Aspect Graphs And Nonlinear Optimization In 3-D Object Recognition

Several researchers have previously described approaches to 3-D object recognition which use nonlinear optimization to control the matching of features of a 3-D object niodel to features found in an image. Recognition, in this context, includes estimating the parameters of translation and orientation of the object. A major problem acknowledged by previous researchers is how to efficiently choose a set of starting paranleter estimates which will avoid recognition errors due to local minima. The unique contribution of this paper is that it outlines an approach for using the perspective projection aspect gruph representation to alleviate the problems encountered by previous researchers, describes a particular implementation of this general approach, and presents data to illustrate the effectiveness (of the approac!].

[1]  Hooshang Hemami,et al.  Identification of Three-Dimensional Objects Using Fourier Descriptors of the Boundary Curve , 1974, IEEE Trans. Syst. Man Cybern..

[2]  J. Brian Burns,et al.  Recognition in 2D Images of 3D Objects from Large Model Bases Using Prediction Hierarchies , 1987, IJCAI.

[3]  Raimund Seidel,et al.  Constructing Arrangements of Lines and Hyperplanes with Applications , 1986, SIAM J. Comput..

[4]  Glen M. Castore,et al.  Solid Modeling, Aspect Graphs, and Robot Vision , 1984 .

[5]  Charles R. Dyer,et al.  Model-based recognition in robot vision , 1986, CSUR.

[6]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[7]  Nancy A. Watts.  Calculating the principal views of a polyhedron , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[8]  Kevin W. Bowyer,et al.  Restructuring Aspect Graphs into Aspect- and Cell-Equivalence Classes for Use in Computer Vision , 1987, WG.

[9]  Charles R. Dyer,et al.  An algorithm for constructing the aspect graph , 1986, 27th Annual Symposium on Foundations of Computer Science (sfcs 1986).

[10]  David Harwood,et al.  An iterative hough procedure for three-dimensional object recognition , 1984, Pattern Recognit..

[11]  Jitendra Malik,et al.  Computing the aspect graph for line drawings of polyhedral objects , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[12]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[13]  Linda G. Shapiro.  A CAD-Model-Based System For Object Localization , 1988, Defense, Security, and Sensing.

[14]  Jean-Pierre Petit,et al.  On the convergence of standard and damped least squares methods , 1976 .

[15]  Ramesh C. Jain,et al.  Three-dimensional object recognition , 1985, CSUR.

[16]  Jan A. Mulder,et al.  An Algorithm which Automatically Constructs Discrimination Graphs in a Visual Knowledge Base , 1987, IJCAI.

[17]  Linda G. Shapiro,et al.  Identification of Space Curves from Two-Dimensional Perspective Views , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Raimund Seidel,et al.  Constructing arrangements of lines and hyperplanes with applications , 1983, 24th Annual Symposium on Foundations of Computer Science (sfcs 1983).

[19]  John R. Kender,et al.  What is a 'Degenerate' View? , 1987, IJCAI.

[20]  Charles R. Dyer,et al.  3-D multiview object representations for model-based object recognition , 1987, Pattern Recognit..

[21]  Donald B. Johnson,et al.  Finding All the Elementary Circuits of a Directed Graph , 1975, SIAM J. Comput..

[22]  Ronald Lumia,et al.  Model-based strategies for high-level robot vision , 1986, Comput. Vis. Graph. Image Process..