Real-time Estimation of Accident Likelihood for Safety Enhancement Jun Oh, Ph.D., PE, PTOE Western Michigan University March 14, 2007.

Slides:



Advertisements
Similar presentations
Analysis, Characterization and Visualization of Freeway Traffic Data in Los Angeles Alain L. Kornhauser Professor, Operations Research & Financial Engineering.
Advertisements

Effect of Electronically Enhanced Driver Behavior on Freeway Traffic Flow Alain L. Kornhauser Professor, Operations Research & Financial Engineering Director,
Scott Evans VP of Engineering Eberle Design Inc
Peng Cheng, Member, IEEE, Zhijun Qiu, and Bin Ran Presented By: Guru Prasanna Gopalakrishnan.
February 9, 2006TransNow Student Conference Using Ground Truth Geospatial Data to Validate Advanced Traveler Information Systems Freeway Travel Time Messages.
TRB Lianyu Chu *, K S Nesamani +, Hamed Benouar* Priority Based High Occupancy Vehicle Lanes Operation * California Center for Innovative Transportation.
Archived Data User Services (ADUS). ITS Produce Data The (sensor) data are used for to help take transportation management actions –Traffic control systems.
June 16, 2004 Dr. Robert Bertini Michael Rose Evaluation of the “COMET” Incident Response Program Oregon Department of Transportation.
1 Statistics of Freeway Traffic. 2 Overview The Freeway Performance Measurement System (PeMS) Computer Lab Visualization of Traffic Dynamics Visualization.
1 Adaptive Kalman Filter Based Freeway Travel time Estimation Lianyu Chu CCIT, University of California Berkeley Jun-Seok Oh Western Michigan University.
Evaluation of the Effectiveness of Potential ATMIS Strategies Using Microscopic Simulation Lianyu Chu, Henry X. Liu, Will Recker PATH ATMS UC.
Fuzzy Logic in Traffic Control State Trafic Departement Baden Württemberg realized by INFORM Software Corporation Martin Pozybill Martin Pozybill Bernhard.
Design Speed and Design Traffic Concepts
Month XX, 2004 Dr. Robert Bertini Using Archived Data to Measure Operational Benefits of ITS Investments: Ramp Meters Oregon Department of Transportation.
Incorporating Temporal Effect into Crash Safety Performance Functions Wen Cheng, Ph.D., P.E., PTOE Civil Engineering Department Cal Poly Pomona.
European Intelligent Transportation Systems Market B Published Feb
1 REAL-TIME IMAGE PROCESSING APPROACH TO MEASURE TRAFFIC QUEUE PARAMETERS. M. Fathy and M.Y. Siyal Conference 1995: Image Processing And Its Applications.
Advanced Lane Management Assist (ALMA) for Partially and Fully Automated Vehicles Robert L. Gordon, P.E. 1.
Signalized Intersection Delay Monitoring for Signal Retiming SafeTrip-21 Safe and Efficient Travel through Innovation and Partnership in the 21 st Century.
A Calibration Procedure for Microscopic Traffic Simulation Lianyu Chu, University of California, Irvine Henry Liu, Utah State University Jun-Seok Oh, Western.
Regional Traffic Monitoring System for Maryland’s Eastern Shore Dr. Gang-Len Chang Traffic Safety and Operations Lab University of Maryland, College Park.
CEE8207 Summer2013 L# Today’s Topic Technology and Sustainable system  Renewable Energy  ITS  Materials CEE8207 Summer2013 L#7 3.
Truths and Myths about Traffic Data Truths and Myths about Traffic Data ITSA Presentation June 2007 AirSage Proprietary & Confidential.
Aaron B Wilson, EIT WesTech Engineering, Inc., SLC, UT Mitsuru Saito, PhD, PE Brigham Young University, Provo, UT ITE Western District Annual Meeting Santa.
Oversaturated Freeway Flow Algorithm
USING PeMS DATA TO EMPIRICALLY DIAGNOSE FREEWAY BOTTLENECK LOCATIONS IN ORANGE COUNTY, CALIFORNIA Robert L. Bertini Portland State University Aaron M.
Technology and Society The DynamIT project Dynamic information services and anonymous travel time registration VIKING Workshop København Per J.
1 Development and Evaluation of Selected Mobility Applications for VII (a.k.a. IntelliDrive) Steven E. Shladover, Sc.D. California PATH Program Institute.
Investigation of Speed-Flow Relations and Estimation of Volume Delay Functions for Travel Demand Models in Virginia TRB Planning Applications Conference.
1 Modeling Active Traffic Management for the I-80 Integrated Corridor Mobility (ICM) Project Terry Klim, P.E. Kevin Fehon, P.E. DKS Associates D.
Incident Management in Central Arkansas: Current Settings and Proposed Extensions Weihua Xiao Yupo Chan University of Arkansas at Little Rock.
Estimating Traffic Flow Rate on Freeways from Probe Vehicle Data and Fundamental Diagram Khairul Anuar (PhD Candidate) Dr. Filmon Habtemichael Dr. Mecit.
The Science of Prediction Location Intelligence Conference April 4, 2006 How Next Generation Traffic Services Will Impact Business Dr. Oliver Downs, Chief.
Accuracy in Real-Time Estimation of Travel Times Galen McGill, Kristin Tufte, Josh Crain, Priya Chavan, Enas Fayed 15 th World Congress on Intelligent.
