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

Efficient three-dimensional metric object modeling from uncalibrated image sequences.

Lee Cadman1, Tardi Tjahjadi

  • 1School of Engineering, University of Warwick, Coventry, CV4 7AL, UK.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|September 21, 2004
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

One to All: Toward a Unified Model for Counting Cereal Crop Heads Based on Few-Shot Learning.

Plant phenomics (Washington, D.C.)·2024
Same author

Variable Temporal Length Training for Action Recognition CNNs.

Sensors (Basel, Switzerland)·2024
Same author

A Multiscale Point-Supervised Network for Counting Maize Tassels in the Wild.

Plant phenomics (Washington, D.C.)·2023
Same author

From Laboratory to Field: Unsupervised Domain Adaptation for Plant Disease Recognition in the Wild.

Plant phenomics (Washington, D.C.)·2023
Same author

A Segmentation-Guided Deep Learning Framework for Leaf Counting.

Frontiers in plant science·2022
Same author

FPGA-based systolic deconvolution architecture for upsampling.

PeerJ. Computer science·2022

This study introduces an image-based geometric modeling scheme using passive sensing. The robust, accurate method reconstructs scene structure and surfaces, even with noisy or missing features.

Area of Science:

  • Computer Vision
  • Geometric Modeling
  • Passive Sensing

Background:

  • Producing accurate geometric models from passive sensing data presents practical challenges.
  • Existing methods struggle with feature appearance/disappearance and noisy image data.

Purpose of the Study:

  • To present a robust and accurate image-based scheme for geometric scene modeling.
  • To address practical issues in structure and surface recovery from passive sensor data.

Main Methods:

  • A recursive structure recovery method using robust corner tracking and a dual extended Kalman filter for structure and motion estimation.
  • A recursive surface reconstruction technique employing visibility constraints to generate triangulated surfaces.
  • The scheme does not require prior knowledge of camera or scene parameters.

Related Experiment Videos

Main Results:

  • The proposed scheme demonstrates robustness and accuracy in metric structure recovery.
  • The surface reconstruction yields triangulated surfaces consistent with original image sequences.
  • The method maintains good numerical stability even with significant noise and feature loss.

Conclusions:

  • The developed image-based scheme effectively addresses practical challenges in geometric modeling.
  • The combination of recursive structure recovery and surface reconstruction offers a reliable approach.
  • The technique is suitable for applications requiring accurate 3D scene reconstruction from passive imagery.