scholarly journals Anomaly Detection for Urban Vehicle GNSS Observation with a Hybrid Machine Learning System

2020 ◽  
Vol 12 (6) ◽  
pp. 971 ◽  
Author(s):  
Yan Xia ◽  
Shuguo Pan ◽  
Xiaolin Meng ◽  
Wang Gao ◽  
Fei Ye ◽  
...  

In urban areas, the accuracy and reliability of global navigation satellite systems (GNSS) vehicle positioning decline due to substantial non-line-of-sight (NLOS) signals and multipath effects. Recently, positioning enhancement approaches with supervised GNSS signal type classification based on 3D building model-aided labelling have received widespread attention. Despite the reduced computing costs and improved real-time performance, the strict requirements of 3D building models on accuracy and timeliness limit the popularization of the technology to some extent. Meanwhile, the diversity of anomalous observation sources is beyond the reach of NLOS/multipath detection methods. This paper attempts to construct an alternative framework for quality identification of GNSS observations combining clustering-based anomaly detection and supervised classification, in which the hierarchical density-based spatial clustering of applications with noise (HDBSCAN) algorithm is used to label the offline dataset as normal and anomalous observations without the aid of 3D building models, and the supervised classifier in the online system learns the classification rule for real-time anomaly detection. The experimental results based on the measured vehicle GPS/BeiDou data show that after excluding anomalous observations the single point positioning accuracy of the offline dataset is improved by 87.0%, 45.9%, and 69.6% in the east, north, and up directions, respectively, and the positioning accuracy of two online datasets is improved by 48.4%/45.7%, 39.6%/63.3%, and 49.6%/49.1% in the three directions. Through a large number of comparative experiments and discussion on key issues, it is certified that the proposed method is highly feasible and has great potential in the practical application of urban GNSS vehicle positioning.

2021 ◽  
Vol 13 (11) ◽  
pp. 2117
Author(s):  
Qi Cheng ◽  
Ping Chen ◽  
Rui Sun ◽  
Junhui Wang ◽  
Yi Mao ◽  
...  

The performance requirements for Global Navigation Satellite Systems (GNSS) are becoming more demanding as the range of mission-critical vehicular applications, including the Unmanned Aerial Vehicle (UAV) and ground vehicle-based applications, increases. However, the accuracy and reliability of GNSS in some environments, such as in urban areas, are often affected by non-line-of-sight (NLOS) signals and multipath effects. It is therefore essential to develop an effective fault detection scheme that can be applied to GNSS observations so as to ensure that the vehicle positioning can be calculated with a high accuracy. In this paper, we propose an online dataset based faulty GNSS measurement detection and exclusion algorithm for vehicle positioning that takes account of the NLOS/multipath affected scenarios. The proposed algorithm enables a real-time online dataset based fault detection and exclusion scheme, which makes it possible to detect multiple faults in different satellites simultaneously and accurately, thereby allowing real-time quality control of GNSS measurements in dynamic urban positioning applications. The algorithm was tested with simulated/artificial step errors in various scenarios in the measured pseudoranges from a dataset acquired from a UAV in an open area. Furthermore, a real-world test was also conducted with a ground-vehicle driving in a dense urban environment to validate the practical efficiency of the proposed algorithm. The UAV based simulation exhibits a fault detection rate of 100% for both single and multi-satellite fault scenarios, with the horizontal positioning accuracy improved to about 1 metre from tens of metres after fault detection and exclusion. The ground vehicle-based real test shows an overall improvement of 26.1% in 3D positioning accuracy in an urban area compared to the traditional least square method.


2011 ◽  
Vol 13 (3) ◽  
pp. 307-323 ◽  
Author(s):  
Nemanja Branisavljević ◽  
Zoran Kapelan ◽  
Dušan Prodanović

The number of automated measuring and reporting systems used in water distribution and sewer systems is dramatically increasing and, as a consequence, so is the volume of data acquired. Since real-time data is likely to contain a certain amount of anomalous values and data acquisition equipment is not perfect, it is essential to equip the SCADA (Supervisory Control and Data Acquisition) system with automatic procedures that can detect the related problems and assist the user in monitoring and managing the incoming data. A number of different anomaly detection techniques and methods exist and can be used with varying success. To improve the performance, these methods must be fine tuned according to crucial aspects of the process monitored and the contexts in which the data are classified. The aim of this paper is to explore if the data context classification and pre-processing techniques can be used to improve the anomaly detection methods, especially in fully automated systems. The methodology developed is tested on sets of real-life data, using different standard and experimental anomaly detection procedures including statistical, model-based and data-mining approaches. The results obtained clearly demonstrate the effectiveness of the suggested anomaly detection methodology.


