A Machine Learning Method for Vehicle Classification by Inductive Waveform Analysis
Bruno R. Vasconcellos, Marcelo Rudek, Marcelo de Souza
Abstract
The classification of vehicles is a matter of great importance for traffic control and management, helping with traffic surveillance as well as in statistical data collection. Among the several vehicular classification techniques, the most popular uses inductive loop sensors, because they achieve high accuracy rate at low cost. This paper proposes 5 different vehicle classification models by inductive waveform analysis: KNN, SVC, Decision Tree, Random Forest, and Voting Classifier. A brief introduction to the mathematical basis of these models and the main forms of vehicle detection are also presented. The obtained results reached an accuracy of 94% and showed how inductive waveform analysis is still a valid option for vehicle classification.