Abstract : Depth perception starts with the binocular
interaction receptive fields of simple cells modeled by two Gabor
functions followed by a half-squaring function. Simple cells do not have
reliable disparity computation. Complex cells combine two simple cells
in quadrature. They are better adapted to encode disparity information.
The image disparity can be determined by fixing the receptive field in
one eye and varying it in the other. Pooling information of spatial
frequency and orientation is very important to improve the quality of
results of real world stereograms. In this work, a bio-inspired method
to calculate binocular disparity based on the energy model for depth
perception of real world images is described and implemented. The
performance of the proposed method is also evaluated in what concerns
the algorithm computational cost, root-mean-square error and percentage
of wrongly matched pixels.
https://hal.inria.fr/hal-01060758 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Friday, November 17, 2017 - 4:35:19 PM Last modification on : Wednesday, November 29, 2017 - 11:37:11 AM Long-term archiving on: : Sunday, February 18, 2018 - 4:57:10 PM
Fernanda C. E C. Faria, Jorge Batista, Helder Araújo. Bio-inspired Binocular Disparity with
Position-Shift Receptive Field. First IFIP WG 5.5/SOCOLNET Doctoral Conference on Computing, Electrical and Industrial Systems (DoCEIS), Feb 2010, Costa de Caparica, Portugal. pp.349-356, ⟨10.1007/978-3-642-11628-5_38⟩. ⟨hal-01060758⟩