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 Experiment Videos

Reducing and filtering point clouds with enhanced vector quantization.

Stefano Ferrari1, Giancarlo Ferrigno, Vincenzo Piuri

  • 1Department of Information Technologies, University of Milano, Crema (CR) 26013, Italy. ferrari@dti.unimi.it

IEEE Transactions on Neural Networks
|February 7, 2007
PubMed
Summary
This summary is machine-generated.

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

STF: A Unified Framework for Joint Pixel-Level Segmentation and Tracking of Tissues in Endoscopic Surgery.

IEEE transactions on bio-medical engineering·2026
Same author

A multifaceted hybrid ES-robotic device for gait training in individuals with neurological disorders.

Nature communications·2025
Same author

Human-Robot Shared Control for Osteotomy Procedure.

IEEE transactions on bio-medical engineering·2025
Same author

EMG-Based Variable Impedance Control for Enhanced Haptic Feedback in Real-Time Material Recognition.

IEEE transactions on haptics·2025
Same author

SAF-IS: A spatial annotation free framework for instance segmentation of surgical tools.

Medical image analysis·2025
Same author

Towards safer robot-assisted surgery: A markerless augmented reality framework.

Neural networks : the official journal of the International Neural Network Society·2024
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Enhanced vector quantization (EVQ) efficiently reduces large 3-D scan data. This novel method significantly speeds up processing, making 3-D mesh generation practical for various applications.

Area of Science:

  • Computer Vision
  • Computer Graphics
  • Data Processing

Background:

  • Modern 3-D scanners generate vast amounts of data.
  • Processing this data for interactive rates requires efficient filtering and cardinality reduction.
  • Existing methods often involve computationally expensive iterative optimization.

Purpose of the Study:

  • Introduce a novel procedure for filtering and reducing 3-D scan data.
  • Develop an optimized version of soft vector quantization (VQ).
  • Create a technique termed enhanced vector quantization (EVQ) for efficient 3-D data mesh generation.

Main Methods:

  • Utilized an optimized version of soft vector quantization (VQ), termed enhanced vector quantization (EVQ).
  • Introduced local computation via hyperbox (HB) partitioning for linear time complexity.

Related Experiment Videos

  • Implemented automatic parameter determination using Zador's criterion.
  • Developed a fully parallelizable algorithm for sublinear time complexity.

    • Main Results:

    • Achieved significant computational time savings (over 80%) compared to classical VQ.
    • Demonstrated linear time complexity with respect to the number of data points (N).
    • Algorithm exhibits sublinear time complexity due to full parallelization.
    • Successfully reconstructed 3-D models from point clouds, including human faces, puppets, and artifacts.

    Conclusions:

    • EVQ offers a computationally efficient and automatic solution for processing large 3-D datasets.
    • The method is suitable for applications requiring fast and manageable 3-D mesh generation.
    • EVQ is a general procedure applicable to large datasets with low-dimensional data spaces.