首页> 外文会议>Transportation Research Board Annual meeting >Measuring Cyclists' Behavior Using Wearable Sensors for Automatic Creation of Safety Behavior Map
【24h】

Measuring Cyclists' Behavior Using Wearable Sensors for Automatic Creation of Safety Behavior Map

机译:使用可穿戴传感器测量骑车人的行为,以自动创建安全行为图

获取原文

摘要

According to the traffic accident report by the National Police Agency, more than 150,000 persons areinjured in bicycle-related traffic accidents in 2009 in Japan. In order to reduce bicycle-related trafficaccidents, collecting cyclists' actual behavior data especially safety-related behavior data under varioustraffic conditions is essential. In this paper, we propose (1) a method for continuously measuring andanalyzing cyclists' turning-head behavior (including both safety visual search behavior and look-awaybehavior) using wearable sensors, (2) an automated method to identify whether the measured turning-headbehavior is safety visual search behavior or look-away behavior requiring no prior information, and (3) amethod for automatic creation of cyclists' safety behavior map showing traffic spots where many cyclistsperform safety visual search behavior. Our method use small wireless three-axis gyro sensors to measurecyclists' head motion. Since gyro sensors and a PDA are both small, wireless and running on battery power,our method can easily adapt to various kinds of situations. By applying independent component analysis(ICA) to reduce bicycle-caused noise, our method allows to detect cyclists' turning-head behavior withprecision of 90.5% and recall of 91.8%. In addition, by focusing on spatial density of turning-headbehavior among cyclists, identification ratio of visual search behavior achieved 18% improvement withoutusing any prior information. Furthermore, safety behavior map created from 36 junior high school students'data showed the fact that almost 60% of all subjects never perform visual search behavior even whenentering blind intersections including accident prone area.
机译:根据国家警察局的交通事故报告,超过15万人 2009年日本自行车相关交通事故中受伤的人。为了减少自行车相关的交通 事故,收集各种情况下骑车人的实际行为数据,尤其是与安全相关的行为数据 交通条件至关重要。在本文中,我们提出(1)一种连续测量和 分析骑车人的转头行为(包括安全视觉搜索行为和视线) 行为)(使用可穿戴式传感器);(2)一种自动方法来识别所测转头是否 行为是不需要先验信息的安全视觉搜索行为或视线行为,以及(3)a 骑自行车者的安全行为图自动创建方法,该图显示了许多骑自行车者所在的交通点 执行安全的视觉搜索行为。我们的方法使用小型无线三轴陀螺仪传感器进行测量 骑车人的头部运动。由于陀螺仪传感器和PDA既小巧又无线,并且依靠电池供电, 我们的方法可以轻松适应各种情况。通过应用独立的成分分析 (ICA)为减少自行车引起的噪音,我们的方法允许通过以下方式检测骑车人的转头行为: 精度为90.5%,召回率为91.8%。此外,通过关注转头的空间密度 骑行者的行为,视觉搜索行为的识别率提高了18%,而没有 使用任何先前的信息。此外,还根据36名初中生的安全行为图绘制了他们的安全行为图 数据表明,即使在以下情况下,几乎60%的受试者从未执行过视觉搜索行为: 进入盲区交叉口,包括容易发生事故的区域。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号