Real-Time Accumulative Computation Motion Detectors

The neurally inspired accumulative computation (AC) method and its application to motion detection have been introduced in the past years. This paper revisits the fact that many researchers have explored the relationship between neural networks and finite state machines. Indeed, finite state machines constitute the best characterized computational model, whereas artificial neural networks have become a very successful tool for modeling and problem solving. The article shows how to reach real-time performance after using a model described as a finite state machine. This paper introduces two steps towards that direction: (a) A simplification of the general AC method is performed by formally transforming it into a finite state machine. (b) A hardware implementation in FPGA of such a designed AC module, as well as an 8-AC motion detector, providing promising performance results. We also offer two case studies of the use of AC motion detectors in surveillance applications, namely infrared-based people segmentation and color-based people tracking, respectively.

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

[2]  D J Heeger,et al.  Model for the extraction of image flow. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[3]  Antonio Fernández-Caballero,et al.  Dynamic visual attention model in image sequences , 2007, Image Vis. Comput..

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

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

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

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

[8]  C Koch,et al.  Analog "neuronal" networks in early vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

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

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

[11]  T.B. Lawton,et al.  Outputs of paired Gabor filters summed across the background frame of reference predict the direction of movement (vision) , 1989, IEEE Transactions on Biomedical Engineering.

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

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

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

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

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

[17]  Norberto M. Grzywacz,et al.  A computational theory for the perception of coherent visual motion , 1988, Nature.

[18]  Chunyan Wang,et al.  Space-variant motion detection for active visual target tracking , 2009, Robotics Auton. Syst..

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

[20]  Nicholas R. Howe.  Flow lookup and biological motion perception , 2005, IEEE International Conference on Image Processing 2005.

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

[22]  Joanne P. Duncan,et al.  Six-Degree-of-Freedom Sensor Fish Design and Instrumentation , 2007, Sensors.

[23]  Claude L. Fennema,et al.  Velocity determination in scenes containing several moving objects , 1979 .

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

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

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

[27]  Alaa Hamdy.  FPGA-Based Real-Time Video-Object Segmentation with Optimization Schemes , 2008 .

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

[29]  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.

[30]  Chi-Cheng Cheng,et al.  Motion Estimation Using the Single-row Superposition-type Planar Compound-like Eye , 2007, Sensors (Basel, Switzerland).

[31]  R. C. Emerson,et al.  Does image movement have a special nature for neurons in the cat's striate cortex? , 1981, Investigative ophthalmology & visual science.

[32]  W Reichardt,et al.  Functional structure of a mechanism of perception of optical movement , 1958 .

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

[34]  Nicolas H. Franceschini,et al.  Bio-inspired optic flow sensors based on FPGA: Application to Micro-Air-Vehicles , 2007, Microprocess. Microsystems.

[35]  José Mira Mira,et al.  Permanence Memory: A System for Real Time Motion Analysis in Image Sequences , 1992, MVA.

[36]  David J. Heeger,et al.  Model of visual motion sensing , 1994 .

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

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

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

[40]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[41]  Javier Díaz,et al.  FPGA-based real-time optical-flow system , 2006, IEEE Transactions on Circuits and Systems for Video Technology.

[42]  Shih-Chii Liu,et al.  Range estimation on a robot using neuromorphic motion sensors , 2005, Robotics Auton. Syst..

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

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

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

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

[47]  D Marr,et al.  Directional selectivity and its use in early visual processing , 1981, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[48]  H. Barlow,et al.  The mechanism of directionally selective units in rabbit's retina. , 1965, The Journal of physiology.

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

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

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

[52]  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.

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

[54]  Aurélio J. C. Campilho,et al.  Real-time implementation of an optical flow algorithm , 2002, Object recognition supported by user interaction for service robots.

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

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

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

[58]  Ellen C. Hildreth,et al.  Measurement of Visual Motion , 1984 .