Review of non-intrusive advanced sensor devices for advanced traffic management systems and recent advances in video detection

P. Michalopoulos, J. Hourdakis

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

As performance requirements for advanced traffic management systems (ATMSs) increase, the need for new sensors leading to the next-generation traffic management systems is manifested. In spite of the wide array of non-intrusive technologies that are available today, most are not new. Even though earlier technologies continue to improve, most are fundamentally unsuitable for traffic detection, and their widespread use does not appear to be imminent. As a result, most traffic management centres (TMCs) being built today continue to rely on an old but established in-pavement technology, namely loop detectors. Perceived cost and reliability notwithstanding, the major physical disadvantage of loops, as well as of most technologies (intrusive or not), is their inability to detect traffic over a wide area and extract critical traffic measurements such as queues, density, stops and others. In this paper, non-intrusive technologies are briefly reviewed, and particular emphasis is given to the most promising and increasingly accepted in the field, namely machine vision. Since the technology is only recently accepted, representative major field deployment projects are also included.

Original languageEnglish (US)
Pages (from-to)345-355
Number of pages11
JournalProceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering
Volume215
Issue number4
DOIs
StatePublished - Dec 1 2001

Keywords

  • Advanced traffic management
  • Machine vision
  • Traffic control
  • Traffic measurements
  • Traffic sensors
  • Traffic surveillance
  • Vehicle detection

Fingerprint Dive into the research topics of 'Review of non-intrusive advanced sensor devices for advanced traffic management systems and recent advances in video detection'. Together they form a unique fingerprint.

Cite this