Algorithmic Lateral Inhibition Formal Model for Real-Time Motion Detection

Recently, the use of the algorithmic lateral inhibition (ALI) method in motion detection has shown to be very effective. The promising results in terms of the goodness of the silhouettes detected and tracked along video sequences lead us to accept the challenge of searching for a real-time implementation of the algorithms. This paper introduces two steps towards that direction: (a) A simplification of the general ALI method is performed by formally transforming it into a finite state machine. (b) A hardware implementation of such a designed ALI module, as well as an 8×8 ALI module, has been tested on several video sequences, providing promising performance results.

[1]  Stefan Wermter,et al.  Emergent Neural Computational Architectures Based on Neuroscience , 2001, Lecture Notes in Computer Science.

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

[3]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[18]  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.