An Iterative Image Registration Technique with an Application to Stereo Vision
Abstract
Image registration finds a variety of applications in computer vision. Unfortunately, traditional image registration techniques tend to be costly. We present a new image registration technique that makes use of the spatial intensity gradient of the images to find a good match using a type of Newton-Raphson iteration. Our technique is faster because it examines far fewer potential matches between the images than existing techniques. Furthermore, this registration technique can be generalized to handle rotation, scaling and shearing. We show how our technique can be adapted for use in a stereo vision system. Note: A more complete version is available as Proceedings DARPA Image Understanding Workshop, April 1981, pp.121-130. When you refer to this work, please refer to the IJCAI paper.
A more complete version is available as Proceedings DARPA Image Understanding Workshop, April 1981, pp.121-130. When you refer to this work, please refer to the IJCAI paper.
BibTeX
@conference{Lucas-1981-15101,author = {Bruce D. Lucas and Takeo Kanade},
title = {An Iterative Image Registration Technique with an Application to Stereo Vision},
booktitle = {Proceedings of 7th International Joint Conference on Artificial Intelligence (IJCAI '81)},
year = {1981},
month = {August},
volume = {2},
pages = {674 - 679},
}