A dynamic key frames approach to object tracking
Author(s)
Wilkens, Christopher A
DownloadFull printable version (594.0Kb)
Other Contributors
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Advisor
David Demirdjian.
Terms of use
Metadata
Show full item recordAbstract
In this thesis, I present a dynamic key frames algorithm for state estimation from observations. The algorithm uses KL-divergence as a metric to identify the frames that contribute the most information to estimation of the system's current state. The algorithm is first presented in a numerical optimization framework and then developed as an extension to the Condensation algorithm. Finally, I present results from a Matlab simulation of the algorithm.
Description
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Includes bibliographical references (p. 95-96).
Date issued
2008Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.