scholarly journals A Noise Robust Automatic Radiolocation Animal Tracking System

2021 ◽  
Author(s):  
Liang Wang ◽  
Foivos Diakogiannis ◽  
Scott Mills ◽  
Nigel Bajema ◽  
Ian Atkinson ◽  
...  
Keyword(s):  
Standard Deviation ◽  
Learning Algorithm ◽  
Tracking System ◽  
Sensor Arrays ◽  
Semantic Segmentation ◽  
Satellite System ◽  
Deep Learning Algorithm ◽  
Small Primary ◽  
Noise Robust ◽  
Global Navigation Satellite

Abstract Agriculture is becoming increasingly reliant upon accurate data from sensor arrays, with localization an emerging application in the livestock industry. Ground-based Time Difference of Arrival (TDoA) radiolocation methods have the advantage of being lightweight and exhibit higher energy effciency than methods reliant upon Global Navigation Satellite System (GNSS). Such methods can employ small primary cell batteries, rather than rechargeable cells, and still deliver a multi-year deployment. In this paper, we present a novel deep learning algorithm adapted from a one dimensional U-Net like a convolutional neural network (CNN) model, originally developed for the task of semantic segmentation. This model both converts TDoA sequences directly to positions and reduces positional errors introduced by sources such as multipathing. We have evaluated the model by using simulated animal movements in the form of TDoA position sequences in combination with known distributions of TDoA error. When errors with a standard deviation of 50 m and 100 m are added to simulated TDoA transmissions the model is able to reduce this error to 22 m and 27 m (RMSE) respectively. Without correction, the standard deviation of these errors is on the order of 90 and 200 m. Accordingly, the model can reduce the error by greater than 80 m (> 80%), demonstrating the effectiveness of this novel 1D CNN U-Net like encoder/decoder for error correction of TDoA position estimates.

scholarly journals A noise robust automatic radiolocation animal tracking system

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Liang Wang ◽  
Foivos Diakogiannis ◽  
Scott Mills ◽  
Nigel Bajema ◽  
Ian Atkinson ◽  
...  
Keyword(s):  
Kalman Filter ◽  
Standard Deviation ◽  
Learning Algorithm ◽  
Tracking System ◽  
Sensor Arrays ◽  
Semantic Segmentation ◽  
Global Navigation Satellite Systems ◽  
Localization Error ◽  
Satellite Systems ◽  
Deep Learning Algorithm

AbstractAgriculture is becoming increasingly reliant upon accurate data from sensor arrays, with localization an emerging application in the livestock industry. Ground-based time difference of arrival (TDoA) radio location methods have the advantage of being lightweight and exhibit higher energy efficiency than methods reliant upon Global Navigation Satellite Systems (GNSS). Such methods can employ small primary battery cells, rather than rechargeable cells, and still deliver a multi-year deployment. In this paper, we present a novel deep learning algorithm adapted from a one-dimensional implementing a convolutional neural network (CNN) model, originally developed for the task of semantic segmentation. The presented model () both converts TDoA sequences directly to positions and reduces positional errors introduced by sources such as multipathing. We have evaluated the model using simulated animal movements in the form of TDoA position sequences in combination with real-world distributions of TDoA error. These animal tracks were simulated at various step intervals to mimic potential TDoA transmission intervals. We compare to a Kalman filter to evaluate the performance of our algorithm to a more traditional noise reduction approach. On average, for simulated tracks having added noise with a standard deviation of 50 m, the described approach was able to reduce localization error by between 66.3% and 73.6%. The Kalman filter only achieved a reduction of between 8.0% and 22.5%. For a scenario with larger added noise having a standard deviation of 100 m, the described approach was able to reduce average localization error by between 76.2% and 81.9%. The Kalman filter only achieved a reduction of between 31.0% and 39.1%. Results indicate that this novel 1D CNN like encoder/decoder for TDoA location error correction outperforms the Kalman filter. It is able to reduce average localization errors to between 16 and 34 m across all simulated experimental treatments while the uncorrected average TDoA error ranged from 55 to 188 m.

