Real-time motion detection by lateral inhibition in accumulative computation

Many researchers have explored the relationship between recurrent neural networks and finite state machines. Finite state machines constitute the best characterized computational model, whereas artificial neural networks have become a very successful tool for modeling and problem solving. In the few last years, the neurally inspired lateral inhibition in accumulative computation (LIAC) method and its application to the motion detection task have been introduced. The article shows how to implement the tasks directly related to LIAC in motion detection by means of a formal model described as finite state machines. This paper introduces two steps towards that direction: (a) A simplification of the general LIAC method is performed by formally transforming it into a finite state machine. (b) A hardware implementation of such a designed LIAC module, as well as an 8x8 LIAC module, has been tested on several video sequences, providing promising performance results.

[1]  Antonio Fernández Caballero,et al.  Parametric improvement of lateral interaction in accumulative computation in motion-based segmentation , 2008 .

[2]  James L. McClelland,et al.  Finite State Automata and Simple Recurrent Networks , 1989, Neural Computation.

[3]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[4]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[5]  Abbes Amira,et al.  Accelerating colour space conversion on reconfigurable hardware , 2005, Image Vis. Comput..

[6]  Wael M. Badawy,et al.  A proposed hardware reference model for spatial transformation and quantization in H.264 , 2006, J. Vis. Commun. Image Represent..

[7]  Issam W. Damaj,et al.  Higher-Level Hardware Synthesis of the KASUMI Algorithm , 2006, Journal of Computer Science and Technology.

[8]  S C Kleene,et al.  Representation of Events in Nerve Nets and Finite Automata , 1951 .

[9]  Antonio Fernández-Caballero,et al.  Spatio-temporal shape building from image sequences using lateral interaction in accumulative computation , 2003, Pattern Recognit..

[10]  Mikel L. Forcada,et al.  Asynchronous translations with recurrent neural nets , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[11]  Antonio Fernández-Caballero,et al.  Parametric improvement of lateral interaction in accumulative computation in motion-based segmentation , 2008, Neurocomputing.

[12]  Giovanni Soda,et al.  Inductive inference from noisy examples using the hybrid finite state filter , 1998, IEEE Trans. Neural Networks.

[13]  Antonio Fernández Caballero,et al.  Knowledge modelling for the motion detection task , 2004 .

[14]  Antonio Fernández-Caballero,et al.  Motion features to enhance scene segmentation in active visual attention , 2006, Pattern Recognit. Lett..

[15]  Octavio Nieto-Taladriz,et al.  FPGA for pseudorandom generator cryptanalysis , 2006, Microprocess. Microsystems.

[16]  Antonio Fernández-Caballero,et al.  Lateral interaction in accumulative computation: a model for motion detection , 2003, Neurocomputing.

[17]  Antonio Fernández-Caballero,et al.  Knowledge modelling for the motion detection task: the algorithmic lateral inhibition method , 2004, Expert Syst. Appl..

[18]  C. Lee Giles,et al.  Constructing deterministic finite-state automata in recurrent neural networks , 1996, JACM.

[19]  Jude W. Shavlik,et al.  Combining Symbolic and Neural Learning , 1994, Machine Learning.

[20]  Mikel L. Forcada,et al.  Neural Networks: Automata and Formal Models of Computation , 2002 .

[21]  Antonio Fernández-Caballero,et al.  On motion detection through a multi-layer neural network architecture , 2003, Neural Networks.

[22]  Mikel L. Forcada,et al.  Finite-State Computation in Analog Neural Networks: Steps towards Biologically Plausible Models? , 2001, Emergent Neural Computational Architectures Based on Neuroscience.

[23]  Marco Lanuzza,et al.  A high-performance fully reconfigurable FPGA-based 2D convolution processor , 2005, Microprocess. Microsystems.

[24]  Marvin Minsky,et al.  Computation : finite and infinite machines , 2016 .

[25]  Rafael C. Carrasco,et al.  Efficient encoding of finite automata in discrete-time recurrent neural networks , 1999 .

[26]  C. Lee Giles,et al.  Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks , 1992, Neural Computation.

[27]  C. Lee Giles,et al.  The Neural Network Pushdown Automaton: Architecture, Dynamics and Training , 1997, Summer School on Neural Networks.

[28]  Antonio Fernández Caballero,et al.  Road-traffic monitoring by knowledge-driven static and dynamic image analysis. , 2008 .

[29]  Reza Sedaghat,et al.  FPGA-Based adaptive digital predistortion for radio-over-fiber links , 2006, Microprocess. Microsystems.

[30]  Antonio Fernández-Caballero,et al.  Modelling the Stereovision-Correspondence-Analysis task by Lateral Inhibition in Accumulative Computation problem-solving method , 2007, Expert Syst. Appl..

[31]  Antonio Fernández Caballero,et al.  Dynamic stereoscopic selective visual attention (dssva): integrating motion and shape with depth in video segmentation , 2008 .

[32]  Antonio Fernández-Caballero,et al.  Segmentation from motion of non-rigid objects by neuronal lateral interaction , 2001, Pattern Recognit. Lett..

[33]  Panagiotis Manolios,et al.  First-Order Recurrent Neural Networks and Deterministic Finite State Automata , 1994, Neural Computation.

[34]  Simon Y. Foo,et al.  Cellular automata PRNG: maximal performance and minimal space FPGA implementations , 2003 .

[35]  Daniel E. O'Leary,et al.  A probability of fuzzy events approach to validating expert systems in a multiple agent environment , 1994 .

[36]  Antonio Fernández-Caballero,et al.  Visual surveillance by dynamic visual attention method , 2006, Pattern Recognit..