DocumentCode :
3283825
Title :
Registration of images with small overlap
Author :
Pires, Bernardo Esteves ; Aguiar, Pedro M Q
Author_Institution :
Institute for Syst. & Robotics, Lisboa, Portugal
fYear :
2004
fDate :
29 Sept.-1 Oct. 2004
Firstpage :
255
Lastpage :
258
Abstract :
We address the problem of building a mosaic from uncalibrated images. The key issue in this problem is the registration of the images, i.e., the estimation of the parameters describing the global motion of the brightness pattern between them. Current approaches to global motion estimation avoid preprocessing steps, e.g., feature detection and matching, by inferring the motion parameters directly from the image intensities, through the minimization of the sum of the square error over a fixed window. This window is usually chosen as a large rectangle within the region where it is expected that the original images overlap. Although this leads to good results when the images to register have a large overlap, it often fails when the images exhibit only a small overlap, due to the requirement of choosing a priori a very small window. To overcome this limitation, we propose in this paper an adaptive window.
Keywords :
feature extraction; image matching; image motion analysis; image registration; parameter estimation; feature detection; global motion estimation; image matching; image registration; parameter estimation; small overlap; Brightness; Computer vision; Image registration; Motion detection; Motion estimation; Parameter estimation; Pixel; Robots; Video compression; Virtual reality;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia Signal Processing, 2004 IEEE 6th Workshop on
Print_ISBN :
0-7803-8578-0
Type :
conf
DOI :
10.1109/MMSP.2004.1436541
Filename :
1436541
Link To Document :
بازگشت