Thesis (Ph. D.)--University of Washington, 2008. / Vita. Includes bibliographical references (leaves 117-127).

Thesis (M.S.)--University of Akron, Dept. of Civil Engineering, 2009. / "May, 2009." Title from electronic thesis title page (viewed 8/2/2009) Advisor, Ping Yi; Committee members, William H. Schneider IV, Anil Patnaik; Department Chair, Wieslaw K. Binienda; Dean of the College, George K. Haritos; Dean of the Graduate School, George R. Newkome. Includes bibliographical references.

Today transportation systems are facing big transitions all over the world. We created fly overs, roads under the ground, bridges over the river and ocean to get efficient access and to increase the road connectivity. Our transportation system is more intelligent than ever. Our traffic signaling system became adaptive. Our vehicles equipped with new gadgets and we developed new tools for more efficient analysis of traffic. Our research relies on existing traffic infrastructure to generate better understanding of traffic. More specifically, this research focused on traffic and UAV cameras to extract information about the traffic. Our first goal was to create an automatic system to count the cars using traffic cameras. To achieve this goal, we implemented Background Subtraction Method (BSM) and OverFeat Framework. BSM compares consecutive frames to detect the moving objects. Because BSM only works for ideal lab conditions, therefor we implemented a Convolutional Neural Network (CNN) based classification algorithm called OverFeat Framework. We created different segments on the road in various lanes to tabulate the number of passing cars. We achieved 96.55% accuracy for car counting irrespective of different visibility conditions of the day and night. Our second goal was to find out traffic density. We implemented two CNN based algorithms: Single Shot Detection (SSD) and MobileNet-SSD for vehicle detection. These algorithms are object detection algorithms. We used traffic cameras to detect vehicles on the roads. We utilized road markers and light pole distances to determine distances on the road. Using the distance and count information we calculated density. SSD is a more resource intense algorithm and it achieved 92.97% accuracy. MobileNet-SSD is a lighter algorithm and it achieved 79.30% accuracy. Finally, from a moving platform we estimated the velocity of multiple vehicles. There are a lot of roads where traffic cameras are not available, also traffic monitoring is necessary for special events. We implemented Faster R-CNN as a detection algorithm and Discriminative Correlation Filter (with Channel and Spatial Reliability Tracking) for tracking. We calculated the speed information from the tracking information in our study. Our framework achieved 96.80% speed accuracy compared to manual observation of speeds. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2019. / FAU Electronic Theses and Dissertations Collection

Thesis (Ph. D.)--University of California, Riverside, 2009. / Includes abstract. Title from first page of PDF file (viewed March 8, 2010). Includes bibliographical references. Issued in print and online. Available via ProQuest Digital Dissertations.

This thesis evaluates the performance of a vehicle detection technology, Automated License Plate Recognition (ALPR) camera systems, with regards to its ability to produce real-time travel time information in active work zones. A literature review was conducted to investigate the ALPR technology as well as to identify other research that has been conducted using ALPR systems to collect travel time information. Next, the ALPR technology was tested in a series of field deployments in both an arterial and a freeway environment. The goal of the arterial field deployment was to evaluate the optimal ALPR camera angles that produce the highest license plate detection rates and accuracy percentages. Next, a series of freeway deployments were conducted on corridors of I-285 in Atlanta, Georgia in order to evaluate the ALPR system in active work zone environments. During the series of I-285 freeway deployments, ALPR data was collected in conjunction with data from Bluetooth and radar technologies, as well as from high definition video cameras. The data collected during the I-285 deployments was analyzed to determine the ALPR vehicle detection rates. Additionally, a script was written to match the ALPR reads across two data collection stations to determine the ALPR travel times through the corridors. The ALPR travel time data was compared with the travel time data produced by the Bluetooth and video cameras with a particular focus on identifying travel time biases associated with each given technology. Finally, based on the knowledge gained, recommendations for larger-scale ALPR work zone deployments as well as suggestions for future research are provided.

