Inappropriate traffic speeds are a major cause of traffic fatalities. Since driving is a task with a substantial contribution from vision, the use of lighting and visual information such as signage could assist in providing appropriate cues to encourage appropriate driving speeds. At locations such as sharp roadway curves, an overall reduction in driving speed might be desirable to prevent rollover crashes.
In this project, the feasibility of using mobile traffic sensors for binary vehicle classification (i.e., to distinguish passengers from trucks) on arterial roads is investigated. Here mobile sensors refer to those that move with the traffic flow they are monitoring such as global positioning system (GPS), smart phones, among others. Features of vehicle dynamics (e.g. speed related, acceleration/deceleration related, among others) are extracted from vehicle traces collected from real world arterial roads.
In this research, the feasibility of using mobile traffic sensors for binary vehicle classification on arterial roads is investigated. Features (e.g. speed related, acceleration/deceleration related, etc.) are extracted from vehicle traces (passenger cars, trucks) collected from real world arterial roads. Machine learning techniques such as support vector machines (SVM) are developed to distinguish passenger cars from trucks using these features.
Bus transportation has traditionally served as the backbone of public transportation. Despite the importance and
efficiency of buses, compared to the automobile, these vehicles are weighted equally with automobiles at traffic
signals where a bus carrying 50 passengers is treated the same as an auto with a single person. Delays caused
by traffic signals and by street traffic congestion increase bus operating costs and degrade transit service quality.
Delays caused by traffic signals and by street traffic congestion
increase bus-operating costs and degrade transit service quality.
Bus signal priority is an attempt to minimize or eliminate delays
to buses at a signalized intersection by temporarily altering the
traffic signal phase so that an approaching bus receives a green
phase when it arrives. The potential savings in bus travel times
can allow buses to maintain its schedule and provide better
reliability in travel times. Although signal priority has proven to
Traditional travel surveys provide essential information on travel patterns, but are time-consuming, expensive, and have seen declining rates of participation. Recently global positioning systems (GPS) technologies have been introduced to facilitate the data collection process. While GPS traces can provide accurate information on the location and time of travel, these traces do not contain explicit information on the mode used (e.g., walking, biking, transit or auto).
Traditional travel surveys provide essential information on travel patterns, but are time-consuming, expensive, and have seen declining rates of participation. Recently global positioning systems (GPS) technologies have been introduced to facilitate the data collection process. While GPS traces can provide accurate information on the location and time of travel, these traces do not contain explicit information on the mode used (e.g., walking, biking, transit or auto).
Finding an effective method for obtaining information on the travel patterns of household members is a critical need for transportation planners and researchers. This is particularly the case for Metropolitan Planning Organizations (MPOs), now being pressured to improve their travel demand forecasting capabilities. An emerging strategy for generating high-quality data is the use of Global Positioning Systems (GPS) trace data to collect travel patterns.
