A Cross-Correlation Technique for Vehicle Detections in Wireless Magnetic Sensor Network
TL;DR: This work proposes two vehicle detection algorithms based on a cross-correlation technique in wireless magnetic sensor networks for on-street parking detection and vehicle speed estimation (VSE).
Abstract: Vehicle detections are an important research field and attract many researchers. Most research efforts have been focused on vehicle parking detection (VPD) in indoor parking lot. For on-street parking, strong noise disturbances affect detection accuracy. To deal with vehicle detections in on-street environment, we propose two vehicle detection algorithms based on a cross-correlation technique in wireless magnetic sensor networks. One is for VPD, and the other one is for vehicle speed estimation (VSE). The proposed VPD algorithm combines the state-machine detection and the cross-correlation detection. In the VSE, speed estimation is based on the calculation of the normalized cross correlation between the signals of two sensors along the road with a certain spacing. Experimental results show that the VPD has an accuracy of 99.65% for arrival and 99.44% for departure, while the VSE has an accuracy of 92%.
Citations
More filters
TL;DR: The experimental results reveal that accurate vehicle detection can be achieved by using sets of passive sensors, and that the detection accuracy can be significantly improved by fusing data from appropriately selected set of sensors.
Abstract: This paper reviews low-cost vehicle and pedestrian detection methods and compares their accuracy. The main goal of this survey is to summarize the progress achieved to date and to help identify the sensing technologies that provide high detection accuracy and meet requirements related to cost and ease of installation. Special attention is paid to wireless battery-powered detectors of small dimensions that can be quickly and effortlessly installed alongside traffic lanes (on the side of a road or on a curb) without any additional supporting structures. The comparison of detection methods presented in this paper is based on results of experiments that were conducted with a variety of sensors in a wide range of configurations. During experiments various sensor sets were analyzed. It was shown that the detection accuracy can be significantly improved by fusing data from appropriately selected set of sensors. The experimental results reveal that accurate vehicle detection can be achieved by using sets of passive sensors. Application of active sensors was necessary to obtain satisfactory results in case of pedestrian detection.
62 citations
Cites methods from "A Cross-Correlation Technique for V..."
...The wireless nodes with magnetic sensors have been also applied for parking vehicle detection in on-street parking [37]....
[...]
TL;DR: Successful applications of individual spintronic sensors in electrical current sensing, transmission and distribution lines monitoring, vehicle detection, and biodetection that can help to fulfill the promises of smart living in energy management, power delivery, transport, and healthcare are reviewed.
Abstract: Smart living is a trending and connected lifestyle that envisions efficient and sustainable energy utilization, stable and reliable power supply, intelligent and coordinated transportation and mobility, and personalized and cost-effective healthcare. Its realization needs the Internet of Things (IoT). IoT is a compelling platform connecting trillions of sensors and collecting data for connectivity and analytics. It is more advanced than traditional monitoring systems where limited sensors and wired communication can merely collect fragmented data in the application domains. Spintronic sensors with the superb measuring ability and multiple unique advantages can be one of the critical sensing devices supporting the IoT and enabling smart living. In this paper, we review successful applications of individual spintronic sensors in electrical current sensing, transmission and distribution lines monitoring, vehicle detection, and biodetection that can help to fulfill the promises of smart living in energy management, power delivery, transport, and healthcare. The wireless spintronic sensor networks (WSSNs) working at the massive interconnected network level are proposed and illustrated to provide pervasive monitoring systems, which facilitate the intelligent surveillance and management over building, power grid, transport, and healthcare. The database of collected information will be of great use to policy making in public services and city planning. This paper provides insights for realizing smart living through the integration of IoT with spintronic sensor technology.
46 citations
Cites background or methods from "A Cross-Correlation Technique for V..."
...(b) Magnetic field reading when a vehicle passes over a triaxial AMR sensor (permission obtained from [75])....
[...]
...Meanwhile, several other algorithms in recent literature including threshold-based algorithms, state machine algorithms, and cross-correlation-based algorithms have been proposed with good results [75], [76], [82], [83]....
[...]
...In [75], the magnetic signature of a vehicle is described as a magnetic point dipole with a magnetic moment m centered...
[...]
...Vehicle detectors based on spintronic sensors including AMR, GMR, and TMR sensors have been widely used for vehicle detection applications [72]–[75]....
[...]
...For the vehicle speed estimation, at least two sensor nodes (S1 and S2) are employed [75], [84], as shown in Fig....
[...]
01 Jan 2019
TL;DR: Experimental results in container terminal show that the fusion algorithm with regional clustering and two-stage SVM has higher efficiency and better truck recognition performance.
