Motion Segmentation and Tracking with Edge Relaxation and Optimization using Fully Parallel Methods in the Cellular Nonlinear Network Architecture

In this paper we outline a fully parallel and locally connected computation model for the segmentation of motion events in video sequences based on spatial and motion information. Extraction of motion information from video series is very time consuming. Most of the computing effort is devoted to the estimation of motion vector fields, defining objects and determining the exact boundaries of these objects. The split and merge segmentation of different small areas, those obtained by oversegmentation, needs an optimization process. In our proposed algorithm the process starts from an oversegmented image, then the segments are merged by applying the information coming from the spatial and temporal auxiliary data: motion fields and motion history, calculated from consecutive image frames. This grouping process is defined through a similarity measure of neighboring segments, which is based on intensity, speed and the time-depth of motion-history. There is also a feedback for checking the merging process, by this feedback we can accept or refuse the cancellation of a segment-border. Our parallel approach is independent of the number of segments and objects, since instead of graph representation of these components, image features are defined on the pixel level. We use simple VLSI implementable functions like arithmetic and logical operators, local memory transfers and convolution. These elementary instructions are used to build up the basic routines such as motion displacement field detection, disocclusion removal, anisotropic diffusion, grouping by stochastic optimization. This relaxation-based motion segmentation can be a basic step of the effective coding of image series and other automatic motion tracking systems. The proposed system is ready to be implemented in a Cellular Nonlinear Network chip-set architecture.

[1]  Tamás Roska,et al.  CNN-based difference-controlled adaptive non-linear image filters , 1998, Int. J. Circuit Theory Appl..

[2]  Tamás Szirányi,et al.  Classes of analogic CNN algorithms and their practical use in complex image processing tasks , 1995 .

[3]  Tamás Roska,et al.  CNN‐based difference‐controlled adaptive non‐linear image filters , 1998 .

[4]  P. Anandan,et al.  A Unified Approach to Moving Object Detection in 2D and 3D Scenes , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Tamás Szirányi,et al.  Anisotropic diffusion as a preprocessing step for efficient image compression , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[6]  Josiane Zerubia,et al.  Satellite image classification using a modified Metropolis dynamics , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  John Chung-Mong Lee,et al.  Motion Compensated Color Video Classification Using Markov Random Fields , 1998, ACCV.

[8]  Tamás Szirányi,et al.  Texture Classification and Segmentation by Cellular Neural Networks Using Genetic Learning , 1998, Comput. Vis. Image Underst..

[9]  Bart M. ter Haar Romeny,et al.  Geometry-Driven Diffusion in Computer Vision , 1994, Computational Imaging and Vision.

[10]  Tibor Kozek,et al.  Analogic Macro Code (AMC) : extended Assembly language for CNN computers : version 1.1 , 1998 .

[11]  Josiane Zerubia,et al.  Multigrid MRF Based Picture Segmentation with Cellular Neural Networks , 1997, CAIP.

[12]  Patrick Bouthemy,et al.  A region-level graph labeling approach to motion-based segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Tamás Roska,et al.  The CNN universal machine: an analogic array computer , 1993 .

[14]  Til Aach,et al.  Statistical model-based change detection in moving video , 1993, Signal Process..

[15]  Ángel Rodríguez-Vázquez,et al.  A 0.8-μm CMOS two-dimensional programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage , 1997, IEEE J. Solid State Circuits.

[16]  Lucia Ballerini,et al.  Time-Varying Image Processing and Moving Object Recognition , 1997 .

[17]  Keith Langley,et al.  Recursive Filters for Optical Flow , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Leon O. Chua,et al.  Estimating optical flow with cellular neural networks , 1998 .

[19]  Josiane Zerubia,et al.  Markov random field image segmentation using cellular neural network , 1997 .

[20]  Josiane Zerubia,et al.  Image Segmentation Using Markov Random Field Model in Fully Parallel Cellular Network Architectures , 2000 .

[21]  Alexander D. Stoyenko,et al.  Real-Time Imaging: Theory, Techniques, and Application , 1996 .

[22]  Tamás Szirányi,et al.  Object Oriented Motion-Segmentation for Video-Compression in the CNN-UM , 1999, J. VLSI Signal Process..

[23]  Azriel Rosenfeld,et al.  Cooperating Processes for Low-Level Vision: A Survey , 1981, Artif. Intell..

[24]  Frank Müller,et al.  Image segmentation using motion estimation , 1997 .

[25]  Murat Kunt,et al.  Spatiotemporal Segmentation Based on Region Merging , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  P. Lions,et al.  Axioms and fundamental equations of image processing , 1993 .

[27]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[28]  Ioannis Pitas,et al.  Parallel Algorithms for Digital Image Processing, Computer Vision and Neural Networks , 1993 .

[29]  Ákos Zarándy,et al.  Implementation of binary and gray-scale mathematical morphology on the CNN universal machine , 1996 .

[30]  Larry S. Davis,et al.  What can projections of flow fields tell us about the visual motion , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[31]  Yun Q. Shi,et al.  Correlation-feedback technique in optical flow determination , 1998, IEEE Trans. Image Process..