Multi-resolution mesh based 3D object recognition

Qing Li, M.-L. Zhou, J. Liu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

We proposed an improved 3D object representation first, which computes the local signatures of a given basic polygon on the surface mesh, and converts the signatures to a 2D array called the distance-angle (DA) images. This representation is adaptive to free-form objects, resistant to occlusion and clutter. Furthermore, it has distinct meaning, and adaptation to different resolution and irregular triangle mesh. Secondly, based on the representation, a novel 3D object recognition algorithm is presented, which is a multi-resolution mesh based, coarse-to-fine recognition. By matching the DA image of a polygon in the scene surface mesh with the DA images of models in low resolution, a model candidate set is obtained. The set is filtered in the neighborhood of the matched polygons in high-resolution mesh and verified by the model candidate sets of other polygons. Experiments show that this algorithm needs less computation, and is very accurate and robust.
Original languageEnglish
Pages (from-to)891-894
Number of pages4
JournalTien Tzu Hsueh Pao/Acta Electronica Sinica
Volume29
Issue number7
Publication statusPublished - 1 Jul 2001
Externally publishedYes

Keywords

  • 3D object recognition
  • Computer vision
  • Multi-resolution mesh
  • Range image

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this