☆ 4.5 Article

GraphPhys: Facial video-based physiological measurement with graph neural network

COMPUTERS & ELECTRICAL ENGINEERING (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Proceedings Paper Computer Science, Artificial Intelligence

EfficientPhys: Enabling Simple, Fast and Accurate Camera-Based Cardiac Measurement

Xin Liu et al.

Summary: This paper proposes two novel and efficient neural models, called EfficientPhys, for camera-based physiological measurement, which eliminate the need for face detection, segmentation, normalization, color space transformation, or any other preprocessing steps. Our models achieve strong accuracy on three public datasets using raw video frames as input, whether using a transformer or convolutional backbone. Furthermore, we evaluate the latency of the proposed networks and demonstrate a 33% improvement in efficiency for our most lightweight network.

2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) (2023)

添加到收藏夹

Article Multidisciplinary Sciences

Contactless facial video recording with deep learning models for the detection of atrial fibrillation

Yu Sun et al.

Summary: This study utilized camera-based remote photoplethysmography (rPPG) and a deep learning model to detect and discriminate atrial fibrillation (AF). By recording facial videos and using a voting algorithm, AF can be predicted with high accuracy. This contactless rPPG technique with a deep learning model may enable large-scale screening or monitoring in the future.

SCIENTIFIC REPORTS (2022)

添加到收藏夹

Article Health Care Sciences & Services

Non-contact physiological monitoring of post-operative patients in the intensive care unit

Joao Jorge et al.

Summary: This study aimed to evaluate the feasibility of introducing a non-contact video camera monitoring system into an acute clinical setting. The results showed that non-contact monitoring accurately assessed heart rate and respiratory rate, detected changes in vital signs, and helped track early signs of physiological deterioration during post-operative care.

NPJ DIGITAL MEDICINE (2022)

添加到收藏夹

Article Biophysics

Algorithmic insights of camera-based respiratory motion extraction

Wenjin Wang et al.

Summary: This study aims to investigate and evaluate the accuracy and performance of video-based respiratory signal measurement algorithms based on body motion by designing a physical phantom. According to the experimental results, the recommended approach achieves high precision and recall rates even in scenarios with significant variations in respiratory motion intensity.

PHYSIOLOGICAL MEASUREMENT (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Real-time realizable mobile imaging photoplethysmography

Hooseok Lee et al.

Summary: In this study, PPGI sensors were mounted on a robot for active and autonomous HR estimation. A proposed algorithm simplified the extraction of facial skin images and selected pixels based on the most frequent saturation value to achieve accurate HR assessment. The algorithm was validated on two datasets, demonstrating high accuracy and processing efficiency.

SCIENTIFIC REPORTS (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer

Zitong Yu et al.

Summary: In this paper, the PhysFormer, a video transformer-based architecture, is proposed for remote photoplethysmography (rPPG), which aims to measure heart activities and physiological signals from facial video without any contact. By adaptively aggregating local and global spatio-temporal features, the PhysFormer enhances the representation of rPPG. It also introduces key modules and optimization methods to improve rPPG modeling performance.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

添加到收藏夹

Article Engineering, Biomedical

Remote estimation of pulse wave features related to arterial stiffness and blood pressure using a camera

Djamaleddine Djeldjli et al.

Summary: This research investigates the similarity in waveform features between imaging photoplethysmography (iPPG) and contact photoplethysmographic (cPPG) signals for the assessment and diagnosis of cardiovascular diseases. By analyzing waveform features such as time, areas, amplitude and second derivative, a high correlation between the two measurement techniques was found, opening new perspectives for the remote assessment and non-contact diagnosis of blood pressure and arterial stiffness.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Dual-GAN: Joint BVP and Noise Modeling for Remote Physiological Measurement

Hao Lu et al.

Summary: This paper proposes an adversarial learning approach using Dual Generative Adversarial Networks to improve feature disentanglement between BVP and noises, achieving better performance in physiological measurement from face videos. Additionally, a plug-and-play ROI alignment and fusion block is proposed to address inconsistencies between different ROIs.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Oxygen Saturation Estimation Based on Optimal Band Selection from Multi-band Video

Ryo Takahashi et al.

Summary: In this study, a method was proposed to estimate oxygen saturation by selecting the best bands from video images captured by a multiband camera. Through a Monte Carlo simulation of light scattering on the skin to simulate pulse waves during oxygen saturation changes, and measuring the signals with a multi-band camera, the optimal combination of bands for estimating oxygen saturation was selected.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

RhythmNet: End-to-End Heart Rate Estimation From Face via Spatial-Temporal Representation

Xuesong Niu et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

AutoHR: A Strong End-to-End Baseline for Remote Heart Rate Measurement With Neural Searching

Zitong Yu et al.

IEEE SIGNAL PROCESSING LETTERS (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Dynamic Graph CNN for Learning on Point Clouds

Yue Wang et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

DeepGCNs: Can GCNs Go as Deep as CNNs?

Guohao Li et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

添加到收藏夹

Article Engineering, Biomedical

Algorithmic Principles of Remote PPG

Wenjin Wang et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

Joao Carreira et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Article Engineering, Biomedical

A Novel Algorithm for Remote Photoplethysmography: Spatial Subspace Rotation

Wenjin Wang et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2016)

添加到收藏夹

Article Engineering, Biomedical

Robust Pulse Rate From Chrominance-Based rPPG

Gerard de Haan et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2013)

添加到收藏夹

Article Engineering, Biomedical

Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam

Ming-Zher Poh et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2011)

添加到收藏夹

Article Optics

Non-contact, automated cardiac pulse measurements using video imaging and blind source separation

Ming-Zher Poh et al.

OPTICS EXPRESS (2010)

添加到收藏夹

Article Optics

Remote plethysmographic imaging using ambient light

Wim Verkruysse et al.

OPTICS EXPRESS (2008)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Comparison of descriptor spaces for chemical compound retrieval and classification

Nikil Wale et al.

KNOWLEDGE AND INFORMATION SYSTEMS (2008)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.