Systems and methods for computer monitoring of remote photoplethysmography based on chromaticity in a converted color space

Inventors

Tao, Nongjian • Yang, Yuting

Assignees

Arizona State University ASU • Arizona State University Downtown Phoenix campus

Abstract

Provided herein are systems and methods for computer monitoring of remote photoplethysmography (rPPG) from camera images based on chromaticity in a converted color space, which reduces motion-induced artifacts in camera images for improved rPPG computer monitoring of physiological parameters. In particular, a rPPG system for monitoring at least one physiological parameter from image data is disclosed herein. A processor subsystem electronically receives a first image data set representative of a series of consecutive images of at least a portion of a living body. The processor subsystem converts the first image data set from a first color space to a second color space to generate a second image data set including first channel data comprising a luminance component and second channel data comprising a chromatic component. The processor subsystem processes the second channel data to monitor the at least one physiological parameter of the living body.

Core Innovation

The invention provides systems and methods for remote photoplethysmography (rPPG) computer monitoring based on chromaticity in a converted color space. Specifically, it discloses a system and method where a processor subsystem receives a first image data set from a camera representing consecutive images of part of a living body, converts this image data from an initial color space (such as RGB) to a second color space (such as CIELab), and generates a second image data set including channel data consisting of luminance and chromatic components. The system then processes the chromatic channel data to monitor at least one physiological parameter of the living body.

The system addresses the problem that traditional rPPG methods, which work well for still subjects in laboratory settings, are subject to significant motion-induced artifacts when used in real-world environments where the subject may move. Most existing methods using RGB color space are particularly vulnerable to these artifacts, resulting in unreliable physiologic monitoring. The need exists for rPPG monitoring devices that minimize the influence of motion-induced artifacts and provide accurate readings in practical, non-laboratory conditions.

To solve this, the disclosed approach uses color space conversion, particularly to perceptually uniform spaces such as CIELab, to separate illumination changes (which are susceptible to motion artifacts) from chromatic changes (which are more closely associated with physiological signals). The system includes automatic selection and tracking of an optimal region of interest (ROI) on the living body, as well as pruning of image frames when the ROI is not captured. This process allows extraction of physiological signals, such as heart rate or breathing patterns, with improved accuracy under normal, everyday conditions and across diverse skin tones.

Claims Coverage

The patent contains multiple independent claims that define several main inventive features, particularly focused on systems, methods, and computer-readable media for improved rPPG monitoring using chromaticity in a specific color space.

The inventive features focus on using the a* chromatic channel within a perceptually uniform color space (such as CIELab) for rPPG monitoring, coupled with automatic selection and management of a region of interest, to achieve improved physiological parameter extraction while reducing motion-induced artifacts.

Stated Advantages

Documented Applications