Arterial Lane Selection Model Moshe Ben-Akiva, Charisma Choudhury, Varun Ramanujam, Tomer Toledo ITS Program January 21, 2007.
NATMEC June 5, 2006 Comparative Analysis Of Various Travel Time Estimation Algorithms To Ground Truth Data Using Archived Data Christopher M. Monsere Research.
© Copyright 2011 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice. HP Confidential. Mahalia.
Prediction of Traffic Density for Congestion Analysis under Indian Traffic Conditions Proceedings of the 12th International IEEE Conference on Intelligent.
November 15, 2005 Dr. Robert Bertini Dr. Sue Ahn Using Archived Data to Measure Operational Benefits of a System-wide Adaptive Ramp Metering (SWARM) System.
Determination of Number of Probe Vehicles Required for Reliable Travel Time Measurement in Urban Network.
Chapter 5: Traffic Stream Characteristics
Traffic Safety and Operations Lab Dept. of Civil and Environmental Engineering University of Maryland, College Park Maryland State Highway Administration.
Highway accident severities and the mixed logit model: An exploratory analysis John Milton, Venky Shankar, Fred Mannering.
Forward-Scan Sonar Tomographic Reconstruction PHD Filter Multiple Target Tracking Bayesian Multiple Target Tracking in Forward Scan Sonar.
Robert L. Bertini Sirisha M. Kothuri Kristin A. Tufte Portland State University Soyoung Ahn Arizona State University 9th International IEEE Conference.
January 23, 2006Transportation Research Board 85 th Annual Meeting Using Ground Truth Geospatial Data to Validate Advanced Traveler Information Systems.
SP2 Progress Meeting – Data Fusion September 2007, Paris 1 Infrastructure Side Data Fusion Tobias Schendzielorz Technische Universität München.
An Algorithm for Event Detection based on a combination of Loop and Journey Time Data Pengjun Zheng, Mike McDonald and David Jeffery Transportation Research.
DEPARTMENT OF CIVIL & ENVIRONMENTAL ENGINEERING Proactive Optimal Variable Speed Limit Control for Recurrently Congested Freeway Bottlenecks by Xianfeng.
Modeling HOV lane choice behavior for microscopic simulation models and its application to evaluation of HOV lane operation strategies Jun-Seok Oh Western.
1 Techniques for Validating an Automatic Bottleneck Detection Tool Using Archived Freeway Sensor Data Jerzy Wieczorek, Rafael J. Fernández-Moctezuma, and.
Effect of Electronically Enhanced Driver Behavior on Freeway Traffic Flow Alain L. Kornhauser Professor, Operations Research & Financial Engineering Director,
The development of a HOV driver behavior model under Paramics Will Recker, UC Irvine Shin-Ting Jeng, UC Irvine Lianyu Chu, CCIT-UC Berkeley.
1 Using Archived ITS Data to Automatically Identify Freeway Bottlenecks in Portland, Oregon Robert L. Bertini, Rafael J. Fernández-Moctezuma, Jerzy Wieczorek,
Hcm 2010: BASIC CONCEPTS praveen edara, ph.d., p.e., PTOE
SAFESPOT Project SP2 WP3 1 Title S. Marco, S. Manfredi (CSST) SP1 Meeting PONTEDERA 1st March 2007 INFRASENS Functional Architecture.
Performance Evaluation of Adaptive Ramp Metering Algorithms in PARAMICS Simulation Lianyu Chu, Henry X. Liu, Will Recker California PATH, UC Irvine H.
Abstract Loop detector data for northbound Autobahn 9 (A9) from Munich to Nurnberg, Germany is analyzed using the cumulative curves methodology. The analysis.
Archived Data Management System in Kentucky Mei Chen, Ph.D. Dept of Civil Engineering University of Kentucky November 7, 2003.
Guidance Tool for Implementation of Traffic Incident Management Performance Measures (NCHRP 07-20) December 16, 2014 Brian Hoeft Freeway and Arterial System.
HCM 2010: FREEWAY FACILITIES PRAVEEN EDARA, PH.D., P.E., PTOE UNIVERSITY OF MISSOURI - COLUMBIA
1 Bottleneck Identification and Forecasting in Traveler Information Systems Robert L. Bertini, Rafael Fernández-Moctezuma, Huan Li, Jerzy Wieczorek, Portland.
By Srinivas S. Pulugurtha, Ph.D., P.E. Assistant Professor of Civil Engineering University of North Carolina, Charlotte Presentation at TRB ABJ60 Workshop.
SHRP2 C05: Understanding the Contributions of Operations, Technology, and Design to Meeting Highway Capacity Needs Freeway Data Freeway data has been collected.
Intelligent and Non-Intelligent Transportation Systems 32 Foundations of Technology Standard 18 Students will develop an understanding of and be able to.
1 Bidoura Khondaker MASc. (Transportation Engg), University of British Columbia, Vancouver. PhD candidate (Transportation Engg.), University of Calgary.
IMAGE PROCESSING APPLIED TO TRAFFIC QUEUE DETECTION ALGORITHM.
Macroscopic Speed Characteristics
Vehicle Segmentation and Tracking in the Presence of Occlusions
Problem 5: Network Simulation
Presentation transcript:

