Processing a video for vascular pattern detection and cardiac function analysis

A system for determining a cardiac function parameter from a video of a subject of interest acquired in a non-contact remote sensing environment, the system comprising:

• a video system comprising at least one video camera that outputs data comprising color values collected for color pixels by at least one visible channel, and at least one infrared (IR) video camera that outputs data comprising intensity values collected for IR pixels by at least one infrared channel;
• and
• a processor in communication with said video camera system and a memory, said processor executing machine readable instructions for performing:
• receiving video of a region of exposed skin of the subject of interest being monitored for cardiac function, said video having been captured using said video system;
• processing said IR pixel intensity values to generate a vascular binary mask that indicates the location of pixels corresponding with a vascular pathway of said subject within said region of exposed skin;
• registering said vascular binary mask with color pixels to isolate said vascular pattern of said subject in said video;
• and
• processing pixels associated with said isolated vascular pattern to determine at least one cardiac function parameter for said subject, said processing comprising:
• integrating information being carried by said color pixels and said IR pixels along vessels of said vascular pattern with respect to time and obtaining a resulting signal;
• normalizing said resulting signal with respect to a value derived from apriori knowledge of cardiac history of said subject;
• converting said normalized signal to a time-series signal;
• and
• isolating desired components of interest in said time-series signal via independent component selection.