A wavelet packet algorithm for classification and detection of moving vehicles

In this paper we propose a robust algorithm that solves two related problem s: 1) Classification of acoustic signals emitted by different moving vehicl es. The recorded signals have to be assigned to pre-existing categories ind ependently from the recording surrounding conditions. 2) Detection of the p resence of a vehicle in a certain class via analysis of its acoustic signat ure against the existing database of recorded and processed acoustic signal s. To achieve this detection with practically no false alarms we construct the acoustic signature of a certain vehicle using the distribution of the e nergies among blocks which consist of wavelet packet coefficients. We allow no false alarms in the detection even under severe conditions; for example when the acoustic recording of target object is a superposition of the aco ustics emitted from other vehicles that belong to other classes. The propos ed algorithm is robust even under severe noise and a range of rough surroun ding conditions. This technology, which has many algorithmic variations, ca n be used to solve a wide range of classification and detection problems wh ich are based on acoustic processing which are not related to vehicles. The se have numerous applications.