Robust Kalman Filters for Prediction , Recognition , andLearningRajesh

Using results from the eld of robust statistics, we derive a class of Kalman lters that are robust to structured and unstructured noise in the input data stream. Each lter from this class maintains robust optimal estimates of the input process's hidden state by allowing the measurement covariance matrix to be a non-linear function of the prediction errors. This endows the lter with the ability to reject outliers in the input stream. Simultaneously, the lter also learns an internal model of input dynamics by adapting its measurement and state transition matrices using two additional Kalman lter-based adaptation rules. We present experimental results demonstrating the eecacy of such lters in mediating appearance-based segmentation and recognition of objects and image sequences in the presence of varying degrees of occlusion, clutter, and noise.

[1]  J. Meditch,et al.  Applied optimal control , 1972, IEEE Transactions on Automatic Control.

[2]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[3]  John Hallam.  Resolving Observer Motion by Object Tracking , 1983, IJCAI.

[4]  Rama Chellappa,et al.  Estimation of Object Motion Parameters from Noisy Images , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[7]  Erkki Oja,et al.  Neural Networks, Principal Components, and Subspaces , 1989, Int. J. Neural Syst..

[8]  M. V. Rossum,et al.  In Neural Computation , 2022 .

[9]  R. Behringer,et al.  Road and relative ego-state recognition , 1992, Proceedings of the Intelligent Vehicles `92 Symposium.

[10]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[11]  Takeo Watanabe,et al.  Neural networks for vision and image processing , 1993 .

[12]  Hiroshi Murase,et al.  Learning and recognition of 3D objects from appearance , 1993, [1993] Proceedings IEEE Workshop on Qualitative Vision.

[13]  K. C. Chou,et al.  Multiscale recursive estimation, data fusion, and regularization , 1994, IEEE Trans. Autom. Control..

[14]  Rajesh P. N. Rao,et al.  An Active Vision Architecture Based on Iconic Representations , 1995, Artif. Intell..

[15]  Bartlett W. Mel.  SEEMORE: a view-based approach to 3-D object recognition using multiple visual cues , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[16]  Rajesh P. N. Rao,et al.  The Visual Cortex as a Hierarchical Predictor , 1996 .

[17]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[18]  Michael Isard,et al.  Contour Tracking by Stochastic Propagation of Conditional Density , 1996, ECCV.

[19]  Rajesh P. N. Rao,et al.  Dynamic Model of Visual Recognition Predicts Neural Response Properties in the Visual Cortex , 1997, Neural Computation.