A Multiple-Hypothesis Map-Matching Method Suitable for Weighted and Box-Shaped State Estimation for Localization

Abdallah, Fahed; Nassreddine, Ghalia; Denœux, Thierry

doi:10.1109/tits.2011.2160856

Cited by 35 publications

(18 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intuitively, this is achieved by comparing the solution points with the nearest segment. This is proven effective for improvement of GPS localization accuracy [13][14][15][16]. However, there are two difficult cases for MM even if assuming the 2D localization result provided by GPS is accurate.…”

Section: B Map Matchingmentioning

confidence: 99%

Intelligent Viaduct Recognition and Driving Altitude Determination Using GPS Data

Hsu

Kamijo

2017

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Abstract-The rapid development of road networks in highly urbanized cities requires a substantial number of viaducts to reduce the increasing traffic burden on urban highways. Unfortunately, this road design deteriorates the performance of global positioning system (GPS) navigators due to the signal blockage between satellite and receiver. As a result, it is difficult for GPS navigators to determine whether the vehicle is driving on the street or viaduct. Misleading information could confuse drivers and lead them to drive irregularly, which is dangerous in heavy traffic. This paper proposes a novel classification algorithm based on the fact that different satellite signals and conditions can be observed in the on-street and on-viaduct cases by the implementation of dynamic Bayesian network (DBN) to distinguish the driving area of a vehicle. In addition, the proposed DBN can also accurately estimate the driving altitude of the vehicle according to the experiment results.

show abstract

Section: B Map Matchingmentioning

confidence: 99%

Intelligent Viaduct Recognition and Driving Altitude Determination Using GPS Data

Hsu

Kamijo

2017

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

show abstract

“…Velaga et al, 2009). This method, however, can yield inaccurate matches in the case of parallel roads due to the overlook of the ACCEPTED MANUSCRIPT ACCEPTED MANUSCRIPT 8 topology of the road network when selecting CRs (Abdallah et al, 2011). The limitation is described using an example shown below.…”

Section: (2) the Limitation In Preparing Crsmentioning

confidence: 99%

“…A topology MM algorithm (Taylor et al, 2001) uses the topology of the road network as a constraint to select CRs based on the last matching result however it would face the same problem that a mismatch may result in a series of ensuing mismatches. A multiple hypothesis MM algorithm (Abdallah et al, 2011) selects a set of CRs using the topology of the digital map and a similarity criterion. The similarity is characterized by a geometrical measure that ignores other important features such as The limitations in obtaining the positioning data and preparing CRs motivate us to develop an integrated tbMM system, which should obtain the vehicle trajectory including the elevation data and take full advantage of the additional data to enhance the trajectory similarity evaluation process.…”

Section: (2) the Limitation In Preparing Crsmentioning

confidence: 99%

“…Approaches for MM include simple search (Kim et al, 1996), geometric (White et al, 2000;Joshi, 2002), topological (Jabbour et al, 2008;Velaga et al, 2009;Velaga et al, 2012), ACCEPTED MANUSCRIPT ACCEPTED MANUSCRIPT 5 probabilistic (Ochieng et al, 2004) and other refined concepts such as Enhanced Kalman Filter (Xu et al, 2010), Dempster-Shafer's mathematical theory (Nassreddine et al, 2009;Abdallah et al, 2011), fuzzy method (e.g. Quddus et al 2006;Zhang et al, 2009;Tsukamoto and Uehara, 2012) and artificial neural network (Su et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Trajectory-Based Map-Matching System for the Driving Road Identification in Vehicle Navigation Systems

Zhang

Yang

et al. 2015

Journal of Intelligent Transportation Systems

View full text Add to dashboard Cite

The driving road identification is the key issue of a vehicle navigation system that supports various services of intelligent transportation systems. The method for driving road identification Downloaded by [New York University] at 02:50 15 May 2015 ACCEPTED MANUSCRIPT ACCEPTED MANUSCRIPT 3 is also known as map matching (MM). In spite of the development of MM algorithms, there still exist limitations in obtaining the positioning data and preparing candidate roads (CRs) that may result in mismatches in some special difficult road configurations such as flyovers and parallel roads. To overcome the limitations, an integrated trajectory-based MM (tbMM) system is proposed based on the trajectory similarity evaluation method. The system can fuse the information from GPS and inertial sensors to generate the vehicle trajectory that represents the vehicle continuous movement in three dimensions. The elevation data of vehicle and roads areinvolved to enhance the trajectory-based matching process. Also it employs an optimized mechanism for generating and maintaining CRs. Using the mechanism, separated road segments in a digital map are reorganized in the form of possible driving roads and the topology among them is guaranteed. Moreover, the CRs are obtained considering all the possibilities in determining the driving road so that the valuable historical information can be effectively reserved to provide more reliable matches in ambiguous situations. The tbMM system was evaluated using a number of real-world vehicle-level test datasets in urban areas in Beijing. Also a comparison test was performed to evaluate the driving road identification accuracy against existing MM algorithms. The results show that the tbMM system can provide reliable matches with about 99% accuracy in all the difficult scenarios and outperform the existing algorithms.

show abstract

“…In [23], the road identification is performed using a Bayesian network. This selection can also be performed using Belief theory as proposed in [7] and in [1]. In [16], the map-matching approach makes use of a strategy that is formalized using Bayesian filtering.…”

Section: Introductionmentioning

confidence: 99%

Matching Raw GPS Measurements on a Navigable Map Without Computing a Global Position

Fouque

Bonnifait

2012

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Abstract-Map-matching means determining the location of a mobile with respect to a road network description stored in a digital map. This problem is usually addressed using GPSlike fixes. Unfortunately, there are many situations in urban areas where few satellites are visible because of outages due to tall buildings. In this paper, map-matching is solved using raw GPS measurements (pseudoranges and Doppler measurements), avoiding the necessity to compute a global position. The problem is formalized in a general Bayesian framework in order to handle noise, which is able to perform multi-hypothesis map-matching when there is not enough information to make unambiguous decisions. This tightly-coupled GPS-Map fusion has to cope simultaneously with identifying the road and estimating the mobile's position on that road. A marginalized particle filter is proposed for solving this hybrid estimation problem efficiently. Real experimental results are reported to show that this approach can be initialized with fewer than four satellites. It is also able to track the location with two satellites only, once the road selection has been solved.

show abstract

A Multiple-Hypothesis Map-Matching Method Suitable for Weighted and Box-Shaped State Estimation for Localization

Cited by 35 publications

References 45 publications

Intelligent Viaduct Recognition and Driving Altitude Determination Using GPS Data

Intelligent Viaduct Recognition and Driving Altitude Determination Using GPS Data

A Trajectory-Based Map-Matching System for the Driving Road Identification in Vehicle Navigation Systems

Matching Raw GPS Measurements on a Navigable Map Without Computing a Global Position

Contact Info

Product

Resources

About