Development of online scalable approach for identifying secondary crashes

Hong Yang, Kaan Ozbay, Ender Faruk Morgul, Bekir Bartin, Kun Xie

Research output: Contribution to journalArticle

Abstract

Secondary crashes are some of the most critical incidents occurring on highways. Such crashes can induce extra traffic delays and affect highway safety performance. Transportation agencies are interested in understanding the mechanism of the occurrence of secondary crashes and implementing appropriate counter measures. However, no well- established procedure identifies secondary crashes; this deficiency in turn impedes the possibility of investigating the underlying mechanism of their occurrence. The intent of this study was to develop an online scalable approach for helping to identify secondary crashes for the large number of highways with insufficient traffic surveillance units to collect the continuous traffic data required to classify such crashes accurately. The developed approach consisted of two major components: (a) acquisition of open source traffic data and (b) identification of secondary crashes through the use of these data. Unlike existing approaches based on static thresholds, queuing models, or infrastructure-based sensor data, the developed approach took advantage of various open-source data to identify traffic conditions in the presence of incidents. This study proposed to develop virtual sensors collecting traffic data from private traffic information providers such as Bing Maps, Google Maps, and MapQuest. The availability of such data greatly expands the ability of transportation agencies to cover more highways without installing infrastructure sensors. The virtual-sensor output provides the basic input to run the developed automatic identification algorithm for identifying secondary crashes. The algorithm is described step by step to provide a readily deployable approach for transportation agencies interested in identifying secondary crashes on their highway networks.

Original languageEnglish (US)
Pages (from-to)24-33
Number of pages10
JournalTransportation Research Record
Volume2470
DOIs
StatePublished - 2014

Fingerprint

Sensors
Availability

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Development of online scalable approach for identifying secondary crashes. / Yang, Hong; Ozbay, Kaan; Morgul, Ender Faruk; Bartin, Bekir; Xie, Kun.

In: Transportation Research Record, Vol. 2470, 2014, p. 24-33.

Research output: Contribution to journalArticle

Yang, Hong ; Ozbay, Kaan ; Morgul, Ender Faruk ; Bartin, Bekir ; Xie, Kun. / Development of online scalable approach for identifying secondary crashes. In: Transportation Research Record. 2014 ; Vol. 2470. pp. 24-33.
@article{c869df3c479f4dadad3c48253e32cf1b,
title = "Development of online scalable approach for identifying secondary crashes",
abstract = "Secondary crashes are some of the most critical incidents occurring on highways. Such crashes can induce extra traffic delays and affect highway safety performance. Transportation agencies are interested in understanding the mechanism of the occurrence of secondary crashes and implementing appropriate counter measures. However, no well- established procedure identifies secondary crashes; this deficiency in turn impedes the possibility of investigating the underlying mechanism of their occurrence. The intent of this study was to develop an online scalable approach for helping to identify secondary crashes for the large number of highways with insufficient traffic surveillance units to collect the continuous traffic data required to classify such crashes accurately. The developed approach consisted of two major components: (a) acquisition of open source traffic data and (b) identification of secondary crashes through the use of these data. Unlike existing approaches based on static thresholds, queuing models, or infrastructure-based sensor data, the developed approach took advantage of various open-source data to identify traffic conditions in the presence of incidents. This study proposed to develop virtual sensors collecting traffic data from private traffic information providers such as Bing Maps, Google Maps, and MapQuest. The availability of such data greatly expands the ability of transportation agencies to cover more highways without installing infrastructure sensors. The virtual-sensor output provides the basic input to run the developed automatic identification algorithm for identifying secondary crashes. The algorithm is described step by step to provide a readily deployable approach for transportation agencies interested in identifying secondary crashes on their highway networks.",
author = "Hong Yang and Kaan Ozbay and Morgul, {Ender Faruk} and Bekir Bartin and Kun Xie",
year = "2014",
doi = "10.3141/2470-03",
language = "English (US)",
volume = "2470",
pages = "24--33",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",

}

TY - JOUR

T1 - Development of online scalable approach for identifying secondary crashes

AU - Yang, Hong

AU - Ozbay, Kaan

AU - Morgul, Ender Faruk

AU - Bartin, Bekir

AU - Xie, Kun

PY - 2014

Y1 - 2014

N2 - Secondary crashes are some of the most critical incidents occurring on highways. Such crashes can induce extra traffic delays and affect highway safety performance. Transportation agencies are interested in understanding the mechanism of the occurrence of secondary crashes and implementing appropriate counter measures. However, no well- established procedure identifies secondary crashes; this deficiency in turn impedes the possibility of investigating the underlying mechanism of their occurrence. The intent of this study was to develop an online scalable approach for helping to identify secondary crashes for the large number of highways with insufficient traffic surveillance units to collect the continuous traffic data required to classify such crashes accurately. The developed approach consisted of two major components: (a) acquisition of open source traffic data and (b) identification of secondary crashes through the use of these data. Unlike existing approaches based on static thresholds, queuing models, or infrastructure-based sensor data, the developed approach took advantage of various open-source data to identify traffic conditions in the presence of incidents. This study proposed to develop virtual sensors collecting traffic data from private traffic information providers such as Bing Maps, Google Maps, and MapQuest. The availability of such data greatly expands the ability of transportation agencies to cover more highways without installing infrastructure sensors. The virtual-sensor output provides the basic input to run the developed automatic identification algorithm for identifying secondary crashes. The algorithm is described step by step to provide a readily deployable approach for transportation agencies interested in identifying secondary crashes on their highway networks.

AB - Secondary crashes are some of the most critical incidents occurring on highways. Such crashes can induce extra traffic delays and affect highway safety performance. Transportation agencies are interested in understanding the mechanism of the occurrence of secondary crashes and implementing appropriate counter measures. However, no well- established procedure identifies secondary crashes; this deficiency in turn impedes the possibility of investigating the underlying mechanism of their occurrence. The intent of this study was to develop an online scalable approach for helping to identify secondary crashes for the large number of highways with insufficient traffic surveillance units to collect the continuous traffic data required to classify such crashes accurately. The developed approach consisted of two major components: (a) acquisition of open source traffic data and (b) identification of secondary crashes through the use of these data. Unlike existing approaches based on static thresholds, queuing models, or infrastructure-based sensor data, the developed approach took advantage of various open-source data to identify traffic conditions in the presence of incidents. This study proposed to develop virtual sensors collecting traffic data from private traffic information providers such as Bing Maps, Google Maps, and MapQuest. The availability of such data greatly expands the ability of transportation agencies to cover more highways without installing infrastructure sensors. The virtual-sensor output provides the basic input to run the developed automatic identification algorithm for identifying secondary crashes. The algorithm is described step by step to provide a readily deployable approach for transportation agencies interested in identifying secondary crashes on their highway networks.

UR - http://www.scopus.com/inward/record.url?scp=84938568400&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938568400&partnerID=8YFLogxK

U2 - 10.3141/2470-03

DO - 10.3141/2470-03

M3 - Article

AN - SCOPUS:84938568400

VL - 2470

SP - 24

EP - 33

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

ER -