Quality-Aware Framework for Video-Derived Respiratory Signals

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nguyen, Nhi, Casado, Constantino Álvarez, Nguyen, Le, Cañellas, Manuel Lage, López, Miguel Bordallo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912767821217792
author Nguyen, Nhi
Casado, Constantino Álvarez
Nguyen, Le
Cañellas, Manuel Lage
López, Miguel Bordallo
author_facet Nguyen, Nhi
Casado, Constantino Álvarez
Nguyen, Le
Cañellas, Manuel Lage
López, Miguel Bordallo
contents Video-based respiratory rate (RR) estimation is often unreliable due to inconsistent signal quality across extraction methods. We present a predictive, quality-aware framework that integrates heterogeneous signal sources with dynamic assessment of reliability. Ten signals are extracted from facial remote photoplethysmography (rPPG), upper-body motion, and deep learning pipelines, and analyzed using four spectral estimators: Welch's method, Multiple Signal Classification (MUSIC), Fast Fourier Transform (FFT), and peak detection. Segment-level quality indices are then used to train machine learning models that predict accuracy or select the most reliable signal. This enables adaptive signal fusion and quality-based segment filtering. Experiments on three public datasets (OMuSense-23, COHFACE, MAHNOB-HCI) show that the proposed framework achieves lower RR estimation errors than individual methods in most cases, with performance gains depending on dataset characteristics. These findings highlight the potential of quality-driven predictive modeling to deliver scalable and generalizable video-based respiratory monitoring solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quality-Aware Framework for Video-Derived Respiratory Signals
Nguyen, Nhi
Casado, Constantino Álvarez
Nguyen, Le
Cañellas, Manuel Lage
López, Miguel Bordallo
Computer Vision and Pattern Recognition
Signal Processing
Video-based respiratory rate (RR) estimation is often unreliable due to inconsistent signal quality across extraction methods. We present a predictive, quality-aware framework that integrates heterogeneous signal sources with dynamic assessment of reliability. Ten signals are extracted from facial remote photoplethysmography (rPPG), upper-body motion, and deep learning pipelines, and analyzed using four spectral estimators: Welch's method, Multiple Signal Classification (MUSIC), Fast Fourier Transform (FFT), and peak detection. Segment-level quality indices are then used to train machine learning models that predict accuracy or select the most reliable signal. This enables adaptive signal fusion and quality-based segment filtering. Experiments on three public datasets (OMuSense-23, COHFACE, MAHNOB-HCI) show that the proposed framework achieves lower RR estimation errors than individual methods in most cases, with performance gains depending on dataset characteristics. These findings highlight the potential of quality-driven predictive modeling to deliver scalable and generalizable video-based respiratory monitoring solutions.
title Quality-Aware Framework for Video-Derived Respiratory Signals
topic Computer Vision and Pattern Recognition
Signal Processing
url https://arxiv.org/abs/2512.14093