A vehicle re-identification algorithm based on multi-sensor correlation

作     者：Yin TIAN Hong-hui DONG Li-min JIA Si-yu LI 

作者机构：State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Shenzhen Graduate School Peking University 

出 版 物：《Journal of Zhejiang University-Science C(Computers and Electronics)》 (浙江大学学报C辑（计算机与电子（英文版）)

年 卷 期：2014年第15卷第5期

页      面：372-382页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 080202[工学-机械电子工程] 080203[工学-机械设计及理论] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(No.61104164) the National High-Tech R&D Program(863)of China(No.2012AA112401) 

主　　题：Vehicle re-identification Magnetic sensor network Correlation Cross matching 

摘      要：Magnetic sensors can be applied in vehicle *** of the existing vehicle recognition algorithms use one sensor node to measure a vehicle’s ***,vehicle speed variation and environmental disturbances usually cause errors during such a *** this paper we propose a method using multiple sensor nodes to accomplish vehicle *** on the matching result of one vehicle’s signature obtained by different nodes,this method determines vehicle status and corrects signature *** co-relationship between signatures is also obtained,and the time offset is corrected by such a *** corrected signatures are fused via maximum likelihood estimation,so as to obtain more accurate vehicle *** show that the proposed algorithm can provide input parameters with higher *** improves the average accuracy of vehicle recognition from 94.0%to 96.1%,and especially the bus recognition accuracy from 77.6%to 92.8%.