• DocumentCode
    2552494
  • Title

    3D part segmentation: a new physics-based approach

  • Author

    Wu, Kenong ; Levine, Martin D.

  • Author_Institution
    Centre for Intelligent Machines, McGill Univ., Montreal, Que., Canada
  • fYear
    1995
  • fDate
    21-23 Nov 1995
  • Firstpage
    311
  • Lastpage
    316
  • Abstract
    We propose a novel approach to 3D part segmentation. From physics it is known that on the surface of a charged conductor, charge tends to accumulate at a sharp convexity and vanishes at a sharp concavity. Thus object part boundaries, which are usually denoted by a sharp surface concavity, can be detected by locating surface points exhibiting focal charge minima. Beginning with multiview range data of a 3D object, we simulate the electrical charge distribution over an object´s surface which has been tessellated by a triangular mesh. We detect the deep surface concavities by tracing local charge density minima and then decompose the object into parts at these points
  • Keywords
    image segmentation; object recognition; 3D part segmentation; charged conductor; electrical charge distribution; object part boundaries; physics-based approach; sharp concavity; sharp convexity; surface points location; Computer vision; Conductors; Data structures; Image segmentation; Object detection; Physics; Quantization; Robustness; Shape; Space charge;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision, 1995. Proceedings., International Symposium on
  • Conference_Location
    Coral Gables, FL
  • Print_ISBN
    0-8186-7190-4
  • Type

    conf

  • DOI
    10.1109/ISCV.1995.477020
  • Filename
    477020