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

Force Classification01:22

Force Classification

1.8K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.8K
Absolute Motion Analysis- General Plane Motion01:24

Absolute Motion Analysis- General Plane Motion

281
Visualize a drone, with its propellers spinning rapidly, hovering mid-air. The fascinating movements and operations of this drone can be comprehended by applying the principle of general plane motion.
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the...
281

You might also read

Related Articles

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

Sort by
Same author

A Novel Ensemble Meta-Model for Enhanced Retinal Blood Vessel Segmentation Using Deep Learning Architectures.

Biomedicines·2025
Same author

Hospital Re-Admission Prediction Using Named Entity Recognition and Explainable Machine Learning.

Diagnostics (Basel, Switzerland)·2024
Same author

Explainable COVID-19 Detection Based on Chest X-rays Using an End-to-End RegNet Architecture.

Viruses·2023
Same author

DCTable: A Dilated CNN with Optimizing Anchors for Accurate Table Detection.

Journal of imaging·2023
Same author

A Review of Recent Advances in Deep Learning Models for Chest Disease Detection Using Radiography.

Diagnostics (Basel, Switzerland)·2023
Same author

Applying Deep Learning for Breast Cancer Detection in Radiology.

Current oncology (Toronto, Ont.)·2022

Related Experiment Video

Updated: Sep 30, 2025

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

1.7K

Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation.

Rafik Ghali1, Moulay A Akhloufi1, Wided Souidene Mseddi2

  • 1Perception, Robotics and Intelligent Machines Research Group (PRIME), Department of Computer Science, Université de Moncton, Moncton, NB E1A 3E9, Canada.

Sensors (Basel, Switzerland)
|March 10, 2022
PubMed
Summary

Early wildfire detection is crucial. Deep learning and vision transformers, using Unmanned Aerial Vehicles, show high accuracy in identifying and segmenting fires, even small ones, improving firefighting efforts.

Keywords:
UAVaerial imagesfire classificationfire segmentationvision transformerswildfire detection

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538

Related Experiment Videos

Last Updated: Sep 30, 2025

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

1.7K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538

Area of Science:

  • Environmental Science
  • Computer Science
  • Artificial Intelligence

Background:

  • Wildfires pose significant global risks, exacerbated by climate change, necessitating advanced detection and prediction methods.
  • Unmanned Aerial Vehicles (UAVs) offer flexible, cost-effective aerial surveillance for early fire detection but face challenges like small fire detection and image quality.
  • Existing systems struggle with complex backgrounds and image degradation, limiting early wildfire identification.

Purpose of the Study:

  • To adapt and optimize Deep Learning (DL) methods for early wildfire detection using aerial imagery.
  • To develop and evaluate a novel deep ensemble learning model for wildfire classification.
  • To employ and assess vision transformers and deep convolutional models for precise wildfire segmentation.

Main Methods:

  • A deep ensemble learning model combining EfficientNet-B5 and DenseNet-201 was developed for wildfire classification.
  • Vision transformers (TransUNet, TransFire) and a deep convolutional model (EfficientSeg) were utilized for semantic segmentation of wildfire regions.
  • The models were trained and evaluated on aerial images to assess their performance in detecting and delineating fire areas.

Main Results:

  • The proposed ensemble model achieved 85.12% accuracy in wildfire classification, outperforming state-of-the-art methods, especially for small fire detection.
  • TransUNet and TransFire achieved high F1-scores (99.9% and 99.82%, respectively) for wildfire segmentation, surpassing recent models.
  • The DL and vision transformer models demonstrated effectiveness in extracting fine wildfire details and overcoming limitations like complex backgrounds and small fire sizes.

Conclusions:

  • Deep Learning and vision transformers show significant promise for accurate wildfire classification and segmentation from aerial images.
  • The developed models effectively address limitations of existing systems, enabling earlier and more precise wildfire detection.
  • These advanced AI techniques can enhance firefighting strategies by providing timely and detailed information on wildfire occurrences.