On the Recognition of Articulated Objects (Generalizing the Generalized Hough Transform)
A new method for model based recognition of articulated objects in cluttered scenes is presented. This method applies for objects consisting of rigid parts connected by either rotary or prismatic joints. It can also handle multiply jointed objects. Our method is based on an extension of the Generalized Hough transform paradigm. It is applicable to various viewing transformations in 2-D from 2-D and 3-D from 3-D recognition situations. A variant of our approach applies also to the recognition of 3-D objects from 2-D images. No significant degradation is expected in performance for recognition of articulated objects compared with the recognition of rigid objects containing similar amount of visual information. The technique is of low polynomial complexity in the number of features representing the objects.
KeywordsReference Frame Object Recognition Coordinate Frame Interest Point Rigid Object
Unable to display preview. Download preview PDF.
- D. IT. Ballard and Brown C. M. Computer Vision. Prentice-Hall, 1982.Google Scholar
- A. Beinglass and H. J. Wolfson. Articulated Object Recognition, or, How to Generalize the Generalized Hough Transform. Technical report, Eskenazy Inst. of Computer Sciences, Tel Aviv University, 1990.Google Scholar
- A. Beinglass and H. J. Wolfson. Articulated Object Recognition, or, How to Generalize the Generalized Hough Transform. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Maui, Hawaii, June 1991. also TR of Eskenazy Inst. of Computer Sciences, Tel Aviv Univ., 1990.Google Scholar
- J. J. Craig. Introduction to Robotics. Addison-Wesley, Readings, MA., 1986.Google Scholar
- R. Goldberg and D. Lowe. Verification of 3-D parametric models in 2-D image data. In Proc. of IEEE Workshop on Computer Vision, pages 255-257, Miami-Beach, Florida, 1987.Google Scholar
- W.E.L. Grimson. Recognition of Object Families Using Parametrized Models. In Proc. of the IEEE Int. Conf. on Computer Vision, pages 93-101, London, England, 1987.Google Scholar
- A.J. Heller and J.R. Stenstrom. Verification of Recognition and Alignment Hypothesis by Means of Edge Verification Statistics. In Proc. of the DARPA IU Workshop, pages 957-966, Palo Alto, Ca., 1989.Google Scholar
- J. Hong and H. J. Wolfson. An Improved Model-Based Matching Method Using Footprints. In Proc. of the Int. Conf. on Pattern Recognition, pages 72-78, Rome, Italy, November 1988.Google Scholar
- Y. Lamdan, J. T. Schwartz, and H. J. Wolfson. Object Recognition by Affine Invariant Matching. In Proc. of the IEEE Conf on Computer Vision and Pattern Recognition, pages 335-344, Ann Arbor, Michigan, June 1988.Google Scholar
- D.W. Thompson and J.L. Mundy. Three-Dimensional Model Matching from an Unconstrained Viewpoint. In Proc. of the IEEE Int. Conf. on Robotics and Automation, pages 208-220, Raleigh, N. Carolina, 1987.Google Scholar