Abstract: With large-scale, integrated, intelligence for ports, many ports begin to use intelligent detection systems to make their operations more efficient. The container truck recognition and positioning system is also beginning to apply into container quayside to assist the joint operations between quay cranes and container trucks. However, the traditional vehicle detection by using motion region detection cannot recognize the type of moving object, and the traditional pattern recognition method cannot meet the requirements in real-time operation. In order to solve these problems, an algorithm fused by regional clustering and two-stage SVM classifier is proposed in this paper. The method consists of two phases, which are independently executed in two camera systems on quay cranes. In the first stage, a fast motion regional clustering algorithm is used to detect moving image patches as the truck candidate sub-windows. In the second stage, the container trucks will be recognized in these sub-windows by an optimized two-stage SVM classifier. Compared with existing traditional algorithm, experimental results in container terminal show that the fusion algorithm with regional clustering and two-stage SVM has higher efficiency and better truck recognition performance.
40 citations
Cites background from "A Cross-Correlation Technique for V..."
...Qifan Wei and Hongmei Zhu et al used magnetic sensors to detect and track vehicles in the roads [22, 28]....
[...]
TL;DR: This paper designs a reinforcement learning based mechanism to perform QoS and energy balanced routing according to the knowledge of reliability and delay in WMSN, and shows that the energy consumption is reduced while ensuring QoS compared with the traditional cooperative protocol and the distributed adaptive cooperative routing protocol.
36 citations
TL;DR: Methods for estimating a car’s length are presented in this paper, as well as the results achieved by using a self-designed system equipped with two anisotropic magneto-resistive (AMR) sensors, which were placed on a road lane.
Abstract: Methods for estimating a car's length are presented in this paper, as well as the results achieved by using a self-designed system equipped with two anisotropic magneto-resistive (AMR) sensors, which were placed on a road lane. The purpose of the research was to compare the lengths of mid-size cars, i.e., family cars (hatchbacks), saloons (sedans), station wagons and SUVs. Four methods were used in the research: a simple threshold based method, a threshold method based on moving average and standard deviation, a two-extreme-peak detection method and a method based on the amplitude and time normalization using linear extrapolation (or interpolation). The results were achieved by analyzing changes in the magnitude and in the absolute z-component of the magnetic field as well. The tests, which were performed in four different Earth directions, show differences in the values of estimated lengths. The magnitude-based results in the case when cars drove from the South to the North direction were even up to 1.2 m higher than the other results achieved using the threshold methods. Smaller differences in lengths were observed when the distances were measured between two extreme peaks in the car magnetic signatures. The results were summarized in tables and the errors of estimated lengths were presented. The maximal errors, related to real lengths, were up to 22%.
23 citations
Additional excerpts
...In the literature a 40 mG [14] or 60 mG [15] signal threshold was chosen to detect a car due to the interference induced by moving vehicles on the adjacent lanes....
[...]
References
More filters
Journal Article•
TL;DR: A robust real-time vehicle detection algorithm for both sensors was developed, and the magnetic sensor was shown to be superior to the acoustic sensor, allowing the wireless sensor network system to be scalable and deployable everywhere in the traffic networks.
Abstract: This report describes the prototype design, development, analysis and performance of a traffic surveillance system that is based on wireless sensor networks. Vehicle classification and reidentification schemes for low-cost, low-power platforms with limited computation resources were developed and tested. Both acoustic and magnetic sensors were tested. A robust real-time vehicle detection algorithm for both sensors was developed, and the magnetic sensor was shown to be superior to the acoustic sensor. The detection accuracy was shown to be comparable to that of inductive loop detectors while also having a much higher configuration flexibility, thus allowing the wireless sensor network system to be scalable and deployable everywhere in the traffic networks.
186 citations
"A Cross-Correlation Technique for V..." refers methods in this paper
...A crosscorrelation-based method was proposed in [17] for on-street vehicle detection....
[...]
TL;DR: Sensys Networks' VDS240 vehicle detection system is a wireless sensor network composed of a collection of sensors put in the center of a lane and a access point (AP) box placed 15' high on the side of the road that measures changes in the earth's magnetic field induced by a vehicle.
Abstract: Sensys Networks’ VDS240 vehicle detection system is a wireless sensor network composed of a collection of 3″ by 3″ by 2″ sensor nodes put in the center of a lane and a 6″ by 4″ by 4″ access point (AP) box placed 15′ high on the side of the road. A node measures changes in the earth’s magnetic field induced by a vehicle, processes the measurements to detect the vehicle, and transfers the processed data via radio to the AP. The AP combines data from the nodes into information for the local controller or the Traffic Management Center (TMC). An AP communicates via radio directly with up to 96 nodes within a range of 150′; a Repeater extends the range to 1000′. This range makes it suitable to deploy VDS240 networks for traffic counts, stop-bar and advance detection, and measurement of queue lengths on ramps and at intersections, as well as parking guidance and enforcement. VDS240 is self-calibrating, IP-addressable and remotely monitored. Data are not lost because unacknowledged data packets are retransmitted. The accuracy of VDS240 for vehicle counts, speed and occupancy is comparable to that of well-tuned loops. Because the nodes report individual vehicle events, the AP also calculates individual vehicle lengths, speeds and inter-vehicle headways—measurements that can be used for new traffic applications. In July 2007, VDS240 systems were deployed in arterials and freeways in several cities and states, and 30 customer trials were underway in the US, Australia, Europe and South Africa.
