基于条件随机场和低采样率浮动车数据的地图匹配算法

doi:10.11896/j.issn.1002-137X.2016.6A.015

计算机科学 ›› 2016, Vol. 43 ›› Issue (Z6): 68-72.doi: 10.11896/j.issn.1002-137X.2016.6A.015

基于条件随机场和低采样率浮动车数据的地图匹配算法

杨旭华,彭朋

浙江工业大学计算机科学与技术学院浙江310023,浙江工业大学计算机科学与技术学院浙江310023

出版日期:2018-12-01 发布日期:2018-12-01
基金资助:
本文受国家自然科学基金(61374152)资助

Map Matching Algorithm Based on Conditional Random Fields and Low-sampling-rate Floating Car Data

YANG Xu-hua and PENG Peng

Online:2018-12-01 Published:2018-12-01

摘要/Abstract

摘要： 提出了一种基于条件随机场和低采样率浮动车数据的地图匹配算法。首先建立道路网络模型,在此基础上,计算GPS观测点可能匹配的候选投影点集合以及集合中每一个候选投影点的观测概率,再计算相邻GPS观测点的候选路径集合以及每两个相邻候选投影点之间的传递概率；然后根据这些候选投影点和候选路径,在滑动窗口内,基于条件随机场模型应用前后向递归算法,计算每个候选投影点的概率权重值；最后根据概率权重值,选取GPS观测点的最佳匹配投影点。该算法(FB-MM)在低采样率的情况下,综合考虑了道路网络的拓扑结构和GPS观测点之间的关联信息,实现了较好的地图匹配效果。

关键词: 浮动车,低采样率,拓扑信息,条件随机场,前后向递归,地图匹配

Abstract: In this paper,a new map matching algorithm(FB-MM) based on conditional random fields and low-sample-rate floating car data was proposed.On the basis of the road network model,the candidate projection points and their observation probability of the GPS observation point can be gained,and the candidate paths and the transfer probability between adjacent candidate projection points can be also gained.Then the probability weight value of every candidate projection points can be computed by using forward and backward recursion algorithm based on the conditional random fields in the sliding window.After that,the best matching projection point can be selected by the probability weight value.Based on low-sampling-rate floating car data,this map matching algorithm can make full use of the topological information of road network and the correlation information between GPS observation points.So it can achieve the better map matching effect.

Key words: Floating car,Low-sampling-rate,Topological information,Conditional random fields,Forward and backward recursion,Map matching

杨旭华,彭朋. 基于条件随机场和低采样率浮动车数据的地图匹配算法[J]. 计算机科学, 2016, 43(Z6): 68-72. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.015

YANG Xu-hua and PENG Peng. Map Matching Algorithm Based on Conditional Random Fields and Low-sampling-rate Floating Car Data[J]. Computer Science, 2016, 43(Z6): 68-72. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.015

参考文献

[1] Cui You-jing,Ge Shu-zhi.Autonomous vehicle positioning with gps in urban canyon environments[J].IEEE Transactions on Robotics and Automation,2003,9(1):15-25
[2] 李清泉,黄练.基于GPS轨迹数据的地图匹配算法[J].测绘学报,2010,9(2):207-212
[3] 王美玲,程林.浮动车地图匹配算法研究[J].测绘学报,2012,1(1):133-138
[4] Hunter T,Abbeel P,Bayen A.The Path Inference Filter:Model-Based Low-Latency Map Matching of Probe Vehicle Data[J].IEEE Transactions on Intelligent Transportation Systems,2014,5(2):507-529
[5] White Christopher E,David B,Kornhauser Alain L.Some map matching algorithms for personal navigation assistants[J].Transportation Research Part C:Emerging Technologies,2000,8(1-6):91-108
[6] Hofleitner A,Cme E,Oukhellou L,et al.Automatic inference of map attributes from mobile data[C]∥IEEE Conference on Intelligent Transportation Systems.2012:1687-1692
[7] Yuan Jing,Zheng Yu,Zhang Cheng-yang,et al.An Interactive-Voting based Map Matching algorithm [C]∥IEEE International Conference on Mobile Data Management.2010:43-52
[8] 卢文涛,周银东,梅顺良,等.基于拓扑结构的地图匹配算法研究[J].测控技术,2010,29(6):73-76
[9] 朱征字,崔明,刘琳.一种基于GPS终端的地图匹配方法[J].计算机科学,2013,40(5):291-295
[10] Carola W,Randall S,Dieter P.Addressing the need for map-matching speed:Localizing global curve-matching algorithms [C]∥Proceedings 18th International Conference on Scientific and Statistical Database Management.2006:379-388
[11] Rafael T M,David B,Franois P.Lane-level integrity provision for navigation and map matching with GNSS,dead reckoning,and enhanced maps[J].IEEE Transactions on Intelligent Transportation Systems,2011,11(1):100-112
[12] Cho Y W,Choi H.Accuracy enhancement of position estimation using adaptive Kalman filter and map matching [J].InternationalJournal of Control and Automation,2014,7(7):167-178
[13] Bierlaire M,Chen Jing-min,Newman J.A probabilistic mapmatching method for smartphone GPS data[J].Transportation Research Part C:Emerging Technologies,2013,6:78-98
[14] Fahed A,Ghalia N,Thierry D.A multiple-hypothesis map-ma-tching method suitable for weighted and box-shaped state estimation for localization [J].IEEE Transactions on Intelligent Transportation Systems,2011,2(4):1495-1510
[15] 唐进君,刘芳.基于路径预测的不确定性推理组合地图匹配算法[J].测绘学报,2010,39(2):207-212
[16] 苏海滨,王光政,王继东.基于模糊神经网络的地图匹配算法[J].北京科技大学学报,2012,34(1):43-47
[17] Chen Bi-yu,Yuan Hui,Li Qing-quan,et al.Map-matching algorithm for large-scale low-frequency floating car data[J].International Journal of Geographical Information Science,2014,8(1):22-38
[18] Tomio M,Daisuke K,Toshiyuki Y,et al.Development of map matching algorithm for low frequency probe data[J].Transportation Research Part C:Emerging Technologies,2012,22(5):132-145
[19] Lafferty J,McCallum A,Pereira F.Conditional random fields:Probabilistic models for segmenting and labeling sequence data[C]∥Proc.18th ICML,San Francisco.CA,USA,2001:282-289
[20] Seymore K,McCallum A,Rosenfeld R.Learning hidden Markov model structure for information extraction[C]∥Proc.AAAI Workshop Mach.Learning Inf.Extraction,1999:37-42
[21] Arvind T,James B,Tomas G,et al.Cooperative transit tracking using smart-phones[C]∥Proceedings of the 8th ACM Con-ference on Embedded Networked Sensor Systems.2010:85-98

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于条件随机场和低采样率浮动车数据的地图匹配算法

Map Matching Algorithm Based on Conditional Random Fields and Low-sampling-rate Floating Car Data

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0