Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Infrared (IR) Spectroscopy: Overview01:09

Infrared (IR) Spectroscopy: Overview

2.4K
When electromagnetic radiation passes through a material, atoms or molecules transition from a lower to a higher energy state by absorbing radiation corresponding to the energy difference between the two states. The absorption of infrared (IR) radiation causes transitions between vibrational energy levels in a molecule. Therefore, IR spectroscopy is a useful analytical tool for determining the molecular structure of molecules.
Different compounds display unique properties due to their...
2.4K
IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

1.2K
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
1.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Energy-Efficient Resource Allocation Scheme Based on Reinforcement Learning in Distributed LoRa Networks.

Sensors (Basel, Switzerland)·2025
Same author

A Novel Deep Learning Model for Human Skeleton Estimation Using FMCW Radar.

Sensors (Basel, Switzerland)·2025
Same author

A Non-Invasive Approach for Facial Action Unit Extraction and Its Application in Pain Detection.

Bioengineering (Basel, Switzerland)·2025
Same author

Accurate Cardiac Duration Detection for Remote Blood Pressure Estimation Using mm-Wave Doppler Radar.

Sensors (Basel, Switzerland)·2025
Same author

A Comparison Study of Person Identification Using IR Array Sensors and LiDAR.

Sensors (Basel, Switzerland)·2025
Same author

Non-Contact Cross-Person Activity Recognition by Deep Metric Ensemble Learning.

Bioengineering (Basel, Switzerland)·2024

Related Experiment Video

Updated: Sep 21, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.2K

An Infrared Array Sensor-Based Approach for Activity Detection, Combining Low-Cost Technology with Advanced Deep

Krishnan Arumugasamy Muthukumar1, Mondher Bouazizi2, Tomoaki Ohtsuki2

  • 1Graduate School of Science and Technology, Keio University, Yokohama 223-8522, Japan.

Sensors (Basel, Switzerland)
|May 28, 2022
PubMed
Summary
This summary is machine-generated.

This study enhances infrared activity detection using deep learning (DL) for super-resolution and denoising. Improved image quality significantly boosts classification accuracy in human activity recognition systems.

Keywords:
CGANactivity detectioncomputer visiondeep learningdenoisinghealthcareinfrared array sensorlow-resolutionsuper-resolution

More Related Videos

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.0K

Related Experiment Videos

Last Updated: Sep 21, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.2K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.0K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Sensor Technology

Background:

  • Low-resolution infrared sensors are cost-effective for activity detection but suffer from image quality issues.
  • Traditional methods struggle with noisy, low-resolution data, limiting activity recognition accuracy.
  • Advanced deep learning techniques offer potential solutions for enhancing infrared image data.

Purpose of the Study:

  • To develop an activity detection system utilizing enhanced low-resolution infrared images.
  • To investigate the impact of super-resolution (SR) and denoising on infrared image quality for activity recognition.
  • To improve the classification accuracy of human activities using hybrid deep learning models.

Main Methods:

  • Collected infrared data at various resolutions (24×32, 12×16, 6×8).
  • Applied deep learning (DL) techniques: Super-Resolution (SR), denoising, and Conditional Generative Adversarial Networks (CGAN) for data augmentation.
  • Utilized a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model for activity classification.

Main Results:

  • Super-resolution and denoising significantly improved infrared image quality.
  • Data augmentation using CGAN increased the diversity of training samples.
  • Classification accuracy improved from 78.32% to 84.43% (6×8 resolution) and 90.11% to 94.54% (12×16 resolution).

Conclusions:

  • Deep learning techniques effectively enhance low-resolution, noisy infrared images for activity detection.
  • The proposed system demonstrates a noticeable improvement in performance and classification accuracy.
  • This approach offers a viable solution for robust human activity recognition in various environments.