Motion Estimation in the 3-D Gabor Domain

Motion estimation methods can be broadly classified as being spatiotemporal or frequency domain in nature. The Gabor representation is an analysis framework providing localized frequency information. When applied to image sequences, the 3-D Gabor representation displays spatiotemporal/spatiotemporal-frequency (st/stf) information, enabling the application of robust frequency domain methods with adjustable spatiotemporal resolution. In this work, the 3-D Gabor representation is applied to motion analysis. We demonstrate that piecewise uniform translational motion can be estimated by using a uniform translation motion model in the st/stf domain. The resulting motion estimation method exhibits both good spatiotemporal resolution and substantial noise resistance compared to existing spatiotemporal methods. To form the basis of this model, we derive the signature of the translational motion in the 3-D Gabor domain. Finally, to obtain higher spatiotemporal resolution for more complex motions, a dense motion field estimation method is developed to find a motion estimate for every pixel in the sequence.

[1]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[2]  Regis J. Crinon,et al.  Motion estimation: the concept of velocity bandwidth , 1992, Other Conferences.

[3]  Janusz Konrad,et al.  Motion analysis in 3D DCT domain and its application to video coding , 2005, Signal Process. Image Commun..

[4]  Eric Dubois,et al.  Coding image sequence intensities along motion trajectories using EC-CELP quantization , 1994, Proceedings of 1st International Conference on Image Processing.

[5]  Harry Wechsler,et al.  Derivation of optical flow using a spatiotemporal-Frequency approach , 1987, Comput. Vis. Graph. Image Process..

[6]  Julian Magarey,et al.  Motion estimation using a complex-valued wavelet transform , 1998, IEEE Trans. Signal Process..

[7]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[8]  Aggelos K. Katsaggelos,et al.  Noise reduction filters for dynamic image sequences: a review , 1995, Proc. IEEE.

[9]  Christoph Stiller,et al.  Object-based estimation of dense motion fields , 1997, IEEE Trans. Image Process..

[10]  Avinash C. Kak,et al.  Error analysis of robust optical flow estimation by least median of squares methods for the varying illumination model , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Riccardo Leonardi,et al.  Determining the optical flow using wavelet coefficients , 1997, Electronic Imaging.

[12]  Frédéric Dufaux,et al.  Vector Quantization-Based Motion Field Segmentation under the Entropy Criterion , 1994, J. Vis. Commun. Image Represent..

[13]  Todd R. Reed,et al.  On the Computation of Optical Flow using the 3-D Gabor Transform , 1998, Multidimens. Syst. Signal Process..

[14]  Gary J. Balas,et al.  Optical flow: a curve evolution approach , 1995, Proceedings., International Conference on Image Processing.

[15]  Shie Qian,et al.  Discrete Gabor transform , 1993, IEEE Trans. Signal Process..

[16]  J. Davenport.  Editor , 1960 .

[17]  Jean-Pierre Leduc,et al.  Analysis of deformational transformations with spatio-temporal continuous wavelet transforms , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[18]  Todd R. Reed,et al.  A Performance Analysis of Fast Gabor Transform Methods , 1997, CVGIP Graph. Model. Image Process..

[19]  Todd R. Reed,et al.  A Spatiotemporal/Spatiotemporal-Frequency Interpretation of Apparent Motion Reversal , 1999, IJCAI.

[20]  C. Stiller,et al.  Estimating motion in image sequences , 1999, IEEE Signal Process. Mag..

[21]  David J. Fleet,et al.  Computation of component image velocity from local phase information , 1990, International Journal of Computer Vision.

[22]  John G. Daugman,et al.  Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression , 1988, IEEE Trans. Acoust. Speech Signal Process..

[23]  Janusz Konrad,et al.  Estimation and compensation of accelerated motion for temporal sequence interpolation , 1995, Signal Process. Image Commun..

[24]  Akira Kojima,et al.  Motion detection using 3D-FFT spectrum , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[25]  Jerry L. Prince,et al.  A frequency domain performance analysis of Horn and Schunck's optical flow algorithm for deformable motion , 1995, IEEE Trans. Image Process..

