Tracking dynamic regions of texture and shape

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2007.

Bibliographic Details
Main Author: Migdal, Joshua N. (Joshua Nicholas), 1979-
Other Authors: W. Eric L. Grimson and John W. Fisher, III.
Format: Thesis
Language:eng
Published: Massachusetts Institute of Technology 2008
Subjects:
Online Access:http://hdl.handle.net/1721.1/42239
_version_ 1826211463244546048
author Migdal, Joshua N. (Joshua Nicholas), 1979-
author2 W. Eric L. Grimson and John W. Fisher, III.
author_facet W. Eric L. Grimson and John W. Fisher, III.
Migdal, Joshua N. (Joshua Nicholas), 1979-
author_sort Migdal, Joshua N. (Joshua Nicholas), 1979-
collection MIT
description Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2007.
first_indexed 2024-09-23T15:06:16Z
format Thesis
id mit-1721.1/42239
institution Massachusetts Institute of Technology
language eng
last_indexed 2024-09-23T15:06:16Z
publishDate 2008
publisher Massachusetts Institute of Technology
record_format dspace
spelling mit-1721.1/422392019-04-10T15:34:08Z Tracking dynamic regions of texture and shape Migdal, Joshua N. (Joshua Nicholas), 1979- W. Eric L. Grimson and John W. Fisher, III. Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2007. Includes bibliographical references (p. 137-142). The tracking of visual phenomena is a problem of fundamental importance in computer vision. Tracks are used in many contexts, including object recognition, classification, camera calibration, and scene understanding. However, the use of such data is limited by the types of objects we are able to track and the environments in which we can track them. Objects whose shape or appearance can change in complex ways are difficult to track as it is difficult to represent or predict the appearance of such objects. Furthermore, other elements of the scene may interact with the tracked object, changing its appearance, or hiding part or all of it from view. In this thesis, we address the problem of tracking deformable, dynamically textured regions under challenging conditions involving visual clutter, distractions, and multiple and prolonged occlusion. We introduce a model of appearance capable of compactly representing regions undergoing nonuniform, nonrepeating changes to both its textured appearance and shape. We describe methods of maintaining such a model and show how it enables efficient and effective occlusion reasoning. By treating the visual appearance as a dynamically changing textured region, we show how such a model enables the tracking of groups of people. By tracking groups of people instead of each individual independently, we are able to track in environments where it would otherwise be difficult, or impossible. We demonstrate the utility of the model by tracking many regions under diverse conditions, including indoor and outdoor scenes, near-field and far-field camera positions, through occlusion and through complex interactions with other visual elements, and by tracking such varied phenomena as meteorological data, seismic imagery, and groups of people. by Joshua Migdal. Ph.D. 2008-09-03T15:02:33Z 2008-09-03T15:02:33Z 2007 2007 Thesis http://hdl.handle.net/1721.1/42239 231626922 eng M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582 142 p. application/pdf Massachusetts Institute of Technology
spellingShingle Electrical Engineering and Computer Science.
Migdal, Joshua N. (Joshua Nicholas), 1979-
Tracking dynamic regions of texture and shape
title Tracking dynamic regions of texture and shape
title_full Tracking dynamic regions of texture and shape
title_fullStr Tracking dynamic regions of texture and shape
title_full_unstemmed Tracking dynamic regions of texture and shape
title_short Tracking dynamic regions of texture and shape
title_sort tracking dynamic regions of texture and shape
topic Electrical Engineering and Computer Science.
url http://hdl.handle.net/1721.1/42239
work_keys_str_mv AT migdaljoshuanjoshuanicholas1979 trackingdynamicregionsoftextureandshape