Symmetry ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 1251 ◽  
Author(s):  
Tsatsral Amarbayasgalan ◽  
Van Huy Pham ◽  
Nipon Theera-Umpon ◽  
Keun Ho Ryu

Automatic anomaly detection for time-series is critical in a variety of real-world domains such as fraud detection, fault diagnosis, and patient monitoring. Current anomaly detection methods detect the remarkably low proportion of the actual abnormalities correctly. Furthermore, most of the datasets do not provide data labels, and require unsupervised approaches. By focusing on these problems, we propose a novel deep learning-based unsupervised anomaly detection approach (RE-ADTS) for time-series data, which can be applicable to batch and real-time anomaly detections. RE-ADTS consists of two modules including the time-series reconstructor and anomaly detector. The time-series reconstructor module uses the autoregressive (AR) model to find an optimal window width and prepares the subsequences for further analysis according to the width. Then, it uses a deep autoencoder (AE) model to learn the data distribution, which is then used to reconstruct a time-series close to the normal. For anomalies, their reconstruction error (RE) was higher than that of the normal data. As a result of this module, RE and compressed representation of the subsequences were estimated. Later, the anomaly detector module defines the corresponding time-series as normal or an anomaly using a RE based anomaly threshold. For batch anomaly detection, the combination of the density-based clustering technique and anomaly threshold is employed. In the case of real-time anomaly detection, only the anomaly threshold is used without the clustering process. We conducted two types of experiments on a total of 52 publicly available time-series benchmark datasets for the batch and real-time anomaly detections. Experimental results show that the proposed RE-ADTS outperformed the state-of-the-art publicly available anomaly detection methods in most cases.


Electronics ◽  
2018 ◽  
Vol 7 (11) ◽  
pp. 276 ◽  
Author(s):  
Jiyoung Jung ◽  
Sung-Ho Bae

The generation of digital maps with lane-level resolution is rapidly becoming a necessity, as semi- or fully-autonomous driving vehicles are now commercially available. In this paper, we present a practical real-time working prototype for road lane detection using LiDAR data, which can be further extended to automatic lane-level map generation. Conventional lane detection methods are limited to simple road conditions and are not suitable for complex urban roads with various road signs on the ground. Given a 3D point cloud scanned by a 3D LiDAR sensor, we categorized the points of the drivable region and distinguished the points of the road signs on the ground. Then, we developed an expectation-maximization method to detect parallel lines and update the 3D line parameters in real time, as the probe vehicle equipped with the LiDAR sensor moved forward. The detected and recorded line parameters were integrated to build a lane-level digital map with the help of a GPS/INS sensor. The proposed system was tested to generate accurate lane-level maps of two complex urban routes. The experimental results showed that the proposed system was fast and practical in terms of effectively detecting road lines and generating lane-level maps.


2017 ◽  
Vol 52 (1) ◽  
pp. 9-18
Author(s):  
Emad El Manaily ◽  
Mahmoud Abd Rabbou ◽  
Adel El-Shazly ◽  
Moustafa Baraka

Abstract Commonly, relative GPS positioning technique is used in Egypt for precise positioning applications. However, the requirement of a reference station is usually problematic for some applications as it limits the operational range of the system and increases the system cost and complexity On the other hand; the single point positioning is traditionally used for low accuracy applications such as land vehicle navigation with positioning accuracy up to 10 meters in some scenarios which caused navigation problems especially in downtown areas. Recently, high positioning accuracy can be obtained through Precise Point Positioning (PPP) technique in which only once GNSS receiver is used. However, the major drawback of PPP is the long convergence time to reach to the surveying grade accuracy compared to the existing relative techniques. Moreover, the PPP accuracy is significantly degraded due to shortage in satellite availability in urban areas. To overcome these limitations, the quad constellation GNSS systems namely; GPS.GLONASS, Galileo and BeiDou can be combined to increase the satellite availability and enhance the satellite geometry which in turn reduces the convergence time. In Egypt, at the moment, the signals of both Galileo and BeiDou could be logged with limited number of satellites up to four and six satellites for both Systems respectively. In this paper, we investigated the performance of the Quad-GNSS positioning in both dual- and single-frequency ionosphere free PPP modes for both high accurate and low cost navigation application, respectively. The performance of the developed PPP models will be investigated through GNSS data sets collected at three Egyptian cities namely, Cairo, Alexandria and Aswan.


Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2302
Author(s):  
Kai Zhu ◽  
Xuan Guo ◽  
Changhui Jiang ◽  
Yujingyang Xue ◽  
Yuanjun Li ◽  
...  

