Decoding MT Motion Response For Optical Flow Estimation : An Experimental Evaluation

Abstract : Motion processing in primates is an intensely studied problem in visual neurosciences and after more than two decades of research, representation of motion in terms of motion energies computed by V1-MT feedforward interactions remains a strong hypothesis. Thus, decoding the motion energies is of natural interest for developing biologically inspired computer vision algorithms for dense optical flow estimation. Here, we address this problem by evaluating four strategies for motion decoding: intersection of constraints, linear decoding through learned weights on MT responses, maximum likelihood and regression with neural network using multi scale-features. We characterize the performances and the current limitations of the different strategies, in terms of recovering dense flow estimation using Middlebury benchmark dataset widely used in computer vision, and we highlight key aspects for future developments .
Liste complète des métadonnées

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01215526
Contributor : Pierre Kornprobst <>
Submitted on : Monday, October 19, 2015 - 6:07:00 PM
Last modification on : Thursday, May 3, 2018 - 1:32:58 PM
Document(s) archivé(s) le : Thursday, April 27, 2017 - 4:25:14 AM

File

Chessa_EUSIPCO.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01215526, version 1

Relations

Citation

Manuela Chessa, N. V. Kartheek Medathati, Guillaume Masson, Fabio Solari, Pierre Kornprobst. Decoding MT Motion Response For Optical Flow Estimation : An Experimental Evaluation. 23rd European Signal Processing Conference (EUSIPCO), Aug 2015, Nice, France. ⟨hal-01215526⟩

Share

Metrics

Record views

248

Files downloads

125