Lucas-Kanade 20 Years On: A Unifying Framework: Part 3

Simon Baker, Ralph Gross, and Iain Matthews
tech. report CMU-RI-TR-03-35, Robotics Institute, Carnegie Mellon University, November, 2003


Download
  • Adobe portable document format (pdf) (580KB)
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.

Abstract
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 variety of extensions have been made to the original formulation. We present an overview of image alignment, describing most of the algorithms 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 cannot. In this paper, Part 3 in a series of papers, we cover the extension of image alignment to allow linear appearance variation. We first consider linear appearance variation when the error function is the Euclidean L2 norm. We describe three different algorithms, the simultaneous, project out, and normalization inverse compositional algorithms, and empirically compare them. Afterwards we consider the combination of linear appearance variation with the robust error functions described in Part 2 of this series. We first derive robust versions of the simultaneous and normalization algorithms. Since both of these algorithms are very inefficient, as in Part 2 we derive efficient approximations based on spatial coherence. We end with an empirical evaluation of the robust algorithms.

Keywords
Image alignment, unifying framework, the Lucas-Kanade algorithm, the inverse compositional algorithm, linear

Notes
Sponsor: U.S. Department of Defense
Grant ID: N41756-03-C4024
Associated Center(s) / Consortia: Vision and Autonomous Systems Center
Associated Lab(s) / Group(s): Vision for Safe Driving, People Image Analysis Consortium, Face Group
Associated Project(s): AAM Fitting Algorithms, Lucas-Kanade 20 Years On, Face Model Building and Fitting, Face and Facial Feature Tracking, AAMs with Occlusion

Text Reference
Simon Baker, Ralph Gross, and Iain Matthews, "Lucas-Kanade 20 Years On: A Unifying Framework: Part 3," tech. report CMU-RI-TR-03-35, Robotics Institute, Carnegie Mellon University, November, 2003

BibTeX Reference
@techreport{Baker_2003_4530,
   author = "Simon Baker and Ralph Gross and Iain Matthews",
   title = "Lucas-Kanade 20 Years On: A Unifying Framework: Part 3",
   booktitle = "",
   institution = "Robotics Institute",
   month = "November",
   year = "2003",
   number= "CMU-RI-TR-03-35",
   address= "Pittsburgh, PA",
}