Vehicle Detection and Classification for Low-Speed Congested Traffic With Anisotropic Magnetoresistive Sensor

Abstract

A vehicle detection and classification system has been developed based on a low-cost triaxial anisotropic magnetoresistive sensor. Considering the characteristics of vehicle magnetic detection signals, especially the signals for low-speed congested traffic in large cities, a novel fixed threshold state machine algorithm based on signal variance is proposed to detect vehicles within a single lane and segment the vehicle signals effectively according to the time information of vehicles entering and leaving the sensor monitoring area. In our experiments, five signal features are extracted, including the signal duration, signal energy, average energy of the signal, ratio of positive and negative energy of x-axis signal, and ratio of positive and negative energy of y-axis signal. Furthermore, the detected vehicles are classified into motorcycles, two-box cars, saloon cars, buses, and Sport Utility Vehicle commercial vehicles based on a classification tree model. The experimental results have shown that the detection accuracy of the proposed algorithm can reach up to 99.05% and the average classification accuracy is 93.66%, which verify the effectiveness of our algorithm for low-speed congested traffic.

A novel dual microwave Doppler radar based vehicle detection sensor for parking lot occupancy detection

“…In these traditional detection methods, cable required systems, such as ultrasonic or camera based solution, has high detection accuracy but suffers from the inconvenience of installation and high infrastructure cost [6]. The magnetometer vehicle detect sensor, which is based on measurement of the earth's magnetic field disturbances caused by a vehicle, has advantages of easy installation, low cost and small size [7,8,9]. However, its detection accuracy could be easily influenced by environmental factors such as background magnetic field drifting, nearby ferromagnetic objects interference and difference of vehicle material [10,11].…”

Research on Vehicle Classification Algorithm Based on Information Fusion of Dual Reluctance Sensor

“…SaowaluckKaekamnerd et al proposed the hierarchical decision tree classification algorithm, which is suitable for micro controller and has small calculation, by analyzing the characteristics of geomagnetic vehicle signal [2,3].BogenCai et al proposed a vehicle classification algorithm based on support vector machine by extracting the feature vector [4,5]. Soner Meta et al used BP neural network algorithm for vehicle classification, regarding feature vector obtained from acquisition waveform as the input of algorithm [6].…”

Traffic Vehicle Counting in Jam Flow Conditions Using Low-Cost and Energy-Efficient Wireless Magnetic Sensors

“…Magnetic sensors have several excellent advantages; they are low-cost, energy-efficient, small, wireless, and weather-independent sensors. Traffic surveillance by magnetic technology and corresponding wireless sensor networks have been proposed and implemented in related research areas, especially vehicle detection and counting [9,10,11,12,13,16,17,18,19,20], speed estimation [10,11,12], and vehicle classification [10,11,13,19,21,22,23,24]. …”

“…Thus, traffic vehicle counting in jam flow conditions will be a significant and practical topic. For low-speed congested traffic in large cities, Yang and Lei [19] proposed a fixed-threshold-state machine algorithm that is based on signal variance to detect vehicles within a single lane. The lack of vehicle samplings in their experiment is very effective for verifying their algorithm.…”