Date of Award

7-2012

Embargo Period

10-11-2013

Degree Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Electrical and Computer Engineering

Advisor(s)

Takeo Kanade

Second Advisor

Daniel Huber

Third Advisor

Marios Savvides

Fourth Advisor

Robert T. Collins

Abstract

Models are useful for many computer vision tasks, such as object detection, recognition, and tracking. Computer vision tasks must handle situations where unknown objects appear and must detect and track some object which is not in the trained database. In such cases, the system must learn or, otherwise derive, descriptions of new objects.

In this dissertation, we investigate creating a representation of previously unknown objects that newly appear in the scene. The representation is to create a viewpoint-invariant and scalenormalized model approximately describing an unknown object. Those properties of the representation facilitate 3D tracking of the object using 2D-to-2D image matching. The representation has both benefits of an implicit model (referred to as a view-based model) and an explicit model (referred to as a shape-based model). The object representation is created using multi-modal sensors. We illustrate the benefits of the object representation with two applications: object detection and 3D tracking. We extend the object representation to an explicit model by imposing a shape prior and combining two existing approaches.

Share

COinS