Abstract
Eye state recognition is a key step in fatigue detection method. However, factors such as occlusion of different types of glasses and changes in lighting conditions may have some impact on eye state recognition. In order to solve these problems, a driver’s eye state recognition method based on deep learning is proposed. Firstly, the driver’s face images are acquired using an infrared acquisition device. Secondly the multi-task cascaded convolution neural networks are used to detect the face bounding box and feature points of the driver’s face image, and then the eye regions are extracted. Finally the Convolution Neural Network (CNN) is adopted to identify the open and closed state of the eyes. Experimental result shows that the proposed method can accurately identify the state of eyes and help to calculate the fatigue parameters of drivers.
Highlights
With the continuous improvement of living conditions and the increasing number of cars, traffic accidents occurs more frequently
On the basis of face detection, according to the good clustering of eye white in YCbCr space, the Gaussian eye white segmentation model was established [3], and the white area of the eye was used as the eye opening and closing index, the algorithm had a low complexity, but it was sensitive to changes in illumination
In this paper, the driver's face images were collected using the infrared acquisition equipment, and the images of the eye regions were acquired by the multi-task cascaded convolutional neural networks (MTCNN) method
Summary
With the continuous improvement of living conditions and the increasing number of cars, traffic accidents occurs more frequently. An eye opening and closing detection method based on the combination of LBP and SVM was proposed [4]. This method has a high detection rate, it has certain limitations when the driver wears sunglasses and the posture changes. This paper locates the face image through the multi-task cascaded convolutional neural networks (MTCNN) [5], and the eye regions are extracted, and the eye state through the CNN are recognized.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
