Safety

This paper describes a development of vision sensor that can detect shockwave propagation
that is one of main factors of accidents in highway traffic flow. In addition, realization of a
driver assistance system that informs arrival of such shockwave to drivers by the vision sen-
sors is shown. To evaluate the reliability of the system, both recall rate and false rate of the
system is investigated by sensing results of the sensors. As a result, it is shown that the detec-
tion of shockwaves and judgment of warning in the system should be decided in downstream
sensors to minimalize these rates.

Institute of Industrial Science the University of Tokyo

Presented at the ITS America Annual Conference and Exposition, November 16-20, 2008, New York, New York

This paper proposes a system of emergency notification based on a black box in a vehicular
environment. Currently, much research is concerned with safety provided by a driving
warning system and an automatic notification system, because many people are injured in and
die in car crashes. There are many studies about sensors and network equipped vehicles, since
they are important components to pre-recognize a car accident and reconstruct the car
accident situations. Research for vehicular black-box is becoming vital to store and process
the data that are from each vehicular sensor.
There are many kinds of emergency standards and services such as eCall and Automatic
Crash Notification (ACN) and others. In light of recent success of emergency standards, there
are several problems with emergency systems. Accordingly, we discuss the shortcomings of
each emergency system and standard that has already been developed in Europe and America.
Then we suggest the solution to the problems and test bed for the suggested solution in the
paper.

Hangyang University

Presented at the 15th World Congress on Intelligent Transport Systems, November 16-20, 2008, New York, New York

A frontal collision warning system (FCWS) for transit buses is introduced. The main purpose
of the transit FCWS is to help bus drivers avoid crashes. Given the fact that buses mostly run
in complex urban and suburban environments, it is a challenge for the system to keep high
sensitivity to frontal collision scenarios and give drivers timely true warnings while
suppressing the excessive nuisance and false warnings. The system architecture and the latest
developments of the warning algorithm are introduced. The verification test of the system is
discussed. The threat assessment in the warning algorithm is described. Categorization and
analyzes of scenarios and the statistic result are presented.

PATH program, Institute of Transportation Studies, University of California at Berkeley, USA

Department of Electronic Engineering, Tsinghua University, Beijing, China

Presented at the 12th World Congress on Intelligent Transport Systems, November 6-10, 2005, San Francisco, California

Monitoring activities in outdoor traffic scenes has applications in areas such as data collection, monitoring for traffic congestion, and surveillance for safety. In this project, we develop a camera based sensing system for monitoring activities at intersections. Two different components of the system are the vision module and the incident detection module, the former being responsible for providing information about the scene such as vehicle position, velocity, shape, etc. The incident detection module is responsible for detecting incidents such as collisions and near misses. The focus of this work is on the vision module, in particular vehicle tracking. Tracking in outdoor scenes using camera is aected by illumination changes, traffic congestion, clutter, and stop-and-go motion of the vehicles. In this paper, we show that we can attain decent tracking despite these conditions by using two different tracking modalities. The rst one is a region tracker which uses the results of the scene segmentation for tracking. The second tracker known as the Mean Shift Tracker, makes use of the color distribution of the vehicles. The results from the two trackers, namely, the vehicle's position
are combined sequentially in each step.
Keywords{ Motion segmentation, tracking, Mean Shift Tracking, data association.

University of Minnesota

Presented at the ITS America Annual Conference and Exposition, April 26 - 28, 2004 San Antonio, Texas

Traffic congestion in many national parks in the United States causes lengthy traffic delays and safety problems that substantially detract from the visitors’ experience at these parks. Recognizing that construction of more roadways and parking lots is not the solution; applications of Intelligent Transportation Systems (ITS) are becoming increasingly popular at several of the National Parks. ITS applications at these parks could help alleviate congestion problems and enhance visitors’ safety while protecting park resources. In order to facilitate application of ITS technologies at National Parks across the nation, an unprecedented joint venture between the US Department of Transportation and the US Department of the Interior has recently been formed. One of the first initiatives under this joint venture is a field operational test (FOT) of ITS applications at one of the most heavily visited National Parks in the nation. Several National Parks were evaluated for selection as the site for this FOT. High volume of visitors and increasing congestion, among other criteria, led to selection of Acadia National Park in Maine as the site for the test.

Science Applications International Corporation

United States Department of Transportation Federal Highway Administration

Presented at the 11th ITS Annual Conference and Exposition, June 4-7, 2001 Miami Beach, Florida