Learning static object segmentation from motion segmentation
Name
70717310-MIT.pdf
Description
Full printable version
Size
19.82 MB
Format
Adobe PDF
Checksum (MD5)
2ea859d513601842b0946eb75a3740c7
Author(s)
Ross, Michael G. (Michael Gregory), 1975-
Advisor(s)
Keslie Pack Kaelbling.
Date Issued
2005
Publisher
Massachusetts Institute of Technology
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.
Description
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2005.
Includes bibliographical references (p. 105-110).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
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.
Persistent DSpace Link
