We consider the problem of reconstructing vehicle trajectories from sparse sequences of GPS points, for which the sampling interval is between 1 s and 2 min. We introduce a new class of algorithms, which are altogether called the path inference filter (PIF), that maps GPS data in real time, for a variety of tradeoffs and scenarios and with a high throughput. Numerous prior approaches in map matching can be shown to be special cases of the PIF presented in this paper. We present an efficient procedure for automatically training the filter on new data, with or without ground-truth observations. The framework is evaluated on a large San Francisco taxi data set and is shown to improve upon the current state of the art. This filter also provides insights about driving patterns of drivers. The PIF has been deployed at an industrial scale inside the Mobile Millennium traffic information system, and is used to map fleets of data in San Francisco and Sacramento, CA, USA; Stockholm, Sweden; and Porto, Portugal.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    The Path Inference Filter: Model-Based Low-Latency Map Matching of Probe Vehicle Data


    Contributors:


    Publication date :

    2014-04-01


    Size :

    2351353 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    The path inference filter: Model-based low-latency map matching of probe vehicle data

    Hunter, Timothy / Abbeel, Pieter / Bayen, Alexandre M. | Tema Archive | 2013



    Path Inference Filter and Route Choice Model Aided Map-Matching for Low-Frequency GPS Data

    Xiao, Pinghui / Fang, Jie / Xu, Mengyun et al. | TIBKAT | 2021



    Vehicle Travel Path Matching Algorithm Based on License Plate Recognition Data

    Wang, Yu / Wang, Lei / Gu, Xinxin et al. | ASCE | 2022