Heterogeneous 3-D Perception across Visual Fragments Project Acronym: EYESHOTS Deliverable no: D2.1 Title of the deliverable: Convolutional network for vergence control.

Agostino Gibaldi, Nikolay Chumerin, Karl Pauwels, Fabio Solari, Marc M. Van Hulle, Fred H. Hamker2009

Abstract

Computational models for the control of horizontal vergence, based on a distributed representation of disparity, are proposed and analyzed. The models directly extract the linear servos from the post-processed response of a population of disparity tuned complex cells, without explicit calculation of the disparity map. The disparity-vergence curves have been either designed on the basis of a desired behavior, or learned by examples. Training and evaluation of the networks are discussed. The resulting vergence controls yield to stable fixation and has small response time to a wide range of disparities.
BibTeX
@misc{gibaldi2009heterogeneous,
  author = {Agostino Gibaldi and Nikolay Chumerin and Karl Pauwels and Fabio Solari and Marc M. Van Hulle and Fred H. Hamker},
  title = {{Heterogeneous 3-D Perception across Visual Fragments Project Acronym: EYESHOTS Deliverable no: D2.1 Title of the deliverable: Convolutional network for vergence control.}},
  year = {2009},
}

Loading related content...

Figure