Author ORCID Identifier

https://orcid.org/0000-0001-5874-238X

Date Available

12-3-2018

Year of Publication

2018

Document Type

Doctoral Dissertation

Degree Name

Doctor of Philosophy (PhD)

College

Engineering

Department/School/Program

Computer Science

Advisor

Dr. Nathan Jacobs

Abstract

The ultimate goal of image understanding is to transfer visual images into numerical or symbolic descriptions of the scene that are helpful for decision making. Knowing when, where, and in which direction a picture was taken, the task of geo-calibration makes it possible to use imagery to understand the world and how it changes in time. Current models for geo-calibration are mostly deterministic, which in many cases fails to model the inherent uncertainties when the image content is ambiguous. Furthermore, without a proper modeling of the uncertainty, subsequent processing can yield overly confident predictions. To address these limitations, we propose a probabilistic model for camera geo-calibration using deep neural networks. While our primary contribution is geo-calibration, we also show that learning to geo-calibrate a camera allows us to implicitly learn to understand the content of the scene.

Digital Object Identifier (DOI)

https://doi.org/10.13023/etd.2018.458

Funding Information

NSF CAREER grant IIS-1553116

ARPA-E Award DE-AR0000594

Google Faculty Research Award

AWS Research Education grant

Intelligence Advanced Research Projects Activity (IARPA) via Air Force Research Laboratory, contract FA8650-12-C-7212

DARPA (contract CSSG D11AP00255)

Share

COinS