Real-Time Distraction Detection Based on Driver's Visual Features

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

“…Tran et al [17] proposed a rel-time driver distraction detection system that is able to identify 10 types of distractions through multiple cameras and microphone and also alerts through a voice message. Alam et al [7], [8] proposed a system that estimates attentional states of driver based on various visual cues. Shibli et al [9] estimated level of attention and detected fatigue during driving based on assessing eye aspect ratio (EAR) and head pose.…”

“…Deviation from the typical position for long period of time (T 3 ) is an indication of distraction. GD can be calculated by (8).…”

“…FD and EGD are estimated using yaw angle α of head and direction of eye center measured using angle θ respectively according to the process described in Section III-A3. GD is calculated using FD and EGD according to (8), which can be left, front or right. SoA is calculated using GD value according to Algorithm 1, which can be attentive or distracted.…”

“…Vision-based attentional information includes facial features and body movements. Most used non-invasive attentional cues in currently available vision-based systems are eyelid movements (e.g.,eye blink frequency, closure duration) [6]- [11], eye gaze [6]- [8], [12], head movement [7]- [9], [13], [14], facial expressions (e.g., yawning, lip movements etc.) [7], [11], [13], [15], and body movements (like hand movement) [15]- [17].…”

“…[7], [11], [13], [15], and body movements (like hand movement) [15]- [17]. However, these existing vision-based systems have some limitations: (i) capturing sensors used by the aforementioned systems are either expensive camera(s) [7]- [10], [14], [15], [17] with any additional sensor/hardware [11], [12], [16], [17] or some specialized imaging sensor (e.g., eye tracker [6] and Kinect [13]); (ii) some of the systems used only single parameters such as pupil [12], PER-CLOS [10] and head pose [14] to estimate driver's attentional state making the system unable to adapt to some situations which are common in the real driving scenario (for example, turning head or wearing sun glass can hide eye) and resulting in incorrect attentional state detection; (iii) some existing systems detect single inattentional state [8]- [14], [17] or limited only to the level of the same state [6], whereas some other focus on detecting driver's activity [15], [16]; (iv) some systems do not have any alert system to warn the driver of any inattentional state when detected during driving [6]- [8], [10], [11], [14]- [16]; (v) some of the previous works [11], [15], [17] were evaluated in a simulated environment and may not work accurately in the real driving scenario; and (vi) no evidence was provided about the systems mentioned above working in diverse situations (e.g. drivers were having different facial features such as beard, moustache, and hairstyles or wearing accessories (e.g.…”