The objective of this project is to detect and classify vehicles into two categories – 1) light vehicles, such as cars and other passenger vehicles and 2) heavy vehicles: trucks, busses, and other commercial vehicles, using video, sound, as well as joint video and sound classifications.
For the video portion, images from a video were analyzed. The physical size of a vehicle was extracted and stored. From this, the classification of different vehicles was made possible. In regards to the sound portion, the vehicles were recorded acoustically and their sound signature was analyzed. From these sound waves, it is desirable to extract not only the energy levels, wideband spectrogram, and converting it to the frequency domain, but to also represent it on a nonlinear mel scale of frequency. This has been frequently done for automatic speech recognition, but it is also feasible to extract the mel-frequency cepstral coefficients to use as features to aid the classification process of vehicles. Using this, one can train a machine learning algorithm - such as an artificial neural network - and have it label vehicles as one of the two classes.
Furthermore, the combination of both the video and the sound portion makes it possible to detect and classify vehicles more accurately than if using each system separately. This potentially allows for a more reliable system, especially when the image classification system by itself is not able to properly detect or classify vehicles, i.e. in heavy fog, or at night.
|Commitee:||Chassiakos, Anastasios, Yeh, Hen-Geul|
|School:||California State University, Long Beach|
|School Location:||United States -- California|
|Source:||MAI 56/06M(E), Masters Abstracts International|
|Keywords:||Classification, Detection, Machine learning, Neural network, Recognition, Vehicle|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be