Superquadric-Based Object Recognition
This paper proposes a technique for object recognition using superquadric built models. Superquadrics, which are three dimensional models suitable for part-level representation of objects, are reconstructed from range images using the recover-and-select paradigm. Using an interpretation tree, the presence of an object in the scene from the model database can be hypothesized. These hypotheses are verified by projecting and re-fitting the object model to the range image which at the same time enables a better localization of the object in the scene.
Keywordssuperquadrics part-level object modeling range images
Unable to display preview. Download preview PDF.
- 1.Barr, A.H.: Superquadrics and Angle-Preserving Transformations. IEEE Computer Graphics and Applications, 1 (January 1981) 11–23Google Scholar
- 4.Grimson W.E.L.: Object Recognition by Computer. MIT Press, Cambridge, MA (1990)Google Scholar
- 6.Jojić N., Huang T.S.: Computer vision and graphics techniques for modeling dressed humans. In: Leonardis A., Solina F., Bajcsy R. (eds.): The confluence of computer vision and computer graphics. Kluwer, Dordrecht (2000) 179–200Google Scholar
- 14.Trucco E., Verri A.: Introductory techniques for 3-D computer vision. Prentice Hall, NJ (1998)Google Scholar