Proceedings Article10.1109/SECON.1992.202378
Exploiting parallelism in 3D object recognition using the Connection Machine
Suchendra M. Bhandarkar,R. Shankar,M. Suk +2 more
- 12 Apr 1992
- pp 396-403
TL;DR: Dihedral feature junctions are shown to be fairly robust to occlusion and offer a viewpoint-independent modeling technique for the curved objects under consideration and a considerable saving in terms of storing the object models as compared to the viewpoint-dependent modeling techniques which need to store multiple views of a single object model.
read more
Abstract: The authors show how data parallelism can be exploited at various stages in the recognition and localization of 3D objects from range data. These stages are edge detection, segmentation, feature extraction; matching, and pose determination. Qualitative classification of surfaces based on the signs of the mean and Gaussian curvature is used to come up with dihedral feature junctions as features for matching and pose determination. Dihedral feature junctions are shown to be fairly robust to occlusion and offer a viewpoint-independent modeling technique for the curved objects under consideration. This offers a considerable saving in terms of storing the object models as compared to the viewpoint-dependent modeling techniques which need to store multiple views of a single object model. Dihedral feature junctions are quite easy to extract and do not require very elaborate segmentation. Experimental results on the Connection Machine showed the advantages of exploiting parallelism in 3D object recognition. >
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Journal Article
Geometric algorithms for digitized pictures on a mesh-connected computer
Russ Miller,Quentin F. Stout +1 more
TL;DR: In this paper, the authors presented new optimal algorithms for computing several geometric properties of figures in an n × n mesh-connected computer, such as determining the extreme points of the convex hull of each component, determining if two sets of processors are linearly separable, deciding if each component is convex, determining the distance to the nearest neighbor component, for counting and marking minimal internal paths in each component and for computing the external diameter.
116
References
•Book
Computational Geometry for Design and Manufacture
I. D. Faux,M. J. Pratt +1 more
- 01 Mar 1979
TL;DR: In this paper, the mathematical techniques for the representation, analysis and synthesis of shape information by computers are discussed, and splines and related means for defining composite curves and "patched" surfaces are discussed.
1.3K
Digital Step Edges from Zero Crossing of Second Directional Derivatives
TL;DR: The facet model is used to accomplish step edge detection and the Marr-Hildreth zero crossing of the Laplacian operator is found that it is the best performer; next is the Prewitt gradient operator.
Segmentation through variable-order surface fitting
Paul J. Besl,Ramesh Jain +1 more
TL;DR: A piecewise-smooth surface model for image data that possesses surface coherence properties is used to develop an algorithm that simultaneously segments a large class of images into regions of arbitrary shape and approximates image data with bivariate functions so that it is possible to compute a complete, noiseless image reconstruction based on the extracted functions and regions.