Acoustic Detection for Vehicle Targets and Recognition by Data Fusion

This paper researches acoustic signals of typical vehicle targets in order to extract features and to recognize vehicle targets. As a data fusion method, the technique of artificial neural networks combined with genetic algorithm (ANNCGA) is applied for recognition of acoustic signals that belong to different kinds of vehicle targets. The technique and its architecture have been presented. The algorithm had been used for classification and recognition of acoustic signals of vehicle targets in the outdoor environment. Through experiments, it can be proven that acoustic properties of target acquired are correct, ANNCGA data fusion method is effective to solve the problem of target recognition