publication . Report . 2014

Que peut-on attendre d'une architecture feedforward classique de V1-MT pour estimer le flot optique?

Solari, Fabio; Chessa, Manuela; Medathati, Kartheek; Kornprobst, Pierre;
Open Access English
  • Published: 01 Oct 2014
  • Publisher: HAL CCSD
Abstract
Motion estimation has been studied extensively in neurosciences in the last two decades. The general consensus that has evolved from the studies in the primate vision is that it is done in a two stage process involving cortical areas V1 and MT in the brain. Spatio temporal filters are leading contenders in terms of models that capture the characteristics exhibited in these areas. Even though there are many models in the biological vision literature covering the optical flow estimation problem based on the spatio-temporal filters little is known in terms of their performance on the modern day computer vision datasets such as Middlebury. In this paper, we start fr...
Subjects
free text keywords: spatio-temporal filters, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], benchmarking, cortical areas V1 and MT, [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], Optical flow, Middlebury dataset, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], motion energy
Funded by
EC| MATHEMACS
Project
MATHEMACS
MATHEmatics of Multi-level Anticipatory Complex Systems
  • Funder: European Commission (EC)
  • Project Code: 318723
  • Funding stream: FP7 | SP1 | ICT
Communities
FET FP7FET Proactive: Dynamics of Multi-Level Complex Systems (DyM-CS)
FET FP7FET Proactive: MATHEmatics of Multi-level Anticipatory Complex Systems
42 references, page 1 of 3

[1] S. Baker, D. Scharstein, J. P. Lewis, S. Roth, M. J. Black, R. Szeliski, A database and evaluation methodology for optical flow, International Journal of Computer Vision 92 (1) (2011) 1-31. [OpenAIRE]

[2] J. A. Perrone, A. Thiele, Speed skills: measuring the visual speed analyzing properties of primate MT neurons, Nature Neuroscience 4 (5) (2001) 526-532.

[3] C. C. Pack, R. T. Born, Temporal dynamics of a neural solution to the aperture problem in visual area MT of macaque brain, Nature 409 (2001) 1040-1042.

[4] P. Bayerl, H. Neumann, Disambiguating visual motion through contextual feedback modulation, Neural Computation 16 (10) (2004) 2041-2066.

[5] N. C. Rust, V. Mante, E. P. Simoncelli, J. A. Movshon, How MT cells analyze the motion of visual patterns, Nature Neuroscience 9 (11) (2006) 1421-1431.

[6] P. Bayerl, H. Neumann, A fast biologically inspired algorithm for recurrent motion estimation, Pattern Analysis and Machine Intelligence, IEEE Transactions on 29 (2) (2007) 246-260. doi:10.1109/TPAMI.2007.24.

[7] E. Tlapale, G. S. Masson, P. Kornprobst, Modelling the dynamics of motion integration with a new luminance-gated diffusion mechanism, Vision Research 50 (17) (2010) 1676- 1692. doi:10.1016/j.visres.2010.05.022. URL http://dx.doi.org/10.1016/j.visres.2010.05.022 [OpenAIRE]

[8] U. Ilg, G. Masson, Dynamics of Visual Motion Processing: Neuronal, Behavioral, and Computational Approaches, SpringerLink: Springer e-Books, Springer Verlag, 2010.

[9] J. Bouecke, E. Tlapale, P. Kornprobst, H. Neumann, Neural mechanisms of motion detection, integration, and segregation: From biology to artificial image processing systems, EURASIP Journal on Advances in Signal Processing 2011, special issue on Biologically inspired signal processing: Analysis, algorithms, and applications. doi:10.1155/2011/ 781561. URL http://www.hindawi.com/journals/asp/2011/781561.html

[10] D. Heeger, Optical flow using spatiotemporal filters, The International Journal of Computer Vision 1 (4) (1988) 279-302.

[11] S. Nowlan, T. Sejnowski, Filter selection model for motion segmentation and velocity integration, J. Opt. Soc. Am. A 11 (12) (1994) 3177-3199.

[12] E. Simoncelli, D. Heeger, A model of neuronal responses in visual area MT, Vision Research 38 (1998) 743-761. [OpenAIRE]

[13] L. C. Sincich, J. C. Horton, The circuitry of v1 and v2: Integration of color, form, and motion, Annual Review of Neuroscience 28 (1) (2005) 303-326, pMID: 16022598. doi: 10.1146/annurev.neuro.28.061604.135731. URL http://dx.doi.org/10.1146/annurev.neuro.28.061604.135731

[14] M. J. Rasch, M. Chen, S. Wu, H. D. Lu, A. W. Roe, Quantitative inference of population response properties across eccentricity from motion-induced maps in macaque v1, Journal of Neurophysiology 109 (5) (2013) 1233-1249. doi:10.1152/jn.00673.2012. [OpenAIRE]

[15] N. Rust, V. Mante, E. Simoncelli, J. Movshon, How MT cells analyze the motion of visual patterns, Nature Neuroscience 9 (2006) 1421-1431.

42 references, page 1 of 3
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue
publication . Report . 2014

Que peut-on attendre d'une architecture feedforward classique de V1-MT pour estimer le flot optique?

Solari, Fabio; Chessa, Manuela; Medathati, Kartheek; Kornprobst, Pierre;