Global feature space neural network for active computer vision

We advance new active computer vision algorithms based on the Feature space Trajectory (FST) representations of objects and a neural network processor for computation of distances in global feature space. Our algorithms classify rigid objects and estimate their pose from intensity images. They also indicate how to automatically reposition the sensor if the class or pose of an object is ambiguous from a given viewpoint and they incorporate data from multiple object views in the final object classification. An FST in a global eigenfeature space is used to represent 3D distorted views of an object. Assuming that an observed feature vector consists of Gaussian noise added to a point on the FST, we derive a probability density function for the observation conditioned on the class and pose of the object. Bayesian estimation and hypothesis testing theory are then used to derive approximations to the maximum a posterioriprobability pose estimate and the minimum probability of error classifier. Confidence measures for the class and pose estimates, derived using Bayes theory, determine when additional observations are required, as well as where the sensor should be positioned to provide the most useful information.

[1]  David Casasent,et al.  Synthetic aperture radar detection, recognition, and clutter rejection with new minimum noise and correlation energy filters , 1997 .

[2]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[3]  Anil K. Jain,et al.  Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Mohamad T. Musavi,et al.  On the training of radial basis function classifiers , 1992, Neural Networks.

[5]  Hiroshi Murase,et al.  Detection of 3D objects in cluttered scenes using hierarchical eigenspace , 1997, Pattern Recognit. Lett..

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

[7]  Thierry Denoeux,et al.  Initializing back propagation networks with prototypes , 1993, Neural Networks.

[8]  Konstantinos A. Tarabanis,et al.  Computing Occlusion-Free Viewpoints , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[10]  David Casasent,et al.  GENERAL METHODOLOGY FOR SIMULTANEOUS REPRESENTATION AND DISCRIMINATION OF MULTIPLE OBJECT CLASSES , 1998 .

[11]  John Krumm,et al.  Eigenfeatures for planar pose measurement of partially occluded objects , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  M. J. D. Powell,et al.  Restart procedures for the conjugate gradient method , 1977, Math. Program..

[13]  M. Kendall.  Elementary Statistics , 1945, Nature.

[14]  Michael G. Thomason,et al.  Syntactic pattern recognition principles , 1974 .

[15]  C. W. Therrien,et al.  Decision, Estimation and Classification: An Introduction to Pattern Recognition and Related Topics , 1989 .

[16]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[17]  Rajesh Shenoy,et al.  Feature space trajectory for distorted-object classification and pose estimation in synthetic aperture radar , 1997 .

[18]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[19]  David Casasent,et al.  Feature spacing trajectory representation and processing for active vision , 1996, Other Conferences.

[20]  Rama Chellappa,et al.  Unsupervised Texture Segmentation Using Markov Random Field Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Frank J. Smieja,et al.  Hard Learning the Easy Way: Backpropagation with Deformation , 1988, Complex Syst..

[22]  Carme Torras,et al.  Vision-based robot positioning using neural networks , 1996, Image Vis. Comput..

[23]  R. Bajcsy.  Active perception , 1988 .

[24]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[25]  David Casasent,et al.  Feature space trajectory neural net classifier , 1995, SPIE Defense + Commercial Sensing.

[26]  Thomas L. Marzetta,et al.  Detection, Estimation, and Modulation Theory , 1976 .

[27]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[28]  Martial Hebert,et al.  3D measurements from imaging laser radars: how good are they? , 1992, Image Vis. Comput..

[29]  Frank P. Ferrie,et al.  Active recognition: using uncertainty to reduce ambiguity , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[30]  Keinosuke Fukunaga,et al.  A Criterion and an Algorithm for Grouping Data , 1970, IEEE Transactions on Computers.

[31]  D P Casasent,et al.  Adaptive-clustering optical neural net. , 1990, Applied optics.

[32]  Keinosuke Fukunaga,et al.  Application of the Karhunen-Loève Expansion to Feature Selection and Ordering , 1970, IEEE Trans. Computers.

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

[34]  David Casasent,et al.  Feature space trajectory neural net classifier: 8-class distortion-invariant tests , 1995, Other Conferences.

[35]  Juyang Weng,et al.  Using Discriminant Eigenfeatures for Image Retrieval , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  William C. Regli,et al.  A repository for design, process planning and assembly , 1997, Comput. Aided Des..

[37]  Daniel M. Gaines,et al.  A National Repository for Design and Process Planning , 1997 .

[38]  Olivier Y. de Vel,et al.  Comparative analysis of statistical pattern recognition methods in high dimensional settings , 1994, Pattern Recognit..

[39]  V. Leitáo,et al.  Computer Graphics: Principles and Practice , 1995 .

[40]  Tony R. Martinez,et al.  The minimum feature set problem , 1994, Neural Networks.

[41]  Hiroshi Murase,et al.  Visual learning and recognition of 3-d objects from appearance , 2005, International Journal of Computer Vision.

[42]  David Casasent,et al.  Feature space trajectory representation for active vision , 1997, Defense, Security, and Sensing.

[43]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[44]  Ferdinand Hergert,et al.  Improving model selection by nonconvergent methods , 1993, Neural Networks.

[45]  M. Carter.  Computer graphics: Principles and practice , 1997 .

[46]  David P. Casasent,et al.  Classifier and shift-invariant automatic target recognition neural networks , 1995, Neural Networks.

[47]  Michael J. Swain,et al.  Promising directions in active vision , 1993, International Journal of Computer Vision.

[48]  Sven J. Dickinson,et al.  Active Object Recognition Integrating Attention and Viewpoint Control , 1994, Comput. Vis. Image Underst..

[49]  H. V. Trees.  Detection, Estimation, And Modulation Theory , 2001 .

[50]  Horst Bischof,et al.  Dealing with occlusions in the eigenspace approach , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[51]  Anil K. Jain,et al.  On the optimal number of features in the classification of multivariate Gaussian data , 1978, Pattern Recognit..

[52]  R. Fisher,et al.  Contributions to Mathematical Statistics , 1951 .