Depth Camera Edge Handling for Accurate Respiratory Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional video-based patient monitoring systems experience errors in depth measurement due to large, inaccurate changes at the edges of a patient's torso, leading to inaccuracies in determining respiratory parameters.
Innovation Solution
The system mitigates these errors by excluding edge portions, interpolating changes using other regions, and using a template to estimate edge depths, thereby improving the accuracy of respiratory parameter determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If edge portions of the ROI are included in depth measurement, then the measurement area is maximized, but measurement precision deteriorates due to large inaccurate changes at edges
Solution Approach 1:
The patent segments the ROI into edge portions and non-edge portions, applying different processing methods to each segment. Edge portions are identified and excluded from direct depth measurement calculations, while non-edge portions are used for accurate measurements. This segmentation allows the system to maintain large overall measurement area while eliminating precision-degrading edge regions from the calculation.
Solution Approach 2:
The patent extracts and removes edge portions from the depth measurement calculation process. By identifying regions with steep depth changes as edge portions and excluding them from the overall change in depth calculation, the system eliminates the source of measurement errors while preserving the measurement of the central, more reliable regions.
2Measurement precision
If edge portions are excluded from measurement, then measurement precision improves, but the measurement area decreases
Solution Approach 1:
The patent applies partial action by measuring only the non-edge portions of the ROI for depth calculations, rather than attempting to correct all edge effects. This selective measurement approach achieves sufficient precision for clinical purposes without requiring complex corrections, accepting that some area is excluded but gaining significant improvement in measurement reliability.
3Measurement precision
If steep changes in depths are excluded from calculation, then accuracy of respiratory parameters improves, but information from those regions is lost
Solution Approach 1:
The patent converts the harmful effect of steep depth changes at edges into a useful indicator for identifying edge portions. By detecting these steep changes, the system can automatically delineate the boundaries between edge and non-edge regions, transforming what would be measurement errors into a useful segmentation tool that improves overall measurement accuracy.
Data Source
AI summary
The present technology relates to the field of medical monitoring, and, in particular, to non-contact detecting and monitoring of patient breathing. Systems, methods, and computer readable media are described for calculating a change in depth of a region of interest (ROI) on a patient. In some embodiments, the systems, methods, and/or computer readable media can identify steep changes in depths. For example, the systems, methods, and/or computer readable media can identify large, inaccurate changes in depths that can occur at edge regions of a patient. In these and other embodiments, the systems, methods, and/or computer readable media can adjust the identified steep changes in depth before determining one or more patient respiratory parameters.