Vehicle Engine Classification Using of Laser Vibrometry Feature Extraction

<p>Used as a non-invasive and remote sensor, the laser Doppler vibrometer (LDV) has been used in many different applications, such as inspection of aircrafts, bridge and structure and remote voice acquisition. However, using LDV as a vehicle surveillance device has not been feasible due to the lack of systematic investigations on its behavioral properties. In this thesis, the LDV data from different vehicles are examined and features are extracted. A tone-pitch indexing (TPI) scheme is developed to classify different vehicles by exploiting the engine’s periodic vibrations that are transferred throughout the vehicle’s body. Using the TPI with a two-layer feed-forward 20 intermediate-nodes neural network to classify vehicles’ engine, the results are encouraging as they can consistently achieve accuracies over 96%. However, the TPI required a length of 1.25 seconds of vibration, which is a drawback of the TPI, as vehicles generally are moving whence the 1.25 second signals are unavailable. Based on the success of TPI, a new normalized tone-pitch indexing (nTPI) scheme is further developed, using the engine’s periodic vibrations, and shortened the time period from 1.25 seconds to a reasonable 0.2 seconds. Keywords: LDV, Machine Learning, Neural network, Deep learning, Vehicle classification</p>

Name thesis:degree_name

Master of Science (M.S.)

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Year dc:date.available

2016

Author dc:creator

• Liu, Chi Him

Contributors dc:contributor

• Jie Wei
• Akira Kawaguchi

• LDV
• Machine learning
• Vehicle classification
• Computer Sciences

Repository record dc:identifier

https://academicworks.cuny.edu/cc_etds_theses/643

OAI identifier oai:identifier

oai:academicworks.cuny.edu:cc_etds_theses-1639