Driver Gaze Tracking and Eyes Off the Road Detection System
Driver Gaze Tracking and Eyes Off the Road Detection System
复制标题
DOI：
10.1109/tits.2015.2396031
复制
发表时间：
2015-08-01
影响因子：
8.5
通讯作者：
Levi, Dan
中科院分区：
文献类型：
--
作者：
Vicente, Francisco;Huang, Zehua;Levi, Dan
分心驾驶是美国汽车碰撞的主要原因之一。被动地监控驾驶员的活动是汽车安全系统的基础，它可以通过估计驾驶员的注意力集中来潜在地减少事故的数量。本文提出了一种廉价的基于视觉的系统来准确检测眼睛偏离道路（EOR）。该系统主要由三个部分组成：1)鲁棒的面部特征跟踪；2)头部姿态和凝视估计；3)三维几何推理检测提高采收率。从安装在方向盘柱上的摄像头的视频流中，我们的系统追踪驾驶员面部特征。利用追踪到的地标和3d面部模型，系统计算出头部姿势和凝视方向。该算法对面部表情变化引起的非刚性变形具有较强的鲁棒性。最后，利用三维几何分析，系统可靠地检测了EOR。该系统不需要任何驾驶员相关的校准或手动初始化，并且可以在白天和晚上实时工作（25 FPS）。为了验证该系统在真实汽车环境中的性能，我们在各种照明条件、面部表情和个体下进行了全面的实验评估。我们的系统在所有测试场景中都实现了90%以上的提高采收率精度。
Distracted driving is one of the main causes of vehicle collisions in the United States. Passively monitoring a driver's activities constitutes the basis of an automobile safety system that can potentially reduce the number of accidents by estimating the driver's focus of attention. This paper proposes an inexpensive vision-based system to accurately detect Eyes Off the Road (EOR). The system has three main components: 1) robust facial feature tracking; 2) head pose and gaze estimation; and 3) 3-D geometric reasoning to detect EOR. From the video stream of a camera installed on the steering wheel column, our system tracks facial features from the driver's face. Using the tracked landmarks and a 3-D facemodel, the system computes head pose and gaze direction. The head pose estimation algorithm is robust to nonrigid face deformations due to changes in expressions. Finally, using a 3-D geometric analysis, the system reliably detects EOR.The proposed system does not require any driver-dependent calibration or manual initialization and works in real time (25 FPS), during the day and night. To validate the performance of the system in a real car environment, we conducted a comprehensive experimental evaluation under a wide variety illumination conditions, facial expressions, and individuals. Our system achieved above 90% EOR accuracy for all tested scenarios.