Vehicle classification by acoustic signature

Nooralahiyan, Amir Y.; Kirby, H R; McKeown, Denis

doi:10.1016/s0895-7177(98)00060-0

Cited by 52 publications

(23 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Anisotropic magnetoresistive sensor (AMR) and microphone sensor were used to investigate the vehicles road direction detection and traffic situation of any road [6]. In addition, a wireless sensor with a magnetometer sensor was used using an acoustic sensor [7], an ultrasonic sensor [8], and video camera analysis systems or ariel images [9]. The detected magnetic field over a certain threshold value was measured on the time axis as a signal, Vehicle detection and various applications like monitoring parking system of the vehicle or vehicles moving on the roads have been developed [10].…”

Section: Related Workmentioning

confidence: 99%

Detection of the Vehicle Direction with Adaptive Threshold Algorithm Using Magnetic Sensor Nodes

Vançin¹,

Erdem²

2018

Journal of Polytechnic

View full text Add to dashboard Cite

Bu makaleye şu şekilde atıfta bulunabilirsiniz(To cite to this article): Vancin S. and Erdem E.," Detection of the vehicle direction with adaptive threshold algorithm using magnetic sensor nodes", Politeknik Dergisi, 21(2): 333-340, (2018).Erişim linki (To link to this article): http://dergipark.gov.tr/politeknik/archive DOI: 10.2339/politeknik.389586 Politeknik Dergisi, 2018;21(2):333-340 Journal of Polytechnic, 2018;21(2):333-340 ABSTRACTIn this paper, we describe how, so as to perform vehicles direction detection in road traffic using proposed method along with the average-constant threshold and contributions of adaptive threshold detection algorithm (ATDA) thanks to special-purpose sensor nodes integrated with magnetic sensors. In this study, proposed algorithm with the adaptive threshold value as a magnetic resultant force has produced more pronounced and precise results than the average-fix threshold value. In this mean, it is clear that detected adaptive threshold generates more correct result for the systems like vehicle existence, direction assignment, and speed detection in different grounds where magnetic field is changeable as a result of environmental measurements. The direction of motion of the vehicles on the x-axis was determined as well as whether it was from left to right or from right to left, and the results were 97% average accurate. The simplicity of the proposed algorithms, the absence of any complex computations, the low cost of the sensor node and integration and the low power depletetion of the communication system show the avantage of this system in comparison with the other studies.Keywords: Wireless sensor networks, magnetic sensor, adaptive threshold detection algorithm (ATDA), vehicle direction detection. ÖZ Bu çalışmada, manyetik algılayıcılarla entegre özel amaçlı sensör düğümleri sayesinde, ortalama sabit eşik ve adaptif eşik algılama algoritmasının (ATDA) katkılarıyla birlikte, önerilen yöntem kullanılarak trafik yollarında araç yönü algılamasının nasıl yapılacağı anlatılmaktadır. Bu çalışmada uyarlanabilir eşik değeri manyetik sonuç kuvveti olarak önerilen algoritma, ortalama düzeltme eşiği değerinden daha belirgin ve kesin sonuçlar vermiştir. Bu anlamda, tespit edilen uyarlanabilir eşik, çevresel ölçümler sonucunda manyetik alanın değiştirilebildiği farklı gerekçelerdeki araç varlığı, yön tahsisi ve hız tespiti gibi sistemler için daha doğru sonuç ürettiği açıktır. Araçların x-ekseni üzerindeki hareket yönü, soldan sağa mı yoksa soldan sağa mı doğru belirlendi ve sonuçların ortalaması% 97 çıkmıştır. Önerilen algoritmaların basitliği, herhangi bir karmaşık hesaplamanın olmaması, sensör düğümünün düşük maliyeti ve entegrasyon ve iletişim sisteminin düşük güç tükenmesi diğer çalışmalara kıyasla bu sistemin avantajını göstermektedir.

show abstract

Section: Related Workmentioning

confidence: 99%

Detection of the Vehicle Direction with Adaptive Threshold Algorithm Using Magnetic Sensor Nodes

Vançin¹,

Erdem²

2018

Journal of Polytechnic

View full text Add to dashboard Cite

show abstract

“…The second method is that in MATLAB we have a toolbox named as MIR toolbox which was designed to process and analyze the signals. Using MIR toolbox we can easily extract the features of the audio file [4]. After training the machine with bike, truck and car data it forms classes depending on the labels given Fig.…”

Section: VImentioning

confidence: 99%

Vehicle Acoustic Signal Classification Using Machine Learning Algorithms

Kodali¹

2017

IJRASET

View full text Add to dashboard Cite

Acoustic signals are vibrations in air produced by the movement of non-living objects in our daily life. These can be due to vehicles, turbines, machines and so many different objects. Classification can be done using Machine Learning techniques where we train the machine with some training data whose labels are known and get the class or label of test data whose class is not known. There are many pre-defined classification algorithms like KNN, SVM, RANDOM FORESTS, etc. In this project we are using KNN, Decision tree, NAÏVE BAYES for classification purpose. As Acoustic signal is a vast topic, here our application of acoustic signals is in vehicle classification. By using microphone we collect large amount of train data and classify vehicles depending on that data. We discuss further in the introduction part.

show abstract

“…They are generally mounted overhead or to the side of the pavement, often on pre-existing structures. Most of these sensors are cost competitive with inductive loop detectors, if not cheaper [49]. & Video image detection systems: Closed-circuit television (CCTV) cameras record traffic images, which are in turn analyzed by machine vision software to monitor freeway conditions, collect data at intersections for traffic control purposes, detect incidents and classify vehicles.…”

Section: Point Sensorsmentioning

confidence: 99%

A Synthesis of emerging data collection technologies and their impact on traffic management applications

Antoniou

Balakrishna²,

Koutsopoulos

2011

Eur. Transp. Res. Rev.

View full text Add to dashboard Cite

Purpose The objective of this research is to provide an overview of emerging data collection technologies and their impact on traffic management applications. Methods Several existing and emerging surveillance technologies are being used for traffic data collection. Each of these technologies has different technical characteristics and operating principles, which determine the types of data collected, accuracy of the measurements, levels of maturity, feasibility and cost, and network coverage. This paper reviews the different sources of traffic surveillance data currently employed, and the types of traffic management applications they may support. Results Automated Vehicle Identification data have several applications in traffic management and many more are certain to emerge as these data become more widely available, reliable, and accessible. Representative examples in this field are presented. Furthermore, the fusion of condition information with traffic data can result in better and more responsive dynamic traffic management applications with a richer data background. ConclusionsThe current state-of-the-art of traffic modeling is discussed, in the context of using emerging data sources for better planning, operations and dynamic management of road networks.

show abstract

Vehicle classification by acoustic signature

Cited by 52 publications

References 2 publications

Detection of the Vehicle Direction with Adaptive Threshold Algorithm Using Magnetic Sensor Nodes

Detection of the Vehicle Direction with Adaptive Threshold Algorithm Using Magnetic Sensor Nodes

Vehicle Acoustic Signal Classification Using Machine Learning Algorithms

A Synthesis of emerging data collection technologies and their impact on traffic management applications

Contact Info

Product

Resources

About