Wireless Magnetic Sensor Network for Road Traffic Monitoring and Vehicle Classification

This paper aims to improve the accuracy of automatic vehicle classifiers for imbalanced datasets. Classification is made through utilizing a single anisotropic magnetoresistive sensor, with the models of vehicles involved being classified into hatchbacks, sedans, buses, and multi-purpose vehicles (MPVs). Using time domain and frequency domain features in combination with three common classification algorithms in pattern recognition, we develop a novel feature extraction method for vehicle classification. These three common classification algorithms are the k-nearest neighbor, the support vector machine, and the back-propagation neural network. Nevertheless, a problem remains with the original vehicle magnetic dataset collected being imbalanced, and may lead to inaccurate classification results. With this in mind, we propose an approach called SMOTE, which can further boost the performance of classifiers. Experimental results show that the k-nearest neighbor (KNN) classifier with the SMOTE algorithm can reach a classification accuracy of 95.46%, thus minimizing the effect of the imbalance.

Section: Introductionmentioning

confidence: 99%

Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor

Chang

Wang

Bao

et al. 2018

“…A method for detection of passing vehicles with use of magnetometers was described in [ 20 ]. The most popular solutions based on the magnetic field sensors enable achieving accuracy of vehicles detection comparable to that of the other methods discussed in this Section [ 31 , 32 ]. However, it should be noted that these solutions require the sensors to be installed inside traffic lanes.…”

Section: Sensing Technologiesmentioning

confidence: 99%

A Survey and Comparison of Low-Cost Sensing Technologies for Road Traffic Monitoring

Bernaś

Płaczek

Korski

et al. 2018

This paper reviews low-cost vehicle and pedestrian detection methods and compares their accuracy. The main goal of this survey is to summarize the progress achieved to date and to help identify the sensing technologies that provide high detection accuracy and meet requirements related to cost and ease of installation. Special attention is paid to wireless battery-powered detectors of small dimensions that can be quickly and effortlessly installed alongside traffic lanes (on the side of a road or on a curb) without any additional supporting structures. The comparison of detection methods presented in this paper is based on results of experiments that were conducted with a variety of sensors in a wide range of configurations. During experiments various sensor sets were analyzed. It was shown that the detection accuracy can be significantly improved by fusing data from appropriately selected set of sensors. The experimental results reveal that accurate vehicle detection can be achieved by using sets of passive sensors. Application of active sensors was necessary to obtain satisfactory results in case of pedestrian detection.

“…The wireless vehicle detection systems using AMR magnetic field sensors are presented in the following works: the work described in [ 5 ] concerns the use of two linear arrays with 16 sensors set at a distance of 3 m and a multi-scale wavelet discontinuity detection method for determining the start and the end of a magnetic vehicle signature. This method bases on the quadratic spline wavelet transform and low-pass and high-pass filtering.…”

Section: Related Workmentioning

confidence: 99%

“…It is precisely for this reason that a vehicle detection with the use of AMR magnetic field sensors is more complicated compared to, e.g., inductive loops. However, it is possible to identify a type of vehicle [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Vehicle Speed and Length Estimation Using Data from Two Anisotropic Magneto-Resistive (AMR) Sensors

Markevičius

Navikas

Idźkowski

et al. 2017

Methods for estimating a car’s length are presented in this paper, as well as the results achieved by using a self-designed system equipped with two anisotropic magneto-resistive (AMR) sensors, which were placed on a road lane. The purpose of the research was to compare the lengths of mid-size cars, i.e., family cars (hatchbacks), saloons (sedans), station wagons and SUVs. Four methods were used in the research: a simple threshold based method, a threshold method based on moving average and standard deviation, a two-extreme-peak detection method and a method based on the amplitude and time normalization using linear extrapolation (or interpolation). The results were achieved by analyzing changes in the magnitude and in the absolute z-component of the magnetic field as well. The tests, which were performed in four different Earth directions, show differences in the values of estimated lengths. The magnitude-based results in the case when cars drove from the South to the North direction were even up to 1.2 m higher than the other results achieved using the threshold methods. Smaller differences in lengths were observed when the distances were measured between two extreme peaks in the car magnetic signatures. The results were summarized in tables and the errors of estimated lengths were presented. The maximal errors, related to real lengths, were up to 22%.