Variable remapping of images from very different sources

TitleVariable remapping of images from very different sources
Publication TypeConference Papers
Year of Publication2011
AuthorsZhang W, Guo Y, Meth R, Sokoloff H, Pope A, Strat T, Chellappa R
Conference Name2011 18th IEEE International Conference on Image Processing (ICIP)
Date Published2011/09/11/14
ISBN Number978-1-4577-1304-0
Keywordsautomatic object identification, Buildings, CAMERAS, Conferences, constrained motion estimation, coordinates system, Estimation, G-RANSAC framework, image context enlargement, Image Enhancement, image registration, image sequence registration, Image sequences, Motion estimation, Robustness, temporal integration, variable image remapping

We present a system which registers image sequences acquired by very different sources, so that multiple views could be transformed to the same coordinates system. This enables the functionality of automatic object identification and confirmation across views and platforms. The capability of the system comes from three ingredients: 1) image context enlargement through temporal integration; 2) robust motion estimation using the G-RANSAC framework with a relaxed correspondence criteria; 3) constrained motion estimation within the G-RANSAC framework. The proposed system has worked successfully on thousands of frames from multiple collections with significant variations in scale and resolution.