Traffic data collection and analysis using video image processing.

Auteur(s)
Dickinson, K.W. Ashworth, R. Darkin, C.G. Hartley, M.G. Hicks, P.J. Wan, C. & Waterfall, R.C.
Jaar
Samenvatting

Traffic flow data are required for a variety of reasons by local and national government and for research purposes. While data can be collected automatically using equipment installed in the carriageway, such installations are generally only suitable at permanent or semi-permanent sites. This paper describes the development of a portable, yet fully automatic, video based traffic data collection and analysis system, which aims eventually to operate in real-time. The system captures an image of the scene using a solid state video camera based on a charge coupled device (CCD) image sensor. CCD cameras offer considerable advantages over vidicon types in this application. A multi microprocessor system is then used to extract moving parts of the scene from a static background and useful data are at present stored on magnetic tape for subsequent analysis. Serial data, output from the camera in analogue form, is digitised by an ADC at a rate too high to allow the necessary processing to be carried out by a single microprocessor. Therefore, a number of microprocessor connected serially in a pipeline fashion each partially process data then pass data to the next microprocessor for further processing in real-time. The paper describes some practical problems encountered while trying to apply simple image processing techniques to observations of traffic scenes and also reports on the results of site trials. (a) for the covering abstract of the seminar see IRRD 273510.

Publicatie aanvragen

4 + 6 =
Los deze eenvoudige rekenoefening op en voer het resultaat in. Bijvoorbeeld: voor 1+3, voer 4 in.

Publicatie

Bibliotheeknummer
C 37319 (In: B 24054) /72 / IRRD 273517
Uitgave

In: Traffic operations and management : proceedings of Seminar K (P-240) held at the PTRC Summer Annual Meeting, University of Sussex, July 4-7, 1983, p. 95-106, 12 ref.

Onze collectie

Deze publicatie behoort tot de overige publicaties die we naast de SWOV-publicaties in onze collectie hebben.