SoftPOSIT: An Algorithm for Registration of 3D Models to Noisy Perspective Images Combining Softassi

We propose an algorithm SoftPOSIT for automatic model to image registration This algorithm combines two techniques a solution to the correspondence problem by an iterative technique called Softassign and a solution to the pose problem by an iterative technique called POSIT These two techniques are combined into a single iteration loop The present report focuses on the description of the algorithm Results of a performance evaluation obtained from Monte Carlo simulations under a variety of levels of clutter occlusion and image noise will be presented in a forthcoming report

[1]  Alan L. Yuille,et al.  The invisible hand algorithm: Solving the assignment problem with statistical physics , 1994, Neural Networks.

[2]  Steven Gold,et al.  A Framework for Non-rigid Matching and Correspondence , 1995, NIPS.

[3]  Richard Sinkhorn.  A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices , 1964 .

[4]  Eric Mjolsness,et al.  New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence , 1998, NIPS.

[5]  S. Ullman.  Aligning pictorial descriptions: An approach to object recognition , 1989, Cognition.

[6]  Walter J. Mueller,et al.  Model supported positioning , 1995, Remote Sensing.

[7]  H. Baird.  Model-Based Image Matching Using Location , 1985 .

[8]  Frédéric Jurie,et al.  Solution of the Simultaneous Pose and Correspondence Problem Using Gaussian Error Model , 1999, Comput. Vis. Image Underst..

[9]  Larry S. Davis,et al.  Recognition and Tracking of 3D Objects by 1D Search , 1993 .

[10]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[11]  Yehezkel Lamdan,et al.  Object recognition by affine invariant matching , 2011, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Todd A. Cass,et al.  Polynomial-Time Object Recognition in the Presence of Clutter, Occlusion, and Uncertainty , 1992, ECCV.

[13]  Larry S. Davis,et al.  Iterative Pose Estimation Using Coplanar Feature Points , 1996, Comput. Vis. Image Underst..

[14]  Thomas M. Breuel,et al.  Fast recognition using adaptive subdivisions of transformation space , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Rama Chellappa,et al.  A unified approach to boundary perception: edges, textures, and illusory contours , 1993, IEEE Trans. Neural Networks.

[16]  John S. Bridle,et al.  Training Stochastic Model Recognition Algorithms as Networks can Lead to Maximum Mutual Information Estimation of Parameters , 1989, NIPS.

[17]  Gerd Hirzinger,et al.  Registration of CAD-models to images by iterative inverse perspective matching , 1996, Proceedings of 13th International Conference on Pattern Recognition.