A model for transition-based visuospatial pattern recognition
Author(s)
Correa, Telmo Luis, Jr
DownloadFull printable version (5.342Mb)
Other Contributors
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Advisor
Patrick H. Winston.
Terms of use
Metadata
Show full item recordAbstract
In my research, I designed and implemented a system for learning and recognizing visual actions based on state transitions. I recorded three training videos of each of 16 actions (approach, bounce, carry, catch, collide, drop, fly over, follow, give, hit, jump, pick, push, put, take, throw), each lasting 10 seconds and 300 frames. After using a prototype system developed by Dr. Satyajit Rao for focus and actor recognition, actions are represented as qualitative state transitions, tied together to form tens of thousands of patterns, which are then available as action classifiers. The resulting system was able to build simple, intuitive classifiers that fit the training data perfectly.
Description
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011. Cataloged from PDF version of thesis. Includes bibliographical references (p. 87).
Date issued
2011Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.