Home/Lucas-Kanade 20 Years On: A Unifying Framework: Part 2

Lucas-Kanade 20 Years On: A Unifying Framework: Part 2

Simon Baker, Ralph Gross, Iain Matthews and Takahiro Ishikawa
Tech. Report, CMU-RI-TR-03-01, Robotics Institute, Carnegie Mellon University, February, 2003

View Publication

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.


Since the Lucas-Kanade algorithm was proposed in 1981, image alignment has become one of the most widely used techniques in computer vision. Applications range from optical flow, tracking and layered motion, to mosaic construction, medical image registration, and face coding. Numerous algorithms have been proposed and a wide variety of extensions have been made to the original formulation. We present an overview of image alignment, describing most of the algorithms and their extensions in a consistent framework. We concentrate on the inverse compositional algorithm, an efficient algorithm that we recently proposed. We examine which of the extensions to the Lucas-Kanade algorithm can be used with the inverse compositional algorithm without any significant loss of efficiency, and which require extra computation. In this paper, Part 2 in a series of papers, we cover the choice of the error function. We first consider weighted L2 norms. Afterwards we consider robust error functions.

author = {Simon Baker and Ralph Gross and Iain Matthews and Takahiro Ishikawa},
title = {Lucas-Kanade 20 Years On: A Unifying Framework: Part 2},
year = {2003},
month = {February},
institution = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-03-01},
keywords = {Image alignment, Lucas-Kanade, a unifying framework,the inverse compositional algorithm, weighted L2 norms, robust errorfunctions.},
} 2017-09-13T10:44:46-04:00