EUVIMEDEUVIMED entdecken
Crossref

3D DenseNet with temporal transition layer for heart rate estimation from real-life RGB videos

Mohammad Khaleel Sallam Ma'aitah, Abdulkader Helwan

Technology and Health Care · 2025

DOI: 10.3233/thc-241104 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology and Health Care, 2025. Verfasst von Mohammad Khaleel Sallam Ma'aitah und 1 weiteren Autor:innen. Hauptthemen laut MEDLINE: Heart Rate, Neural Networks, Computer, Video Recording, Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Deep learning has demonstrated superior performance over traditional methods for the estimation of heart rates in controlled contexts. However, in less controlled scenarios this performance seems to vary based on the training dataset and the architecture of the deep learning models. OBJECTIVES: In this paper, we develop a deep learning-based model leveraging the power of 3D convolutional neural networks (3DCNN) to extract temporal and spatial features that lead to an accurate heart rates estimation from RGB no pre-defined region of interest (ROI) videos. METHODS: We propose a 3D DenseNet with a 3D temporal transition layer for the estimation of heart rates from a large-scale dataset of videos that appear more hospital-like and real-life than other existing facial video-based datasets. RESULTS: Experimentally, our model was trained and tested on this less controlled dataset and showed heart rate estimation performance with root mean square error (RMSE) of 8.68 BPM and mean absolute error (MAE) of 3.34 BPM. CONCLUSION: Moreover, we show that such a model can also achieve better results than the state-of-the-art models when tested on the VIPL-HR public dataset.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Heart RateNeural Networks, ComputerVideo RecordingDeep LearningHumansFemaleMaleAdultFace

Stichwörter der Autor:innen

3D convolutional neural networksHeart ratedeep learningno pre-defined region of interest (ROI)rPPG

Zitieren

APA

Khaleel Sallam Ma'aitah, M., & Helwan, A. (2025). 3D DenseNet with temporal transition layer for heart rate estimation from real-life RGB videos. Technology and Health Care. https://doi.org/10.3233/thc-241104

Vancouver

Khaleel Sallam Ma'aitah M, Helwan A. 3D DenseNet with temporal transition layer for heart rate estimation from real-life RGB videos. Technology and Health Care. 2025. doi:10.3233/thc-241104

BibTeX
@article{KhaleelSallamMaaitah2025,
  author = {Khaleel Sallam Ma'aitah, Mohammad and Helwan, Abdulkader},
  title = {3D DenseNet with temporal transition layer for heart rate estimation from real-life RGB videos},
  journal = {Technology and Health Care},
  year = {2025},
  doi = {10.3233/thc-241104}
}
Kostenlos starten →