Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.
Author ORCID Identifier
AccessType
Open Access Dissertation
Document Type
dissertation
Degree Name
Doctor of Philosophy (PhD)
Degree Program
Computer Science
Year Degree Awarded
2020
Month Degree Awarded
February
First Advisor
Erik Learned-Miller
Subject Categories
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces
Abstract
The ability to recognize motion is one of the most important functions of our visual system. Motion allows us both to recognize objects and to get a better understanding of the 3D world in which we are moving. Because of its importance, motion is used to answer a wide variety of fundamental questions in computer vision such as: (1) Which objects are moving independently in the world? (2) Which objects are close and which objects are far away? (3) How is the camera moving?
My work addresses the problem of moving object segmentation in unconstrained videos. I developed a probabilistic approach to segment independently moving objects in a video sequence, connecting aspects of camera motion estimation, relative depth and flow statistics. My work consists of three major parts:
- Modeling motion using a simple (rigid) motion model strictly following the principles of perspective projection and segmenting the video into its different motion components by assigning each pixel to its most likely motion model in a Bayesian fashion.
- Combining piecewise rigid motions to more complex, deformable and articulated objects, guided by learned semantic object segmentations.
- Learning highly variable motion patterns using a neural network trained on synthetic (unlimited) training data. Training data is automatically generated strictly following the principles of perspective projection. In this way well-known geometric constraints are precisely characterized during training to learn the principles of motion segmentation rather than identifying well-known structures that are likely to move.
This work shows that a careful analysis of the motion field not only leads to a consistent segmentation of moving objects in a video sequence, but also helps us understand the scene geometry of the world we are moving in.
DOI
https://doi.org/10.7275/w9vx-9171
Recommended Citation
Bideau, Pia Katalin, "Motion Segmentation - Segmentation of Independently Moving Objects in Video" (2020). Doctoral Dissertations. 1812.
https://doi.org/10.7275/w9vx-9171
https://scholarworks.umass.edu/dissertations_2/1812
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons