2026-09-18T21:23:45Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/344702022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

Keslie Pack Kaelbling. Ross, Michael G. (Michael Gregory), 1975- Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2006-11-07T12:24:54Z 2006-11-07T12:24:54Z 2005 2005 http://hdl.handle.net/1721.1/34470 70717310 Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2005. Includes bibliographical references (p. 105-110). This thesis describes the SANE (Segmentation According to Natural Examples) algorithm for learning to segment objects in static images from video data. SANE uses background subtraction to find the segmentation of moving objects in videos. This provides object segmentation information for each video frame. The collection of frames and segmentations forms a training set that SANE uses to learn the image and shape properties that correspond to the observed motion boundaries. Then, when presented with new static images, the model infers segmentations similar to the observed motion segmentations. SANE is a general method for learning environment-specific segmentation models. Because it is self-supervised, it can adapt to a new environment and new objects with relative ease. Comparisons of its output to a leading image segmentation algorithm demonstrate that motion-defined object segmentation is a distinct problem from traditional image segmentation. The model outperforms a trained local boundary detector because it leverages the shape information it learned from the training data. by Michael Gregory Ross. Ph.D. 110 p. 20783141 bytes 20782946 bytes application/pdf application/pdf 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. Learning static object segmentation from motion segmentation Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="6dc337b8-5a5a-4d73-8c5c-8c899924ea6c"> <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>Learning static object segmentation from motion segmentation</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2005</PublicationDate> <Authors> <Author> <DisplayName>Ross, Michael G. (Michael Gregory), 1975-</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>This thesis describes the SANE (Segmentation According to Natural Examples) algorithm for learning to segment objects in static images from video data. SANE uses background subtraction to find the segmentation of moving objects in videos. This provides object segmentation information for each video frame. The collection of frames and segmentations forms a training set that SANE uses to learn the image and shape properties that correspond to the observed motion boundaries. Then, when presented with new static images, the model infers segmentations similar to the observed motion segmentations. SANE is a general method for learning environment-specific segmentation models. Because it is self-supervised, it can adapt to a new environment and new objects with relative ease. Comparisons of its output to a leading image segmentation algorithm demonstrate that motion-defined object segmentation is a distinct problem from traditional image segmentation. The model outperforms a trained local boundary detector because it leverages the shape information it learned from the training data.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>