%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2012/12.17.14.01
%2 sid.inpe.br/sibgrapi/2012/12.17.14.01.37
%@isbn 978-85-7669-271-3
%T Obtaining surface curvature and depth information with a disparity-based photometric stereo
%D 1993
%A Torreão, José Ricardo de Almeida,
%A Pimentel, Cecílio José Lins,
%A Roe, Edward,
%@affiliation Departamento de Informática da Universidade Federal de Pernambuco (UFPE)
%@affiliation Departamento de Informática da Universidade Federal de Pernambuco (UFPE)
%@affiliation Departamento de Informática da Universidade Federal de Pernambuco (UFPE)
%E Figueiredo, Luiz Henrique de,
%E Gomes, Jonas de Miranda,
%B Simpósio Brasileiro de Computação Gráfica e Processamento de Imagens, 6 (SIBGRAPI)
%C Recife, PE, Brazil
%8 19-22 Oct. 1993
%I Sociedade Brasileira de Computação
%J Porto Alegre
%V 1
%P 239-246
%S Anais
%K Disparity-Based Photometric Stereo, computer vision, photometric images.
%X Disparity-Based Photometric Stereo (DBPS) is a recently introduced Computer Vision process which extracts a disparity field from two or more photometric stereo images by tracking the displacement of pixel intensities resulting from the change in the illumination of the observed scene. Such photometric-disparity field is akin to the disparity field due to the change of viewing position in Stereoscopy, and can be obtained through essentially the same stereo correspondence algorithms. In the present article, we relate the photometric-disparity field to the curvature of the imaged surfaces, and also show how it can be used for the inference of depth through a new version of the Dual Photometric Stereo process, which employs two cameras and multiple illuminations. We illustrate our approach with a neural net simulation of the stereo correspondence algorithms.
%9 Visão por Computador
%@language en
%3 28 Obtaining surface curvature.pdf