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

Three-Dimensional Sound Source Localization with Microphone Array Combining Spatial Entropy Quantification and Machine Learning Correction.

Entropy (Basel, Switzerland)·2025
See all related articles

Related Experiment Video

Updated: Jun 12, 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

2.7K

A Hierarchical Neural Network for Point Cloud Segmentation and Geometric Primitive Fitting.

Honghui Wan1, Feiyu Zhao1,2

  • 1College of Computer Science, South-Central Minzu University, No. 182 Minzu Avenue, Hongshan District, Wuhan 430074, China.

Entropy (Basel, Switzerland)
|September 27, 2024
PubMed
Summary
This summary is machine-generated.

This study presents a new hierarchical neural network for generating geometric models from point cloud data. The method accurately identifies geometric primitives and is robust to noise, outperforming existing techniques.

Keywords:
computer visionpoint cloudprimitive fittingsegmentation

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

8.6K
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.7K

Related Experiment Videos

Last Updated: Jun 12, 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

2.7K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.7K

Area of Science:

  • Computer Vision
  • Geometric Modeling
  • Machine Learning

Background:

  • Automated geometric model generation from point clouds is crucial for applications like shape modeling and object recognition.
  • Existing methods often struggle with accuracy and noise resilience.

Purpose of the Study:

  • To introduce a novel hierarchical neural network for accurate geometric primitive detection and parameter computation from point cloud data.
  • To enhance the robustness and accuracy of automated geometric modeling.

Main Methods:

  • Developed a hierarchical neural network employing recursive PointConv operations on nested point set subdivisions.
  • The network performs feature extraction, point cloud segmentation, and geometric primitive identification.

Main Results:

  • Achieved superior fine-grained primitive detection accuracy, outperforming SPFN by 18.5% and CPFN by 11.2%.
  • Demonstrated consistent low absolute errors in parameter prediction, even with varying noise levels.
  • Validated the method's robustness and superiority over existing approaches.

Conclusions:

  • The proposed hierarchical neural network offers a robust and accurate solution for automated geometric modeling from point clouds.
  • This method significantly advances the state-of-the-art in geometric primitive detection and parameter estimation.