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

• Author(s): Martins, J. C. ; Farrajota, Miguel ; Lam, Roberto Célio Lau ; Rodrigues, J. M. F. ; Tersic, K. ; du Buf, J. M. H.
• Date: 2012
• Persistent ID: http://hdl.handle.net/10400.1/2108
• Origin: Sapientia - Universidade do Algarve
• Subject(s): Visão humana; Córtex
• Document Type: Conference Object
• Language: English

Description

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.