Dangerous State Detection in Vehicle Cabin Based on Audiovisual Analysis with Smartphone Sensors

The paper presents the context-based approach for monitoring in-vehicle driver behavior based on the audiovisual analysis with aid of smartphone sensors, essentially utilizing front-facing camera and microphone. We propose the approach of driver monitoring system focused on recognizing situations whether the driver is drowsy or distracted, and reducing traffic accidents rate by generating context-relevant recommendations and perceiving driver’s feedback in a form of requested audio response to certain speech commands given by the smartphone. We efficiently utilize the information about driving behavior and the context to make sure that the driver actually followed the given recommendations that in the result will aid to reduce the probability of traffic accident. For example, audio signal produced by the smartphone’s microphone is used to check whether the driver increased or decreased the music volume inside the vehicle cabin. If the driver did not proceed with the recommendations, the driver is prompted to response with the voice command, and in this way, to confirm its alertness to current driving situation.