基于四元数视觉注意模型的肇事车辆匹配方法  

Vehicle Matching Based on Quaternion Visual Attention Model

作　　者：徐航[1,2] 臧笛[1,2] 程成[1,2] 张亚英[1,2] 

机构地区：[1]同济大学计算机科学与技术系,上海201804 [2]同济大学嵌入式系统与服务计算教育部重点实验室,上海201804

出　　处：《计算机科学》2014年第6期269-274,303,共7页Computer Science

基　　金：科技部国际合作专项(2012DFG11580);铁道部科研开发计划(2012X014-E);国家自然科学基金项目(61003221;61103071);上海市自然科学基金(11ZR1440200)资助

摘　　要：在交通监控录像中快速准确地检索匹配肇事车辆是智能交通系统的重要任务。与传统的匹配方法相比,视觉注意模型融合了多种底层特征,为肇事车辆匹配提供了新的思路。针对车辆匹配的特点,提出了一种新的颜色信息提取方法,并在四元数数学框架下与亮度、方向特征相结合,将标量显著性转换成四元数显著性,提出了一种四元数视觉注意模型。将四元数显著性作为新的特征用于肇事车辆匹配。实验表明,该匹配方法可以根据肇事车辆信息有效地缩小搜索范围,具有较好的准确性和鲁棒性。Searching and matching the vehicle which caused traffic accidents is a challenging problem of great importance in Intelligent Transport System （ITS）.Compared with the traditional methods,visual attention model provides a new perspective by merging several fundamental features.This paper presented a new method to extract color information from an image aiming at vehicle matching problem.By combining with intensity and orientations under the framework of quatemions,a quaternion visual attention model was proposed.Experiments use the quaternion saliency as the new feature to match the vehicle which caused traffic accidents and the results demonstrate that the proposed approach is able to narrow the searching range effectively with good accuracy and robustness.

关 键 词：肇事车辆 匹配 视觉注意模型 显著性 四元数 颜色特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]