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

RETRACTED: Martínez-Revuelta et al. Numerical Study of a Solar Cell to Achieve the Highest InGaN Power Conversion Efficiency for the Whole In-Content Range. <i>Micromachines</i> 2022, <i>13</i>, 1828.

Micromachines·2025
Same author

Plant Stress Detection Using a Three-Dimensional Analysis from a Single RGB Image.

Sensors (Basel, Switzerland)·2024
Same author

Non-Invasive Fish Biometrics for Enhancing Precision and Understanding of Aquaculture Farming through Statistical Morphology Analysis and Machine Learning.

Animals : an open access journal from MDPI·2024
Same author

Theoretical and Computational Analysis of a Wurtzite-AlGaN DUV-LED to Mitigate Quantum-Confined Stark Effect with a Zincblende Comparison Considering Mg- and Be-Doping.

Nanomaterials (Basel, Switzerland)·2022
Same author

RETRACTED: Numerical Study of a Solar Cell to Achieve the Highest InGaN Power Conversion Efficiency for the Whole In-Content Range.

Micromachines·2022
Same author

ECG-Based Identification of Sudden Cardiac Death through Sparse Representations.

Sensors (Basel, Switzerland)·2021

Related Experiment Video

Updated: May 10, 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

430

Three-Dimensional Landing Zone Segmentation in Urbanized Aerial Images from Depth Information Using a Deep Neural

N A Morales-Navarro1, J A de Jesús Osuna-Coutiño1, Madaín Pérez-Patricio1

  • 1Department of Science, Tecnológico Nacional de México/IT de Tuxtla Gutiérrez, Carr. Panamericana Km. 1080, Tuxtla Gutiérrez 29050, Chiapas, Mexico.

Sensors (Basel, Switzerland)
|April 26, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel 3D landing zone segmentation method for autonomous aerial vehicles, improving safety by assessing surface accessibility. The deep neural network (DNN) approach significantly enhances landing zone detection accuracy.

Keywords:
deep learninglanding zone detectionsuperpixel segmentationthree-dimensional semantic segmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

319

Related Experiment Videos

Last Updated: May 10, 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

430
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

319

Area of Science:

  • Robotics
  • Computer Vision
  • Artificial Intelligence

Background:

  • Current landing zone detection for autonomous aerial vehicles primarily uses RGB cameras, lacking depth perception and surface accessibility assessment.
  • RGB-based methods can identify non-viable landing zones due to irregular or inaccessible terrain.
  • Utilizing 3D depth information presents challenges in correctly interpreting depth ambiguity.

Purpose of the Study:

  • To develop a 3D landing zone segmentation methodology for autonomous aerial vehicles.
  • To improve the accuracy and safety of landing zone detection by incorporating depth perception and accessibility analysis.
  • To address the limitations of RGB-only methods in identifying suitable landing areas.

Main Methods:

  • A DNN-Superpixel approach for 3D landing zone segmentation.
  • Clustering depth information using superpixels to segment and delimit zones.
  • Feature extraction from adjacent objects using bounding boxes.
  • Deep Neural Network (DNN) for classifying 3D areas as landable or non-landable based on accessibility.

Main Results:

  • The proposed methodology achieved a 0.953 average recall, correctly identifying 95.3% of landing zone pixels.
  • An average precision of 0.949 indicates that 94.9% of segmented landing zones were accurate.
  • Experimental results demonstrate the feasibility and promise of the DNN-Superpixel approach for 3D landing zone detection.

Conclusions:

  • The DNN-Superpixel methodology effectively segments 3D landing zones, considering surface accessibility for autonomous aerial vehicles.
  • This approach overcomes the limitations of RGB-only systems by integrating depth information.
  • The high recall and precision values suggest a significant improvement in landing zone detection accuracy and safety.