- Title Information
- Title
- Compression of 2-d and 3-d Dynamic Scenes
- Name:
Personal
- Name Part
- Biris, Octavian
- Role
- Role Term:
Text
- creator
- Origin Information
- Copyright Date
- 2015
- Physical Description
- Extent
- xi, 115 p.
- digitalOrigin
- born digital
- Note
- Thesis (Ph.D. -- Brown University (2015)
- Name:
Personal
- Name Part
- Mundy, Joseph
- Role
- Role Term:
Text
- Director
- Name:
Personal
- Name Part
- Taubin, Gabriel
- Role
- Role Term:
Text
- Reader
- Name:
Personal
- Name Part
- Felzenzswalb, Pedro
- Role
- Role Term:
Text
- Reader
- Name:
Corporate
- Name Part
- Brown University. ENGINEERING: Electrical Sciences and Computer Engineering
- Role
- Role Term:
Text
- sponsor
- Genre (aat)
- theses
- Abstract
- This thesis is dedicated to exploring compression methods for large dynamic scenes. The first part
presents a case study of compressing aerial video using background modeling and JPEG2000. The
concepts used in the case study relate to state of the art compression frameworks and lay down the
foundation for the methods used to compress 4-d scenes in the second part. The algebra of random
variables and multiresolution analysis are used throughout this thesis as a means of compressing
large dynamic data. The second part of thesis presents a novel method to estimate dense scene
flow using volumetric and probabilistic 3-d models. The method first reconstructs 3-d models at
each time step using images synchronously captured from multiple views. Then, the 3-d motion
between two consecutive 3-d models is estimated using a formulation that is the analog of Horn and
Schunck’s optical flow method. This particular choice of 3-d model representation allows estimat-
ing highly dense scene flow results, tracking of surfaces undergoing topological change and reliably
recovering large motion displacements. The benefits of the method and the accuracy of 3-d flow
results are demonstrated on recent multi-view datasets. The second goal of this work is to compress
and reconstruct 3-d scenes at various time points using the estimated flow. A new method of scene
warping is proposed that involves partitioning the optical flow field in regions of coherent motion
which are subsequently parametrized by affine transformations. The compression objective of this
work is achieved by the low storage requirements of the affine parameters that describe the optical
flow field and the efficient reconstruction method through warping.
- Subject
- Topic
- Optical Flow
- Subject
- Topic
- 3-d
- Subject
- Topic
- JPEG2000
- Subject
- Topic
- Background Modeling
- Subject
- Topic
- Segmentation
- Subject (FAST)
(authorityURI="http://id.worldcat.org/fast", valueURI="http://id.worldcat.org/fast/1909702")
- Topic
- Image segmentation
- Record Information
- Record Content Source (marcorg)
- RPB
- Record Creation Date
(encoding="iso8601")
- 20150601
- Language
- Language Term:
Code (ISO639-2B)
- eng
- Language Term:
Text
- English
- Identifier:
DOI
- 10.7301/Z0T43RGD
- Access Condition:
rights statement
(href="http://rightsstatements.org/vocab/InC/1.0/")
- In Copyright
- Access Condition:
restriction on access
- Collection is open for research.
- Type of Resource (primo)
- dissertations