[26]  Yao Wang,et al.  Active mesh-a feature seeking and tracking image sequence representation scheme , 1994, IEEE Trans. Image Process..

[27]  C. Stiller,et al.  Estimating Motion in Image Sequences A tutorial on modeling and computation of 2 D motion , 2022 .

[28]  David V. Anderson,et al.  Performance analysis of a correlation-based optical flow algorithm under noisy environments , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[29]  M. Bastiaans,et al.  Gabor's expansion of a signal into Gaussian elementary signals , 1980, Proceedings of the IEEE.

[30]  Eric Dubois,et al.  Estimation of motion fields from image sequences with illumination variation , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[31]  Harpreet S. Sawhney,et al.  Compact Representations of Videos Through Dominant and Multiple Motion Estimation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Georgios B. Giannakis,et al.  Spatiotemporal approach for time-varying global image motion estimation , 1996, IEEE Trans. Image Process..

[33]  Josef Kittler,et al.  A Gradient-Based Method for General Motion Estimation and Segmentation , 1993, J. Vis. Commun. Image Represent..

[34]  Jason Wexler,et al.  Discrete Gabor expansions , 1990, Signal Process..

[35]  Jogikal M. Jagadeesh,et al.  Wavelet functions to estimate velocity in spatiotemporal signals , 1998, IEEE Trans. Signal Process..

[36]  Guido M. Cortelazzo,et al.  Frequency domain analysis of rotational motion , 1993, Multidimens. Syst. Signal Process..

[37]  Luca Lucchese,et al.  A noise-robust frequency domain technique for estimating planar roto-translations , 2000, IEEE Trans. Signal Process..

[38]  Jesús Chamorro-Martínez,et al.  A frequency-domain approach for the extraction of motion patterns , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[39]  Steven K. Rogers,et al.  Discrete, spatiotemporal, wavelet multiresolution analysis method for computing optical flow , 1994 .

[40]  Christophe P. Bernard,et al.  Discrete Wavelet Analysis: A New Framework for Fast Optic Flow Computation , 1998, ECCV.

[41]  T. R. Reed,et al.  Spatiotemporal/spatiotemporal-frequency representations for the integrated analysis of dynamic scenes , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[42]  Todd R. Reed,et al.  The analysis of motion in natural scenes using a spatiotemporal/spatiotemporal-frequency representation , 1997, Proceedings of International Conference on Image Processing.

[43]  D. Ghosh,et al.  An architecture for affine motion estimation in real-time video coding , 2003, 9th Asia-Pacific Conference on Communications (IEEE Cat. No.03EX732).

[44]  Guido M. Cortelazzo,et al.  A differential equation approach to the computation of the Fourier transform of the images of translating objects , 1994, IEEE Trans. Inf. Theory.

[45]  Guido M. Cortelazzo,et al.  A frequency domain technique for estimating rigid planar rotations , 1996, 1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96.

[46]  Eric Dubois,et al.  Bayesian Estimation of Motion Vector Fields , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[47]  Yehoshua Y. Zeevi,et al.  The Generalized Gabor Scheme of Image Representation in Biological and Machine Vision , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[48]  R. Ding,et al.  Oversampled wavelet motion compensation and its hierarchical block-matching algorithm , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[49]  A. Murat Tekalp,et al.  Simultaneous motion estimation and segmentation , 1997, IEEE Trans. Image Process..

[50]  Anthony G. Constantinides,et al.  Variable size block matching motion compensation with applications to video coding , 1990 .

[51]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[52]  Guido M. Cortelazzo,et al.  Frequency Domain Analysis of Translations with Piecewise Cubic Trajectories , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[53]  Todd Randall Reed,et al.  Digital image sequence processing, compression, and analysis , 2004 .

[54]  Hyun Wook Park,et al.  Motion estimation using low-band-shift method for wavelet-based moving-picture coding , 2000, IEEE Trans. Image Process..