Image processing application in toll collection

Abstract

Abstract — The toll rate charged for the usage of facilities such as a tunnel or a bridge is usually proportional to the number of axles possessed by a vehicle. However, it is sometimes difficult to determine the number of axles of a vehicle by the toll-booth operator and therefore, an automatic system that can identify the number of axles is sought. Instead of detecting the axle, wheels of a vehicle are tested and a method based on the Hough transform for detecting circles is proposed. As the system must be able to detect the correct number of wheels in real-time, sub-sampling based on the Haar Wavelet transform is applied. Experimental results show that the system is able to identify the wheel correctly and to process the input images in real-time.