Active Vision-Based Attention Monitoring System for Non-Distracted Driving

Abstract

Inattentive driving is a key reason of road mishaps causing more deaths than speeding or drunk driving. Research efforts have been made to monitor drivers' attentional states and provide support to drivers. Both invasive and non-invasive methods have been applied to track driver's attentional states, but most of these methods either use exclusive equipment which are costly or use sensors that cause discomfort. In this paper, a vision-based scheme is proposed for monitoring the attentional states of the drivers. The system comprises four major modules such as cue extraction and parameter estimation, monitoring and decision making, level of attention estimation, and alert system. The system estimates the attentional level and classifies the attentional states based on the percentage of eyelid closure over time (PERCLOS), the frequency of yawning and gaze direction. Various experiments were conducted with human participants to assess the performance of the suggested scheme, which demonstrates the system's effectiveness with 92% accuracy.

Optimization of extreme position landmarks identification algorithm for driver fatigue state

“…The geometric relationship between determines the degree of driver fatigue. Literature [16] uses MTCNN, a cascaded face detection algorithm, to identify possible faces first, then use maximum value suppression to determine the face with the highest probability, and finally determine the corresponding face landmarks position, The driver's fatigue state is judged by eye aspect ratio, mouth aspect ratio and nodding frequency, combined with PRECLOS value and other fatigue features, and compared with the AdaBoost algorithm in the experiment, it proves that the deep learning algorithm MTCNN has a stronger Environmental adaptability and higher detection accuracy; the visual algorithm based on deep learning in the literature [17] extracts landmarks information and classifies fatigue status according to the percentage of eyelid closure time (PERCLOS), yawning frequency and gaze direction; in In the literature [18] , the Dlib algorithm is used to identify the landmarks of the face, and the determined EAR threshold is used as a basis for judging eye closure to determine whether the driver is tired. At the same time, the yawning threshold is also determined, and the yawning threshold is determined through this threshold.…”

Gaze Estimation Based on Attention Mechanism Combined With Temporal Network

“…The utilization of a camera positioned above the screen to capture changes in the observers' eyes and determine their gaze positions has emerged as a prominent trend. This approach finds extensive applications in domains such as humancomputer interaction [1][2], virtual reality [3], and assisted driving [4] [5], enabling a better understanding of what draws observers' attention.…”

Innovative Framework for Distracted-Driving Alert System Based on Deep Learning

“…Accordingly, some studies focus on gaze tracking to estimate driver distraction. Alam et al [36] used a DCNN facial landmark detector to detect the position of the eye and mouth. Then, they calculated eyes aspect ratio and percentage of eyelid closure over the pupil over time for drowsiness detection, yawning frequency for fatigue detection, and gaze direction for detecting distraction.…”