scholarly journals Investigating the Benefits of Vector-Based GNSS Receivers for Autonomous Vehicles under Challenging Navigation Environments

Signals ◽  
2020 ◽  
Vol 1 (2) ◽  
pp. 121-137
Author(s):  
Haidy Y. F. Elghamrawy ◽  
Mohamed Tamazin ◽  
Aboelmagd Noureldin
Keyword(s):  
Autonomous Vehicles ◽  
Tracking System ◽  
Satellite System ◽  
Velocity Estimation ◽  
Estimation Accuracy ◽  
Positioning Accuracy ◽  
Gps Receivers ◽  
Car Industry ◽  
Vector Tracking ◽  
Global Navigation Satellite

There is a growing demand for robust and accurate positioning information for various applications, including the self-driving car industry. Such applications rely mainly on the Global Navigation Satellite System (GNSS), including the Global Positioning System (GPS). However, GPS positioning accuracy relies on several factors, such as satellite geometry, receiver architecture, and navigation environment, to name a few. In urban canyons in which there is a significant probability of signal blockage of one or more satellites and/or interference, the positioning accuracy of scalar-based GPS receivers drastically deteriorates. On the other hand, vector-based GPS receivers exhibit some immunity to momentary outages and interference. Therefore, it is becoming necessary to consider vector-based GPS receivers for several applications, especially safety-critical applications, including next-generation navigation technologies for autonomous vehicles. This paper investigates a vector-based receiver’s performance and compares it to its scalar counterpart in signal degraded conditions. The realistic simulation experiments in this paper are conducted on GPS L1 C/A signals generated using the SpirentTM simulation system to create a fully controlled environment to examine and validate the performance. The results show that the vector tracking system outperforms the scalar tracking in terms of position and velocity estimation accuracy in signal-degraded environments.

scholarly journals Automatic Tunnel Crack Detection Based on U-Net and a Convolutional Neural Network with Alternately Updated Clique

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 717 ◽  
Author(s):  
Gang Li ◽  
Biao Ma ◽  
Shuanhai He ◽  
Xueli Ren ◽  
Qiangwei Liu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Crack Width ◽  
Crack Detection ◽  
Detection Method ◽  
Learning Algorithm ◽  
Semantic Segmentation ◽  
Fully Convolutional Networks ◽  
Deep Learning Algorithm ◽  
Mean Width

Regular crack inspection of tunnels is essential to guarantee their safe operation. At present, the manual detection method is time-consuming, subjective and even dangerous, while the automatic detection method is relatively inaccurate. Detecting tunnel cracks is a challenging task since cracks are tiny, and there are many noise patterns in the tunnel images. This study proposes a deep learning algorithm based on U-Net and a convolutional neural network with alternately updated clique (CliqueNet), called U-CliqueNet, to separate cracks from background in the tunnel images. A consumer-grade DSC-WX700 camera (SONY, Wuxi, China) was used to collect 200 original images, then cracks are manually marked and divided into sub-images with a resolution of 496   ×   496 pixels. A total of 60,000 sub-images were obtained in the dataset of tunnel cracks, among which 50,000 were used for training and 10,000 were used for testing. The proposed framework conducted training and testing on this dataset, the mean pixel accuracy (MPA), mean intersection over union (MIoU), precision and F1-score are 92.25%, 86.96%, 86.32% and 83.40%, respectively. We compared the U-CliqueNet with fully convolutional networks (FCN), U-net, Encoder–decoder network (SegNet) and the multi-scale fusion crack detection (MFCD) algorithm using hypothesis testing, and it’s proved that the MIoU predicted by U-CliqueNet was significantly higher than that of the other four algorithms. The area, length and mean width of cracks can be calculated, and the relative error between the detected mean crack width and the actual mean crack width ranges from −11.20% to 18.57%. The results show that this framework can be used for fast and accurate crack semantic segmentation of tunnel images.

