Recognition strategies for 3-D objects in occluded environments

Two different types of approaches will be discussed: one for a model-driven system and the other for generic shape recognition. The model-driven system, called 3D-POLY, has a computational complexity of only O(n 2 ) for single object recognition, where n is the number of surfaces on the model object. This system achieves its computational efficiency by associating a special a priori defined attribute with each object feature and then organizing the object features with respect to this attribute. The generic shape recognition system, called INGEN, is intended for domains where precise models of the objects involved are not available, such as the postal domain; objects in these domains are categorized by their overall shapes with considerable latitude regarding the metrical parameters involved. A unique feature of INGEN, which sets it apart from 3D-POLY, is that object hypotheses are tested by their volumetric consistency, meaning that the hypothesized objects must not violate conditions not only over the space that is visible to the sensor but also over space that may not be visible to the sensor due to occlusions. In other words, while 3D-POLY forms and verifies object hypotheses on the basis of only what is visible to the sensor, INGEN also reasons over the space that is occluded. 3D-POLY is by design limited to drawing all its inferences from the visible data, even in the presence of occlusions, since industrial objects can possess highly complex shape that preclude the kind of volumetric analysis carried out in INGEN.

[1]  Theo Pavlidis,et al.  Algorithms for Graphics and Imag , 1983 .

[2]  W. Grimson,et al.  Model-Based Recognition and Localization from Sparse Range or Tactile Data , 1984 .

[3]  Chien-Huei Chen,et al.  3d-poly: a robot vision system for recognizing objects in occluded environments , 1988 .

[4]  Scott D. Roth,et al.  Ray casting for modeling solids , 1982, Comput. Graph. Image Process..

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

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

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

[8]  T. Pavlidis.  Algorithms for Graphics and Image Processing , 1981, Springer Berlin Heidelberg.

[9]  Ramakant Nevatia,et al.  Matching 3-D objects using surface descriptions , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[10]  Tony Kasvand,et al.  Recognition and positioning of three-dimensional objects by combining matchings of primitive local patterns , 1988, Comput. Vis. Graph. Image Process..

[11]  H. Kenner.  Geodesic Math and How to Use It , 1976 .

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

[13]  Anthony Pugh,et al.  Polyhedra: A Visual Approach , 1976 .

[14]  R. Bajcsy,et al.  Three dimensional object representation revisited , 1987 .

[15]  W. Eric L. Grimson,et al.  Handey: A robot system that recognizes, plans, and manipulates , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[16]  Olivier D. Faugeras,et al.  A 3-D Recognition and Positioning Algorithm Using Geometrical Matching Between Primitive Surfaces , 1983, IJCAI.

[17]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[18]  D. W. Murray.  Model-based recognition using 3D shape alone , 1987, Comput. Vis. Graph. Image Process..