The latest developments in wireless technologies as well as the widespread usage of sensors have led to the recent prevalence of Intelligent Transportation Systems (ITS) for realistic and effective monitoring, decision-making, and management of the transportation systems. Considering the large size of the transportation data, variety of the data (different modalities and resolutions), and frequent changes of the data, the integration, visualization, querying and analysis of such data for large-scale real-time systems are intrinsically challenging data management tasks. Due to these challenges, current ITS applications only support limited data monitoring and analysis capabilities.

Here we present a real-world datadriven framework, dubbed ST (short for Smart Transportation), which enables real-time visualization, querying, and analysis of dynamic transportation systems. We build ST with a three-tier architecture (presentation tier, query-interface tier, and data tier) that allows users to create customized spatiotemporal queries through an interactive webbased map interface. With this architecture, we particularly address the fundamental data management and visualization challenges in 1) effective management of dynamic and largescale transportation data, and 2) efficient processing of real-time and historical spatiotemporal queries on transportation networks.

ST fuses a rich set of real transportation data obtained from RIITS (Regional Integration of Intelligent Transportation Systems) and NAVTEQ. The RIITS dataset is collected by various organizations based in Los Angeles County including Caltrans D7, Metro, LADOT, and CHP. This dataset includes both inventory and real-time data (with update rate as high as every 1 minute) for freeway and arterial congestion, bus location, events, and CCTV snapshots. Moreover, in order to support diverse ITS applications, ST contains the transportation network of the entire US, as well as a wide variety of point-of-interest data provided by NAVTEQ.

Subprojects

Year 2012 - 2013

• BigData Pricing Schemes
  • Team: Prof. Hamid Nazerzadeh (Industrial Engineering)
  • Description: Design and development of revenue-maximizing pricing schemes for Big-data marketplaces, with focus on Transportation sensor data.

• Archived Traffic Data Management System
  • Team: Prof. Genevieve Giuliano (USC Sol Price School of Public Policy)
  • Description: Implement Online Analytical Processing (OLAP) techniques to analyze archived traffic sensor data towards transportation decision making and planning.

• Study of Congested Corridors in Los Angeles
  • Team: Prof. James Elliott Moore, II (Industrial Engineering)
  • Description: Study the most congested corridors of Los Angeles County using historical traffic sensor data, and make before and after analysis of Carmegedons.

• ClearPath (Continued from 2011)
  • Team: Karen Kerr and Juan Felipe Vallejo (USC Stevens)
  • Description: Next-generation route planning application that takes into account the real-time and predictive traffic conditions on road networks.

Year 2011 - 2012

• Urban Goods Movement
  • Team: Prof. James Elliott Moore, II (Industrial Engineering)
  • Description: Develop efficient methods to optimize delivery of goods in urban areas and evaluate impacts across the supply chain.
  • Delivered:
    • 2 research papers
      IIE’12 and TRB’12 Journal (under review)
    • A Research prototype application

• Traffic Sensor Data Analysis and Corridor Monitoring
  • Team: Prof. Genevieve Giuliano and Prof. Lisa Schweitzer (USC Sol Price School of Public Policy)
  • Description: Analyze real-time and historical traffic sensor data to develop new policies towards enhancing the efficacy of the transportation systems.
  • Delivered:
    • 4 peer reviewed research papers
      DASFAA’12, SSTD’11, ACMGIS’11, TRA’12 (under review)
    • A research prototype on transportation decision making
      Click to link

• ClearPath
  • Team: Krisztina Holly, Karen Kerr and Juan Felipe Vallejo (USC Stevens)
  • Description: Next-generation route planning application that takes into account the real-time and predictive traffic conditions on road networks.
  • Delivered:
    • 2 patents (filed)
    • 3 research papers
      DASFAA’12, SSTD'11 and ACM GIS'11

• Realtime Traffic Video Analysis
  • Joint work with Prof. Jonathan Taplin (Annenberg Innovation Lab) and Intel Corp.
  • Develop vision-based algorithms to extract traffic flow data from traffic monitoring video streams using Intel's coprocessor.
  • Detailed slides can be found here.
  • General introductory presentation.

  • Technical demo presentation.