A multistage procedure of mobile vehicle acoustic identification for single-sensor embedded device

Abstract—Mobile vehicle identification has a wide application field for both civilian and military uses. Vehicle identification may be achieved by incorporating single or multiple sensor solutions and through data fusion. This paper considers a single-sensor multistage hierarchical algorithm of acoustic signal analysis and pattern recognition for the identification of mobile vehicles in an open environment. The algorithm applies several standalone techniques to enable complex decision-making during event iden-tification. Computationally inexpensive procedures are specifi-cally chosen in order to provide real-time operation capability. The algorithm is tested on pre-recorded audio signals of civilian vehicles passing the measurement point and shows promising classification accuracy. Implementation on a specific embedded device is also presented and the capability of real-time operation on this device is demonstrated. Keywords—vehicle identification, acoustic signal analysis, fea-ture extraction, classification, fuzzy logic I