3D object recognition using invariant feature indexing of interpretation tables

Abstract This paper proposes a technique for 3D object recognition from range data. Our technique (which was motivated by recent work in geometric hashing) employs precompiled interpretation tables as a source of prototype hypotheses. These tables are indexed by invariant features computed from triples of surface patches. We describe a method for automated construction of interpretation tables from CAD models. Invariant features extracted from the input image are used to index the tables, retrieve prototype hypotheses, and bind them to scene entities. These candidate hypotheses are then ranked via computation of a matching score. The use of precompiled tables of hypotheses offers the potential for greater efficiency in the recognition step than techniques such as constrained search. Experiments demonstrate significant reductions in the number of incorrect hypotheses produced over a constrained search mechanism.

[1]  Jake K. Aggarwal,et al.  Recent progress in the recognition of objects from range data , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[2]  Anil K. Jain,et al.  Evidence-Based Recognition of 3-D Objects , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Robert M. Haralick,et al.  Optimal affine-invariant point matching , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[4]  Patrick J. Flynn.  Saliencies and symmetries: toward 3D object recognition from large model databases , 1992, CVPR.

[5]  Gerard Medioni,et al.  Object recognition using geometric hashing on the Connection Machine , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[6]  Thomas C. Henderson,et al.  CAGD-Based Computer Vision , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Anil K. Jain,et al.  CAD-Based Computer Vision: From CAD Models to Relational Graphs , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  I. Rigoutsos,et al.  Implementation of geometric hashing on the Connection Machine , 1991, [1991 Proceedings] Workshop on Directions in Automated CAD-Based Vision.

[9]  Marc H. Raibert,et al.  Running With Symmetry , 1986 .

[10]  Avinash C. Kak,et al.  A robot vision system for recognizing 3D objects in low-order polynomial time , 1989, IEEE Trans. Syst. Man Cybern..

[11]  Takeo Kanade,et al.  Automatic generation of object recognition programs , 1988, Proc. IEEE.

[12]  Anil K. Jain,et al.  3D object recognition using invariant feature indexing of interpretation tables , 1991, CVGIP Image Underst..

[13]  Anil K. Jain,et al.  BONSAI: 3D Object Recognition Using Constrained Search , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Yehezkel Lamdan,et al.  On the error analysis of 'geometric hashing' , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Avinash C. Kak,et al.  Applying uncertainty reasoning to model based object recognition , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Gérard G. Medioni,et al.  Structural hashing: efficient three dimensional object recognition , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Yehezkel Lamdan,et al.  Affine invariant model-based object recognition , 1990, IEEE Trans. Robotics Autom..

[18]  Yehezkel Lamdan,et al.  Geometric Hashing: A General And Efficient Model-based Recognition Scheme , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[19]  Patrick Joseph Flynn,et al.  Cad-based computer vision: modeling and recognition strategies , 1990 .

[20]  Robert C. Bolles,et al.  3DPO: A Three- Dimensional Part Orientation System , 1986, IJCAI.

[21]  W. Eric L. Grimson,et al.  On the sensitivity of geometric hashing , 1990, [1990] Proceedings Third International Conference on Computer Vision.