Feasibility of road vibrations-based vehicle property sensing

Hostettler, Roland; Birk, Wolfgang; Nordenvaad, Magnus Lundberg

doi:10.1049/iet-its.2010.0046

Cited by 25 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The plotted signal is the raw output from the sensor, without any applied signal processing, such as filtering. By applying filtering techniques, the presence of a nearby vehicle could be detected [35].…”

Section: Vehicle Detectionmentioning

confidence: 99%

A feasibility study of SOA-enabled networked rock bolts

Eliasson

Pereira

Mäkitaavola

et al. 2014

Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA)

View full text Add to dashboard Cite

Abstract-The use of rock bolts in the mining industry is a widely used approach for increasing mine stability. However, when compared to the automation industry, where the use of sensors and real-time monitoring of processes have evolved rapidly, the use rock bolts have not changed a lot during the last 100 years. What is missing are technologies for keeping installed rock bolts under real-time and online monitoring. One problem is that rock bolts can become damaged by seismic activities or movements within the rock, and thus lose their load bearing capacity. If that happens, the outer shell of a tunnel's walls or ceiling can collapse, with disaster as a result. Therefore, there is a clear need for online and real-time monitoring solutions for strain and thereby stress, as well as seismic activity.In this paper, the current state of art in research around intelligent rock bolts is presented. An intelligent rock bolt is the combination of a traditional rock bolt with an Internet of Things device, i.e. a rock bolt with embedded sensors, actuators, processing capabilities and wireless communication. In the proposed architecture, every rock bolt has its own IPv6 address and can establish a wireless mesh network in an ad-hoc manner. By measuring strain and seismic activity and exposing the sensors in the form of services, large gains in terms of safety and efficiently can be achieved. A number of mining related activities such as stress on the rock bolt can be detected, falling rocks and the presence of mobile machinery can be observed. Since the network is based on standard communication protocols such as IPv6, it is vital to add security mechanisms to prevent eavesdropping and tampering of data traffic.By utilizing the real-time monitoring capabilities of a network of Internet-connected intelligent rock bolt, it is possible to drastically improve monitoring of mining activities and thereby providing workers with a safer working environment.

show abstract

Section: Vehicle Detectionmentioning

confidence: 99%

A feasibility study of SOA-enabled networked rock bolts

Eliasson

Pereira

Mäkitaavola

et al. 2014

Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA)

View full text Add to dashboard Cite

show abstract

“…Furthermore, in [7] it was shown how to use a road-surface mounted micro accelerometer and a neural networks-based algorithm to distinguish between diesel, gasoline, and heavy diesel engine vehicles using the frequency spectrum genereted by a passing vehicle. The works in [8], [9] also used accelerometer-based vehicle detection. The authors developed a peak detection algorithm to detect individual vehicle axles followed by a table lookup.…”

Section: Introductionmentioning

confidence: 99%

Vehicle classification using road side sensors and feature-free data smashing approach

Kleyko

Hostettler

Lyamin

et al. 2016

2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

. Vehicle classification using road side sensors and feature-free data smashing approach. In 2016 IEEE 19th International Conference on Intelligent Transportation Systems, ITSC 2016 (pp. 1988-1993 Abstract-The main contribution of this paper is a study of the applicability of data smashing -a recently proposed data mining method -for vehicle classification according to the "Nordic system for intelligent classification of vehicles" standard, using measurements of road surface vibrations and magnetic field disturbances caused by passing vehicles. The main advantage of the studied classification approach is that it, in contrast to the most of traditional machine learning algorithms, does not require the extraction of features from raw signals. The proposed classification approach was evaluated on a large dataset consisting of signals from 3074 vehicles. Hence, a good estimate of the actual classification rate was obtained. The performance was compared to the previously reported results on the same problem for logistic regression. Our results show the potential trade-off between classification accuracy and classification method's development efforts could be achieved.

show abstract

“…Recently, solutions that employ low-cost, low-complexity sensors such as microphones [10], [13], magnetometers [14], [15], or accelerometers [16] have emerged.…”

Section: Introductionmentioning

confidence: 99%

“…In this work, we address vehicle tracking by combining magnetometer and accelerometer measurements in a single sensor unit that is mounted on the road surface as illustrated in [16]. Even though tracking using individual sensors has been addressed before [14]- [16], the combination of the two sensors has not been considered yet.…”

Section: Introductionmentioning

confidence: 99%

Vehicle Tracking Based on Fusion of Magnetometer and Accelerometer Sensor Measurements With Particle Filtering

Hostettler

Djurić

2015

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

This is a post-print of a paper published in IEEE Transactions on Vehicular Technology. When citing this work, you must always cite the original article:R. Hostettler and P. M. Djurić, "Vehicle tracking based on fusion of magnetometer and accelerometer sensor measurements with particle filtering," Vehicular Technology, IEEE Transactions on, vol. 64,no. 11, Abstract-In this article, we propose a method for vehicle tracking on roadways using measurements of magnetometers and accelerometers. The measurements are used to build a low-cost, low-complexity vehicle tracking sensor platform for highway traffic monitoring. First, the problem is formulated by introducing the process model for the motion of the vehicle on the road and two measurement models, one for each of the sensors. Second, it is shown how the measurements of the sensors can be fused using particle filtering. The standard sampling importance resampling (SIR) particle filter is extended for processing of multi-rate sensor measurements and models that employ unknown static parameters. The latter are treated by Rao-Blackwellization. The performance of the method is demonstrated by computer simulations. It is found that it is feasible to fuse the two sensors for vehicle tracking and that the proposed multi-rate particle filter performs better than particle filters that process only measurements of one of the sensors. The main contribution of this paper is the novel approach of fusing the measurements of road-mounted magnetometers and accelerometers for vehicle tracking and traffic monitoring.

show abstract

Feasibility of road vibrations-based vehicle property sensing

Cited by 25 publications

References 12 publications

A feasibility study of SOA-enabled networked rock bolts

A feasibility study of SOA-enabled networked rock bolts

Vehicle classification using road side sensors and feature-free data smashing approach

Vehicle Tracking Based on Fusion of Magnetometer and Accelerometer Sensor Measurements With Particle Filtering

Contact Info

Product

Resources

About