Adaptive Motion Pooling and Diffusion for Optical Flow Computation

We propose to extend a state of the art bio-inspired model for optic flow computation through adaptive processing by focusing on the role of local context indicative of the local velocity estimates reliability. We set a network structure representative of cortical areas V1, V2 and MT, and incorporate three functional principles observed in primate visual system: contrast adaptation, adaptive afferent pooling and MT diffusion that are adaptive dependent upon the 2D image structure (Adaptive Motion Pooling and Diffusion, AMPD). We assess the AMPD performance on Middlebury optical flow estimation dataset, showing that the proposed AMPD model performs better than the baseline one and its overall performance is comparable with many computer vision methods.

[1]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

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

[3]  D C Van Essen,et al.  Functional properties of neurons in middle temporal visual area of the macaque monkey. I. Selectivity for stimulus direction, speed, and orientation. , 1983, Journal of neurophysiology.

[4]  E. Adelson,et al.  The analysis of moving visual patterns , 1985 .

[5]  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.

[6]  S. Grossberg,et al.  Neural dynamics of form perception: boundary completion, illusory figures, and neon color spreading. , 1985, Psychological review.

[7]  H. Wilson,et al.  A psychophysically motivated model for two-dimensional motion perception , 1992, Visual Neuroscience.

[8]  D. V. Essen,et al.  Neural mechanisms of form and motion processing in the primate visual system , 1994, Neuron.

[9]  Peter Kovesi,et al.  Image Features from Phase Congruency , 1995 .

[10]  E. Adelson,et al.  Slow and Smooth: A Bayesian theory for the combination of local motion signals in human vision , 1998 .

[11]  Peter E. Latham,et al.  Statistically Efficient Estimation Using Population Coding , 1998, Neural Computation.

[12]  Eero P. Simoncelli,et al.  A model of neuronal responses in visual area MT , 1998, Vision Research.

[13]  R. Shapley,et al.  Contrast's effect on spatial summation by macaque V1 neurons , 1999, Nature Neuroscience.

[14]  R. Zemel,et al.  Information processing with population codes , 2000, Nature Reviews Neuroscience.

[15]  E H Adelson,et al.  Adventures with Gelatinous Ellipses—Constraints on Models of Human Motion Analysis , 2000, Perception.

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

[17]  Nicholas J. Priebe,et al.  The Neural Representation of Speed in Macaque Area MT/V5 , 2003, The Journal of Neuroscience.

[18]  L. Paninski.  Maximum likelihood estimation of cascade point-process neural encoding models , 2004, Network.

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

[20]  David J. Heeger,et al.  Optical flow using spatiotemporal filters , 2004, International Journal of Computer Vision.

[21]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.

[22]  D. Bradley,et al.  Structure and function of visual area MT. , 2005, Annual review of neuroscience.

[23]  J. Weickert,et al.  Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods , 2005 .

[24]  Kenneth D. Miller,et al.  Adaptive filtering enhances information transmission in visual cortex , 2006, Nature.

[25]  Eero P. Simoncelli,et al.  How MT cells analyze the motion of visual patterns , 2006, Nature Neuroscience.

[26]  T. Albright,et al.  Adaptive Surround Modulation in Cortical Area MT , 2007, Neuron.

[27]  Heiko Neumann,et al.  A Fast Biologically Inspired Algorithm for Recurrent Motion Estimation , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Richard Szeliski,et al.  A Database and Evaluation Methodology for Optical Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[29]  D. Bradley,et al.  Velocity computation in the primate visual system , 2008, Nature Reviews Neuroscience.

[30]  Guy A Orban,et al.  Higher order visual processing in macaque extrastriate cortex. , 2008, Physiological reviews.

[31]  Guillaume S. Masson,et al.  Dynamics of Visual Motion Processing , 2010 .

[32]  Heiko Neumann,et al.  A model of neural mechanisms in monocular transparent motion perception , 2010, Journal of Physiology-Paris.

[33]  P. Kornprobst,et al.  Modelling the dynamics of motion integration with a new luminance-gated diffusion mechanism , 2010, Vision Research.

[34]  Heiko Neumann,et al.  Interactions of motion and form in visual cortex – A neural model , 2008, Journal of Physiology-Paris.

[35]  Ramón López-Cózar,et al.  Predicting user mental states in spoken dialogue systems , 2011, EURASIP J. Adv. Signal Process..

[36]  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..

[37]  Kamiar Rahnama Rad,et al.  Information Rates and Optimal Decoding in Large Neural Populations , 2011, NIPS.

[38]  Shin'ya Nishida,et al.  Advancement of motion psychophysics: review 2001-2010. , 2011, Journal of vision.

[39]  Michael J. Black,et al.  A Naturalistic Open Source Movie for Optical Flow Evaluation , 2012, ECCV.

[40]  Smith-Kettlewell,et al.  BIOLOGICAL IMAGE MOTION PROCESSING : A REVIEW , 2012 .

[41]  Eero P. Simoncelli,et al.  A functional and perceptual signature of the second visual area in primates , 2013, Nature Neuroscience.

[42]  Guillaume S. Masson,et al.  Dynamics of Visual Motion Processing: Neuronal, Behavioral, and Computational Approaches , 2014 .

[43]  Manuela Chessa,et al.  What can we expect from a classical V1-MT feedforward architecture for optical flow estimation? , 2014 .

[44]  Wei Ji Ma,et al.  Neural coding of uncertainty and probability. , 2014, Annual review of neuroscience.

[45]  Agustín Salgado de la Nuez,et al.  Preserving accurate motion contours with reliable parameter selection , 2014, ICIP.

[46]  Adrienne Fairhall,et al.  The receptive field is dead. Long live the receptive field? , 2014, Current Opinion in Neurobiology.

[47]  Manuela Chessa,et al.  What can we expect from a V1-MT feedforward architecture for optical flow estimation? , 2015, Signal Process. Image Commun..

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

[49]  Michael J. Black,et al.  Optical Flow Estimation Using a Spatial Pyramid Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).