Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Comparing Breast Hemangiomas to Breast Angiosarcomas: An Imaging Based Review.

Current problems in diagnostic radiology·2023

Same author

Data augmentation using image translation for underwater sonar image segmentation.

PloS one·2022

Same author

Multiple Object Detection Based on Clustering and Deep Learning Methods.

Sensors (Basel, Switzerland)·2020

Same author

Study on the Classification Performance of Underwater Sonar Image Classification Based on Convolutional Neural Networks for Detecting a Submerged Human Body.

Sensors (Basel, Switzerland)·2019

Same author

Negative myoclonus associated with pregabalin.

Yeungnam University journal of medicine·2019

Same author

Frusemide aids diagnostic interpretation of <sup>68</sup> Ga-PSMA positron emission tomography/CT in men with prostate cancer.

Journal of medical imaging and radiation oncology·2017

Search research articles

Related Experiment Video

Updated: Mar 15, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Image Inpainting-Based Point Cloud Restoration for Enhancing Tactical Classification of Unmanned Surface Vehicles.

Hyunjun Jeon¹, Eon-Ho Lee², Jane Shin³

¹Department of Mechanical Engineering, Kongju National University, Cheonan 31080, Republic of Korea.

Sensors (Basel, Switzerland)

|March 14, 2026

Summary

This summary is machine-generated.

This study introduces a novel framework to restore incomplete LiDAR data for Unmanned Surface Vehicles (USVs). The method enhances surface vessel classification accuracy, improving situational awareness in challenging maritime environments.

Keywords:

3D point cloud data LiDAR (light detection and ranging)inpainting object classification surface vehicle

More Related Videos

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

Related Experiment Videos

Last Updated: Mar 15, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

Area of Science:

Robotics and Autonomous Systems
Computer Vision
Sensor Data Fusion

Background:

Unmanned Surface Vehicles (USVs) require robust situational awareness for operational effectiveness.
LiDAR sensors provide 3D perception but suffer from data incompleteness due to sparsity and occlusion.
Incomplete data hinders accurate surface vessel classification and navigation.

Purpose of the Study:

To develop and evaluate a framework for restoring incomplete 3D LiDAR point clouds for enhanced surface vessel classification.
To improve the reliability of USV perception systems in data-scarce maritime scenarios.
To enable efficient and accurate object recognition for USVs operating in contested environments.

Main Methods:

A framework combining 2D area projection for heading estimation and a descriptor to resolve orientation ambiguity.
Conversion of 3D point clouds to 2D multi-channel images for deep learning-based inpainting.
Application of high-density keypoint extraction on restored point clouds for feature generation and classification.

Main Results:

The proposed framework significantly improves surface vessel classification accuracy using restored LiDAR data.
Enhanced performance was observed at extended distances (>70 m) and critical aspect angles (0°, 180°).
The image-based approach demonstrates computational efficiency and faster inference speeds.

Conclusions:

The framework effectively addresses perception failures caused by sparse or incomplete LiDAR data.
This approach supports the operational capabilities of USVs in complex and contested maritime settings.
The method offers a viable solution for deploying advanced perception on resource-constrained platforms.