179 citations
"A Cross-Correlation Technique for V..." refers background in this paper
...However, most of these solutions are based on threshold criteria, including simple threshold solution [10], [11] and state-machine solution [12], [13]....
[...]
TL;DR: A vehicle detector which includes a magnetic and an optical sensor and is intended as sensor node for use with a WSN, combined with power-efficient event-based software is presented.
Abstract: Vehicle detectors provide essential information about parking occupancy and traffic flow. To cover large areas that lack a suitable electrical infrastructure, wired sensors networks are impractical because of their high deployment and maintenance costs. Wireless sensor networks (WSNs) with autonomous sensor nodes can be more economical. Vehicle detectors intended for a WSN should be small, sturdy, low power, cost-effective, and easy to install and maintain. Currently available vehicle detectors based on inductive loops, ultrasound, infrared, or magnetic sensors do not fulfill the requirements above, which has led to the search for alternative solutions. This paper presents a vehicle detector which includes a magnetic and an optical sensor and is intended as sensor node for use with a WSN. Magnetic sensors based on magnetoresistors are very sensitive and can detect the magnetic anomaly in the Earth's magnetic field that results from the presence of a car, but their continuous operation would drain more than 1.5 mA at 3 V, hence limiting the autonomy of a battery-supplied sensor node. Passive, low-power optical sensors can detect the shadow cast by car that covers them, but are prone to false detections. The use of optical triggering to wake-up a magnetic sensor, combined with power-efficient event-based software, yields a simple, compact, reliable, low-power sensor node for vehicle detection whose quiescent current drain is 5.5 μA. This approach of using a low-power sensor to trigger a second more specific sensor can be applied to other autonomous sensor nodes.
154 citations
"A Cross-Correlation Technique for V..." refers background in this paper
...This disturbance can be detected by a magnetic sensor [21]....
[...]
TL;DR: It is shown that the sensor system can be used to reliably count the number of right turns at an intersection, with an accuracy of 95% and is compact, portable, wireless, and inexpensive.
Abstract: This paper focuses on the development of a portable roadside magnetic sensor system for vehicle counting, classification, and speed measurement. The sensor system consists of wireless anisotropic magnetic devices that do not require to be embedded in the roadway-the devices are placed next to the roadway and measure traffic in the immediately adjacent lane. An algorithm based on a magnetic field model is proposed to make the system robust to the errors created by larger vehicles driving in the nonadjacent lane. These false calls cause an 8% error if uncorrected. The use of the proposed algorithm reduces this error to only 1%. Speed measurement is based on the calculation of the cross correlation between longitudinally spaced sensors. Fast computation of the cross correlation is enabled by using frequency-domain signal processing techniques. An algorithm for automatically correcting for any small misalignment of the sensors is utilized. A high-accuracy differential Global Positioning System is used as a reference to measure vehicle speeds to evaluate the accuracy of the speed measurement from the new sensor system. The results show that the maximum error of the speed estimates is less than 2.5% over the entire range of 5-27 m/s (11-60 mi/h). Vehicle classification is done based on the magnetic length and an estimate of the average vertical magnetic height of the vehicle. Vehicle length is estimated from the product of occupancy and estimated speed. The average vertical magnetic height is estimated using two magnetic sensors that are vertically spaced by 0.25 m. Finally, it is shown that the sensor system can be used to reliably count the number of right turns at an intersection, with an accuracy of 95%. The developed sensor system is compact, portable, wireless, and inexpensive. Data are presented from a large number of vehicles on a regular busy urban road in the Twin Cities, MN, USA.
145 citations
TL;DR: In this article, the detection of a moving ferromagnetic target using a static three-axis referenced magnetometer has been studied using orthonormal basis functions, out of which the dominant basis function is chosen as the detector, which provides output responses to any target magnetic moment orientation.
Abstract: Magnetic anomaly detection is a good method for detecting ferromagnetic objects, particularly hidden targets. In this work, we address the detection of a moving ferromagnetic target using a static three-axis referenced magnetometer. The analysis and the results are also applicable to the converse case of a static ferromagnetic target and a moving three-axis referenced magnetometer. We use the three magnetometer outputs to build a total magnetic field of the target. This signal is decomposed into a set of orthonormal basis functions, out of which the dominant basis function is chosen as the detector. The detector provides output responses to any target magnetic moment orientation. We support the analysis by a computer simulation and real-world experimental results. The high detection probability and the simple implementation of the proposed method make it attractive for real-time applications.
109 citations
"A Cross-Correlation Technique for V..." refers background in this paper
...In contrast to other solutions, magnetic sensor is quite small, sensitive, and immune to environment noise such as fog, rain, and wind [7]....
[...]