Respiratory Rate Determination Using Depth-Based Camera System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-contact video-based monitoring systems face challenges in accurately determining respiratory rate due to smaller movements, which can lead to inaccurate measurements, especially at low respiratory rates where the frequency domain methodology may not provide clear results and at high rates where noise becomes a significant issue.
Innovation Solution
The system employs a combination of flow signal and power spectrum analysis to determine respiratory rate, using flow-based and spectrum-based methods depending on the respiratory rate threshold, with the flow signal method suitable for low rates and the power spectrum method for high rates, and combines results for accurate determination near thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If non-contact video-based monitoring is used to detect respiratory rate, then patient movement can be monitored without contact, but measurement accuracy deteriorates due to smaller movements
Solution Approach 1:
The patent transitions from analyzing 2D video images to using 3D depth maps to measure respiratory movements. By capturing depth information in the z-dimension, the system can accurately detect small chest movements during breathing without requiring large amplitude motions, thereby maintaining measurement precision while preserving non-contact monitoring capability
Solution Approach 2:
The system changes the measurement parameter from 2D image plane coordinates to 3D depth values. By measuring the displacement of chest surface points in the depth dimension, the system achieves higher sensitivity to small respiratory movements, resolving the contradiction between non-contact operation and measurement accuracy
2Measurement precision
If flow signal analysis is used for low respiratory rates, then measurement accuracy is improved, but noise interference worsens at high respiratory rates
Solution Approach 1:
The patent implements a dynamic selection mechanism that adapts the analysis method based on the detected respiratory rate. When the respiratory rate is below a threshold, flow signal analysis is used; when above the threshold, power spectrum analysis is used. This dynamic adaptation allows the system to maintain high measurement precision across different respiratory conditions while minimizing noise interference by selecting the appropriate method for each scenario
Solution Approach 2:
The system changes the analytical approach parameter based on the respiratory rate parameter. By switching between time-domain flow signal analysis and frequency-domain power spectrum analysis according to the respiratory rate threshold, the system optimizes measurement accuracy while reducing noise impact for each operating condition
3Object-affected harmful factors
If power spectrum analysis is used for high respiratory rates, then noise resistance is improved, but measurement clarity deteriorates at low respiratory rates
Solution Approach 1:
The patent employs a dynamic method selection strategy that switches between power spectrum analysis and flow signal analysis based on respiratory rate thresholds. For high respiratory rates where noise resistance is critical, power spectrum analysis is applied. For low respiratory rates where signal clarity is paramount, flow signal analysis is used. This dynamic approach ensures both noise resistance and signal clarity are optimized for their respective operating conditions
Solution Approach 2:
The system dynamically changes the signal processing parameter based on the respiratory rate condition. By selecting appropriate analysis methods (power spectrum for high rates, flow signal for low rates), the system maintains optimal noise resistance and signal clarity across the full range of respiratory rates
Data Source
AI summary
Methods for improving the accurate determination of respiratory rate, the respiratory rate being measured or monitored from depth measurements from a non-contact monitoring system. The methods include analyzing a waveform obtained from a respiratory parameter and discarding data that does not meet criteria. The respiratory rate may be obtained from an original waveform, a processed waveform, or from a power spectrum derived from the original or processed waveform.