Real-time categorization of driver's gaze zone using the deep learning techniques

Abstract

This paper presents a study in which driver's gaze zone is categorized using new deep learning techniques. Since the sequence of gaze zones of a driver reflects precisely what and how he behaves, it allows us infer his drowsiness, focusing or distraction by analyzing the images coming from a camera. A Haar feature based face detector is combined with a correlation filter based MOSS tracker for the face detection task to handle a tough visual environment in the car. Driving database is a big-data which was constructed using a recording setup within a compact sedan by driving around the urban area. The gaze zones consist of 9 categories depending on where a driver is looking at during driving. A convolutional neural network is trained to categorize driver's gaze zone from a given face detected image using a multi-GPU platform, and then its network parameters are transferred to a GPU within a PC running on Windows to operate in the real-time basis. Result suggests that the correct rate of gaze zone categorization reaches to 95% in average, indicating that our system outperforms the state-of-art gaze zone categorization methods based on conventional computer vision techniques.