PROJECT TITLE :

Detecting Drivers' Mirror-Checking Actions and Its Application to Maneuver and Secondary Task Recognition

ABSTRACT:

This study explores the feasibility of detecting drivers' mirror-checking actions using noninvasive sensors. Checking the mirrors is an important primary driving action that allows drivers to keep up their situational awareness, significantly once they are planning to turn or modification lanes. Recognizing when drivers are checking the mirrors can facilitate the detection of hazard situations by considering contextual info (e.g., turning while not checking mirrors, lack of mirror-checking actions signaling cognitive distractions, or distinction between gazes thanks to primary or secondary tasks). This study analyzes drivers' mirror-checking actions underneath various real driving conditions. We tend to analyze the drivers' mirror-checking actions underneath normal conditions, along with when the drivers are engaged in secondary tasks like tuning the radio or operating a cellular phone. We tend to additionally compare mirror-checking behaviors observed during totally different maneuver actions: driving straight, turning, and switching lanes. This study reveals statistically significant differences in mirror-checking actions among most of the comparisons. The results counsel that mirror-checking actions can be useful indicators in recognizing drivers engaged in secondary tasks, and in detecting driving maneuvers. We propose to detect mirror-checking actions using options extracted from multiple noninvasive sensors (CAN-Bus and cameras facing the motive force and therefore the road). We tend to think about three machine learning algorithms for unbalanced data sets, achieving an F-score of ninety onepercent. The recognized mirror-checking actions are used as further options to boost the performance of secondary task detection and maneuver recognition. These promising results suggest that it's attainable to detect mirror-checking actions, providing contextual data to improve new driver monitoring systems.