MVD:A Novel Methodology and Dataset for Acoustic Vehicle Type Classification
This provides a cost-effective solution for traffic monitoring in urban areas, though it is incremental with new datasets and a hybrid method.
The authors tackled acoustic vehicle type classification by introducing two open datasets (MVD and MVDA) and a novel method using cepstrum/spectrum features with a multi-input neural network, achieving accuracies of 91.98% and 96.66% on the datasets.
Rising urban populations have led to a surge in vehicle use and made traffic monitoring and management indispensable. Acoustic traffic monitoring (ATM) offers a cost-effective and efficient alternative to more computationally expensive methods of monitoring traffic such as those involving computer vision technologies. In this paper, we present MVD and MVDA: two open datasets for the development of acoustic traffic monitoring and vehicle-type classification algorithms, which contain audio recordings of moving vehicles. The dataset contain four classes- Trucks, Cars, Motorbikes, and a No-vehicle class. Additionally, we propose a novel and efficient way to accurately classify these acoustic signals using cepstrum and spectrum based local and global audio features, and a multi-input neural network. Experimental results show that our methodology improves upon the established baselines of previous works and achieves an accuracy of 91.98% and 96.66% on MVD and MVDA Datasets, respectively. Finally, the proposed model was deployed through an Android application to make it accessible for testing and demonstrate its efficacy.