A Low-cost Vehicle Detection and Classification System based on Unmodulated Continuous-wave Radar

Vehicle detection and classification system is an important part of the intelligent transportation systems (ITS). Its function is to measure traffic parameters such as flow-rate, speed, and vehicle types, which are valuable information for applications of road surveillance, traffic signal control, road planning, and so on. This paper presents a novel low-cost vehicle detection and classification system which is based on a K-band unmodulated CW radar. This system utilizes time-frequency analysis, multi-threshold detection, and Hough transform as the major signal processing methods to extract speed and shape information of vehicles from Doppler signature they generate. It can perform vehicle detection, speed measurement, and vehicle classification simultaneously. Experimental results show that the proposed system and algorithms can provide promising performance and accuracy.