scholarly journals RTK GNSS-Assisted Terrestrial SfM Photogrammetry without GCP: Application to Coastal Morphodynamics Monitoring

2020 ◽  
Vol 12 (11) ◽  
pp. 1889 ◽  
Author(s):  
Marion Jaud ◽  
Stéphane Bertin ◽  
Mickaël Beauverger ◽  
Emmanuel Augereau ◽  
Christophe Delacourt
Keyword(s):  
Standard Deviation ◽  
Low Cost ◽  
Laser Scanner ◽  
Satellite System ◽  
Mean Error ◽  
Ground Control Points ◽  
Participatory Science ◽  
Gnss Network ◽  
Global Navigation Satellite

The present article describes a new and efficient method of Real Time Kinematic (RTK) Global Navigation Satellite System (GNSS) assisted terrestrial Structure-from-Motion (SfM) photogrammetry without the need for Ground Control Points (GCPs). The system only requires a simple frame that mechanically connects a RTK GNSS antenna to the camera. The system is low cost, easy to transport, and offers high autonomy. Furthermore, not requiring GCPs enables saving time during the in situ acquisition and during data processing. The method is tested for coastal cliff monitoring, using both a Reflex camera and a Smartphone camera. The quality of the reconstructions is assessed by comparison to a synchronous Terrestrial Laser Scanner (TLS) acquisition. The results are highly satisfying with a mean error of 0.3 cm and a standard deviation of 4.7 cm obtained with the Nikon D800 Reflex camera and, respectively, a mean error of 0.2 cm and a standard deviation of 3.8 cm obtained with the Huawei Y5 Smartphone camera. This method will be particularly interesting when simplicity, portability, and autonomy are desirable. In the future, it would be transposable to participatory science programs, while using an open RTK GNSS network.

scholarly journals AIOSAT - Autonomous Indoor & Outdoor Safety Tracking System

2019 ◽  
Vol 26 (1) ◽  
pp. 21-32
Author(s):  
Iñigo Adin ◽  
Paul Zabalegui ◽  
Alejandro Perez ◽  
Jaione Arrizabalaga ◽  
Jon Goya ◽  
...  
Keyword(s):  
Rural Areas ◽  
Tracking System ◽  
Dead Reckoning ◽  
Wide Band ◽  
Satellite System ◽  
System Level ◽  
Horizon 2020 ◽  
Rescue Workers ◽  
Global Navigation Satellite ◽  
Map Data

Abstract Even though satellite-based positioning increases rescue workers’ safety and efficiency, signal availability, reliability, and accuracy are often poor during fire operations, due to terrain formation, natural and structural obstacles or even the conditions of the operation. In central Europe, the stakeholders report a strong necessity to complement the location for mixed indoor-outdoor and GNSS blocked scenarios. As such, location information often needs to be augmented. For that, European Global Navigation Satellite System Galileo could help by improving the availability of the satellites with different features. Moreover, a multi-sensored collaborative system could also take advantage of the rescue personnel who are already involved in firefighting and complement the input data for positioning. The Autonomous Indoor & Outdoor Safety Tracking System (AIOSAT) is a multinational project founded through the Horizon 2020 program, with seven partners from Spain, Netherlands and Belgium. It is reaching the first year of progress (out of 3) and the overarching objective of AIOSAT system is to advance beyond the state of the art in tracking rescue workers by creating a high availability and high integrity team positioning and tracking system. On the system level approach, this goal is achieved by fusing the GNSS, EDAS/EGNOS, pedestrian dead reckoning and ultra-wide band ranging information, possibly augmented with map data. The system should be able to work both inside buildings and rural areas, which are the test cases defined by the final users involved in the consortium and the advisory board panel of the project

scholarly journals Preliminary validation of refractivity from a new radio occultation sounder GNOS/FY-3C

