Traffic incident validation and correlation using text alerts and images

Wye Huong Yan, Justin Ong, Shen Shyang Ho, Jim Cherian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

One of the major challenges during the process of extracting infor-mation from multiple spatio-temporal data sources of diverse data types is the matching and fusion of extracted knowledge (e.g. inter-esting nearby events detected from text, estimated density or flow from a set of geo-coded images). In this demonstration, we present PETRINA ("PErsonalized TRaffic INformation Analytics"), a sys-tem that provides traffic-related incident monitoring, mapping, and analytics services. In particular, we showcase two main functional-ities: (1) text traffic alert validation based on traffic condition infor-mation derived from traffic camera images and (2) traffic incident correlation based on spatio-temporal proximity of different inci-dent types (e.g., accidents and heavy traffic). Despite the fact that the images are sparse (available every three minutes), the regularity makes it possible to validate whether a text traffic alert is outdated or not, and to more accurately estimate the time elapsed and total incident time. Multiple traffic incidents can be grouped together as a single event based on the traffic incident correlation to reduce information redundancy. Such enhanced real-time traffic informa-tion enables PETRINA to offer services such as dynamic routing with traffic incident advices, spatiotemporal traffic incident visual analytics, and congestion analysis.

Original languageEnglish (US)
Title of host publication22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014
EditorsMarkus Schneider, Michael Gertz, Yan Huang, Jagan Sankaranarayanan, John Krumm
PublisherAssociation for Computing Machinery
Pages601-604
Number of pages4
ISBN (Electronic)9781450331319
DOIs
StatePublished - Nov 4 2014
Event22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014 - Dallas, United States
Duration: Nov 4 2014Nov 7 2014

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems
Volume04-07-November-2014

Other

Other22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014
CountryUnited States
CityDallas
Period11/4/1411/7/14

All Science Journal Classification (ASJC) codes

  • Earth-Surface Processes
  • Computer Science Applications
  • Modeling and Simulation
  • Computer Graphics and Computer-Aided Design
  • Information Systems

Fingerprint Dive into the research topics of 'Traffic incident validation and correlation using text alerts and images'. Together they form a unique fingerprint.

Cite this