Edge handling methods for associated depth sensing camera devices, systems, and methods
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.
1. A method, comprising:
defining a region of interest (ROI) on a patient;
capturing two or more images of the ROI using an image capture device;
calculating an overall change in depth of the ROI within the two or more images, wherein calculating the overall change in depth of the ROI includes:
measuring changes in depths of portions of the ROI;
recognizing steep changes in depths in the measured changes in depths; and
adjusting the recognized steep changes in depths; and
determining a tidal volume of the patient using all or a subset of the measured changes in depths excluding the recognized steep changes in depths and all or a subset of the adjusted changes in depths.
2. The method of claim 1 , wherein adjusting the recognized steep changes in depths includes excluding the recognized steep changes in depths from the calculation of the overall change in depth of the ROI.
3. The method of claim 1 , wherein adjusting the recognized steep changes in depths includes (i) excluding measured changes in depths corresponding to an outer percentage of the ROI and/or to an edge region of the patient and/or (ii) excluding a percentage of the measured changes in depths surrounding a recognized steep change in depth.
4. The method of claim 1 , wherein adjusting the recognized steep changes in depths comprises including only measured changes in depths up to and/or between one or more recognized steep changes in depths in the calculation of the overall change in depth of the ROI.
5. The method of claim 1 , wherein adjusting the recognized steep changes in depths includes interpolating and/or extrapolating over the recognized steep changes in depths using one or more other measured changes in depths.
6. The method of claim 1 , wherein adjusting the recognized steep changes in depths includes using a template to approximate changes in depths at portions of the ROI corresponding to the recognized steep changes in depths.
7. The method of claim 6 , wherein the template is a default template, the template is generated from a prior body scan of the patient, and/or the template is an aggregate shape determined from a population-based analysis of body shapes.
8. The method of claim 6 , wherein the template corresponds to a current position within the patient's respiratory cycle and/or the template corresponds to one or more other measured changes in depths.
9. The method of claim 1 , wherein the image capture device is a first image capture device, and wherein adjusting the recognized steep change in depths includes adjusting the recognized steep changes in depths using data captured by a second image capture device.
10. The method of claim 1 , wherein recognizing the steep changes in depths includes identifying measured changes in depths having a magnitude greater than or equal to a threshold value.
11. The method of claim 10 , wherein the threshold value is a predefined value and/or a value defined based on one or more previously measured changes in depths corresponding to the patient.
12. The method of claim 1 , wherein recognizing the steep changes includes interrogating all or a subset of the measured changes in depths.
13. A video-based patient monitoring system, comprising:
at least one processor configured to define a region of interest (ROI) on a patient; and
a non-contact detector having at least a first image capture device, wherein:
at least the first image capture device is configured to capture two or more images of the ROI,
the at least one processor is further configured to calculate an overall change in depth of the ROI within the two or more images,
to calculate the overall change in depth of the ROI within the two or more images, the at least one processor is further configured to:
measure changes in depths of portions of the ROI within the two or more images;
recognize steep changes in depths in the measured changes in depths; and
adjust the recognized steep changes in depths; and
the at least one processor is further configured to determine a tidal volume of the patient using all or a subset of the measured changes in depths excluding the recognized steep changes in depths and all or a subset of the adjusted changes in depths.
14. The video-based patient monitoring system of claim 13 , wherein, to adjust the recognized steep changes in depths, the at least one processor is further configured to:
exclude the recognized steep changes in depths from the calculation of the overall change in depth of the ROI;
exclude measured changes in depths corresponding to an outer percentage of the ROI and/or to an edge region of the patient;
exclude a percentage of the measured changes in depths surrounding a recognized steep change in depth;
include only measured changes in depths up to and/or between one or more recognized steep changes in depths in the calculation of the overall change in depth of the ROI;
interpolate and/or extrapolate over the recognized steep changes in depths using one or more other measured changes in depths;
use a template to approximate changes in depths at portions of the ROI corresponding to the recognized steep changes in depths; and/or
adjust the recognized steep changes in depths using data captured by a second image capture device.
15. The video-based patient monitoring system of claim 13 , wherein, to adjust the recognized steep changes in depths, the at least one processor is further configured to use a template to approximate changes in depths at portions of the ROI corresponding to the recognized steep changes in depths, and wherein the template is generated from a prior body scan of the patient and/or is an aggregated shape from a population-based analysis of body shapes.
16. The video-based patient monitoring system of claim 13 , wherein, to recognize steep changes in depths in the measured changes in depths, the at least one processor is further configured to interrogate all or a subset of the measured changes in depths and to identify measured changes in depths having a magnitude greater than or equal to a threshold value.