The First Vision For Vitals (V4V) Challenge for Non-Contact Video-Based Physiological Estimation

Revanur, Ambareesh; Li, Zhihua; Ciftci, Umur Aybars; Liu, Yin; Jeni, László A.

doi:10.1109/iccvw54120.2021.00310

Cited by 27 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this subsection, we include two datasets that we dealt with during our work procedure. The first dataset is the Vision for Vitals (V4V) dataset [ 24 , 25 ], which we used to train our models to accomplish noninvasive estimation of blood pressure. The second dataset is our own dataset, which provides the subjects’ respiratory rate at every minute and which we used to create new a criterion to test the validity of our models as we explain later.…”

Section: Methodsmentioning

confidence: 99%

Neural Network Model Combination for Video-Based Blood Pressure Estimation: New Approach and Evaluation

Hamoud

Kashevnik

Othman

et al. 2023

Sensors

View full text Add to dashboard Cite

One of the most effective vital signs of health conditions is blood pressure. It has such an impact that changes your state from completely relaxed to extremely unpleasant, which makes the task of blood pressure monitoring a main procedure that almost everyone undergoes whenever there is something wrong or suspicious with his/her health condition. The most popular and accurate ways to measure blood pressure are cuff-based, inconvenient, and pricey, but on the bright side, many experimental studies prove that changes in the color intensities of the RGB channels represent variation in the blood that flows beneath the skin, which is strongly related to blood pressure; hence, we present a novel approach to blood pressure estimation based on the analysis of human face video using hybrid deep learning models. We deeply analyzed proposed approaches and methods to develop combinations of state-of-the-art models that were validated by their testing results on the Vision for Vitals (V4V) dataset compared to the performance of other available proposed models. Additionally, we came up with a new metric to evaluate the performance of our models using Pearson’s correlation coefficient between the predicted blood pressure of the subjects and their respiratory rate at each minute, which is provided by our own dataset that includes 60 videos of operators working on personal computers for almost 20 min in each video. Our method provides a cuff-less, fast, and comfortable way to estimate blood pressure with no need for any equipment except the camera of your smartphone.

show abstract

Section: Methodsmentioning

confidence: 99%

Neural Network Model Combination for Video-Based Blood Pressure Estimation: New Approach and Evaluation

Hamoud

Kashevnik

Othman

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In these experiments, the deep-learning-based approaches outperform the model-based approaches under constant lighting conditions, but model-based approaches (ICA, CHROM, and POS) show more accurate and robust results than neuronal networks in varying lighting conditions [37]. The recent ICCV Vision-for-Vitals (V4V) challenge [27] comparing different model-based as well as network-based approaches [7,10,14,27] for the measurement of the HR, shows similar results.…”

Section: Related Workmentioning

confidence: 99%

Perfusion assessment via local remote photoplethysmography (rPPG)

Kossack

Wisotzky

Eisert

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

This paper presents an approach to assess the perfusion of visible human tissue from RGB video files. We propose metrics derived from remote photoplethysmography (rPPG) signals to detect whether a tissue is adequately supplied with blood. The perfusion analysis is done in three different scales, offering a flexible approach for different applications. We perform a plane-orthogonal-to-skin rPPG independently for locally defined regions of interest on each scale. From the extracted signals, we derive the signalto-noise ratio, magnitude in the frequency domain, heart rate, perfusion index as well as correlation between specific rPPG signals in order to locally assess the perfusion of a specific region of human tissue. We show that locally resolved rPPG has a broad range of applications. As exemplary applications, we present results in intraoperative perfusion analysis and visualization during skin and organ transplantation as well as an application for liveliness assessment for the detection of presentation attacks to authentication systems.

show abstract

“…However, all of these methods are evaluated on episodic scores over windowed intervals. To tackle this limitation, the Vision-for-Vitals workshop [20] held at ICCV introduced multiple metrics to promote instantaneous prediction of HR and RR. In our work, we aim to evaluate all methods including ours over these metrics.…”

Section: Video Based Physiology Extractionmentioning

confidence: 99%

“…We use the V4V training dataset for training the model and report the performance of our model on both V4V validation set and V4V test set. We follow the evaluation protocol set forth in the V4V challenge [20] and report continuous MAE (cM AE) and continuous RMSE (cRM SE). where, HR i and HR i are the predicted HR and ground-truth HR for the frame i respectively and N is total number of frames in test-set.…”

Section: Datasets and Evaluation Protocolmentioning

confidence: 99%

“…This evaluation gap has been considered in a recent physiological challenge organized at the ICCV conference called "Vision-for-Vitals" (V4V). Instead of using nonoverlapping windows to measure the error, the challenge organizers [20] proposed using an instantaneous (a.k.a. continuous) evaluation protocol that measures the performance of a method at a per-frame level.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Instantaneous Physiological Estimation using Video Transformers

Revanur¹,

Dasari²,

Tucker³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Video-based physiological signal estimation has been limited primarily to predicting episodic scores in windowed intervals. While these intermittent values are useful, they provide an incomplete picture of patients' physiological status and may lead to late detection of critical conditions. We propose a video Transformer for estimating instantaneous heart rate and respiration rate from face videos. Physiological signals are typically confounded by alignment errors in space and time.To overcome this, we formulated the loss in the frequency domain. We evaluated the method on the large scale Vision-for-Vitals (V4V) benchmark. It outperformed both shallow and deep learning based methods for instantaneous respiration rate estimation. In the case of heart-rate estimation, it achieved an instantaneous-MAE of 13.0 beats-per-minute.

show abstract

The First Vision For Vitals (V4V) Challenge for Non-Contact Video-Based Physiological Estimation

Cited by 27 publications

References 23 publications

Neural Network Model Combination for Video-Based Blood Pressure Estimation: New Approach and Evaluation

Neural Network Model Combination for Video-Based Blood Pressure Estimation: New Approach and Evaluation

Perfusion assessment via local remote photoplethysmography (rPPG)

Instantaneous Physiological Estimation using Video Transformers

Contact Info

Product

Resources

About