Indexing without Invariants in 3D Object Recognition

We present a method of indexing 3D objects from single 2D images. The method does not rely on invariant features. This allows a richer set of shape information to be used in the recognition process. We also suggest the kd-tree as an alternative indexing data structure to the standard hash table. This makes hypothesis recovery more efficient in high-dimensional spaces, which are necessary to achieve specificity in large model databases. Search efficiency is maintained in these regimes by the use of best-bin first search. Neighbors recovered from the index are used to generate probability estimates, local within the feature space, which are then used to rank hypotheses for verification. On average, the ranking process greatly reduces the number of verifications required. Our approach is general in that it can be applied to any real-valued feature vector. In addition, it is straightforward to add to our index information from real images regarding the true probability distributions of the feature groupings used for indexing.

[1]  Raashid Malik,et al.  Angle Densities and Recognition of 3D Objects , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  David A. Forsyth,et al.  Invariance-a new framework for vision , 1990, [1990] Proceedings Third International Conference on Computer Vision.

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

[4]  J.B. Burns,et al.  View Variation of Point-Set and Line-Segment Features , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Gérard G. Medioni,et al.  Structural Indexing: Efficient 3-D Object Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  David A. Forsyth,et al.  Efficient model library access by projectively invariant indexing functions , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Jezekiel Ben-Arie.  The Probabilistic Peaking Effect of Viewed Angles and Distances with Application to 3-D Object Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Dinesh K. Pai,et al.  Model-based telerobotics with vision , 1997, Proceedings of International Conference on Robotics and Automation.

[10]  Eamon B. Barrett,et al.  General methods for determining projective invariants in imagery , 1991, CVGIP Image Underst..

[11]  Peter C. Wayner,et al.  Efficiently using invariant theory for model-based matching , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Katsushi Ikeuchi,et al.  Sensor Modeling, Probabilistic Hypothesis Generation, and Robust Localization for Object Recognition , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Bernt Schiele,et al.  Object Recognition Using Multidimensional Receptive Field Histograms , 1996, ECCV.

[14]  Rakesh Mohan,et al.  Multidimensional Indexing for Recognizing Visual Shapes , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

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

[16]  David G. Lowe,et al.  Fitting Parameterized Three-Dimensional Models to Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  David W. Jacobs,et al.  Space and Time Bounds on Indexing 3D Models from 2D Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Jon Louis Bentley,et al.  An Algorithm for Finding Best Matches in Logarithmic Expected Time , 1977, TOMS.

[21]  David G. Lowe,et al.  Similarity Metric Learning for a Variable-Kernel Classifier , 1995, Neural Computation.

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

[23]  David G. Lowe,et al.  Indexing without invariants in model-based object recognition , 1997 .

[24]  Azriel Rosenfeld,et al.  3-D Shape Recovery Using Distributed Aspect Matching , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Gérard G. Medioni,et al.  Structural Indexing: Efficient 2D Object Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Jean Ponce,et al.  Probabilistic 3D object recognition , 1995, Proceedings of IEEE International Conference on Computer Vision.

[27]  R. Nelson,et al.  Large-scale tests of a keyed, appearance-based 3-D object recognition system , 1998, Vision Research.

[28]  Hanan Samet,et al.  The Design and Analysis of Spatial Data Structures , 1989 .

[29]  Azriel Rosenfeld,et al.  From volumes to views: An approach to 3-D object recognition , 1992, CVGIP Image Underst..

[30]  Bernt Schiele,et al.  Probabilistic object recognition using multidimensional receptive field histograms , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[31]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.