Traffic Scene Understanding using Sound-based Localization, SVM Classification and Clustering
Loading...
Authors
Rajagopal, Shreyas Kodasara
Issue Date
1-Dec-10
Type
Thesis
Language
en_US
Keywords
Alternative Title
Abstract
The thesis is about an embedded system application aimed at identifying the semantics of traffic based on acoustic data. Sound localization, classification and clustering are used for scene understanding. The report presents a set of experiments used to simulate different traffic scenarios. An alternative implementation for sound localization is also explored, where fixed point representation of rational numbers is used instead of floating point numbers. The results for both the implementations are compared in terms of execution speed and accuracy for a Programmable System-on-Chip (PSoC).
Description
43 pg.
Citation
Publisher
The Graduate School, Stony Brook University: Stony Brook, NY.