A Comparative Evaluation of Heart Rate Estimation Methods using Face Videos

• URL: http://arxiv.org/abs/2005.11101v1
• Date: Fri, 22 May 2020 10:54:49 GMT
• Title: A Comparative Evaluation of Heart Rate Estimation Methods using Face Videos
• Authors: Javier Hernandez-Ortega, Julian Fierrez, Aythami Morales, David Diaz
• Abstract summary: Four alternatives from the literature are tested, three based in hand crafted approaches and one based on deep learning. Experiments show that the learning-based method achieves much better accuracy than the hand crafted ones. The low error rate achieved by the learning based model makes possible its application in real scenarios.
• Score: 25.413558889761127
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents a comparative evaluation of methods for remote heart rate estimation using face videos, i.e., given a video sequence of the face as input, methods to process it to obtain a robust estimation of the subjects heart rate at each moment. Four alternatives from the literature are tested, three based in hand crafted approaches and one based on deep learning. The methods are compared using RGB videos from the COHFACE database. Experiments show that the learning-based method achieves much better accuracy than the hand crafted ones. The low error rate achieved by the learning based model makes possible its application in real scenarios, e.g. in medical or sports environments.

Related papers

• A Comparison of Bounding Box and Landmark Detection Methods for Video-Based Heart Rate Estimation [0.0]
  Remote Photoplethysmography uses the cyclic variation of skin tone on a person's forehead region to estimate that person's heart rate. This paper compares two methods: a bounding box-based method and a landmark-detection-based method to estimate heart rate.
  arXiv  Detail & Related papers  (2023-10-01T18:39:25Z)
• RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy [83.4885991036141]
  RIDE is a learning-based method for rotation-equivariant detection and invariant description. It is trained in a self-supervised manner on a large curation of endoscopic images. It sets a new state-of-the-art performance on matching and relative pose estimation tasks.
  arXiv  Detail & Related papers  (2023-09-18T08:16:30Z)
• Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluation [64.0476282000118]
  Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. It is currently difficult to compare the performance of these VCE methods as the evaluation procedures largely vary and often boil down to visual inspection of individual examples and small scale user studies. We propose a framework for systematic, quantitative evaluation of the VCE methods and a minimal set of metrics to be used.
  arXiv  Detail & Related papers  (2023-08-11T12:22:37Z)
• Precise localization of corneal reflections in eye images using deep learning trained on synthetic data [9.150553995510217]
  We present a deep learning method for accurately localizing the center of a single corneal reflection (CR) in an eye image. We use a convolutional neural network (CNN) that was trained solely using simulated data. We conclude that our method provides a precise method for CR center localization and provides a solution to the data availability problem.
  arXiv  Detail & Related papers  (2023-04-12T07:49:21Z)
• Visual Heart Rate Estimation from RGB Facial Video using Spectral Reflectance [0.23438564092609357]
  We propose a reliable HR estimation framework using the spectral reflectance of the user, which makes it robust to motion and illumination disturbances. We employ deep learning-based frameworks such as Faster RCNNs to perform face detection as opposed to the Viola Jones algorithm employed by previous approaches.
  arXiv  Detail & Related papers  (2022-08-09T04:34:04Z)
• The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled Video [10.479541955106328]
  The ability to reliably estimate physiological signals from video is a powerful tool in low-cost, pre-clinical health monitoring. We propose a new approach to remote photoplethysmography (r) - the measurement of blood volume changes from observations of a person's face or skin.
  arXiv  Detail & Related papers  (2021-11-18T15:21:33Z)
• Low-resolution Human Pose Estimation [49.531572116079026]
  We propose a novel Confidence-Aware Learning (CAL) method for low-resolution pose estimation. CAL addresses two fundamental limitations of existing offset learning methods: inconsistent training and testing, decoupled heatmap and offset learning. Our method outperforms significantly the state-of-the-art methods for low-resolution human pose estimation.
  arXiv  Detail & Related papers  (2021-09-19T09:13:57Z)
• Self-Attentive 3D Human Pose and Shape Estimation from Videos [82.63503361008607]
  We present a video-based learning algorithm for 3D human pose and shape estimation. We exploit temporal information in videos and propose a self-attention module. We evaluate our method on the 3DPW, MPI-INF-3DHP, and Human3.6M datasets.
  arXiv  Detail & Related papers  (2021-03-26T00:02:19Z)
• MetaPhys: Few-Shot Adaptation for Non-Contact Physiological Measurement [17.038017337552724]
  We present a novel meta-learning approach called MetaPhys for personalized video-based cardiac measurement. Our method uses only 18-seconds of video for customization and works effectively in both supervised and unsupervised manners.
  arXiv  Detail & Related papers  (2020-10-05T04:41:03Z)
• Self-Supervised Human Depth Estimation from Monocular Videos [99.39414134919117]
  Previous methods on estimating detailed human depth often require supervised training with ground truth' depth data. This paper presents a self-supervised method that can be trained on YouTube videos without known depth. Experiments demonstrate that our method enjoys better generalization and performs much better on data in the wild.
  arXiv  Detail & Related papers  (2020-05-07T09:45:11Z)
• Deep-HR: Fast Heart Rate Estimation from Face Video Under Realistic Conditions [62.68522031911656]
  We propose a simple yet efficient approach to benefit the advantages of the Deep Neural Network (DNN) by simplifying HR estimation from a complex task to learning from very correlated representation to HR. To be more accurate and work well on low-quality videos, two deep encoder-decoder networks are trained to refine the output of FE. Experimental results on HR-D and MAHNOB datasets confirm that our method could run as a real-time method and estimate the average HR better than state-of-the-art ones.
  arXiv  Detail & Related papers  (2020-02-12T07:00:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.