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

First order augmentation to tensor voting for boundary inference and multiscale analysis in 3D.

Wai-Shun Tong1, Chi-Keung Tang, Philippos Mordohai

  • 1Department of Computer Science, Hong Kong University of Science & Technology, Clear Water Bay, Hong Kong. cstws@cs.ust.hk

IEEE Transactions on Pattern Analysis and Machine Intelligence
|October 6, 2004
PubMed
Summary

This study enhances computer vision by integrating first-order voting into tensor voting for robust boundary detection. The method effectively handles data issues and improves automatic scale selection for feature preservation.

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

Glissando-Net: Deep Single View Category Level Pose Estimation and 3D Reconstruction.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Occlusion-Aware Instance Segmentation Via BiLayer Network Architectures.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Inlier Clustering based on the Residuals of Random Hypotheses.

Pattern recognition letters·2021
Same author

On the Synergies Between Machine Learning and Binocular Stereo for Depth Estimation From Images: A Survey.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

Relative CNN-RNN: Learning Relative Atmospheric Visibility From Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2018

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Geometry

Background:

  • Reliable boundary detection is crucial for computer vision applications.
  • Challenges include outliers, missing data, discontinuities, and occlusion.
  • Existing tensor voting methods are limited to second-order properties.

Purpose of the Study:

  • To extend the tensor voting framework with first-order representation for improved boundary detection.
  • To develop an algorithm for automatic scale selection in data grouping.
  • To enable simultaneous perceptual organization of curves, surfaces, volumes, and their boundaries.

Main Methods:

  • Complementing tensor voting with first-order representation and voting.
  • Defining first-order voting fields for 3D boundaries and curve endpoints.

Related Experiment Videos

  • Implementing an algorithm for multi-scale analysis and detail preservation.

    • Main Results:

    • The proposed approach successfully detects boundaries in challenging conditions (outliers, occlusion).
    • The automatic scale selection algorithm preserves fine details while ensuring continuity.
    • Unified representation accommodates smooth features, boundaries, and outliers effectively.

    Conclusions:

    • The enhanced tensor voting framework offers a robust solution for boundary inference in computer vision.
    • The method facilitates accurate perceptual organization of complex data.
    • The approach avoids oversmoothing and handles discontinuities efficiently.