With the rapid development of autonomous vehicles, the demand for reliable positioning results is urgent. Currently, the ground vehicles heavily depend on the Global Navigation Satellite System (GNSS) and the Inertial Navigation System (INS) providing reliable and continuous navigation solutions. In dense urban areas, especially narrow streets with tall buildings, the GNSS signals are possibly blocked by the surrounding tall buildings, and under this condition, the geometry distribution of the in-view satellites is very poor, and the None-Line-Of-Sight (NLOS) and Multipath (MP) heavily affects the positioning accuracy. Further, the INS positioning errors will quickly diverge over time without the GNSS correction. Aiming at improving the position accuracy under signal challenging environment, in this paper, we developed an MIMU(Micro Inertial Measurement Unit)/Odometer integration system with vehicle state constraints (MO-C) for improving the vehicle positioning accuracy without GNSS. MIMU/Odometer integration model and the constrained measurements are given in detail. Several field tests were carried out for evaluating and assessing the MO-C system. The experiments were divided into two parts, firstly, field testing with data post-processing and real-time processing was carried out for fully assessing the performance of the MO-C system. Secondly, the MO-C was implemented in the BeiDou Satellite Navigation System (BDS)/integrated navigation system (INS) for evaluating the MO-C performance during the BDS signal outage. The MIMU standalone positioning accuracy was compared with that from the MIMU/Odometer integration (MO), MO-C and MIMU with constraints (M-C) for assessing the Odometer, and the influence of the constraint on the positioning errors reduction. The results showed that the latitude and longitude errors could be suppressed with Odometer assisting, and the height errors were suppressed while the state constraints were included.


2019 ◽  
Vol 15 (11) ◽  
pp. 155014771989131 ◽  
Author(s):  
Zengwei Zheng ◽  
Mingxuan Zhou ◽  
Yuanyi Chen ◽  
Meimei Huo ◽  
Dan Chen

To discover road anomalies, a large number of detection methods have been proposed. Most of them apply classification techniques by extracting time and frequency features from the acceleration data. Existing methods are time-consuming since these methods perform on the whole datasets. In addition, few of them pay attention to the similarity of the data itself when vehicle passes over the road anomalies. In this article, we propose QF-COTE, a real-time road anomaly detection system via mobile edge computing. Specifically, QF-COTE consists of two phases: (1) Quick filter. This phase is designed to roughly extract road anomaly segments by applying random forest filter and can be performed on the edge node. (2) Road anomaly detection. In this phase, we utilize collective of transformation-based ensembles to detect road anomalies and can be performed on the cloud node. We show that our method performs clearly beyond some existing methods in both detection performance and running time. To support this conclusion, experiments are conducted based on two real-world data sets and the results are statistically analyzed. We also conduct two experiments to explore the influence of velocity and sample rate. We expect to lay the first step to some new thoughts to the field of real-time road anomalies detection in subsequent work.


2020 ◽  
Vol 55 (2) ◽  
pp. 77-86 ◽  
Author(s):  
Valanon Uaratanawong ◽  
Chalermchon Satirapod ◽  
Toshiaki Tsujii

AbstractNowadays, the use of multi-Global Navigation Satellite System (GNSS) has improved positioning accuracy in autonomous driving, navigation and tracking systems utilized by general users. However, signal quality in urban areas is degraded by poor satellite geometry and severe multipath errors, which may disturb up to a hundred-meter-ranging error as a consequence. In this study, the performance of several satellite selection methods in multipath mitigation was evaluated, based on the concept that better quality signals and more accurate solutions will be obtained, the more multipath signals can be excluded. Three methods were performed and compared: 1) azimuth-dependent elevation mask based on fisheye image technique, 2) receiver autonomous integrity monitoring (RAIM), and 3) signal-to-noise ratio (SNR) mask in the SPP method. To examine the effect of the satellite selection methods on multipath error, the static test (single-point positioning (SPP) in real-time 1 Hz test) was performed in a multipath environment. The preliminary results showed a possible impact on improving the horizontal positioning accuracy of SPP. Among the three techniques assessed in this study, the results indicated that the SNR mask set at 36 dB-Hz in every elevation showed the most promising result. The SNR mask method could improve positioning accuracy by up to 46.80% compared to the SPP method.


2011 ◽  
Vol 64 (3) ◽  
pp. 417-430 ◽  
Author(s):  
Paul D. Groves

The Global Positioning System (GPS) is unreliable in dense urban areas, known as urban canyons, which have tall buildings or narrow streets. This is because the buildings block the signals from many of the satellites. Combining GPS with other Global Navigation Satellite Systems (GNSS) significantly increases the availability of direct line-of-sight signals. Modelling is used to demonstrate that, although this will enable accurate positioning along the direction of the street, the positioning accuracy in the cross-street direction will be poor because the unobstructed satellite signals travel along the street, rather than across it. A novel solution to this problem is to use 3D building models to improve cross-track positioning accuracy in urban canyons by predicting which satellites are visible from different locations and comparing this with the measured satellite visibility to determine position. Modelling is used to show that this shadow matching technique has the potential to achieve metre-order cross-street positioning in urban canyons. The issues to be addressed in developing a robust and practical shadow matching positioning system are then discussed and solutions proposed.


Sign in / Sign up

Export Citation Format

Share Document