Driver Glance Behavior Modeling Based on Semi-Supervised Clustering and Piecewise Aggregate Representation
Driver Glance Behavior Modeling Based on Semi-Supervised Clustering and Piecewise Aggregate Representation
复制标题
基于半监督聚类和分段聚合表示的驾驶员视线行为建模
DOI：
10.1109/tits.2021.3080322
复制
发表时间：
2022-07
影响因子：
8.5
通讯作者：
Xiaohua Zhao
中科院分区：
文献类型：
--
作者：
Jianling Huang;Yan Long;Xiaohua Zhao
扫视行为是重要的，因为驾驶员是否以及如何扫描和观察驾驶场景与驾驶安全密切相关。本文旨在提高扫视行为建模的准确性，实现扫视行为的时空表示和可视化。招募了40名受试者使用驾驶模拟器执行高速公路驾驶任务。车辆数据由模拟器收集。驾驶员的注视点由眼动仪收集。通过统计分析获得的关于注视点的先验知识被提供给K均值（KM）以形成半监督K均值（SSKM），其将注视点分类到不同的注视区域。并将分类结果与KM分类结果进行了比较。此外，提出了一种基于聚类中心的分段聚集表示（CCPAR）来表征扫视行为。以机动目标识别为例，对该方法进行了验证.基于CCPAR相似性的k-最近邻（KNN）将驾驶机动识别为车道保持、左车道变换和右车道变换。将识别结果与隐马尔可夫模型（HMM）的识别结果进行了比较。KM和SSKM的平均分类准确率分别为55.28%和94.75%。CCPAR-KNN和HMM识别机动的准确率分别为87.50%和85.83%。结果表明，SSKM和CCPAR用于扫视行为建模是可行的。SSKM消除了初始聚类中心选择的随机性，提高了注视点分类的准确性。CCPAR能够直观、方便地描述和可视化扫视行为的时空特征。
Glance behavior is significant because whether and how the driver is scanning and observing the driving scene is closely related to driving safety. This paper aims to improve the accuracy of glance behavior modeling and realize the spatiotemporal representation and visualization of glance behavior. Forty subjects were recruited to perform a freeway driving task using a driving simulator. The vehicle data were collected by the simulator. Drivers’ gaze points were collected by an eye tracker. The prior knowledge on gaze points obtained through a statistical analysis were provided for K-means (KM) to form a semi-supervised K-means (SSKM), which classifies gaze points into different fixation zones. The classification results were compared with the results of KM. Furthermore, a clustering center-based piecewise aggregate representation (CCPAR) was proposed to characterize glance behavior. Maneuvers identification was taken as a case to evaluate the proposed method. The k-nearest neighbour (KNN) based on the similarity of CCPAR identified driving maneuvers into lane-keeping, left lane change, and right lane change. The identification results were compared with the results of the Hidden Markov Model (HMM). The average classification accuracies of KM and SSKM were 55.28% and 94.75%, respectively. The accuracies of maneuvers identified by CCPAR-KNN and by HMM were 87.50% and 85.83%, respectively. The results indicate that SSKM and CCPAR are feasible for glance behavior modeling. SSKM eliminates the randomness of initial cluster center selection and improves the accuracy of gaze points classification. CCPAR is intuitive and convenient to describe and visualize the spatiotemporal characteristics of glance behavior.