2026-09-19T06:14:28Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/849052022-01-13T07:54:01Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
William T. Freeman.
Bouman, Katherine L. (Katherine Louise)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2014-02-10T17:01:24Z
2014-02-10T17:01:24Z
2013
http://hdl.handle.net/1721.1/84905
868903611
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 49-51).
We present a framework for predicting the physical properties of moving deformable objects observed in video. We apply our framework to analyze videos of fabrics moving under various unknown wind forces, and recover two key material properties of the fabric: stiffness and mass. We extend features previously developed to compactly represent static image textures to describe video textures such as fabric motion. A discriminatively trained regression model is then used to predict the physical properties of fabric from these features. The success of our model is demonstrated on a new database of fabric videos with corresponding measured ground truth material properties that we have collected. We show that our predictions are well correlated with both measured material properties and human perception of material properties. Our contributions include: (a) a method for predicting the material properties of fabric from a video, (b) a database that can be used for training and testing algorithms for predicting fabric properties containing RGB and RGBD videos of real videos with associated material properties and rendered videos of simulated fabric with associated model parameters, and (c) a perceptual study of humans' ability to estimate the material properties of fabric from videos and images.
by Katherine L. Bouman.
S.M.
51 pages
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.
Estimating the material properties of fabric through the observation of motion
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="a73e84f3-7e55-4b5e-9dee-79a1822040c0">
<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>Estimating the material properties of fabric through the observation of motion</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2013</PublicationDate>
<Authors>
<Author>
<DisplayName>Bouman, Katherine L. (Katherine Louise)</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>We present a framework for predicting the physical properties of moving deformable objects observed in video. We apply our framework to analyze videos of fabrics moving under various unknown wind forces, and recover two key material properties of the fabric: stiffness and mass. We extend features previously developed to compactly represent static image textures to describe video textures such as fabric motion. A discriminatively trained regression model is then used to predict the physical properties of fabric from these features. The success of our model is demonstrated on a new database of fabric videos with corresponding measured ground truth material properties that we have collected. We show that our predictions are well correlated with both measured material properties and human perception of material properties. Our contributions include: (a) a method for predicting the material properties of fabric from a video, (b) a database that can be used for training and testing algorithms for predicting fabric properties containing RGB and RGBD videos of real videos with associated material properties and rendered videos of simulated fabric with associated model parameters, and (c) a perceptual study of humans' ability to estimate the material properties of fabric from videos and images.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>