An accurate vehicle counting approach based on block background modeling and updating

Vehicle flow volume on the motorway in the urban area is successfully used to realize traffic decision-making and guidance. In this research, we introduced some critical components into a vehicle flow detection system. In order to enhance the accuracy and instantaneity of the vehicle counting in quick-change traffic conditions, an adaptive modeling and updating method of background was proposed. In the vehicle flow detection system, first a number of simplified and comprehensive pretreatments were used as preceding conditions, especially in detection region setting and calibration. Next, a novel background modeling and updating strategy was adopted in background subtraction. Then a location patching method was applied for vehicle recognition and counting. Experimental results show that the new approach can detect and count vehicle timely and accurately in a variety of traffic situations, meanwhile the accuracy rate of the counting is over 97%, which demonstrates this novel approach is robust and powerful enough.