基于图像显著性特征的交通标志注视点预测方法  

Prediction of Traffic Sign Fixation Based on the Image Saliency Feature

作　　者：徐志[1,2] 关宏志[1] 严海[1] 陈二慧[1] 

机构地区：[1]北京工业大学建筑工程学院,北京100124 [2]天津市城市规划设计研究院,天津300201

出　　处：《武汉理工大学学报（交通科学与工程版）》2014年第1期93-97,共5页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家"十一五"科技支撑计划项目(批准号:2006BAJ18B06);北京工业大学研究生科技基金支撑项目(批准号:ykj-2010-3396)资助

摘　　要：基于图像显著性特征对交通标志的驾驶员注视点进行了预测.以Ltti的视觉注意模型为基础,通过高斯金字塔的生成、多通道图像特征的提取及特征图的生成以及显著性图的生成等步骤,建立了针对交通标志的注视点预测模型.以眼动仪为手段,对模型进行了验证.以相似度和线性距离两项指标对模型精度作了评价,实验结果显示,该模型对复杂交通标志的注视点预测具有良好的精度.The prediction of fixation on traffic signs was conducted based on image characteristics .The fixation prediction model which based on model of visual attention built up by Ltti was set up through the process of Gaussian pyramid creation ,visual feature extraction and feature map generation as well as the saliency map generation .The model was validated with the aid of eye tracking system .Similari-ty and linear distance were selected as two indicators to evaluate the accuracy of model ,and the exper-imental results show that the model has a good accuracy on the prediction of complicated traffic sign .

关 键 词：图像显著性特征 交通标志 注视点 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]