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

Attenuated Total Reflectance (ATR) Infrared Spectroscopy: Overview01:13

Attenuated Total Reflectance (ATR) Infrared Spectroscopy: Overview

1.1K
Attenuated total reflectance (ATR) infrared spectroscopy is a powerful analytical technique used to study the composition of materials. It is widely employed in chemistry, materials science, forensic science, and other fields where sample characterization is required. ATR has several advantages over traditional transmission IR spectroscopy, including the requirement of little to no sample preparation and the ability to analyze a wide range of samples.
The ATR process begins by directing a beam...
1.1K
Ultraviolet and Visible (UV–Vis) Spectroscopy: Overview01:02

Ultraviolet and Visible (UV–Vis) Spectroscopy: Overview

4.4K
Ultraviolet–visible (UV–visible or UV–Vis) spectroscopy is an analytical technique that investigates the interaction between matter and UV–Vis light within the electromagnetic spectrum. This method is widely used for its versatility, simplicity, and relatively quick data acquisition, making it valuable for both qualitative and quantitative analysis. When UV–Vis radiation passes through a material,  molecules absorb light depending on the energy required for...
4.4K

You might also read

Related Articles

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

Sort by
Same author

Correction: Removal of iodine from organic media using diethylene triamine-grafted vinylbenzyl chloride-divinylbenzene resin.

RSC advances·2026
Same author

Retraction Note: The invisible architects: microbial communities and their transformative role in soil health and global climate changes.

Environmental microbiome·2026
Same author

Design and evaluation of an intent-based web of things query framework for smart device discovery.

Scientific reports·2026
Same author

Retraction notice to "Effect of soil texture and zinc oxide nanoparticles on growth and accumulation of cadmium by wheat; a life cycle study" [Environ. Res. 216 (2023)114397].

Environmental research·2026
Same author

Laser-programmable glycosaminoglycan-based nanocarriers co-deliver hypocrellin B and doxorubicin for spatiotemporal chemo-photothermal therapy of hepatocellular carcinoma.

Colloids and surfaces. B, Biointerfaces·2026
Same author

Explainable Text-Based Depression and Suicide Risk Prediction from Social Media Using Deep Learning and Graph Neural Networks.

Healthcare (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jan 10, 2026

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.2K

Tri branch attention enhanced 3DUNet for remote sensing based hyperspectral image classification.

Mahmood Ashraf1, Tahir Abbas2, Sajid Iqbal3

  • 1Department of Communication and Cyber Security, Bahauddin Zakariya University, Multan, 60000, Pakistan.

Scientific Reports
|November 27, 2025
PubMed
Summary

A novel three-branched 3D U-Net architecture enhances hyperspectral image (HSI) classification by extracting spectral and spatial features. This deep learning approach overcomes class imbalance and resolution degradation, achieving superior accuracy on benchmark datasets.

Keywords:
Fully connected layerHyperspectral image classificationRemote sensingSpatial-spectral attentionTri-3DUNet

More Related Videos

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

434
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.0K

Related Experiment Videos

Last Updated: Jan 10, 2026

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.2K
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

434
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.0K

Area of Science:

  • Remote Sensing
  • Computer Vision
  • Deep Learning

Background:

  • Deep learning models like U-Net struggle with high-resolution hyperspectral images (HSIs) due to class imbalance and resolution degradation.
  • Conventional methods ignore both local and global data, hindering classification accuracy for HSIs with limited labeled data.

Purpose of the Study:

  • To propose a novel three-branched 3D U-Net architecture to overcome the limitations of conventional U-Net for hyperspectral image classification.
  • To enhance the extraction of spectral and spatial features and their joint representation for improved HSI classification accuracy.

Main Methods:

  • A three-branched 3D U-Net architecture was developed, with specialized branches for spectral dependencies, spatial feature learning, and combined spectral-spatial cues.
  • Each branch incorporates an attention mechanism to extract relevant features, which are then integrated and processed through a fully connected layer.
  • The model was evaluated on benchmark HSI datasets (Indian Pines, Pavia University, Houston-2018) using overall accuracy (OA) and average accuracy (AA).

Main Results:

  • The proposed model achieved remarkable classification accuracies: 99.67% on Pavia University, 98.02% on Indian Pines, and 99.88% on Houston-2018.
  • The architecture effectively addresses class imbalance and resolution degradation issues inherent in high-resolution HSIs.
  • The integrated spectral and spatial feature extraction, augmented by attention mechanisms, significantly improved the handling of diverse and diminished pixel information.

Conclusions:

  • The proposed three-branched 3D U-Net architecture demonstrates superior robustness and performance for hyperspectral image classification compared to existing models.
  • The method effectively integrates spectral and spatial information, leading to enhanced feature representation and classification accuracy.
  • This approach offers a promising solution for accurate HSI classification, particularly in scenarios with limited labeled data and complex data characteristics.