Abstract
We use integral images of a three-dimensional (3D) scene to estimate the longitudinal depth of multiple objects present in the scene. With this information, we digitally reconstruct the objects in three dimensions and compute 3D correlations of input objects. We investigate the use of nonlinear techniques for 3D correlations. We present experimental results for 3D reconstruction and correlation of 3D objects. We demonstrate that it is possible to perform 3D segmentation of 3D objects in a scene. We finally present experiments to demonstrate that the 3D correlation is more discriminant than the two-dimensional correlation.
© 2002 Optical Society of America
Full Article | PDF ArticleMore Like This
Yann Frauel, Enrique Tajahuerce, Osamu Matoba, Albertina Castro, and Bahram Javidi
Appl. Opt. 43(2) 452-462 (2004)
Seung-Hyun Hong, Ju-Seog Jang, and Bahram Javidi
Opt. Express 12(3) 483-491 (2004)
Xin Shen, Adam Markman, and Bahram Javidi
Appl. Opt. 56(9) D151-D157 (2017)