3D matching using statistically significant groupings

Vision programming is defined as the task of constructing explicit object models to be used in object recognition. These object models specify the features to be used in recognizing the object as well as the exact order in which they have to be used. In this article, we describe a vision programming approach to matching 3D models to 2D images. Our system considers feature clusters instead of individual features and dynamically orders unmatched feature clusters based on the existing state of the match. The dynamic feature cluster ordering is achieved through the use of a new dynamic cost function. The automatic vision programming framework is general enough to be used by any feature-based recognition system, and in this article, it is shown to lead to dramatic improvements in the performance of a correspondence-based object recognition system.

[1]  Linda G. Shapiro,et al.  Appearance-Based 3D Object Recognition , 1994, Object Representation in Computer Vision.

[2]  M. S. Costa,et al.  Scene analysis using appearance-based models and relational indexing , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[3]  Prasanna G. Mulgaonkar,et al.  Automatic vision programs from predicted features , 1992, Other Conferences.

[4]  Robert A. Hummel,et al.  Massively parallel model matching: geometric hashing on the Connection Machine , 1992, Computer.

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

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

[7]  Linda G. Shapiro,et al.  Parallel algorithm for object recognition and its implementation on a MIMD machine , 1995, Proceedings of Conference on Computer Architectures for Machine Perception.

[8]  Linda G. Shapiro,et al.  PERFORM: A Fast Object Recognition Method Using Intersection of Projection Error Regions , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  David W. Jacobs,et al.  Error propagation in full 3D-from-2D object recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[10]  R. Bolles,et al.  Recognizing and Locating Partially Visible Objects: The Local-Feature-Focus Method , 1982 .

[11]  Prasanna G. Mulgaonkar,et al.  Automatic vision programming , 1992, CVGIP Image Underst..

[12]  Kari Pulli.  TRIBORS: A Triplet-Based Object Recognition System , 1995 .

[13]  Linda G. Shapiro,et al.  Fast parallel object recognition , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 2 - Conference B: Computer Vision & Image Processing. (Cat. No.94CH3440-5).