Machine Learning and Intelligent Communications. 4th International Conference, MLICOM 2019, Nanjing, China, August 24–25, 2019, Proceedings

Research Article

BMI-Matching: Map-Matching with Bearing Meta-information

Download
17 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-32388-2_58,
        author={DaWei Wang and JingJing Gu},
        title={BMI-Matching: Map-Matching with Bearing Meta-information},
        proceedings={Machine Learning and Intelligent Communications. 4th International Conference, MLICOM 2019, Nanjing, China, August 24--25, 2019, Proceedings},
        proceedings_a={MLICOM},
        year={2019},
        month={10},
        keywords={Map-matching HMM R-tree},
        doi={10.1007/978-3-030-32388-2_58}
    }
    
  • DaWei Wang
    JingJing Gu
    Year: 2019
    BMI-Matching: Map-Matching with Bearing Meta-information
    MLICOM
    Springer
    DOI: 10.1007/978-3-030-32388-2_58
DaWei Wang1,*, JingJing Gu1,*
  • 1: Nanjing University of Aeronautics and Astronautics
*Contact email: wangdawei673@163.com, gujingjing@nuaa.edu.cn

Abstract

Map-matching is a fundamental pre-processing step for many applications which aligns a trajectory represented by a sequence of sampling points with the city road network on a digital map. With the help of GPS-embedded devices, a lot of GPS trajectories can be collected. However, the raw positions captured by GPS devices usually can not reflect the real positions because of physical constraints such as GPS signals blocked by buildings. And low-sampling-rate data is another challenge for map-matching. Although many approaches have been proposed to solve these problems, unfortunately, most of them only consider the position of the object or the topology structures of the road network. So it becomes significant to accurately match GPS trajectories to road network. We propose a method called BMI-matching (map-matching with earing eta-nformation) which not only considers the two factors above but also focuses on the moving object bearing. Based on bearing, we can calculate the direction similarity between moving object and road segments to determine selecting which road segment is appropriate. We conduct experiments on real dataset and compare our method with two state-of-the-art algorithms. The results show that our approach gets better performance on matching accuracy.