Intelligentwarning System Monitoring Vehicle Surrounding and Driver’s Behavior

Abstract

A driving assistance system can warn drivers to danger and plays an important role in avoiding serious accidents. However, there are few works considering bidirectional interaction between the system and users. In this paper, we propose a novel system named Intelligent Warning System (IWS) that can warn drivers with appropriate timing and warning level according to surrounding environment and drivers’ behavior. A contribution of IWS includes following two factors: 1) A light-weight object detection method for setting an appropriate warning level depends on potential risks of surrounding objects. 2) A time-series learning method of driver’s facial orientation for setting an appropriate warning timing depends on driver’s behavior with user-friendly interaction. Experimental results suggest that subjects want to use IWS for their daily driving and they realize the difference of its warning style that is adapted by their behaviors, especially for safety confirmation of approaching objects.