2015 ◽  
Vol 8 (9) ◽  
pp. 9009-9044 ◽  
Author(s):  
M. Liao ◽  
P. Zhang ◽  
G. L. Yang ◽  
Y. M. Bi ◽  
Y. Liu ◽  
...  
Keyword(s):  
Standard Deviation ◽  
Radio Occultation ◽  
Weather Prediction ◽  
Satellite System ◽  
Navigation Satellite ◽  
Near Surface ◽  
Vertical Range ◽  
New Radio ◽  
Atmospheric Sounding ◽  
Global Navigation Satellite

Abstract. As a new member of space-based radio occultation sounder, the GNOS (Global Navigation Satellite System Occultation Sounder) mounted on FY-3C has been carrying out the atmospheric sounding since 23 September 2013. GNOS takes a daily measurement up to 800 times with GPS (Global Position System) and Chinese BDS (BeiDou navigation satellite) signals. The refractivity profiles from GNOS are compared with the co-located ECMWF (European Centre for Medium-Range Weather Forecasts) analyses in this paper. Bias and standard deviation have being calculated as the function of altitude. The mean bias is about 0.2 % from the near surface to 35 km. The average standard deviation is within 2 % while it is down to about 1 % in the range 5–30 km where best soundings are usually made. To evaluate the performance of GNOS, COSMIC (Constellation Observing System for Meteorology, Ionosphere and Climate) and GRAS/METOP-A (GNSS Receiver for Atmospheric Sounding) data are also compared to ECMWF analyses as the reference. The results show that GNOS/FY-3C meets the requirements of the design well. It possesses a sounding capability similar to COSMIC and GRAS in the vertical range of 0–30 km, though it needs improvement in higher altitude. Generally, it provides a new data source for global NWP (numerical weather prediction) community.

scholarly journals An overview of methodologies for real-time detection, characterisation and tracking of traveling ionospheric disturbances developed in the TechTIDE project

2020 ◽  
Vol 10 ◽  
pp. 42
Author(s):  
Anna Belehaki ◽  
Ioanna Tsagouri ◽  
David Altadill ◽  
Estefania Blanch ◽  
Claudia Borries ◽  
...  
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Tracking System ◽  
Warning System ◽  
Satellite System ◽  
Ionospheric Disturbances ◽  
Time Activity ◽  
Travelling Ionospheric Disturbances ◽  
Additional Information ◽  
Global Navigation Satellite

The main objective of the TechTIDE project (warning and mitigation technologies for travelling ionospheric disturbances effects) is the development of an identification and tracking system for travelling ionospheric disturbances (TIDs) which will issue warnings of electron density perturbations over large world regions. The TechTIDE project has put in operation a real-time warning system that provides the results of complementary TID detection methodologies and many potential drivers to help users assess the risks and develop mitigation techniques tailored to their applications. The TechTIDE methodologies are able to detect in real time activity caused by both large-scale and medium-scale TIDs and characterize background conditions and external drivers, as an additional information required by the users to assess the criticality of the ongoing disturbances in real time. TechTIDE methodologies are based on the exploitation of data collected in real time from Digisondes, Global Navigation Satellite System (GNSS) receivers and Continuous Doppler Sounding System (CDSS) networks. The results are obtained and provided to users in real time. The paper presents the achievements of the project and discusses the challenges faced in the development of the final TechTIDE warning system.

Aircraft positioning using SPP method in GPS system

2018 ◽  
Vol 90 (8) ◽  
pp. 1213-1220 ◽  
Author(s):  
Kamil Krasuski
Keyword(s):  
Standard Deviation ◽  
Satellite System ◽  
Least Square ◽  
Civil Aviation ◽  
Navigation Satellite ◽  
Least Square Estimation ◽  
Protection Level ◽  
Content Type ◽  
Average Value ◽  
Global Navigation Satellite

