Hadi Sadoghi Yazdi - Department of Electrical Engineering, Tarbiat Modares University, P.O.Box ۱۴۱۱۵-۱۴۳, Tehran, Iran
Mojtaba Lotfizad - Department of Electrical Engineering, Tarbiat Modares University, P.O.Box ۱۴۱۱۵-۱۴۳, Tehran, Iran
Mahmood Fathy - Faculty of Computer Engineering, Iran University of Science and Technology, Tehran, Iran
Ehsanollah Kabir - Department of Electrical Engineering, Tarbiat Modares University, P.O.Box ۱۴۱۱۵-۱۴۳, Tehran, Iran

In this paper, a model for normal behavior of drivers is presented. In this model, the mutual effect of vehicles is employed. The spatio-temporal features and motion history are utilized for developing the model. This model has three main parts: The first part concerns with the history of trajectory, in the form of Centers Transition Matrix, CTM. The second part is based on the linguistic features, including forward, turn right and left, line changing to right and left. The third part is constituted from low level features which contain velocity and distance to neighboring vehicles. The average value of the correct recognition obtained is 81.2%, for normal behavior.

Normal behavior of driver, Spatio-temporal features, Centers transition matrix, Linguistic features,Multi-object tracking