Research on fatigue detection based on visual features

Abstract

The high incidence of traffic accidents brings immeasurable losses to life. In order to avoid such crises, researchers and automakers have used many methods to solve this problem. Among them, technology based on visual features is widely used in driver fatigue detection. As fatigue detection plays a vital role in the driving process, the high accuracy of fatigue monitoring is very important. This paper focuses on the method based on convolutional neural network to detect driver fatigue. First, in the face detection part, the Single-Shot Multi-Box Detector algorithm is used to improve the speed and accuracy of face detection to extract the eye and mouth regions; second, the VGG16 network is used to learn fatigue features, which is performed on the NTHU-Drowsy Driver Detection (NTHU-DDD) data set and the other two modified data sets Training test. The main result of this work is that the accuracy of fatigue monitoring is higher than other methods including the original method, with an accuracy rate of over 90%. And it has better generalization ability than the multi-physical feature fusion detection method. At the same time, we propose the fatigue detection method based on convolutional neural network to improve the advanced driver assistance system (ADAS) to make it more robust and reliable decision making.

Cause-and-Effect Analysis of ADAS: A Comparison Study between Literature Review and Complaint Data

“…A larger number of studies focused on developing advanced algorithms to improve the performance of ADAS that were able to improve driver trust and less vulnerable to different weather and road conditions (e.g., [18,25,28]). Another important finding was that researchers were also interested in modeling and monitoring driver behavior to help improve the joint performance of the human-vehicle system (e.g., [67,70,72]. However, in the consumer complaint dataset, we emphasized the possible consequences of the ADAS issues despite the fact that there were a small number of solutions to ADAS issues provided by dealers, mechanics, or automotive companies, but these might be temporary solutions since many ADAS problems were still persistent (e.g., tl* the contact owns a 2019 honda cr-v. while the contact was driving approximately 45 mph, another vehicle pausing on the passenger side of the contact's vehicle caused the automatic braking system to activate.…”

“…Therefore, researchers proposed algorithms to detect and predict the intentions of drivers to alert them of risky traffic situations and make decisions about whether to take over the driver's control of the vehicle [18,25,28]. Other studies also examined the methods to improve driver's behavior modeling and detection, such as eye gaze detection, fatigue detection, and other driving behavior detection for better monitoring performance [64,67,[70][71][72][73][74]. In terms of drivers' intentional disuse of the system, Meuller et al [43] proposed a driver monitoring system based on driver behavior tracking to detect deliberate disengagement and misuse of ADAS, the system then used attention reminders and proactive methods to keep drivers engaged in the driver-system interactions and maintain the system's functionalities.…”

Driver Fatigue Detection Based on Residual Channel Attention Network and Head Pose Estimation

“…Ji et al [16] used MTCNN detect face and design ESR-Net and MSR-Net to detect the facial state. Zhao et al [17] used the single-shot multi-box detector algorithm to detect the face region and used VGG-16 to classify the facial state. With the development of deep learning, the introduction of the channel attention mechanism in the convolutional neural network has been proved to be effective in improving the accuracy of image classification [18].…”

Smart education case: a detection method of the driver's smoking behavior

“…The parallel line detection method is based on the fact that the lateral contour of a cigarette can generally be regarded as two parallel straight lines. Therefore, it can detect the presence of two parallel lines similar to the contour of the cigarette in the image near the driver's mouth, in order to determine whether the driver has smoking behavior [3].…”