Contactless recognition of respiration phases using web camera

Lukac, Tomas; Pucik, Jozef; Chrenko, Lukas

doi:10.1109/radioelek.2014.6828427

Cited by 9 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The overall motion matrix is then factorized into separate motion trajectories, which is a strategy that is previously described by Hou et al [14]. A drawback, however, is that pixel-based motion derivatives are inherently sensitive to subtle changes and often deviate from one another, i.e., they are noisy to be clustered into a factorized basis.…”

Section: Mid-level Respiratory Descriptorsmentioning

confidence: 99%

“…Similar to Li et al [9] and Lukáč et al [14], we extract the respiratory signal by using pixel-based motion vectors as features (e.g., optical flows) and motion factorization (e.g., singular value Figure 1. The flowchart of the proposed video-based respiration monitoring system.…”

Section: Introductionmentioning

confidence: 99%

“…Previously, several approaches have been proposed to monitor respiration with a camera based on the respiratory-induced movements of chest and abdomen (Wiesner and Yaniv 2007, Tan et al 2010, Bartula et al 2013, Li et al 2014, Lukac et al 2014. Tan et al (2010) used frame differencing to detect respiratory motion between two adjacent frames.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Video-based respiration monitoring with automatic region of interest detection

et al. 2015

View full text Add to dashboard Cite

Abstract. Vital signs monitoring is ubiquitous in clinical environments and emerging in home-based healthcare applications. Still, since current monitoring methods require uncomfortable sensors, respiration rate remains the least measured vital sign. In this paper, we propose a video-based respiration monitoring method that automatically detects respiratory Region of Interest (RoI) and signal using a camera. Based on the observation that respiration induced chest/abdomen motion is an independent motion system in a video, our basic idea is to exploit the intrinsic properties of respiration to find the respiratory RoI and extract the respiratory signal via motion factorization. We created a benchmark dataset containing 148 video sequences obtained on adults under challenging conditions and also neonates in the neonatal intensive care unit (NICU). The measurements obtained by the proposed video respiration monitoring (VRM) method are not significantly different from the reference methods (guided breathing or contact-based ECG; p-value=0.6), and explain more than 99% of the variance of the reference values with low limits of agreement (−2.67 to 2.81 bpm). VRM seems to provide a valid solution to ECG in confined motion scenarios, though precision may be reduced for neonates. More studies are needed to validate VRM under challenging recording conditions, including upper-body motion types.

show abstract

Section: Mid-level Respiratory Descriptorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Video-based respiration monitoring with automatic region of interest detection

et al. 2015

View full text Add to dashboard Cite

show abstract

“…However, the most frequently utilised methods were tracking and optical flow based methods. Lukac et al [19] proposed to use a KLT tracker [18] for the opical flow. This idea was extended with a PCA by Koolen et al [20] and applied on the chest of a person by Li et al [21].…”

Section: Respiration Ratementioning

confidence: 99%

An evaluation study of vital parameter determination with RGB cameras in the field of ambient assisted living

Wiede

Richter

Hirtz

2017

Current Directions in Biomedical Engineering

View full text Add to dashboard Cite

Abstract:The remote determination of vital parameters can contribute to the field of ambient assisted living (AAL) to face the challenges of a steadily ageing society. In this study, we examined the possibility to remotely measure the four vital parameters heart rate, respiration rate, oxygen saturation and blood pressure in AAL environments. For this, we evaluated the state of the art, implementations and concepts. While, the determination of heart and respiration rate is ready for usage, further attention has to be paid to the determination of oxygen saturation and blood pressure.

show abstract

“…In that work, principal component analysis (PCA), empirical mode decomposition, and the Hilbert Huang Transform have been used in order to estimate the heart rate. Monkaresi et al [11] presented a method for heart rate measurement using a web-camera, while Lukác et al [12] used a web camera in order to estimate respiration rate. In another work, Gupta et al [13] proposed a system utilising a web camera that has been tested on 20 subjects and achieved very good results (a mean error of 1.8 bpm).…”

Section: Introductionmentioning

confidence: 99%

Remote Heart Rate Extraction Using Microsoft KinectTM v2.0

Malasinghe

Katsigiannis

Ramzan

et al. 2018

Proceedings of the 2018 10th International Conference on Bioinformatics and Biomedical Technology

View full text Add to dashboard Cite

Remote and contactless heart rate detection is still an open research issue of great clinical importance. Available approaches lack the necessary accuracy and reliability for acceptance by medical experts. In this study, we propose a new method for remote heart rate extraction using the Microsoft Kinect TM v2.0 image sensor. The proposed approach relies on signal processing and machine learning methods in order to create a model for accurate estimation of the heart rate via RGB and infrared face videos. Electrocardiography (ECG) recordings and RGB and infrared face videos, captured using the Kinect TM v2.0 image sensor, were acquired from 17 subjects and used to create a machine learning model for remote heart rate detection. Experimental evaluation through supervised regression experiments showed that the proposed approach achieved a mean absolute error of 6.972 bpm, demonstrating the capabilities of the underlying technology.

show abstract

Contactless recognition of respiration phases using web camera

Cited by 9 publications

References 4 publications

Video-based respiration monitoring with automatic region of interest detection

Video-based respiration monitoring with automatic region of interest detection

An evaluation study of vital parameter determination with RGB cameras in the field of ambient assisted living

Remote Heart Rate Extraction Using Microsoft KinectTM v2.0

Contact Info

Product

Resources

About