Self-adaptive matrix completion for heart rate estimation from face videos under realistic conditions

US10335045B2 · kind B2 · utility

Assignees

• UNIVERSITA' DEGLI STUDI DI TRENTO · IT
• Fondazione Bruno Kessler · IT
• The Research Foundation for The State University of New York · US
• University of Pittsburgh—Of the Commonwealth System of Higher Education · US

Inventors

• Niculae Sebe · Povo, IT
• Xavier Alameda-Pineda · Trento, IT
• Sergey Tulyakov · Santa Monica, US
• Elisa Ricci · Trento, IT
• Lijun Yin · Vestal, US
• Jeffrey Cohn · Las Vegas, US

Key dates

• Filing date: Jun 23, 2017
• Grant date: Jul 2, 2019
• Expiry date: Jun 23, 2037

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V40/15
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Recent studies in computer vision have shown that, while practically invisible to a human observer, skin color changes due to blood flow can be captured on face videos and, surprisingly, be used to estimate the heart rate (HR). While considerable progress has been made in the last few years, still many issues remain open. In particular, state-of-the-art approaches are not robust enough to operate in natural conditions (e.g. in case of spontaneous movements, facial expressions, or illumination changes). Opposite to previous approaches that estimate the HR by processing all the skin pixels inside a fixed region of interest, we introduce a strategy to dynamically select face regions useful for robust HR estimation. The present approach, inspired by recent advances on matrix completion theory, allows us to predict the HR while simultaneously discover the best regions of the face to be used for estimation. Thorough experimental evaluation conducted on public benchmarks suggests that the proposed approach significantly outperforms state-of-the-art HR estimation methods in naturalistic conditions.