2026-09-19T21:34:55Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/612902022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Richard W. Madison and Tomaso A. Poggio.
Xu, Yuetian
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2011-02-23T14:42:33Z
2011-02-23T14:42:33Z
2009
2009
http://hdl.handle.net/1721.1/61290
702644367
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. ).
Automatic understanding of video content is a problem which grows in importance every day. Video understanding algorithms require accuracy, robustness, speed, and scalability. Accuracy generates user confidence in usage. Robustness enables greater autonomy and reduced human intervention. Applications such as navigation and mapping demand real-time performance. Scalability is also important for maintaining high speed while expanding capacity to multiple users and sensors. In this thesis, I propose a "bag-of-phrases" model to improve the accuracy and robustness of the popular "bag-of-words" models. This model applies a "geometric grammar" to add structural constraints to the unordered "bag-of-words." I incorporate this model into an architecture which combines an object recognizer, a tracker, and a geolocation module. This architecture has the ability to use the complementarity of its components to compensate for its weaknesses. This allows for improvements in accuracy, robustness, and speed. Subsequently, I introduce VICTORIOUS, a fast implementation of the proposed architecture. Evaluation on computer-generated data as well as Caltech-101 indicate that this implementation is accurate, robust, and capable of performing in real time on current generation hardware. This implementation, together with the "bag-of-phrases" model and integrated architecture, forms a step towards meeting the requirements for an accurate, robust, real-time vision system.
by Yuetian Xu.
M.Eng.
p.
eng
Massachusetts Institute of Technology
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
Electrical Engineering and Computer Science.
VICTORIOUS : video indexing with combined tracking and object recognition for improved object understanding in scenes
Video indexing with combined tracking and object recognition for improved object understanding in scenes
Thesis
application/pdf
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="7281e5da-06a5-44cd-aa69-4e119850493d">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>VICTORIOUS : video indexing with combined tracking and object recognition for improved object understanding in scenes</Title>
<Subtitle>Video indexing with combined tracking and object recognition for improved object understanding in scenes</Subtitle>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2009</PublicationDate>
<Authors>
<Author>
<DisplayName>Xu, Yuetian</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Automatic understanding of video content is a problem which grows in importance every day. Video understanding algorithms require accuracy, robustness, speed, and scalability. Accuracy generates user confidence in usage. Robustness enables greater autonomy and reduced human intervention. Applications such as navigation and mapping demand real-time performance. Scalability is also important for maintaining high speed while expanding capacity to multiple users and sensors. In this thesis, I propose a "bag-of-phrases" model to improve the accuracy and robustness of the popular "bag-of-words" models. This model applies a "geometric grammar" to add structural constraints to the unordered "bag-of-words." I incorporate this model into an architecture which combines an object recognizer, a tracker, and a geolocation module. This architecture has the ability to use the complementarity of its components to compensate for its weaknesses. This allows for improvements in accuracy, robustness, and speed. Subsequently, I introduce VICTORIOUS, a fast implementation of the proposed architecture. Evaluation on computer-generated data as well as Caltech-101 indicate that this implementation is accurate, robust, and capable of performing in real time on current generation hardware. This implementation, together with the "bag-of-phrases" model and integrated architecture, forms a step towards meeting the requirements for an accurate, robust, real-time vision system.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>