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

Wai Shun Tong, Chi Keung Tang, Philippos Mordohai, Gérard Medioni

Research output: Contribution to journalArticlepeer-review

64 Scopus citations

Abstract

Most computer vision applications require the reliable detection of boundaries. In the presence of outliers, missing data, orientation discontinuities, and occlusion, this problem is particularly challenging. We propose to address it by complementing the tensor voting framework, which was limited to second order properties, with first order representation and voting. First order voting fields and a mechanism to vote for 3D surface and volume boundaries and curve endpoints in 3D are defined. Boundary inference is also useful for a second difficult problem in grouping, namely, automatic scale selection. We propose an algorithm that automatically infers the smallest scale that can preserve the finest details. Our algorithm then proceeds with progressively larger scales to ensure continuity where it has not been achieved. Therefore, the proposed approach does not oversmooth features or delay the handling of boundaries and discontinuities until model misfit occurs. The interaction of smooth features, boundaries, and outliers is accommodated by the unified representation, making possible the perceptual organization of data in curves, surfaces, volumes, and their boundaries simultaneously. We present results on a variety of data sets to show the efficacy of the improved formalism.

Original languageEnglish
Pages (from-to)594-611
Number of pages18
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume26
Issue number5
DOIs
StatePublished - May 2004

Keywords

  • 3D perceptual organization
  • Boundary inference
  • Discontinuities
  • First order voting
  • Multiscale analysis
  • Tensor voting

Fingerprint

Dive into the research topics of 'First order augmentation to tensor voting for boundary inference and multiscale analysis in 3D'. Together they form a unique fingerprint.

Cite this