M. Tech. (Information Technology, Faculty of Applied and Computer Sciences), Vaal University of Technology / Traffic congestion is a concern within the main arteries that link Johannesburg to Pretoria. In this study Matlab function Randperm is used to generate random vehicle speeds on a simulated highway. Randperm is used to mimic vehicle speed sensors capturing vehicle traffic on the highway. Java sockets are used to send vehicle speed to the Road Traffic Control Centre (RTCC)-database server through a wireless medium. The RTCC-database server uses MySQL to store vehicle speed data. The domain controller with active directory together with a certificate server is used to manage and provide security access control to network resources. The wireless link used by speed sensors to transmit vehicle speed data is protected using PEAP with EAP-TLS which employs the use of digital certificates during authentication. A java database connectivity driver is used to retrieve data from MySQL and a multilayer perceptron (MLP) model is used to predict future traffic status on the highway being monitored i.e. next 5 minutes from previous 5 minutes captured data. A dataset of 402 instances was divided as follows: 66 percent training data was used to train the MLP model, 15 percent data used during validation and the remaining 19 percent was used to test the trained MLP model. An excel spreadsheet was used to introduce novel (19 percent data not used during training) data to the trained MLP model to predict. Assuming that the spreadsheet data represent captured highway vehicle data for the last 5 minutes, the model showed 100 percent accuracy in predicting the four classes: congested, out congested, into congested and normal traffic flow. Predicted traffic status is displayed for the motorist on the highway to know. Ability of the proposed model to continuously capture the traffic pattern on the highway (monitor) helps in redirecting (controlling) the highway traffic during periods of congestion. Implementation of this project will definitely decrease traffic congestion across main arteries of Johannesburg. Pollution normally experienced when cars idle for a long time during congestion will be reduced by free highway traffic flow. Frequent servicing of motor vehicles will no longer be required by the motorists. Furthermore the economy of Gauteng and South Africa as a whole will benefit due to increase in production. Consumers will also benefit in obtaining competitive prices from organizations that depend on haulage services.

This thesis descries the evolution and testing of a fully portable, inductive loop vehicle counter system. As a component of the NFS Embedded Distributed Simulation for Transportation System Management project, the system's cellular modem transmits real-time data to servers at Georgia Institute of Technology. From there, the data can be fed into simulations predicting travel behavior. Researchers revised both the detector circuit, and the temporary, reusable loop pad several times over multiple rounds of field testing. The final tested version of this system demonstrates the efficacy of uncommonly small inductive loops. When paired with a reliable data transmission channel, the system was shown to capture nearly 96% of actual through traffic.

A 15.5-mile portion of the I-85 high-occupancy vehicle (HOV) lane in the metropolitan area of Atlanta, GA was converted to a high-occupancy toll (HOT) lane as part of a federal demonstration project designed to provide a reliable travel option through this congested corridor. Results from the I-85 demonstration project provided insight into the results that may follow the Georgia Department of Transportation's planned implementation of a $16 billion HOT lane network along metropolitan Atlanta's other major roadways [2]. To evaluate the impacts of the conversion, it was necessary to measure changes in corridor travel speed, reliability, vehicle throughput, passenger throughput, lane weaving, and user demographics. To measure such performance, a monitoring project, led by the Georgia Institute of Technology collected various forms of data through on-site field deployments, GDOT video, and cooperation from the State Road and Toll Authority (SRTA). Changes in the HOT lane's speed, reliability or other performance measure can affect the demographic and vehicle characteristics of those who utilize the corridor. The purpose of this particular study was to analyze the changes to the vehicle characteristics by comparing vehicle occupancy, vehicle classifications, and vehicle registration data to their counterparts from before the HOV-to-HOT conversion. As part of the monitoring project, the Georgia Tech research team organized a two-year deployment effort to collect data along the corridor during morning and afternoon peak hours. One year of data collection occurred before the conversion date to establish a control and a basis from which to compare any changes. The second year of data collection occurred after the conversion to track those changes and observe the progress of the lane's performance. While on-site, researchers collected data elements including visually-observed vehicle occupancy, license plate numbers, and vehicle classification [25]. The research team obtained vehicle records by submitting the license plate tag entries to a registration database [26]. In previous work, vehicle occupancy data were collected independently of license plate records used to establish the commuter shed. For the analyses reported in this thesis, license plate data and occupancy data were collected concurrently, providing a link between occupancy records of specific vehicles and relevant demographic characteristics based upon census data. The vehicle records also provided characteristics of the users' vehicles (light-duty vehicle vs. sport utility vehicle, model year, etc.) that the researchers aggregated to identify general trends in fleet characteristics. The analysis reported in this thesis focuses on identifying changes in vehicle characteristics that resulted from the HOV-to-HOT conversion. The data collected from post-conversion are compared to pre-conversion data, revealing changes in vehicle characteristics and occupancy distributions that most likely resulted from the implementation of the HOT lane. Plausible reasons affecting the vehicle characteristics alterations will be identified and further demographic research will enhance the data currently available to better pinpoint the cause and effect relationship between implementation and the current status of the I-85 corridor. Preliminary data collection outliers were identified by using vehicle occupancy data. However, future analysis will reveal the degree of their impact on the project as a whole. Matched occupancy and license plate data revealed vehicle characteristics for HOT lane users as well as indications that the tested data collectors are predominantly synchronized when concurrently collecting data, resulting in an argument to uphold the validity of the data collection methods. Chapter two provides reasons for why HOT lanes were sought out to replace I-85's HOV lanes. Chapter two will also provide many details regarding how the HOT lanes function and it will describe the role the Georgia Institute of Technology played in the assessment the HOV-to-HOT conversion. Chapter three includes the methodologies used to complete this document while chapter four provides results and analysis for the one year period before the conversion and the one year period after the conversion.