System and method for detecting physiological state
First Claim
Patent Images
1. A system for detecting physiological states from a captured image sequence of a subject, the system comprising:
- a camera configured to capture an image sequence of the subject, the image sequence comprising a query set of images;
a processing unit trained to determine a set of bitplanes of a plurality of images in the captured image sequence that represent hemoglobin concentration (HC) changes of the subject and that maximize signal differentiation between different physiological states, wherein the set of bitplanes that represent HC changes are determined for a selected plurality of regions of interest (ROI) of the subject that are relevant as an indicator of physiological state;
a classification machine, trained using a training set comprising HC changes of subjects with known physiological states, and configured to;
detect the subject'"'"'s physiological states based on HC changes in the set of bitplanes; and
output the detected physiological states,wherein the processing unit is further configured to extract from the HC changes of one or more ROI a heart beat signal of the subject, process the heat beat signal to determine heart beat interval time series data of the subject, perform Fourier transforms on the heart beat interval time series data to obtain a stress level index, compare the stress level index with a predetermined normative stress index distribution profile to determine the subject'"'"'s comparative stress level, and provide the subject'"'"'s comparative stress level to the classification machine for use in detecting the subject'"'"'s physiological states.
1 Assignment
0 Petitions
Accused Products
Abstract
A system and method for health diagnostics and more specifically to an image-capture based system and method for detecting physiological state for a subject. The system provides a remote and non-invasive approach by which to detect physiological state with a high confidence. The system enables monitoring of hemoglobin concentration changes by optical imaging and related detection systems.
16 Citations
16 Claims
-
1. A system for detecting physiological states from a captured image sequence of a subject, the system comprising:
-
a camera configured to capture an image sequence of the subject, the image sequence comprising a query set of images; a processing unit trained to determine a set of bitplanes of a plurality of images in the captured image sequence that represent hemoglobin concentration (HC) changes of the subject and that maximize signal differentiation between different physiological states, wherein the set of bitplanes that represent HC changes are determined for a selected plurality of regions of interest (ROI) of the subject that are relevant as an indicator of physiological state; a classification machine, trained using a training set comprising HC changes of subjects with known physiological states, and configured to; detect the subject'"'"'s physiological states based on HC changes in the set of bitplanes; and output the detected physiological states, wherein the processing unit is further configured to extract from the HC changes of one or more ROI a heart beat signal of the subject, process the heat beat signal to determine heart beat interval time series data of the subject, perform Fourier transforms on the heart beat interval time series data to obtain a stress level index, compare the stress level index with a predetermined normative stress index distribution profile to determine the subject'"'"'s comparative stress level, and provide the subject'"'"'s comparative stress level to the classification machine for use in detecting the subject'"'"'s physiological states. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method for detecting physiological states from a captured image sequence of a subject, the method comprising:
-
capturing, by a camera, an image sequence of the subject, the image sequence comprising a query set of images; processing the captured image sequence, by a trained processing unit, to determine a set of bitplanes of a plurality of images in the captured image sequence that represent hemoglobin concentration (HC) changes of the subject and that maximize signal differentiation between different physiological states, the set of bitplanes that represent HC changes are determined for a selected plurality of regions of interest (ROI) of the subject that are relevant as an indicator of physiological state; extracting, by the trained processing unit, from the HC changes of one or more ROI a heart beat signal of the subject; processing, by the trained processing unit, the heat beat signal to determine heart beat interval time series data of the subject; performing, by the trained processing unit, Fourier transforms on the heart beat interval time series data to obtain a stress level index; comparing, by the trained processing unit, the stress level index with a predetermined normative stress index distribution profile to further determine the subject'"'"'s comparative stress level; processing the set of bitplanes, by a classification machine trained using a training set comprising HC changes of subjects with known physiological states, to; detect the subject'"'"'s physiological states based on HC changes in the set of bitplanes and the subject'"'"'s comparative stress level; and output the detected physiological states. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
Specification