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

Advancements, challenges, and future prospects of smart grid technology in India.

Frontiers in artificial intelligence·2024
See all related articles

Related Experiment Video

Updated: Sep 18, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.0K

Optimizing Remote Sensing Image Retrieval Through a Hybrid Methodology.

Sujata Alegavi1, Raghvendra Sedamkar2

  • 1Internet of Things Department, Thakur College of Engineering and Technology, Mumbai 400101, Maharashtra, India.

Journal of Imaging
|June 25, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a hybrid approach for enhanced remote sensing image retrieval, improving classification accuracy and similarity measurement. The novel system achieves 86.66% average accuracy, outperforming traditional methods.

Keywords:
Convolutional Neural Networks (CNNs)classificationhybrid networkhyperspectral images (HSIs)pretrained networksretrievalsynthetic aperture radar images (SAR)

More Related Videos

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

2.5K
Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.4K

Related Experiment Videos

Last Updated: Sep 18, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.0K
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

2.5K
Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.4K

Area of Science:

  • Remote Sensing
  • Computer Vision
  • Machine Learning

Background:

  • Retrieving high-resolution remote sensing images from large databases is challenging due to data volume and complexity.
  • Current AI techniques and compression algorithms limit semantic-based image retrieval and target-specific data access.
  • Scaling and rotation variations in image acquisition further complicate accurate data retrieval.

Purpose of the Study:

  • To propose an innovative hybrid approach for enhancing the retrieval of remotely sensed images.
  • To improve classification accuracy, similarity measurement, and computational efficiency in remote sensing image retrieval systems.
  • To address limitations in semantic-based retrieval and data compression challenges.

Main Methods:

  • A hybrid system combining multilevel classification and multiscale feature extraction.
  • Active learning using the Multiscale Multiangle Mean-shift with Breaking Ties (MSMA-MSBT) algorithm for sample selection.
  • Modified Deep Image Registration using Dynamic Inlier (IRDI) for image registration, and feature extraction via MSMA-CLBP and a hybrid CNN structure.
  • Fusion of low-level and high-level features with soft thresholding and region-based similarity measurement.

Main Results:

  • The proposed method achieved an average accuracy of 86.66% on high-resolution remote sensing datasets.
  • Demonstrated superior performance compared to traditional algorithms in classification accuracy and similarity measurement.
  • Showcased significant improvements in computational efficiency over state-of-the-art methods.

Conclusions:

  • The developed hybrid retrieval system effectively enhances the retrieval of remotely sensed images.
  • The combination of multiscale features, advanced registration, and hybrid classification significantly boosts retrieval performance.
  • The approach offers a robust solution for managing and exploiting large volumes of high-resolution remote sensing data.