公开(公告)号：US12036021B2

公开(公告)日：2024-07-16

申请号：US18511919

申请日：2023-11-16

Applicant: CENTRAL CHINA NORMAL UNIVERSITY

Inventor： Liang Zhao ,  Sannyuya Liu ,  Zongkai Yang ,  Xiaoliang Zhu ,  Jianwen Sun ,  Qing Li ,  Zhicheng Dai

IPC: A61B8/14 ,  A61B5/00 ,  A61B5/0205 ,  A61B5/1171 ,  A61B5/16 ,  G06N3/0464 ,  G06N3/08 ,  G06V10/30 ,  G06V40/16 ,  A61B5/024 ,  A61B5/08

CPC classification number: A61B5/16 ,  A61B5/0205 ,  A61B5/1176 ,  A61B5/725 ,  A61B5/726 ,  A61B5/7264 ,  G06N3/0464 ,  G06N3/08 ,  G06V10/30 ,  G06V40/161 ,  A61B5/02427 ,  A61B5/0816 ,  G06V2201/03

Abstract: The present disclosure provides a non-contact fatigue detection system and method based on rPPG. The system and method adopt multi-thread synchronous communication for real-time acquisition and processing of rPPG signal, enabling fatigue status detection. In this setup, the first thread handles real-time rPPG data capture, storage and concatenation, while the second thread conducts real-time analysis and fatigue detection of rPPG data. Through a combination of skin detection and LUV color space conversion, rPPG raw signal extraction is achieved, effectively eliminating interference from internal and external environmental facial noise; Subsequently, an adaptive multi-stage filtering process enhances the signal-to-noise ratio, and a multi-dimensional fusion CNN model ensures accurate detection of respiration and heart rate. The final step involves multi-channel data fusion of respiration and heartbeats, succeeding in not only learning person-independent features for fatigue detection but also detecting early fatigue with very high accuracy.