原文传递
Detecting Driver Distraction.
| 题名： | Detecting Driver Distraction. |
| 作者： | Eskenazi, M.; Black, A. W.; Keller, T.; Shah, S.; Hu, T. |
| 关键词： | Traffic crashes, Warning devices, Distracted drivers, Naturalistic data, Crash causes, Detection and identification, Distraction, Drivers, Driving simulators, Driving conditions |
| 摘要： | The goal of this project was to set up an environment that could be used for data collection for the study of distracted driving with the long term goal of automatically detecting when a driver is distracted and to collect data from 50 subjects driving the course we set up. We decided to use a simulator after determining that in order to collect enough naturalistic data to be able to create statistical models, we would have to collect an immense database (over 5000 subjects) and then employ labelers to go in and find situations where the driver was distracted. Even with such a significant amount of data, we would not be assured to capture instances where certain driving conditions coexisted and where the driver’s activities were distracting. By using a simulator, we were could decide at what point distracting events would take place. This decision both eliminated the need to annotate the data and enabled us to choose the combination of cellphone and route events so that individual causes of distraction could be teased out or combinations of causes could be studied as they interact with one another. |
| 报告类型： | 科技报告 |
相关文献
- Multimodal Detection of Driver Distraction.
- AN ALTERNATE METHOD TO EVALUATE DRIVER DISTRACTION.
- Research Framework for Studying Transit Bus Driver Distraction.
- Overview of the National Highway Traffic Safety Administration's Driver Distraction Program.
- Examination of Driver Distraction as Recorded in NHTSA Databases.
- THE ROLE OF DRIVER INATTENTION IN CRASHES; NEW STATISTICS FROM THE 1995 CRASHWORTHINESS DATA SYSTEM.
检索历史
应用推荐
