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

You might also read

Related Articles

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

Sort by
Same author

Transductive Few-shot Learning With Enhanced Spectral-Spatial Embedding for Hyperspectral Image Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

Fully-Connected Transformer for Multi-Source Image Fusion.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Probing Synergistic High-Order Interaction for Multi-Modal Image Fusion.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Artificial intelligence for geoscience: Progress, challenges, and perspectives.

Innovation (Cambridge (Mass.))·2024
Same author

Interpretable foundation models as decryptors peering into the Earth system.

Innovation (Cambridge (Mass.))·2024
Same author

VOGTNet: Variational Optimization-Guided Two-Stage Network for Multispectral and Panchromatic Image Fusion.

IEEE transactions on neural networks and learning systems·2024

Related Experiment Video

Updated: Apr 27, 2026

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

7.3K

Hyperspectral image segmentation using a new spectral unmixing-based binary partition tree representation.

Miguel A Veganzones1, Guillaume Tochon1, Mauro Dalla-Mura1

  • 1Department Image and SignalGIPSA-Laboratory, Grenoble-INP, Saint Martin d'Heres Cedex, France.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|June 22, 2014
PubMed
Summary

This study introduces a new method for analyzing hyperspectral images using a binary partition tree (BPT) and spectral unmixing. The approach optimizes image segmentation for better data representation and analysis.

More Related Videos

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

17.0K
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

2.0K

Related Experiment Videos

Last Updated: Apr 27, 2026

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

7.3K
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

17.0K
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

2.0K

Area of Science:

  • Computer Vision
  • Remote Sensing
  • Image Analysis

Background:

  • The binary partition tree (BPT) offers a hierarchical image representation for multi-scale exploration.
  • Pruning BPTs is crucial for creating compact representations and optimal image partitions for specific tasks.
  • Hyperspectral image analysis benefits from efficient segmentation and representation techniques.

Purpose of the Study:

  • To propose a novel binary partition tree (BPT) construction and pruning strategy tailored for hyperspectral images.
  • To leverage spectral unmixing concepts for improved image partitioning and reconstruction error minimization.
  • To demonstrate the effectiveness of the proposed method on diverse hyperspectral datasets.

Main Methods:

  • Developed a new BPT construction algorithm incorporating spectral unmixing principles.
  • Implemented a pruning strategy based on local spectral unmixing within image regions.
  • Utilized linear spectral unmixing to identify endmembers and fractional abundances.

Main Results:

  • The proposed methodology achieves a global minimum reconstruction error through optimized partitioning.
  • The novel BPT approach effectively represents hyperspectral data at various segmentation scales.
  • Successful application and validation on real-world hyperspectral datasets with varying characteristics.

Conclusions:

  • The integration of spectral unmixing with BPTs provides an effective strategy for hyperspectral image analysis.
  • The developed method offers a robust and scalable solution for hyperspectral image segmentation and representation.
  • This approach enhances the utility of BPTs for tasks requiring optimal image partitioning in hyperspectral imaging.