Physical Signal Classification Via Deep Neural Networks
This addresses vehicle identification for surveillance or monitoring applications, but appears incremental as it applies existing deep neural networks to a new dataset.
The paper tackled the problem of classifying physical signatures from sensor measurements to identify vehicle types and models, achieving classification of gasoline and diesel-powered vehicles and other devices using acoustic, acceleration, geophonic, and magnetic data.
A Deep Neural Network is applied to classify physical signatures obtained from physical sensor measurements of running gasoline and diesel-powered vehicles and other devices. The classification provides information on the target identities as to vehicle type and even vehicle model. The physical measurements include acoustic, acceleration (vibration), geophonic, and magnetic.