Date of Award

Spring 2011

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computational Modeling & Simulation Engineering

Program/Concentration

Modeling and Simulation

Committee Director

Mecit Cetin

Committee Member

Jiang Li

Committee Member

Roland R. Mielke

Call Number for Print

Special Collections LD4331.E58 R37 2011

Abstract

Vehicle re-identification is the process by which vehicle attributes measured at one point on a road network are compared to vehicle attributes measured at another point in an effort to match vehicles without using any unique identifiers such as license plate numbers. A match is made if the two measurements are estimated to belong to the same vehicle. Vehicle attributes can be sensor readings such as loop induction signatures, or they can also be actual vehicle characteristics such as length, weight, number of axles, etc. This research makes use of vehicle length, travel time, axle spacing and axle weights for re-identification . The data to support this research comes from weigh-in-motion (WIM) sites in Oregon that collect axle spacing and weight data for all trucks that are passing through the WIM sites. In this thesis, neural networks are trained to recognize whether pairs of attributes be long to the same vehicle or not. Since some of the trucks are already equipped with transponders having unique identification numbers, the true matches are known for a subset of trucks. Numerous neural network mode ls are trained and evaluated to determine the best neural network parameters, i.e. the number of hidden layer neurons, learning rate and momentum. Furthermore, an optimization process called Simulated Annealing (SA) is used to find out the optimal settings (if any) for these neural network parameters. The experiments conducted in this thesis show that the use of neural networks can be effective in solving the vehicle re-identification problem. A comparison with an already established technique (Bayesian model for vehicle re-identification) shows that the neural network models have a comparable accuracy (5% to I 0% less accurate than the Bayesian mode l).

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/36q7-zc14

Download

Share

COinS