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

702
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...
702

You might also read

Related Articles

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

Sort by
Same author

Prediction of Flight Time Deviation for Lithuanian Airports Using Supervised Machine Learning Model.

Computational intelligence and neuroscience·2020
Same journal

Towards video-based injury risk assessment: predicting lifting loads from body pose trajectories.

Machine vision and applications·2025
Same journal

Unsupervised learning of probabilistic subspaces for multi-spectral and multi-temporal image-based disaster mapping.

Machine vision and applications·2024
Same journal

Persistent animal identification leveraging non-visual markers.

Machine vision and applications·2023
Same journal

Semantic scene upgrades for trajectory prediction.

Machine vision and applications·2023
Same journal

Fill in the blank for fashion complementary outfit product Retrieval: VISUM summer school competition.

Machine vision and applications·2023
Same journal

Real-time pedestrian pose estimation, tracking and localization for social distancing.

Machine vision and applications·2022
See all related articles

Related Experiment Video

Updated: Nov 1, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

729

Deep learning-based object recognition in multispectral satellite imagery for real-time applications.

Povilas Gudžius1, Olga Kurasova1, Vytenis Darulis1

  • 1Institute of Data Science and Digital Technologies, Vilnius University, Akademijos street 4, 08412 Vilnius, Lithuania.

Machine Vision and Applications
|June 28, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a novel fully convolutional neural network (FCN) for analyzing satellite imagery, achieving 97.67% accuracy in object recognition. This advancement enables faster, more accurate economic activity prediction for real-time industrial applications.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.2K

Related Experiment Videos

Last Updated: Nov 1, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

729
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.2K

Area of Science:

  • Earth Observation
  • Computer Vision
  • Artificial Intelligence

Background:

  • Satellite imagery provides unprecedented global coverage for economic analysis.
  • Manual analysis of vast satellite data is infeasible due to volume and cost.
  • Existing computer vision models lack the accuracy and speed for real-time applications.

Purpose of the Study:

  • To develop an accurate and fast object recognition model for multispectral satellite imagery.
  • To improve upon current computer vision methods for analyzing satellite data.
  • To enable real-time economic activity prediction using satellite imagery.

Main Methods:

  • Proposed a fully convolutional neural network (FCN) architecture.
  • Optimized model design, training, and regularization for object recognition.
  • Utilized multispectral satellite imagery for training and validation.

Main Results:

  • Achieved state-of-the-art accuracy of 97.67% across multiple sensors.
  • Demonstrated generalization capabilities across diverse geographical areas.
  • Obtained a fivefold improvement in training time and rapid prediction speeds.

Conclusions:

  • The developed FCN model surpasses human-level performance in satellite image analysis.
  • The computationally efficient architecture is suitable for latency-sensitive industrial applications.
  • Findings are applicable to algorithmic trading and other real-time systems, supported by a new public dataset.