Thesis (Ph.D )--Tufts University, 2000. / Adviser: Robert J. K. Jacob. Submitted to the Dept. of Computer Science. Includes bibliographical references (leaves 297-316). Access restricted to members of the Tufts University community. Also available via the World Wide Web;

Thesis (DDes) - Faculty of Design, Swinburne University of Technology, 2007. / [Submitted in total fulfillment of the requirements of the degree] Doctorate in Design, Swinburne University of Technology - 2007. Typescript. Includes bibliographical references (p. 63-74).

Thesis (M.S. in Computer Science)--Naval Postgraduate School, September 1992. / Thesis Advisors: Rowe, Neil C. ; Wu, C. Thomas. "September 1992." Description based on title screen as viewed on April 16, 2009. Includes bibliographical references (p. 46-47). Also available in print.

Thesis (Ph. D.)--University of Canterbury, 2007. / Typescript (photocopy). Includes bibliographical references (p. 211-229). Also available via the World Wide Web.

Thesis (m.s.)--University of Kentucky, 2005. / Title from document title page (viewed Jan. 5, 2005). Document formatted into pages; contains xiii, 103p. : ill. Includes abstract and vita. Includes bibliographical references (p. 97-102).

Thesis (Master of Computer Science) Naval Postgraduate School, March 1996. / "March 1996." Thesis advisor(s): Cynthia E. Irvine, Michael J. Zyda. BIbliography: p. 125-127. Also available online.

Thesis (M.S.C.I.T.)--Regis University, Denver, Colo., 2006. / Title from PDF title page (viewed on Jan. 31, 2007). Includes bibliographical references.

Thesis (Ph. D.)--Oklahoma State University, 1997. / Includes bibliographical references (leaves 114-123).

Thesis (M. Sc.)--University of Canterbury, 2006. / Typescript (photocopy). Includes bibliographical references (leaves 108-110). Also available via the World Wide Web.

Objects can exhibit different dynamics at different scales, a property that isoftenexploited by visual tracking algorithms. A local dynamicmodel is typically used to extract image features that are then used as inputsto a system for tracking the entire object using a global dynamic model.Approximate local dynamicsmay be brittle---point trackers drift due to image noise and adaptivebackground models adapt to foreground objects that becomestationary---but constraints from the global model can make them more robust.We propose a probabilistic framework for incorporating globaldynamics knowledge into the local feature extraction processes.A global tracking algorithm can beformulated as a generative model and used to predict feature values thatinfluence the observation process of thefeature extractor. We combine such models in a multichain graphicalmodel framework.We show the utility of our framework for improving feature tracking and thusshapeand motion estimates in a batch factorization algorithm.We also propose an approximate filtering algorithm appropriate for onlineapplications, and demonstrate its application to problems such as backgroundsubtraction, structure from motion and articulated body tracking.