An iterative image registration technique with an application to stereo vision

DMCA

An iterative image registration technique with an application to stereo vision (1981)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Bruce D. Lucas , Takeo Kanade

Venue:	In IJCAI81
Citations:	2895 - 30 self

BibTeX

@INPROCEEDINGS{Lucas81aniterative,
    author = {Bruce D. Lucas and Takeo Kanade},
    title = {An iterative image registration technique with an application to stereo vision},
    booktitle = {In IJCAI81},
    year = {1981},
    pages = {674--679}
}

OpenURL

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 show our technique can be adapted for use in a stereo vision system. 2. The registration problem The translational image registration problem can be characterized as follows: We are given functions F(x) and G(x) which give the respective pixel values at each location x in two images, where x is a vector. We wish to find the disparity vector h which minimizes some measure of the difference between F(x + h) and G(x), for x in some region of interest R. (See figure 1). 1.

Keyphrases

iterative image registration technique new image registration technique image registration respective pixel value registration problem disparity vector good match stereo vision system translational image registration problem potential match traditional image registration technique newton-raphson iteration registration technique computer vision spatial intensity gradient

DMCA