Object-oriented image analysis using the CNN universal machine: new analogic CNN algorithms for motion compensation, image synthesis, and consistency observation

Image-analysis algorithms are of great interest in the context of object-oriented coding schemes. With reference to the utilization of the cellular neural network (CNN) universal machine for object-oriented image analysis, this paper presents new analogic CNN algorithms for obtaining motion compensation, image synthesis, and consistency observation. Along with the already developed segmentation and object labeling technique, the proposed method represents a framework for implementing CNN-based real-time image analysis. Simulation results, carried out for different video sequences, confirm the validity of the approach developed herein.

[1]  Ákos Zarándy.  ACE Box: High-performance Visual Computer based on the ACE4k Analogic Array Processor Chip , 2001 .

[2]  Norbert Diehl,et al.  Object-oriented motion estimation and segmentation in image sequences , 1991, Signal Process. Image Commun..

[3]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[4]  Jörn Ostermann,et al.  Object-based analysis-synthesis coding based on the source model of moving rigid 3D objects , 1994, Signal Process. Image Commun..

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

[6]  A. Rodriguez-Vazquez,et al.  Realization of non-linear templates using the CNNUC3 prototype , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[7]  Ángel Rodríguez-Vázquez,et al.  MOST-Based Design and Scaling of Synaptic Interconnections in VLSI Analog Array Processing CNN Chips , 1999, J. VLSI Signal Process..

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

[9]  Ákos Zarándy,et al.  Implementation of large-neighbourhood non-linear templates on the CNN universal machine , 1998, Int. J. Circuit Theory Appl..

[10]  S. Espejo,et al.  A CNN universal chip in CMOS technology , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[11]  Gustavo Liñán Cembrano,et al.  Implementation of non-linear templates using a decomposition technique by a 0.5 /spl mu/m CMOS CNN universal chip , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[12]  M. Hotter,et al.  Optimization and efficiency of an object-oriented analysis-synthesis coder , 1994 .

[13]  Ángel Rodríguez-Vázquez,et al.  ACE16k: A Programmable Focal Plane Vision Processor with 128 x 128 Resolution , 2001 .

[14]  Leon O. Chua,et al.  On object-oriented video coding using the CNN Universal Machine , 1996 .

[15]  Tamás Roska.  Computer-Sensors: Spatial-Temporal Computers for Analog Array Signals, Dynamically Integrated with Sensors , 1999, J. VLSI Signal Process..

[16]  M. Kunt,et al.  Second-generation image-coding techniques , 1985, Proceedings of the IEEE.

[17]  Peter Pirsch,et al.  VLSI architectures for video compression-a survey , 1995, Proc. IEEE.

[18]  G. Linan,et al.  The CNNUC3: an analog I/O 64x64 CNN universal machine chip prototype with 7-bit analog accuracy , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[19]  Leon O. Chua,et al.  Object‐oriented image analysis for very‐low‐bitrate video‐coding systems using the CNN universal machine , 1997 .