Hands on Wheel Classification Based on Depth Images and Neural Networks

This paper describes a system to automatically observe if the driver has his hands on the wheel, which is important to know that he can intervene if necessary. To accomplish this an artificial neural network is used, which utilizes depth information captured by a camera in the roof module of the car. This means that the driver and the steering wheel are viewed from above. The created classification system is described. It is designed to require as little computational effort as possible, since the target application is on an embedded system in the car. A dataset is presented and the effect of a class imbalance that is incorporated in it is studied. Furthermore, it is examined which part, i.e. the depth or the intensity image, of the available data is important to achieve the best possible performance. Finally, by examining a learning curve, an experiment is made to find out whether the recording of further training data would be reasonable.