Classification of moving vehicle using multi-frame time domain features

This research work is mainly focused on recognition of different vehicles and its position using acoustic sound source to assist the Differentially Hearing Ability Abled (DHAA). In this paper, a simple protocol has been designed to record the noise emanated by the moving vehicles under different weather conditions and also at different vehicle speed. Two feature extraction methods namely Auto regressive and statistical feature methods are used to extract the features from the recorded acoustic signature. The Radial Basis Function Network (RBFN) model was used for classification. The networks effectiveness has been validated through stimulation.