SenseMag: Enabling Low-Cost Traffic Monitoring Using Noninvasive Magnetic Sensing

被引:16
作者
Wang, Kafeng [1 ,2 ,3 ]
Xiong, Haoyi [4 ]
Zhang, Jie [5 ]
Chen, Hongyang [6 ]
Dou, Dejing [4 ]
Xu, Cheng-Zhong [7 ,8 ]
机构
[1] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China
[2] Chinese Acad Sci, Guangdong Hong Kong Macao Joint Lab Human Machine, Shenzhen 518055, Peoples R China
[3] Univ Chinese Acad Sci, Shenzhen 518055, Peoples R China
[4] Baidu Inc, Big Data Lab, Beijing 100085, Peoples R China
[5] Peking Univ, Key Lab High Confidence Software Technol, Beijing 100871, Peoples R China
[6] Zhejiang Lab, Res Ctr Intelligent Network, Hangzhou 311121, Peoples R China
[7] Univ Macau, State Key Lab Internet Things Smart City, Macau, Peoples R China
[8] Univ Macau, Dept Comp & Informat Sci, Macau, Peoples R China
关键词
Magnetic domains; Sensors; Magnetic sensors; Time-frequency analysis; Monitoring; Roads; Perpendicular magnetic anisotropy; Internet of Vehicles (IoV); magnetic sensing; traffic monitoring; vehicle-type classification; VEHICLE CLASSIFICATION; SENSORS; SYSTEM;
D O I
10.1109/JIOT.2021.3074907
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The operation and management of intelligent transportation systems (ITS), such as traffic monitoring, relies on real-time data aggregation of vehicular traffic information, including vehicular types (e.g., cars, trucks, and buses), in the critical roads and highways. While traditional approaches based on vehicular-embedded GPS sensors or camera networks would either invade drivers' privacy or require high deployment cost, this article introduces a low-cost method, namely, SenseMag, to recognize the vehicular type using a pair of noninvasive magnetic sensors deployed on the straight road section. SenseMag filters out noises and segments received magnetic signals by the exact time points that the vehicle arrives or departs from every sensor node. Furthermore, SenseMag adopts a hierarchical recognition model to first estimate the speed/velocity, then identify the length of the vehicle using the predicted speed, sampling cycles, and the distance between the sensor nodes. With the vehicle length identified and the temporal/spectral features extracted from the magnetic signals, SenseMag classifies the types of vehicles accordingly. Some semiautomated learning techniques have been adopted for the design of filters, features, and the choice of hyperparameters. Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i.e., seven types by SenseMag versus four types by the existing work in comparisons). To be specific, our field experiment results validate that SenseMag is with at least 90% vehicle type classification accuracy and less than 5% vehicle length classification error.
引用
收藏
页码:16666 / 16679
页数:14
相关论文
共 57 条
[1]   Measurement-Based Worst-Case Execution Time Estimation Using the Coefficient of Variation [J].
Abella, Jaume ;
Padilla, Maria ;
Del Castillo, Joan ;
Cazorla, Francisco J. .
ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS, 2017, 22 (04)
[2]   Application of probability distributions mixture of safety indicator in risk assessment problems [J].
Aleksandrovskaya, Lidiya N. ;
Ardalionova, Anna E. ;
Papic, Ljubisa .
INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT, 2019, 10 (SUPPL 1) :3-11
[3]   Intelligent Vehicle Counting and Classification Sensor for Real-Time Traffic Surveillance [J].
Balid, Walid ;
Tafish, Hasan ;
Refai, Hazem H. .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2018, 19 (06) :1784-1794
[4]   Development of Portable Wireless Sensor Network System For Real-time Traffic Surveillance [J].
Balid, Walid ;
Tafish, Hasan ;
Refai, Hazem H. .
2015 IEEE 18TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, :1630-1637
[5]   Traffic Vehicle Counting in Jam Flow Conditions Using Low-Cost and Energy-Efficient Wireless Magnetic Sensors [J].
Bao, Xu ;
Li, Haijian ;
Xu, Dongwei ;
Jia, Limin ;
Ran, Bin ;
Rong, Jian .
SENSORS, 2016, 16 (11)
[6]   A Probabilistic Approach to Improve the Accuracy of Axle-Based Automatic Vehicle Classifiers [J].
Bitar, Naim ;
Refai, Hazem H. .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2017, 18 (03) :537-544
[7]  
Burney A., 2017, Journal of Computer and Communications, V6, P275, DOI [DOI 10.4236/JCC.2018, 10.4236/jcc.2018]
[8]  
Caruso M. J., 1999, Proceedings SENSORS EXPO Baltimore, P477
[9]   Support vector machines for histogram-based image classification [J].
Chapelle, O ;
Haffner, P ;
Vapnik, VN .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05) :1055-1064
[10]   Neural Feature Search: A Neural Architecture for Automated Feature Engineering [J].
Chen, Xiangning ;
Lin, Qingwei ;
Luo, Chuan ;
Li, Xudong ;
Zhang, Hongyu ;
Xu, Yong ;
Dang, Yingnong ;
Sui, Kaixin ;
Zhang, Xu ;
Qiao, Bo ;
Zhang, Weiyi ;
Wu, Wei ;
Chintalapati, Murali ;
Zhang, Dongmei .
2019 19TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2019), 2019, :71-80