Vehicle classification based on magnetic sensor signal

Abstract

We extend our work in vehicle classification proposed in [6] and [7]. Our system is based on a low complexity wireless sensor network. The system consists of a low power microprocessor together with AMR magnetic sensors and an RF transceiver. Two AMR magnetic sensors are employed to extracts dominant low-complexity features including vehicle count, speed, length, Hill-pattern peaks, and normalized energy. These features are studied in [6] and [7] and yield a promising result when vehicle classification is based on sizes (96%). However, when classification of similar sizes, e.g. cars, vans, pickup trucks are studied. The results are relatively lower at 77%. The contribution of this paper include (1) the implementation of feature extraction (count, speed, length) on sensor board and (2) the study for additional different lowcomplexity features such that better classification rate of small vehicles is obtained. These features include Hill-pattern peaks and magnetic signal differential energy normalized to the vehicle speed and length. This paper proposed vehicle classification tree based on above extraction features. Our work focuses on low computational feature extraction and classification processes suitable for implementing on micro-controller. The same data set employed in [7] is analyzed. The classification yields promising improved results over [6] and [7]. The classification rate yield 100 percent for motorcycle, 82.46 percent for car, 78.57 percent for van and 65.71 percent for pickup. The overall accuracy is 81.69 percent.

Decision tree-based machine learning algorithm for in-node vehicle classification

“…The work detailed in [6] and [7] uses two AMR sensors attached to a microcontroller. Their algorithm is based on a decision tree with the data obtained by extracting various features from the signal received from the AMR sensors.…”

Vehicle classification by estimation of the direction angle in a mixed traffic flow

“…The vehicle classification can help monitor traffic flow on the roadway lanes corresponding to each type of vehicle. An approach using magnetic fields and radio waves studies the vehicle size, where cameras are mounted in each lane to monitor vehicle behaviour and therefore this solution seems to be expensive and inappropriate for multiple line roadways, and unwieldy operation [2]. Another method in [3][4] also investigate vehicle size, however applicable for car or non-cars only and not including motorcycles.…”

Application and Modeling of a Magnetic WSN for Target Localization

“…For examp le, WSNs have been proposed for the estimation of road traffic patterns and traffic measurement, object detection schemes [1], [2] and intelligent traffic guidance systems [3], [4]. In particular, object classification was done by magnetic sensors in [2], [5], [6]. In these studies target identification is based on magnetic signatures of the ferro magnetic objects.…”