3D imaging systems, making them cost-prohibitive for non-contact, remote sensing in developing countries, and are uncomfortable for patients, especially the elderly and those with chronic conditions, while 2D monocular video systems struggle to derive volumetric data effectively.
Innovation Solution
A method using a 2D monocular video acquisition system processes video signals by reconstructing 3D surface maps from distortions in patterns on the thoracic region, estimating respiratory functions like tidal chest volume and respiration rate, without the need for expensive equipment, by characterizing spatial distortions relative to a known reference pattern.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expensive multi-modular 3D imaging systems are used, then measurement precision of respiratory function is improved, but device complexity and cost increase making them cost-prohibitive
Solution Approach 1:
The patent uses a 2D monocular video camera to capture images of a patterned surface on the patient's chest, then reconstructs 3D surface maps from these 2D images by analyzing spatial distortions of the known pattern. This copying approach allows derivation of volumetric data from inexpensive 2D video signals without requiring expensive 3D imaging hardware.
Solution Approach 2:
The patent replaces complex mechanical 3D imaging systems with a computational approach using standard 2D video cameras. By substituting hardware complexity with image processing algorithms that analyze pattern distortions, the system achieves 3D measurement capabilities using inexpensive monocular video acquisition.
2Measurement precision
If contact-based sensing devices are worn on the patient's chest, then respiratory measurement accuracy is improved, but patient comfort and dignity deteriorate
Solution Approach 1:
The patent introduces a patterned surface (such as a patterned garment or sticker) as an intermediary between the camera and the patient's body. This intermediary allows the system to measure respiratory motion optically from a distance without requiring direct contact with sensors on the patient's skin, thereby maintaining measurement accuracy while improving comfort and dignity.
Solution Approach 2:
The patent replaces contact-based mechanical sensors with non-contact optical measurement using video imaging. By substituting physical sensors that require skin contact with optical pattern recognition from video frames, the system eliminates discomfort associated with wearing devices while preserving measurement capability.
3Device complexity
If 2D monocular video systems are used, then device cost and complexity are reduced, but ability to derive volumetric data deteriorates
Solution Approach 1:
The patent recovers 3D surface information from 2D video images by analyzing spatial distortions of a known pattern on the chest surface. By detecting how the 2D projection of the 3D pattern changes with breathing motion, the system reconstructs depth information and generates 3D surface maps, effectively adding a depth dimension to standard 2D video data.
Solution Approach 2:
The patent transforms the measurement approach by changing from direct 3D sensing to analyzing 2D parameter changes. By monitoring how 2D pattern coordinates, orientations, and scales change across video frames, the system derives 3D volumetric information through computational analysis of these parameter variations rather than direct 3D measurement.
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
Enables non-contact, remote sensing of respiratory functions, providing accurate estimates of tidal chest volume and respiration rate, facilitating early detection of fatal respiratory events without discomfort or high costs, suitable for resource-constrained settings.
Implementation Method 1
construct a temporal sequence of 3D surface maps of the patterned target region by characterizing an amount of spatial distortion detected in the pattern over time
Data Source
AI summary
What is disclosed is a system and method for processing a video acquired using a 2D monocular video camera system to assess respiratory function of a subject of interest. In various embodiments hereof, respiration-related video signals are obtained from a temporal sequence of 3D surface maps that have been reconstructed based on an amount of distortion detected in a pattern placed over the subject's thoracic region (chest area) during video acquisition relative to known spatial characteristics of an undistorted reference pattern. Volume data and frequency information are obtained from the processed video signals to estimate chest volume and respiration rate. Other respiratory function estimations of the subject in the video can also be derived. The obtained estimations are communicated to a medical professional for assessment. The teachings hereof find their uses in settings where it is desirable to assess patient respiratory function in a non-contact, remote sensing environment.