Vehicle Classification Based on Multi-Frequency Resistance and Reactance Magnetic Profiles

This paper presents the application of inductive loop (IL) sensor technology to classify vehicles in traffic lanes. Two wide and two slim IL sensors were installed in the traffic lane. The wide and slim IL sensors feature distinct structural designs and varying levels of sensitivity. An advanced multi-frequency impedance measurement (MFIM) system was used to operate the IL sensors. For a passing vehicle, the impedance of every IL sensor at three different operating frequencies is computed and finally recorded at a sampling frequency of 1 kHz. Each of the 12 recorded signals provides a complex-value vehicle magnetic profile (VMP). Based on the VMPs from two IL sensors positioned one after the other, an accurate measurement of vehicle speed is obtained. Furthermore, the system can capture images of vehicles. A reference database of VMPs was created for various vehicle categories. The software selects 10 statistical features from each real and imaginary VMP part. Eight machine learning algorithms were implemented using ready-made Python3 implementations. Cross-validation accuracy was tested for five feature configurations, including slim and wide IL sensors. The Random Forest (RF) algorithm, utilizing 20 features from the complex VMP, achieved an accuracy of 99.8 % for the wide IL sensor. No errors were made by the Voting Classifier and RF algorithm when they incorporated a fusion of features from complex VMPs with MFIM system, utilizing both slim and wide IL sensors.