Open AccessHidden Markov model and driver path preference for floating car trajectory map matching
Author(s) -
Song Chengbo,
Yan Xuefeng,
Stephen Nkyi,
Khan Arif Ali
Publication year - 2018
Publication title -
iet intelligent transport systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.579
H-Index - 45
eISSN - 1751-9578
pISSN - 1751-956X
DOI - 10.1049/iet-its.2018.5132
Subject(s) - matching (statistics) , map matching , hidden markov model , computer science , trajectory , feature (linguistics) , sampling (signal processing) , context (archaeology) , path (computing) , markov chain , artificial intelligence , algorithm , ground truth , pattern recognition (psychology) , mathematics , computer vision , statistics , machine learning , global positioning system , geography , telecommunications , physics , astronomy , programming language , linguistics , philosophy , archaeology , filter (signal processing)
Here, a hidden Markov model (HMM) and driver path preference (DPP)‐based algorithm was proposed for floating car trajectory map matching. The algorithm focused on two improvements over existing HMM‐based map matching algorithm: (i) the use of distance difference feature and average speed difference feature for transition probability calculation, which reasonably describe the context information between the two adjacent sampling points. It results in a more accurate matching capability; (ii) the DPP overcomes the shortcoming of feature attenuation in calculating the transition probability at low floating car sampling rates. It assures the matching accuracy of the algorithm at low sampling rates. The algorithm was evaluated using ground truth data and the results of the experiment show that the new transition probability significantly improves the matching capability. The proposed DPP can significantly help to maintain the matching accuracy under the condition of low sampling rates.