DSP based acoustic vehicle classification for multi-sensor real-time traffic surveillance

Vehicles may be recognized from the sound they emit when driving along a road. Characteristic acoustic finger prints and audio features can be used to increase the robustness of existing video based vehicle tracking and classification algorithms. Using this information in a multisensor surveillance system helps to improve various parameters such as recognition rates, detection times and robustness. We propose a two-fold approach, where vehicle detection and classification are handled separately. We demonstrate the feasibility of the proposed method using outdoor audio sequences of traffic situations.