%0 Conference Proceedings
%A Silva, JosÚ Demisio Sim§es,
%A Simoni, Paulo Ouvera,
%A Bharadwaj, Kamal Kant,
%T Multiple correspondences in stereo vision under a genetic algorithm approach
%B Brazilian Symposium on Computer Graphics and Image Processing, 13 (SIBGRAPI)
%E Carvalho, Paulo Cezar Pinto,
%E Walter, Marcelo,
%J Los Alamitos
%I IEEE Computer Society
%C Gramado, RS, Brazil
%K stereo image processing, stereo vision multiple correspondences, genetic algorithm, multiple point hierarchical approach, computer vision, low-level processing, area-and-token hybrid method, search, experimental results.
%X This paper presents a multiple point hierarchical approach to the stereo correspondence problem in computer vision. The low-level processing employs an area-and-token hybrid method to obtain, for distinctive points in one image, a set of points in the other image that are candidates for correspondence. The refinement of the set of low-level correspondences obtained is performed by a high-level N-point simultaneous correspondence process, a new constraint introduced for this problem. The high-level processing uses a genetic algorithm approach for searching the solution space. Experimental results show the effectiveness of the method on real world scenes.
%O The conference was held in Gramado, RS, Brazil, from October 17 to 20.
%1 SBC - Brazilian Computer Society