Type
Text
Type
Thesis
Advisor
Doboli, Alex
Date
2013-12-01
Keywords
Computer engineering | Auditory Classification, Machine Learning, Scene understanding, Support Vector Machine, Vehicle sounds
Department
Department of Computer Engineering.
Language
en_US
Source
This work is sponsored by the Stony Brook University Graduate School in compliance with the requirements for completion of degree.
Identifier
http://hdl.handle.net/11401/77227
Publisher
The Graduate School, Stony Brook University: Stony Brook, NY.
Format
application/pdf
Abstract
There have been numerous studies on the classification of auditory signals. In contrast,there have been very few studies in the implementation and classification of vehicles using purely auditory signals. This thesis presents an implementation of auditory vehicle identification using support vector machines. It explores how granular classification can be, from what type of vehicle to what action the vehicle is preforming. The granularity of the classification will greatly aid in auditory scene understanding. The classifications are done with computational complexity in mind, so embedded systems can utilize the findings. A simple averaging algorithm will also be explored that aids in classification significantly. | 44 pages
Recommended Citation
Kaghaz-Garan, Scott Bejan, "Auditory Classification of Vehicles for Scene Understanding" (2013). Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions). 3055.
https://commons.library.stonybrook.edu/stony-brook-theses-and-dissertations-collection/3055