Miller, Marty; Herbers, Eileen; Walters, Jacob; Neurauter, Luke (SAFE-D: Safety Through Disruption National University Transportation Center, 2022-07)
Driver inattention poses a significant problem on today’s roadways, increasing risk for all road users. This report details our efforts in developing algorithms to detect driver inattention. A benchmark dataset was developed based on video review of driving events. Buffer-based algorithms were developed and compared using this benchmark dataset. The benchmark events were also used as a training dataset for machine learning models. Driver glance locations were important for determining driver attentiveness. In addition, vehicle speed was important for understanding the driving context, which was found to have a large impact on driver behavior.