Research for Increasing FCD Map Matching Accuracy Based on Feature Extraction of Continuous Traffic Flow and Interrupted Traffic Flow

  • Zhiping ZhangEmail author
  • Hangfei Lin
Part of the GeoJournal Library book series (GEJL, volume 122)


Statistics and forecasting of road traffic conditions is a key element for transportation planning. Because of the accuracy limitations of FCD (floating car devices, such as BEIDOU or GPS devices installed on a vehicle), it is very difficult to do map matching and route deriving for elevated and ground road networks when using FCD data. Because of this, the accuracy of road traffic judgment is very low. This study deeply analyzed and mined FCD data obtained from taxi on-board devices for Shanghai city, used grey relational analysis theory and fuzzy pattern recognition theory to extract features of continuous traffic flow and interrupted traffic flow, and improved accuracy for recognizing real traffic conditions. As the result, the recognition rate increased greatly—to more than 90 %.


FCD data processing Continuous traffic flow and interrupted traffic flow Feature extraction Grey relational analysis theory Fuzzy pattern recognition theory 


  1. Guirong Guo.(1993) “Fuzzy pattern recognition”. Hunan. Guofang Science and Technology University pressGoogle Scholar
  2. S.Brakatsoulas, D.Pfoser, and N.Tryfona.(2005) “Practical data management techniques for vehicle tracking data”. In Proc.21st ICNE conf, 324-325Google Scholar
  3. Sifeng Liu.(2007) “Grey system theories and applications”. Beijing. Science pressGoogle Scholar
  4. Stoiris Brakatsouls, Dleter Pfoser, Randall Salas and Carola Wenk.(2005). “On Map-Matching Vehicle Tracking Data”. The International Conference on Very Large Data Bases, Trondheim, Norway, 2005. VLDB Journal, Vol.14: 853-864 .Google Scholar
  5. Weifeng Li and Dongdong Wu. (2009) “Algorithm of heuristic path deriving based on vector recognition”. Computer Journal, 32(7), 1443-1450Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.School of Transportation EngineeringTongji UniversityShanghaiChina

Personalised recommendations