Local gist vision of man-made objects

Martins, J. C.; Rodrigues, J. M. F.; du Buf, J. M. H.

http://hdl.handle.net/10400.1/2104

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
RAW2011.pdf		558.46 KB	Adobe PDF	Download

Send Feedback

Authors

Martins, J. C.

Rodrigues, J. M. F.

du Buf, J. M. H.

Abstract(s)

Attention is usually modelled by sequential fixation of peaks in saliency maps. Those maps code local conspicuity: complexity, colour and texture. Such features have no relation to entire objects, unless also disparity and optical flow are considered, which often segregate entire objects from their background. Recently we developed a model of local gist vision: which types of objects are about where in a scene. This model addresses man-made objects which are dominated by a small shape repertoire: squares, rectangles, trapeziums, triangles, circles and ellipses. Only exploiting local colour contrast, the model can detect these shapes by a small hierarchy of cell layers devoted to low- and mid-level geometry. The model has been tested successfully on video sequences containing traffic signs and other scenes, and partial occlusions were not problematic.

Keywords

Visão humana

URI

http://hdl.handle.net/10400.1/2104

Citation

Martins, J.C.; Rodrigues, J.M.F.; du Buf, J.M.H. Local gist vision of man-made objects, Trabalho apresentado em IV Rovereto Attention Workshop, In Web Proc. IV Rovereto Attention Workshop, Rovereto, Italy, 27-29 Oct. [http://events.unitn.it/en/cimec-raw2011] , Rovereto, Italy, 2011