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

An Efficient and Precise Remote Sensing Optical Image Matching Technique Using Binary-Based Feature Points.

Sensors (Basel, Switzerland)·2021
Same author

Development of Nationwide Road Quality Map: Remote Sensing Meets Field Sensing.

Sensors (Basel, Switzerland)·2021
Same author

Implementation of Non-Linear Non-Parametric Persistent Scatterer Interferometry and Its Robustness for Displacement Monitoring.

Sensors (Basel, Switzerland)·2021
Same author

Extraction of Land Information, Future Landscape Changes and Seismic Hazard Assessment: A Case Study of Tabriz, Iran.

Sensors (Basel, Switzerland)·2020
Same author

Ground Displacement in East Azerbaijan Province, Iran, Revealed by L-band and C-band InSAR Analyses.

Sensors (Basel, Switzerland)·2020
Same author

Spatiotemporal deformation patterns of the Lake Urmia Causeway as characterized by multisensor InSAR analysis.

Scientific reports·2018

Related Experiment Video

Updated: Dec 17, 2025

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

3.2K

FWNet: Semantic Segmentation for Full-Waveform LiDAR Data Using Deep Learning.

Takayuki Shinohara1, Haoyi Xiu1, Masashi Matsuoka1

  • 1Department of Architecture and Building Engineering, Tokyo Institute of Technology, Yokohama 226-8502, Japan.

Sensors (Basel, Switzerland)
|July 1, 2020
PubMed
Summary

This study introduces FWNet, a deep learning model for semantic segmentation of airborne full-waveform lidar data. FWNet effectively utilizes both geometric and radiometric information for improved classification accuracy.

Keywords:
deep learningfull-waveform lidar datasemantic segmentationsupervised learning

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

10.3K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.9K

Related Experiment Videos

Last Updated: Dec 17, 2025

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

3.2K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.3K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.9K

Area of Science:

  • Computer Vision
  • Remote Sensing
  • Geospatial Data Analysis

Background:

  • Deep learning models excel in 3D point cloud analysis, including classification and segmentation.
  • Existing methods often overlook radiometric information in airborne laser scanning (ALS) data.
  • Applying deep learning to full-waveform lidar data presents challenges due to its complex nature.

Purpose of the Study:

  • To investigate the use of deep learning for semantic segmentation of airborne full-waveform lidar data.
  • To propose a novel deep learning model, FWNet, capable of processing raw waveform data.
  • To demonstrate the effectiveness of FWNet in extracting both geometric and radiometric features.

Main Methods:

  • Developed FWNet, a PointNet-based deep learning architecture.
  • FWNet directly processes full-waveform lidar data without 2D projection or handcrafted features.
  • Employed 1D convolutional layers for classification based on extracted local and global features.

Main Results:

  • FWNet achieved superior performance in recall, precision, and F1 score on unseen test data compared to existing methods.
  • Achieved a mean recall of 0.73, mean precision of 0.81, and mean F1 score of 0.76.
  • Ablation studies and feature vector visualization confirmed the model's effectiveness.

Conclusions:

  • FWNet successfully performs semantic segmentation on full-waveform lidar data by leveraging both geometric and radiometric properties.
  • The proposed method eliminates the need for expert knowledge or data conversion into 2D/voxels.
  • FWNet offers a robust, data-driven approach for advanced lidar data analysis.