Research on Vehicle Identification Algorithm Based on Sound Signal

With the fast development of information technology, the collection of traffic information plays a pivotal role in the intelligent management of traffic. The core of traffic information collection system is confirmed in vehicle detection, speed judgment and vehicle type identification. As an important part of intelligent transportation, it is widely used in toll collection system, traffic data statistics and other related work, especially in Expressway Automatic Toll Collection System, The automatic identification of vehicle type plays an extremely important role. The sound signal of engine generated by the driving vehicle is used as the research object in this paper. After signal preprocessing, wavelet denoising and AR feature extraction, it is sent to the BP neural network algorithm for classification and recognition. The simulation results show that the system has high recognition rate and strong stability, and can meet the needs of practical application.