University System of Maryland

National Institutes of Health, a Component of the US Dept. of Health & Human Services

North Carolina State University

Mingliang Chen

Min Wu

Qiang Zhu

Chau-Wai Wong

Quanzeng Wang

Zachary Lazri

An apparatus for vital sign extraction. The apparatus may receive a vital signal of a subject from a sensing device. The apparatus may also perform a preprocessing procedure on the vital signal via bandpass filtering and normalization to obtain a preprocessed signal. The apparatus may also perform a time-frequency analysis of the preprocessed signal, and estimate a heart rate of the subject from a dominant component of the preprocessed signal by finding location of a maximum spectral energy of the time-frequency analysis. In addition, the apparatus may identify guard components in the preprocessed signal in view of the dominant component, and derive a respiratory rate of the subject from a length of an interval between the dominant component and each of the guard components.

Modulation model of photoplethysmography signal for vital sign extraction

Systems, methods, apparatuses, and computer program products for contact-free heart rate monitoring and/or measurement are provided. One method may include receiving video(s) that include visual frame(s) of individual(s) performing exercises, detecting some exposed skin from the video(s), and performing motion compensation to generate color signals for the exposed skin to precisely align frames of the exposed skin. The method may also include generating the color signals by estimating a skin color for each frame by taking a spatial average over pixels of a cheek of the face(s) for R, G, and B channels, respectively, applying an operation to remove remaining motion traces from the frames such that the heart rate traces dominate, and extracting and/or outputting the heart rate of the individuals using a frequency estimator of the skin color signals.

System and method for heart rate measurement using facial video

Systems, methods, apparatuses, and computer program products for tracking weak signal traces under severe noise and/or distortions. A method may include tracking at least one candidate frequency trace from a time-frequency representation of a signal. The method may also include identifying a frequency trace of the signal based on tracking results. In addition, the method may include outputting an estimated frequency vector related to the frequency trace. Further, the tracking may be performed under a noisy condition environment.

Methods and apparatuses for implementing adaptive multi-trace carving to track signal traces

Systems, methods, apparatuses, and computer program products for providing an anti-piracy framework for Deep Neural Networks (DNN). A method may include receiving authorized raw input at a protective transform module. The method may also include receiving unauthorized raw input at a restrictive deep neural network. The method may further include processing the authorized raw input at the protective transform module to generate a processed input. In addition, the method may include feeding the processed input into the restrictive deep neural network. The method may also include generating a result based on the processed input and the unauthorized raw input. Further, the result may include a different learning performance between the authorized raw input and the unauthorized raw input.

Growing community of inventors

Greenbelt, MD, United States of America

Mingliang Chen