Accuracy of Video Detection Systems for Traffic Counting
Madhav Chitturi, Juan Carlos Medina, Rahim Farahnak Benekohal · ITE 2007 Annual Meeting and ExhibitInstitute of Transportation Engineers (ITE) · 2007
This paper will discuss how Video Detection (VD) systems for intersection signal operation are becoming more popular. Some agencies are using the counting feature of the VD system for traffic volume counts. The accuracy of the VD systems for traffic counting is evaluated in this paper and counts obtained from two VD systems are compared with the actual traffic counts in both cloudy day and night conditions. Multiple datasets are used for comparison. For both the systems it was found that the VD system’s error is lower under cloudy conditions. Under night conditions the counts are consistently higher because of the false calls caused by the headlights of the vehicles in the adjacent lanes. The paper recommended the use of a longer time interval for the counts in order to reduce the range of error that exists for short time period counts.