A study on the prediction of driver's pedestrian detectability considering characteristics of human fields-of-view while driving
A study on the prediction of driver's pedestrian detectability considering characteristics of human fields-of-view while driving
复制标题
考虑人眼视野特征的驾驶员行人可探测性预测研究
DOI：
--
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Murase Hiroshi
中科院分区：
文献类型：
--
作者：
Tanishige Ryunosuke;Doman Keisuke;D. Daisuke;Mekada Yoshito;Ide Ichiro;Murase Hiroshi
近来，行人检测技术的进步已经导致了向驾驶员通知行人的存在的驾驶辅助系统的开发。然而，警告所有现有的行人会干扰驾驶员的注意力。因此，有必要开发一种方法来预测驾驶员对行人的可检测性。本报告提出了一种方法，预测行人检测考虑到人类视野的特点。为了准确预测行人的可检测性，该方法构造了一个特定于每个视场的预测器。所提出的方法的输出和地面的行人可检测性之间的比较表明，所提出的方法显着降低了预测误差与现有的方法相比。
Recently, advances in pedestrian detection technology have resulted in the development of driving assistance systems that notify the drivers of the presence of pedestrians. However, warning of all existing pedestrians would interfere with the driver’s concentration. Therefore, it is necessary to develop a method to predict the detectability of a pedestrian by the driver. This report proposes a method that predicts the pedestrian detectability considering the characteristics of human fields-of-view. In order to predict the pedestrian detectability precisely, the proposed method constructs a predictor specific to each fields-of-view. Comparison between the output of the proposed method and the ground-truth of pedestrian detectability showed that the proposed method significantly reduced the prediction error in comparison with the existing methods.