Motion segmentation based on motion/brightness integration and oscillatory correlation

A segmentation method based on the integration of motion and brightness is proposed for image sequences. The method is composed of two parallel pathways that process motion and brightness, respectively. Inspired by the visual system, the motion pathway has two stages. The first stage estimates local motion at locations with reliable information. The second stage performs segmentation based on local motion estimates. In the brightness pathway, the input scene is segmented into regions based on brightness distribution. Subsequently, segmentation results from the two pathways are integrated to refine motion estimates. The final segmentation is performed in the motion network based on refined estimates. For segmentation, locally excitatory globally inhibitory oscillator network (LEGION) architecture is employed whereby the oscillators corresponding to a region of similar motion/brightness oscillate in synchrony and different regions attain different phases. Results on synthetic and real image sequences are provided, and comparisons with other methods are made.

[1]  J. Gibson,et al.  Motion parallax as a determinant of perceived depth. , 1959, Journal of experimental psychology.

[2]  P. Anandan.  Measuring Visual Motion From Image Sequences , 1987 .

[3]  Christof Koch,et al.  Computing Optical Flow in the Primate Visual System , 1989, Neural Computation.

[4]  Edward H. Adelson,et al.  Representing moving images with layers , 1994, IEEE Trans. Image Process..

[5]  Ting Chen,et al.  Artificial neural networks for 3-D motion analysis-Part II: Nonrigid motion , 1995, IEEE Trans. Neural Networks.

[6]  Terrence J. Sejnowski,et al.  Filter selection model for motion segmentation and velocity integration , 1994 .

[7]  Josef Kittler,et al.  Nonlinear Motion Estimation Using the Supercoupling Approach , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Noboru Ohnishi,et al.  Robust extraction of moving objects through grouping edges along with optical flow , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[9]  Roger A. Samy.  Infrared target motion estimation using a neural network , 1990, Defense, Security, and Sensing.

[10]  A J Ahumada,et al.  Model of human visual-motion sensing. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[11]  DeLiang Wang,et al.  Image Segmentation Based on Oscillatory Correlation , 1997, Neural Computation.

[12]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[13]  Ting Chen,et al.  Artificial neural networks for 3-D motion analysis. I. Rigid motion , 1995, IEEE Trans. Neural Networks.

[14]  Margaret E. Sereno.  Neural Computation of Pattern Motion: Modeling Stages of Motion Analysis in the Primate Visual Cortex , 1993 .

[15]  Stephen Grossberg,et al.  Neural dynamics of motion grouping: from aperture ambiguity to object speed and direction , 1997 .

[16]  Yair Weiss.  Bayesian motion estimation and segmentation , 1998 .

[17]  Deliang Wang,et al.  Global competition and local cooperation in a network of neural oscillators , 1995 .

[18]  Eero P. Simoncelli.  Distributed representation and analysis of visual motion , 1993 .

[19]  DeLiang Wang,et al.  Locally excitatory globally inhibitory oscillator networks , 1995, IEEE Transactions on Neural Networks.

[20]  E. Adelson,et al.  Phenomenal coherence of moving visual patterns , 1982, Nature.

[21]  Michael J. Black,et al.  Estimating Optical Flow in Segmented Images Using Variable-Order Parametric Models With Local Deformations , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  W. Reichardt.  Autokorrelations-Auswertung als Funktionsprinzip des Zentralnervensystems , 1957 .

[23]  R A Andersen,et al.  Transparent motion perception as detection of unbalanced motion signals. III. Modeling , 1994, The Journal of neuroscience : the official journal of the Society for Neuroscience.

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

[25]  Hajime Kita,et al.  A neural network model of long-range apparent motion in the human vision , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[26]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[27]  Jonathan A. Marshall,et al.  Self-organizing neural networks for perception of visual motion , 1990, Neural Networks.

[28]  George A. Kaplan,et al.  Kinetic disruption of optical texture: The perception of depth at an edge , 1969 .

[29]  Michael J. Black.  Robust incremental optical flow , 1992 .

[30]  Michael J. Black,et al.  The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields , 1996, Comput. Vis. Image Underst..