Cross-domain unrolling-based imaging photoplethysmography systems and methods for estimating vital signs

A computer-implemented method for estimating a vital sign signal of a subject, comprising:

• receiving a sequence of imaging photoplethysmography (iPPG) signals measured from different regions of a skin of the subject in a time domain, wherein the iPPG signals correspond to non-contact optical measurements of the skin of the subject, and wherein the non-contact optical measurements are obtained from at least one detector disposed remotely from the subject;
• obtaining a reconstructed iPPG signals as an output of an iPPG neural network trained in a frequency domain with machine learning to enforce a learned structure on frequency coefficients of the reconstructed iPPG signals;
• executing a cross-domain unrolling optimization iteratively minimizing a difference between the received iPPG signals and the reconstructed iPPG signals, wherein the reconstructed iPPG signals have the frequency coefficients determined in the frequency domain and transformed into the time domain of the received iPPG signals before computation of the difference between the received iPPG signals and the reconstructed iPPG signals
• determining the vital sign signal of the subject from the frequency coefficients of the reconstructed iPPG signals upon reaching a termination condition of the cross-domain unrolling optimization;
• and
• outputting the vital sign signal corresponding to the reconstructed iPPG signals via an output interface.

A non-transitory computer readable medium having stored thereon computer-executable instructions which when executed by a computer, cause the computer to perform a method for estimating a vital sign signal of a subject, the method comprising:

• receiving a sequence of imaging photoplethysmography (iPPG) signals measured from different regions of a skin of the subject in a time domain, wherein the iPPG signals correspond to non-contact optical measurements of the skin of the subject, and wherein the non-contact optical measurements are obtained from at least one detector disposed remotely from the subject;
• obtaining a reconstructed iPPG signals as an output of an iPPG neural network trained in a frequency domain with machine learning to enforce a learned structure on frequency coefficients of the reconstructed iPPG signals;
• executing a cross-domain unrolling optimization iteratively minimizing a difference between the received iPPG signals and the reconstructed iPPG signals, wherein the reconstructed iPPG signals have the frequency coefficients determined in the frequency domain and transformed into the time domain of the received iPPG signals before computation of the difference between the received iPPG signals and the reconstructed iPPG signals;
• determining the vital sign signal of the subject from the frequency coefficients of the reconstructed iPPG signals upon reaching a termination condition of the cross-domain unrolling optimization;
• and
• outputting the vital sign signal corresponding to the reconstructed iPPG signals via an output interface.