|
|
|
| A vehicle re-identification algorithm based on multi-sensor correlation |
| Yin Tian, Hong-hui Dong, Li-min Jia, Si-yu Li |
| State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, China; Shenzhen Graduate School, Peking University, Shenzhen 518055, China |
|
|
|
Abstract Magnetic sensors can be applied in vehicle recognition. Most of the existing vehicle recognition algorithms use one sensor node to measure a vehicle’s signature. However, vehicle speed variation and environmental disturbances usually cause errors during such a process. In this paper we propose a method using multiple sensor nodes to accomplish vehicle recognition. Based on the matching result of one vehicle’s signature obtained by different nodes, this method determines vehicle status and corrects signature segmentation. The co-relationship between signatures is also obtained, and the time offset is corrected by such a co-relationship. The corrected signatures are fused via maximum likelihood estimation, so as to obtain more accurate vehicle signatures. Examples show that the proposed algorithm can provide input parameters with higher accuracy. It 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%.
|
|
Received: 16 October 2013
Published: 06 May 2014
|
|
|
基于多传感器相关关系的车型重识别算法
研究目的：地磁传感器可以用于车型识别及分类。目前大多数地磁检测系统采用单一传感器节点进行识别。为了降低单一节点识别带来的误差，本文引入一种多节点组成的地磁传感器网络。通过研究各节点之间的信号相关关系及时空关联关系，结合特定交通流情况下的车型分类错误模型，探讨多传感器节点联合检测环境下的高精度车型分类重识别算法。
创新要点：本文介绍一种基于多节点的车型识别感知网络，通过对该网络组成成员的相关关系的分析，给出感知网络内各节点的时空关系模型，结合对实际工程使用中出现的误判断错误集的分类与纠偏，提供一种可靠的车型识别算法。
方法提亮：用于车型重识别的时空关联算法具有如下三个特点：一、有效提高现有算法车型识别的准确率（如表3中大型车辆的识别准确率对比）；二、能够准确辨识车辆停留在传感器节点上造成的错误；三、能避免传统检测方法中分由于两个小型车间距过小而识别为一个大车的错误。
重要结论：本文提出一种利用多传感器检测信号的相关关系对车型进行重识别的方法，能够为现有车型识别提供更加准确的输入参数，进而提高车型识别准确率。理论与实践证实，该方法利用多传感器对同一车辆进行多次识别，减小车型识别中因车距、车速、环境噪声等干扰造成的误差，可以有效解决现有识别算法中无法处理的错误，如车辆停留、两车粘滞等。
关键词：
车型分类,
重识别,
地磁传感器网络,
相关关系,
交叉匹配
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
