Monitoring of natural scenes for feature extraction and tracking an independent component analysis (ICA) approach

An independent component analysis (ICA) approach to monitoring of natural scenes empirically generates robust image features for localization and tracking of potentially-occluded targets. The ICA-based empirical model utilizes statistical techniques that assist analysts in characterizing the underlying criteria that enables such feature extraction. Thus, this approach provides a basis for analyzing how the empirically generated feature localization and tracking models and related algorithms to perform their function.

[1]  Aapo Hyvärinen,et al.  Simple-Cell-Like Receptive Fields Maximize Temporal Coherence in Natural Video , 2003, Neural Computation.

[2]  Aapo Hyvärinen,et al.  Connection between multilayer perceptrons and regression using independent component analysis , 2003, Neurocomputing.

[3]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[4]  Thomas S. Huang,et al.  Basis pursuit for tracking , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[5]  W. C. Torrez,et al.  Performance measures for neural nets using Johnson distributions , 1993, IEEE International Conference on Neural Networks.

[6]  N L JOHNSON,et al.  Bivariate distributions based on simple translation systems. , 1949, Biometrika.

[7]  W. C. Torrez,et al.  Johnson Distributions for Fitting Weighted Sums of Sigmoided Neuron Outputs , 1993 .

[8]  Thomas S. Huang,et al.  Parametric contour tracking using unscented Kalman filter , 2002, Proceedings. International Conference on Image Processing.

[9]  A. Hyvärinen,et al.  A multi-layer sparse coding network learns contour coding from natural images , 2002, Vision Research.

[10]  N. L. Johnson,et al.  Systems of frequency curves generated by methods of translation. , 1949, Biometrika.

[11]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[12]  Aapo Hyv.  Fast and Robust Fixed-Point Algorithms for Independent Component Analysis , 1999 .

[13]  Aapo Hyvärinen,et al.  Estimating Overcomplete Independent Component Bases for Image Windows , 2002, Journal of Mathematical Imaging and Vision.

[14]  Knut Liestøl,et al.  Generalized projection pursuit regression , 1998, SIAM J. Sci. Comput..