Real-time Estimation of Accident Likelihood for Safety Enhancement Jun Oh, Ph.D., PE, PTOE Western Michigan University March 14, 2007

Background / Motivation  Is it possible to predict occurrence of accidents? Maybe NOT. / Almost impossible  Are there certain traffic conditions that lead to more accidents? Maybe YES.  Then, is it possible to identify such traffic conditions? What will be possible indicators?

Contents  Previous Studies  Traffic Dynamics and Accident  Empirical Example  Accident Likelihood Estimation  Issues on Accident Study  Advanced Surveillance System

So far, previous studies...  Analyzed long term historical data  To identify relationships between traffic variables or geometric elements and accidents  off-line studies  Incident detection and incident traffic management  after-incident

Objectives  To enhance traffic safety under ITS  To identify traffic conditions leading to more accidents Real time Before accident  To estimate accident likelihood

Occurrence of Traffic Accidents Accident Traffic Dynamics Environment Vehicle Characteristics Driver Characteristics

Accident Indicator TIME Traffic Dynamics (Indicator) Normal traffic condition Disruptive traffic condition T T-x Implication starts Accident occurs

Empirical Example  Freeway traffic data I-880, California Volume, Occupancy, and Speed (double-loop) 10-second periods from upstream detector stations Accident profiles (52 accidents)  Traffic Variables Occupancy, Flow, and Speed 5 minute Mean and STD

Pattern Classification  Two traffic conditions Normal traffic condition: a 5-minute period apart from traffic accident (more than 30 minutes apart) Disruptive traffic condition: a 5-minute period right before an accident  Non-parametric density estimation kernel smoothing technique  Best indicator: STD of speed

Estimation PDF

Bayesian Model for Accident Likelihood P(A/X) = Posterior probability that given traffic measurement belongs to traffic conditions leading to an accident occurrence P(A) = Prior probability that given traffic measurement belongs to disruptive traffic condition P(N) = Prior probability that given traffic measurement belongs to normal traffic conditions

Estimation of Accident Likelihood

Real-time Application

Identification of Accidents * The percentage of time when P(A/X) was above the given threshold Threshold # accidents identified % accidents identified % time*

GIS Database for Enhanced System  Traffic Accident Data Mapping Linear Referencing & Dynamic Segmentation  Reconstruction of highway segments  Detector location and accident location  Other Characteristics Weather Highway Geometry  Real-time Traffic Data

Database Example Real-time Traffic Data Accident location and type

Possible Application Framework Real-time estimation of accident likelihood Provide safety information at upstream via VMS Real-time traffic measurement with highway geometry and weather Drive safely Caution! Traffic Unstable Is traffic condition stable? No Yes

Issues on Accident Study  Accident data availability and accuracy Need more data Accurate accident occurrence time Accident duration  Other measures? Wide-area detection Individual vehicle tracking  Need better surveillance systems

An Advanced Surveillance System  Present traffic surveillance systems mostly use inductive loop detectors (ILDs) have significant limitations (e.g. point estimates) and errors reduce the ability to effectively manage and control freeway and arterial traffic systems, and to implement ATMIS  Advanced sensor systems Integration of weather and surface sensors Individual vehicle detection for details Vehicle reidentification techniques utilizing existing and future infrastructure

Vehicle Reidentification Matching Inductive Vehicle Signatures Volume (veh/interval) Travel Time (sec) Downstream OfframpLane 1 HOV Lane 2 HOV Lane 3Lane 4Lane 5Lane 6 Up-stream Up-stream Lane 1 HOV-81 veh sec 18 veh sec 6 veh sec --- Lane 2--3 veh sec 203 veh sec 4 veh sec 5 veh sec - Lane veh sec 164 veh sec 16 veh sec - Lane veh sec 108 veh sec 2 veh sec Lane 527 veh sec ---4 veh sec 21 veh sec 69 veh sec Lane 610 veh sec veh sec 16 veh sec Lane veh sec 5 veh sec  Volume  Occupancy  Speed  Vehicle Types  Section Density  Section Delay  Travel Time  Level of service  Lane-by-lane travel time  Lane changing pattern

Concluding Comments  Speed variance can be a good surrogate Traffic dynamics reflects hazardous factors Temporal spatial speed variation  Advanced surveillance systems may provide better exposure Lane-by-lane travel time Lane-changing pattern  Possible to identify traffic conditions leading to more accidents (Accident Likelihood) Integration of traffic, weather, and geometry information

Thank you Q & A Jun Oh