A probabilistic map matching method for smartphone GPS data

Bierlaire, Michel; Chen, Jingmin; Newman, J. C.

doi:10.1016/j.trc.2012.08.001

Cited by 174 publications

(100 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bierlaire, Chen and Newman [4] proposed a probabilistic map matching approach that generates a set of potentially true paths, and associates a likelihood score to each of them. Their model calculates the probability that a GPS recording device would have generated a specific sequence of measurements while following the given path.…”

Section: Related Workmentioning

confidence: 99%

Spatio-Temporal Localization of Agricultural Machinery Operations

Vidaković¹,

Malbaša²,

Konjović³

et al. 2017

Proceedings of the International Scientific Conference - Sinteza 2017

View full text Add to dashboard Cite

Abstract:The utilization of agricultural mechanization is crucial to its efficient exploitation that, in turn, significantly influences the entire agricultural economy as well as soil quality. Contemporary agricultural machines are GPS enabled, allowing localization and recording of their motion. In this paper we present an approach to spatio-temporal localization of agricultural mechanization operations based on a linear classifier in fuzzy linear space. We trained a classifier on data labeled using a fuzzy linear classifier in order to create a training set for a data mining predictor that may be helpful in automated management of records describing agricultural machinery's dynamics. The training set was comprised of spatial coordinates of the machine recorded from a GPS device and then manually classified into two classes, denoting whether the machine is utilized for its primary purpose (productive operations like sowing, cultivating, spraying, etc.) or for non-productive operations such as moving the machine in transport from/to fields.

show abstract

Section: Related Workmentioning

confidence: 99%

Spatio-Temporal Localization of Agricultural Machinery Operations

Vidaković¹,

Malbaša²,

Konjović³

et al. 2017

Proceedings of the International Scientific Conference - Sinteza 2017

View full text Add to dashboard Cite

show abstract

“…Recent studies on map matching focus not only on localization of GPS samples on a map but also on inference of the travel path (Bierlaire et al 2013;Chen and Bierlaire 2015;Hunter et al 2014;Lou et al 2009;Miwa et al 2012;Thiagarajan et al 2009). Some of these studies focus on travel routes with sparse GPS samples (Chen and Bierlaire 2015;Hunter et al 2014;Lou et al 2009;Miwa et al 2012;Thiagarajan et al 2009).…”

Section: Related Workmentioning

confidence: 99%

“…However, linear interpolation of virtual samples is not always a correct assumption and can lead to problems when the number of virtual GPS samples outweighs the number of real GPS samples. Another approach for extracting routes between observations is to compute shortest paths between observations (Bierlaire et al 2013;Chen and Bierlaire 2015;Goh et al 2012;Lou et al 2009). Shortest paths may not always be the right choice, especially in urban networks (Hunter et al 2014), as explained in Fig.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid HMM model for travel path inference with sparse GPS samples

2016

View full text Add to dashboard Cite

In this study, we propose a novel method for a travel path inference problem from sparse GPS trajectory data. This problem involves localization of GPS samples on a road network and reconstruction of the path that a driver might have been following from a low rate of sampled GPS observations. Particularly, we model travel path inference as an optimization problem in both the spatial and temporal domains and propose a novel hybrid hidden Markov model (HMM) that uses a uniform cost search (UCS)-like novel combinational algorithm. We provide the following improvements over the previous studies that use HMM-based methods: (1) for travel path inference between matched GPS positions, the proposed hybrid HMM algorithm evaluates all candidate paths to find the most likely path for both the temporal and spatial domains. In contrast, previous studies either create interpolated trajectories or connect matched GPS positions using the shortest path assumption, which might not be true, especially in urban road networks (Goh et al. 2012;Lou et al. 2009). (2) The proposed algorithm uses legal speed limits for the evaluation of discrepancy in the temporal domain as in Goh et al. (2012), andLou et al. (2009) only if there is not sufficient historical average speed data; otherwise, we use historical average speed computed from data. Our experiments with real datasets show that our algorithm performs better than the state of the art VTrack algorithm (Thiagarajan et al. 2009), especially for cases where GPS data is sampled infrequently.

show abstract

“…For example, using GPS trace data from smartphones, the researchers [13,14] have demonstrated how to reconstruct travel paths, which precisely match the road network geometry.…”

Section: Introductionmentioning

confidence: 99%