A disparity energy model improved by line, edge and keypoint correspondences

Martins, J. C.; Farrajota, Miguel; Lam, Roberto; Rodrigues, J. M. F.; Terzic, Kasim; du Buf, J. M. H.

http://hdl.handle.net/10400.1/2108

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
ecvp2012a.pdf		3.65 MB	Adobe PDF	Download

Send Feedback

Authors

Abstract(s)

Disparity energy models (DEMs) estimate local depth information on the basis ofVl complex cells. Our recent DEM (Martins et al, 2011 ISSPlT261-266) employs a population code. Once the population's cells have been trained with randorn-dot stereograms, it is applied at all retinotopic positions in the visual field. Despite producing good results in textured regions, the model needs to be made more precise, especially at depth transitions.

Keywords

Visão humana Córtex

URI

http://hdl.handle.net/10400.1/2108

Citation

Martins, J.C.; Miguel Farrajota; Lam, R.; Rodrigues, J.M.F.; K. Tersic; du Buf, J.M.H. A disparity energy model improved by line, edge and keypoint correspondences, Trabalho apresentado em European Conf. on Visual Perception, In Proc European Conf. on Visual Perception, Alghero, Italy, 2-6 Sept., Perception Vol. 41 Suppl., Alghero, Italy, 2-6 Sept., 2012.