PurposeThe purpose of this paper is based on implementation of Global Navigation Satellite System (GNSS) technique in civil aviation for recovery of aircraft position using Single Point Positioning (SPP) method in kinematic mode.Design/methodology/approachThe aircraft coordinates in ellipsoidal frame were obtained based on Global Positioning System (GPS) code observations for SPP method. The numerical computations were executed in post-processing mode in the Aircraft Positioning Software (APS) package. The mathematical scheme of equation observation of SPP method was solved using least square estimation in stochastic processing. In the experiment, airborne test using Cessna 172 aircraft on September 07, 2011 in the civil aerodrome in Mielec was realized. The aircraft position was recovery using observations data from Topcon HiperPro dual-frequency receiver with interval of 1 second.FindingsIn this paper, the average value of standard deviation of aircraft position is about 0.8 m for Latitude, 0.7 m for Longitude and 1.5 m for ellipsoidal height, respectively. In case of the Mean Radial Spherical Error (MRSE) parameter, the average value equals to 1.8 m. The standard deviation of receiver clock bias was presented in this paper and the average value amounts to 34.4 ns. In this paper, the safety protection levels of Horizontal Protection Level (HPL) and Vertical Protection Level (VPL) were also showed and described.Research limitations/implicationsIn this paper, the analysis of aircraft positioning is focused on application the least square estimation in SPP method. The Kalman filtering operation can be also applied in SPP method for designation the position of the aircraft.Practical implicationsThe SPP method can be applied in civil aviation for designation the position of the aircraft in Non-Precision Approach (NPA) GNSS procedure at the landing phase. The typical accuracy of aircraft position is better than 220 m for lateral navigation in NPA GNSS procedure. The limit of accuracy of aircraft position in vertical plane in NPA GNSS procedure is not available.Social implicationsThis paper is destined for people who works in the area of aviation and air transport.Originality/valueThe work presents that SPP method as a universal technique for recovery of aircraft position in civil aviation, and this method can be also used in positioning of aircraft based on Global Navigation Satellite System (GLONASS) code observations.

scholarly journals Spatiotemporal functional modeling of postseismic deformations after the 2011 Tohoku-Oki earthquake

2022 ◽  
Vol 74 (1) ◽  
Author(s):  
Satoshi Fujiwara ◽  
Mikio Tobita ◽  
Shinzaburo Ozawa
Keyword(s):  
Standard Deviation ◽  
Statistical Data ◽  
Functional Model ◽  
Satellite System ◽  
Physical Processes ◽  
Linear Deformation ◽  
Practical Applications ◽  
Long Period ◽  
Global Navigation Satellite ◽  
Physical Phenomena

AbstractPostseismic deformations continue to occur for a long period after major earthquakes. Temporal changes in postseismic deformations can be approximated using simple functions. Since the 2011 Tohoku-Oki earthquake, operating global navigation satellite system stations have been continuously accumulating a remarkable amount of relevant data. To verify the functional model, we performed statistical data processing on postseismic deformations due to this earthquake and obtained their spatiotemporal distribution. Moreover, we approximated the postseismic deformations over a relatively wide area with a standard deviation of residuals of 1 cm for approximately 10 years using a combined functional model of two logarithmic and one exponential functions; however, the residuals from the functional model exhibited a marked deviation since 2015. Although the pattern of postseismic deformations remained unaltered after the earthquake, a change in the linear deformation occurred from 2015 to date. We reduced the overall standard deviation of the residuals of > 200 stations distributed over > 1000 km to < 0.4 cm in the horizontal component by enhancing the functional model to incorporate this linear deformation. Notably, time constants of the functions were similarly applicable for all stations and components. Furthermore, the spatial distribution of the coefficients of each time constant were nonrandom, and the distribution was spatially smooth, with minute changes in the short wavelengths in space. Thus, it is possible to obtain a gridded model in terms of a spatial function. The spatial distributions of short- and long-period components of the functional model and afterslip and viscoelastic relaxation calculated using the physical model were similar to each other, respectively. Each time function revealed a connotation regarding the physical processes, which provided an understanding of the physical phenomena involved in seismogenesis. The functional model can be used to practical applications, such as discerning small variations and modeling for precise positioning. Graphical Abstract

Sign in / Sign up

Export Citation Format

Share Document