1 Citation (Scopus)
7 Downloads (Pure)


Modern urban-transport planning requires evidence-based insights into current transport flows to better understand the needs and impacts of policymaking. Urban transport includes passenger and freight vehicles, which have different behavior, and the need for such a separation is often ignored in research and practice [1]. New digital data sources provide an opportunity to better understand urban transport and identify where policy interventions are required. We review the literature on digital counting techniques to monitor transport flows, including loops, Automatic-Number Plate Recognition (ANPR) cameras and floating car data. We further investigate the potential of ANPR cameras, which are widely deployed, and which can be augmented with vehicle category information. This article presents the methodology that we follow for transforming raw augmented ANPR camera data into practical knowledge for city planners. Our is aim is to provide a better understanding of passenger and freight vehicle movements and stops, identifying similarities and differences between vehicle categories. We demonstrate our methodology on a case study for the Mechelen-Willebroek district in Belgium, encompassing augmented data from 122 ANPR cameras for a period of two weeks. Additionally, we also look at the car-reduced zone and how time restrictions affect the different vehicle categories’ actions. The findings are validated with GPS data from heavy-good vehicles in the same period. The potential of augmented ANPR camera data and promising themes and applications of this data source are illustrated through the case study.
Original languageEnglish
Article number37
Pages (from-to)1-17
Number of pages17
JournalEuropean Transport Research Review
Issue number1
Publication statusPublished - 29 May 2020


  • ANPR cameras
  • Big data
  • Transport planning
  • Urban transport

Fingerprint Dive into the research topics of 'Analyzing passenger and freight vehicle movements from automatic-Number plate recognition camera data'. Together they form a unique fingerprint.

Cite this