Exploiting parallelism in 3D object recognition using the Connection Machine

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.<<ETX>>

[1]  Ramakant Nevatia,et al.  Segmented descriptions of 3-D surfaces , 1987, IEEE Journal on Robotics and Automation.

[2]  R. Paul.  Robot manipulators : mathematics, programming, and control : the computer control of robot manipulators , 1981 .

[3]  Hongbin Zha,et al.  Determining orientation, location and size of primitive surfaces by a modified hough transformation technique , 1988, Pattern Recognit..

[4]  R. Haralick,et al.  The Topographic Primal Sketch , 1983 .

[5]  Russ Miller,et al.  Geometric Algorithms for Digitized Pictures on a Mesh-Connected Computer , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  George C. Stockman,et al.  Object recognition and localization via pose clustering , 1987, Comput. Vis. Graph. Image Process..

[7]  I. Faux,et al.  Computational Geometry for Design and Manufacture , 1979 .

[8]  Ramesh C. Jain,et al.  Invariant surface characteristics for 3D object recognition in range images , 1985, Comput. Vis. Graph. Image Process..

[9]  M. Hebert,et al.  The Representation, Recognition, and Locating of 3-D Objects , 1986 .

[10]  Russ Miller,et al.  Data Movement Techniques for the Pyramid Computer , 1987, SIAM J. Comput..

[11]  Michel Dhome,et al.  Polyhedra Recognition by Hypothesis Accumulation , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Michael D. Howard,et al.  HBA Vision Architecture: Built and Benchmarked , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  W. Daniel Hillis,et al.  Data parallel algorithms , 1986, CACM.

[14]  Anil K. Jain,et al.  Segmentation and Classification of Range Images , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Jake K. Aggarwal,et al.  Recognition of Polyhedra from Range Data , 1986, IEEE Expert.

[16]  Minsoo Suk,et al.  Pose determination using vertex-pairs on the Connection Machine , 1989, [Proceedings 1989] IEEE International Workshop on Tools for Artificial Intelligence.

[17]  W. Daniel Hillis,et al.  The connection machine , 1985 .

[18]  Jake K. Aggarwal,et al.  Curvature-based representation of objects from range data , 1986, Image Vis. Comput..

[19]  Granino A. Korn,et al.  Mathematical handbook for scientists and engineers , 1961 .

[20]  Suchendra M. Bhandarkar,et al.  Hough Clustering Technique for Surface Matching , 1988, MVA.

[21]  Jorge L. C. Sanz,et al.  Hypercube and Shuffle-Exchange Algorithms for Image Component Labeling , 1987, J. Algorithms.

[22]  Baba C. Vemuri,et al.  Representation and recognition of objects from dense range maps , 1987 .

[23]  James J. Little,et al.  Algorithmic Techniques for Computer Vision on a Fine-Grained Parallel Machine , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Massimo Maresca,et al.  Polymorphic-Torus Architecture for Computer Vision , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Suchendra M. Bhandarkar,et al.  Sensitivity analysis for matching and pose computation using dihedral junctions , 1991, Pattern Recognit..

[26]  Ramesh C. Jain,et al.  Segmentation through Variable-Order Surface Fitting , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  W. Eric L. Grimson,et al.  Localizing Overlapping Parts by Searching the Interpretation Tree , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Guy E. Blelloch,et al.  Vector Models for Data-Parallel Computing , 1990 .

[29]  Katsushi Ikeuchi,et al.  Generating an interpretation tree from a CAD model for 3D-object recognition in bin-picking tasks , 1987, International Journal of Computer Vision.

[30]  Ramesh C. Jain,et al.  Spline-based surface fitting on range images for CAD applications , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[31]  Robert M. Haralick,et al.  Digital Step Edges from Zero Crossing of Second Directional Derivatives , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.