Accelerating bioinspired lateral interaction in accumulative computation for real-time moving object detection with graphics processing units

Biologically-inspired computer vision is a research area that offers prominent directions in a large variety of fields. Several processing algorithms inspired in natural vision enable detecting moving objects from video sequences so far. One example is lateral interaction in accumulative computation (LIAC), a classical bioinspired method that has been applied to numerous environments and applications. LIAC is the implementation for computer vision of two biologically-inspired methods denominated algorithmic lateral interaction and accumulative computation. The method has traditionally reached high precision but unfortunately requires high computing times. This paper introduces a proposal based on graphics processing units in order to speed up the original sequential code. This way not only excellent performance in terms of accuracy is maintained, but also real-time is obtained. A speed-up of 67× from the parallel over its sequential counterpart is achieved for several tested video sequences.

[1]  Antonio Fernández-Caballero,et al.  A historical perspective of algorithmic lateral inhibition and accumulative computation in computer vision , 2011, Neurocomputing.

[2]  Robert de Simone,et al.  Explicit routing schemes for implementation of cellular automata on processor arrays , 2013, Natural Computing.

[3]  José Mira Mira,et al.  What Can We Compute with Lateral Inhibition Circuits? , 2001, IWANN.

[4]  Jie Cheng,et al.  Programming Massively Parallel Processors. A Hands-on Approach , 2010, Scalable Comput. Pract. Exp..

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

[6]  Heiko Neumann,et al.  Disambiguating Visual Motion Through Contextual Feedback Modulation , 2004, Neural Computation.

[7]  Antonio Fernández Caballero,et al.  Real-time motion detection by lateral inhibition in accumulative computation. , 2010 .

[8]  Thomas L. Dean,et al.  Neural Networks and Neuroscience-Inspired Computer Vision , 2014, Current Biology.

[9]  Mario J. Pérez-Jiménez,et al.  Parallel simulation of Population Dynamics P systems: updates and roadmap , 2016, Natural Computing.

[10]  Lin Ma,et al.  A Neuro-inspired Adaptive Motion Detector , 2013 .

[11]  Pierre Kornprobst,et al.  Neural Mechanisms of Motion Detection, Integration, and Segregation: From Biology to Artificial Image Processing Systems , 2011, EURASIP J. Adv. Signal Process..

[12]  M. Ibañes,et al.  Lateral inhibition and neurogenesis: novel aspects in motion. , 2013, International Journal of Developmental Biology.

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

[14]  F. R. Waugh,et al.  Connection Topology and Dynamics in Lateral Inhibition Networks , 1990, NIPS.

[15]  David C. O'Carroll,et al.  Contrast sensitivity and the detection of moving patterns and features , 2014, Philosophical Transactions of the Royal Society B: Biological Sciences.

[16]  Roberto Moreno-Díaz,et al.  A Neurocybernetic Model of Modal Co‐operative Decisions in the Kilmer‐McCulloch Space , 1989 .

[17]  Andrzej Skowron,et al.  Interactive computations: toward risk management in interactive intelligent systems , 2013, Natural Computing.

[18]  Sankar K. Pal,et al.  Neighborhood granules and rough rule-base in tracking , 2016, Natural Computing.

[19]  Senén Barro,et al.  Local Accumulation of Persistent Activity at Synaptic Level: Application to Motion Analysis , 1995, IWANN.

[20]  Maria Pachalska.  A neurocybernetic model of image processing , 1991 .

[21]  Antonio Fernández-Caballero,et al.  A Model of Neural Inspiration for Local Accumulative Computation , 2003, EUROCAST.

[22]  G. Francis.  Cortical dynamics of lateral inhibition: Visual persistence and ISI , 1996, Perception & psychophysics.

[23]  Nikolaus Kriegeskorte,et al.  Deep neural networks: a new framework for modelling biological vision and brain information processing , 2015, bioRxiv.

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

[25]  C. W. G Clifford,et al.  Fundamental mechanisms of visual motion detection: models, cells and functions , 2002, Progress in Neurobiology.

[26]  Arpan Kumar Kar,et al.  Bio inspired computing - A review of algorithms and scope of applications , 2016, Expert Syst. Appl..

[27]  Pierre Kornprobst,et al.  Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision , 2016, Comput. Vis. Image Underst..

[28]  Antonio Fernández-Caballero,et al.  Real-Time Accumulative Computation Motion Detectors , 2009, Sensors.

[29]  Satya Gautam Vadlamudi,et al.  Anytime pack search , 2015, Natural Computing.

[30]  Shimon Ullman,et al.  Atoms of recognition in human and computer vision , 2016, Proceedings of the National Academy of Sciences.