Respiratory Mask for Non-Contact Depth Signal Noise Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional medical monitoring systems face challenges in accurately measuring respiratory parameters like respiration rate, tidal volume, and oxygen saturation due to motion noise introduced by patient movement, especially in non-contact video-based monitoring where the camera's remote position creates a moving frame of reference and morphing of the monitored tissue.
Innovation Solution
The method involves using a non-contact patient monitoring system that extracts depth data from a region of interest (ROI) to calculate respiratory parameters by analyzing changes in depth and light intensity, applying a mask to filter out noise, and combining depth data with background images to produce a visual respiration overlay, utilizing depth sensing cameras and projectors to project features onto the patient's surface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If non-contact video-based monitoring is used to avoid patient contact, then patient comfort and infection risk are improved, but motion noise from patient movement degrades measurement accuracy
Solution Approach 1:
The patent divides the field of view into multiple depth regions (near, mid, far) and applies different processing strategies to each region. The mask identification algorithm segments respiratory regions from non-respiratory regions by analyzing depth data patterns, allowing selective processing that isolates useful respiratory signals from motion noise in different spatial zones.
Solution Approach 2:
The patent extracts depth data from specific regions of interest and separates respiratory depth variations from other motion artifacts. By extracting only the depth information corresponding to respiratory movements and excluding regions identified as non-respiratory, the system isolates the useful physiological signal from harmful motion noise.
2Adaptability or versatility
If the monitoring system covers a large field of view to monitor more patient areas, then monitoring versatility is improved, but noise from non-respiratory regions degrades signal quality
Solution Approach 1:
The patent segments the broad field of view into multiple depth regions and further identifies specific respiratory versus non-respiratory zones within those regions. This multi-level segmentation allows the system to maintain broad monitoring coverage while selectively processing only those regions containing useful respiratory signals, excluding noise from other areas.
Solution Approach 2:
The patent applies different processing qualities to different regions: full processing to respiratory regions of interest, reduced processing or exclusion to non-respiratory regions. This local differentiation allows the system to optimize signal quality in critical areas while managing computational load and noise from peripheral regions.
3Loss of information
If depth data from all regions is processed to ensure complete coverage, then data completeness is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent extracts and processes only the essential depth data from regions identified as containing respiratory signals, while excluding or minimally processing data from non-respiratory regions. This selective extraction maintains the completeness of useful respiratory information while significantly reducing the total data volume requiring complex processing.
Solution Approach 2:
The patent performs preliminary mask identification and region classification before full respiratory parameter extraction. By pre-identifying which regions contain respiratory signals and which are noise sources, the system prepares a processing roadmap that avoids unnecessary computation on non-respiratory regions, reducing overall processing complexity while maintaining data completeness for respiratory analysis.
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 improves signal accuracy by isolating physiological contributions, reduces noise interference, and allows for accurate measurement of respiratory parameters despite patient movement, enhancing the reliability of non-contact monitoring systems.
Implementation Method 1
determining depth data between a non-contact patient monitoring system and the patient
Implementation Method 2
projectors to project features onto the patient's surface
Data Source
AI summary
Methods and systems for non-contact monitoring of a patient to determine a respiratory parameter such as respiration rate. The systems and methods receive a depth signal from the patient to determine patient movement indicative of respiration. The methods include analyzing multiple regions in a region of interest (ROI) to determine whether or not respiration is occurring in the analyzed region, and preparing a mask with the regions determined to have respiration. The mask is used to determine the respiratory parameter of the patient in the masked ROI.