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

Classification of Signals01:30

Classification of Signals

1.5K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.5K

You might also read

Related Articles

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

Sort by
Same author

Light-driven intracellular and extracellular polymer dynamics regulate colony morphology and buoyancy in Microcystis.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

A Terrain-Constrained TIN Approach for High-Precision DEM Reconstruction Using UAV Point Clouds.

Journal of imaging·2026
Same author

The telomere-to-telomere genome assembly of the Triplophysa erythraea (Nemacheilidae hypogean fishes).

Scientific data·2025
Same author

The AMEE-PPI Method to Extract Typical Outcrop Endmembers from GF-5 Hyperspectral Images.

Sensors (Basel, Switzerland)·2025
Same author

Hyperspectral quantitative retrieving of soil iron oxide and Zn content combining feature selection and machine learning algorithms.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2025
Same author

Research on the Quantitative Inversion of Soil Iron Oxide Content Using Hyperspectral Remote Sensing and Machine Learning Algorithms in the Lufeng Annular Structural Area of Yunnan, China.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Mar 15, 2026

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.9K

HL-Mamba: A High-Low Frequency Interaction Mamba Network for Hyperspectral Image Classification.

Yehong Teng1, Shu Gan1,2, Xiping Yuan1,2

  • 1School of Land and Resources Engineering, Kunming University of Science and Technology, Kunming 650093, China.

Sensors (Basel, Switzerland)
|March 14, 2026
PubMed
Summary

This study introduces HL-Mamba, a novel deep learning network for hyperspectral image (HSI) classification. HL-Mamba effectively separates and integrates high- and low-frequency features, significantly improving classification accuracy by enhancing spectral-spatial representations.

Keywords:
cross-frequency interactiondeep learningfrequency alignment losshigh–low frequency decompositionhyperspectral image classification

More Related Videos

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.5K
Author Spotlight: Unveiling the Potential of VSFG Microscopy in Studying Mesoscopically Heterogeneous Self-Assembled Structures
08:49

Author Spotlight: Unveiling the Potential of VSFG Microscopy in Studying Mesoscopically Heterogeneous Self-Assembled Structures

Published on: December 1, 2023

2.1K

Related Experiment Videos

Last Updated: Mar 15, 2026

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.9K
Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.5K
Author Spotlight: Unveiling the Potential of VSFG Microscopy in Studying Mesoscopically Heterogeneous Self-Assembled Structures
08:49

Author Spotlight: Unveiling the Potential of VSFG Microscopy in Studying Mesoscopically Heterogeneous Self-Assembled Structures

Published on: December 1, 2023

2.1K

Area of Science:

  • Remote Sensing
  • Computer Vision
  • Deep Learning

Background:

  • Hyperspectral image (HSI) classification faces challenges due to high dimensionality and spectral-spatial correlations, leading to information redundancy and feature entanglement.
  • Existing deep learning methods struggle to effectively capture both global structures and fine-grained details in HSIs.

Purpose of the Study:

  • To propose a novel high-low frequency interaction Mamba network (HL-Mamba) for improved HSI classification.
  • To effectively decouple and interact global structures and edge details in the frequency domain for enhanced spectral-spatial representation.

Main Methods:

  • A high-low frequency decomposition Mamba module separates HSIs into low-frequency structural and high-frequency edge detail components.
  • Two parallel Mamba branches model long-range dependencies, mitigating redundancy and enabling efficient global modeling.
  • A cross-frequency interaction module with dynamic attention integrates high- and low-frequency features, refining spectral-spatial representations.

Main Results:

  • The proposed HL-Mamba achieved superior performance on four benchmark datasets, with overall accuracies of 94.07% (Indian Pines), 93.82% (Pavia University), 95.28% (WHU-Hi-HanChuan), and 87.32% (Houston).
  • Significantly outperformed eight comparison methods, demonstrating the effectiveness of the proposed approach.
  • Ablation studies confirmed the efficacy of the core components within the HL-Mamba network.

Conclusions:

  • HL-Mamba offers an effective solution for HSI classification by leveraging frequency domain analysis and Mamba architecture.
  • The network's ability to learn complementary information between structural and detail features enhances classification accuracy.
  • The proposed frequency alignment loss further boosts the consistency and complementarity of features, leading to more discriminative representations.