JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE C

Accepted manuscript available online (unedited version)

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

Author(s): Yin Tian, Hong-hui Dong, Li-min Jia, Si-yu Li
Affiliation(s): State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, China; more
Corresponding email(s): 10114241@bjtu.edu.cn, lmjia@bjtu.edu.cn
Key Words: Vehicle re-identification, Magnetic sensor network, Correlation, Cross matching

Share this article to： More <<< Previous Paper \|Next Paper >>>

Yin Tian, Hong-hui Dong, Li-min Jia, Si-yu Li. A vehicle re-identification algorithm based on multi-sensor correlation[J]. Journal of Zhejiang University Science C,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.C1300291

@article{title="A vehicle re-identification algorithm based on multi-sensor correlation",
author="Yin Tian, Hong-hui Dong, Li-min Jia, Si-yu Li",
journal="Journal of Zhejiang University Science C",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.C1300291"
}

%0 Journal Article
%T A vehicle re-identification algorithm based on multi-sensor correlation
%A Yin Tian
%A Hong-hui Dong
%A Li-min Jia
%A Si-yu Li
%J Journal of Zhejiang University SCIENCE C
%P 372-382
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.C1300291"

TY - JOUR
T1 - A vehicle re-identification algorithm based on multi-sensor correlation
A1 - Yin Tian
A1 - Hong-hui Dong
A1 - Li-min Jia
A1 - Si-yu Li
J0 - Journal of Zhejiang University Science C
SP - 372
EP - 382
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.C1300291"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

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%.

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。

关键词组：车型分类；重识别；地磁传感器网络；相关关系；交叉匹配

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Abdulhai, B., Tabib, S.M., 2003. Spatio-temporal inductance-pattern recognition for vehicle re-identification. Transp. Res. Part C Emerg. Technol., 11(3):223-239.

[2]Ahmed, M.M., Abdel-Aty, M.A., 2012. The viability of using automatic vehicle identification data for real-time crash prediction. IEEE Trans. Intell. Transp. Syst., 13(2):459-468.

[3]Cheung, S.Y., Varaiya, P.P., 2007. Traffic Surveillance by Wireless Sensor Networks: Final Report. California PATH Program, Institute of Transportation Studies, University of California at Berkeley.

[4]Cheung, S.Y., Coleri, S., Dundar, B., et al., 2005. Traffic measurement and vehicle classification with single magnetic sensor. J. Transp. Res. Board, 1917(1):173-181.

[5]Coifman, B., 1998. Vehicle re-identification and travel time measurement in real-time on freeways using existing loop detector infrastructure. J. Transp. Res. Board, 1643(1):181-191.

[6]Fritsch, F.N., Carlson, R.E., 1980. Monotone piecewise cubic interpolation. SIAM J. Numer. Anal., 17(2):238-246.

[7]Gandhi, T., Trivedi, M.M., 2006. Panoramic appearance map (PAM) for multi-camera based person re-identification. IEEE Int. Conf. on Video and Signal Based Surveillance, p.78.

[8]Gunay, B., 2012. Using automatic number plate recognition technology to observe drivers’ headway preferences. J. Adv. Transp., 46(4):305-317.

[9]Haoui, A., Kavaler, R., Varaiya, P., 2008. Wireless magnetic sensors for traffic surveillance. Transp. Res. Part C Emerg. Technol., 16(3):294-306.

[10]Kaewkamnerd, S., Pongthornseri, R., Chinrungrueng, J., et al., 2009. Automatic vehicle classification using wireless magnetic sensor. IEEE Int. Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, p.420-424.

[11]Keawkamnerd, S., Chinrungrueng, J., Jaruchart, C., 2008. Vehicle classification with low computation magnetic sensor. 8th Int. Conf. on ITS Telecommunications, p.164-169.

[12]Kwong, K., Kavaler, R., Rajagopal, R., et al., 2009. Arterial travel time estimation based on vehicle re-identification using wireless magnetic sensors. Transp. Res. Part C Emerg. Technol., 17(6):586-606.

[13]Kwong, K., Kavaler, R., Rajagopal, R., et al., 2010. Real-time measurement of link vehicle count and travel time in a road network. IEEE Trans. Intell. Transp. Syst., 11(4):814-825.

[14]Lin, W.H., Tong, D., 2011. Vehicle re-identification with dynamic time windows for vehicle passage time estimation. IEEE Trans. Intell. Transp. Syst., 12(4):1057-1063.

[15]Lotufo, R.A., Morgan, A.D., Johnson, A.S., 1990. Automatic number-plate recognition. IEE Colloquium on Image Analysis for Transport Applications, p.6/1-6/6.

[16]Ndoye, M., Totten, V.F., Krogmeier, J.V., et al., 2011a. Sensing and signal processing for vehicle reidentification and travel time estimation. IEEE Trans. Intell. Transp. Syst., 12(1):119-131.

[17]Ndoye, M., Barker, A.M., Krogmeier, J.V., et al., 2011b. A recursive multiscale correlation-averaging algorithm for an automated distributed road-condition-monitoring system. IEEE Trans. Intell. Transp. Syst., 12(3):795-808.

[18]Sanchez, R.O., Flores, C., Horowitz, R., et al., 2011. Vehicle re-identification using wireless magnetic sensors: algorithm revision, modifications and performance analysis. IEEE Int. Conf. on Vehicular Electronics and Safety, p.226-231.

[19]Sharma, A., Bullock, D.M., Bonneson, J.A., 2007. Input-output and hybrid techniques for real-time prediction of delay and maximum queue length at signalized intersections. J. Transp. Res. Board, 2035(1):69-80.

[20]Tam, M.L., Lam, W.H., 2011. Application of automatic vehicle identification technology for real-time journey time estimation. Inform. Fusion, 12(1):11-19.

[21]Zhang, W., Tan, G., Ding, N., et al., 2008. Vehicle classification algorithm based on binary proximity magnetic sensors and neural network. 11th Int. IEEE Conf. on Intelligent Transportation Systems, p.145-150.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

基于多传感器相关关系的车型重识别算法

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference