Measurement of some traffic signal parameters via un-calibrated video camera

In this paper, a new method is proposed for measuring some traffic parameters of a signalized intersection. This method is based on image processing techniques. These parameters are the number of stopped vehicles behind the red light and the number of vehicles passing through intersection in green phase. At first, based on image reticulation concept, a new method is presented for calculating the number of stopped vehicles behind the red light which the proposed method has no need to precise information of camera specifications such as: the height, the angle and the lens amplitude. Then by applying the virtual loops, a new method is proposed for counting the number of vehicles passing through intersection in green phase. These loops could be superseded the inductive loops which have wide applications in intelligent transportation systems (ITS).