Georgia Institute of Technology
Encoding 3D contextual information for dynamic scene understanding
Abstract
dc:description.abstractThis thesis aims to demonstrate how using 3D cues improves semantic labeling and object classification. Specifically, we will consider depth, surface normals, object classification, and pixel-wise semantic labeling in this work. The works outlined in this document aim to validate the following thesis statement: Shape, used as an additional context, improves segmentation, unsupervised clustering, object classification and semantic labeling with little computational overhead. The thesis will show that: Combining shape and object labels improves results while (1) requiring few extra parameters, (2) provides better results using surface normals than depth, and (3) combining shape with labels improves accuracy for each task.} We describe various methods to combine shape and object classification and then discuss our extensions of the work which focus on surface normal prediction, depth prediction, and semantic labeling specifically.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Interactive Computing
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Hickson, Steven D.
- Advisor dc:contributor.advisor
-
- Essa, Irfan
- Committee members dc:contributor.committeemember
-
- Dellaert, Frank
- Hoffman, Judy
- Kira, Zsolt
- Sukthankar, Rahul
Subjects
dc:subject × 15Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1853/62869