
软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software,2018,29(11):3500−3516 [doi: 10.13 328/j.cnki.jos.005297] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563
基于偏好的个性化路网匹配算法
∗
高
需
1,2
,
武延军
2
,
郭黎敏
3
,
丁治明
3
,
陈军成
3
1
(中国科学院大学,北京 100049)
2
(中国科学院 软件研究所 协同创新中心,北京 100190)
3
(北京工业大学 计算机学院,北京 100124)
通讯作者: 高需, E-mail: gaoxu@nfs.iscas.ac.cn
摘 要: 定位技术的普遍应用,使得随时随地获取个人位置成为可能,进一步推动了基于位置的服务等新型应用
的发展,产生了海量轨迹数据.精确的路网匹配对提高这些新型应用的服务质量具有重要的研究意义,然而受众多因
素的影响,大部分轨迹的采样率较低,比如由签到类应用或低功耗设备生成的低采样轨迹,给路网匹配带来了巨大的
挑战.研究基于偏好的个性化路网匹配(driving preference based personalized map-matching,简称 DPMM),提出了在动
态道路交通网络中的用户驾驶偏好模型.基于该模型,提出了两阶段路网匹配算法:局部匹配搜索用户最可能采用的
几条局部 Skyline 路径;设计了全局匹配的动态规划算法,该算法返回在用户驾驶偏好下最可能的多条全局路径作
为最终匹配结果.实验结果充分表明,该方法是有效的和高效的,具有一定的使用价值.
关键词: 时空数据;轨迹;路网匹配;多目标优化;Skyline 路径;动态规划
中图法分类号: TP181
中文引用格式: 高需,武延军,郭黎敏,丁治明,陈军成.基于偏好的个性化路网匹配算法.软件学报,2018,29(11):3500−3516.
http://www.jos.org.cn/1000-9825/5297.htm
英文引用格式: Gao X, Wu YJ, Guo LM, Ding ZM, Chen JC. Personalized map-matching algorithm based on driving preference.
Ruan Jian Xue Bao/Journal of Soft ware, 2018,29(11):3500−3516 (in Chines e). http ://www.jos.org.cn/10 00-9825/5297.htm
Personalized Ma p-Matc hing Algorithm Base d on Drivi ng Preference
GAO Xu
1,2
, WU Yan-Jun
2
, GUO Li-Min
3
, DING Zhi-Ming
3
, CHEN Jun-Cheng
3
1
(University of Chinese Academy of S ciences, Beijing 10 0049, Chin a)
2
(Collaborative Innovation Center, Ins titute of Software , Th e Chin ese Academy of Sciences, Beijing 100190 , China)
3
(School of Computer, Beijing University of Technology, Beijing 100124, China)
Abstra ct : With the increasing proliferation of position technologies, there comes huge volumes of trajectory data, which are used in
many modern applications such as path planning and location based services. Accurate road network matching can improve the service
quality of these new applications. However, the low sampling trajectories bring a major challenge for map-matching. This paper studies
the problem of matching individual law-sampling trajectory to a dynamic multi-criteri a road network based on user ’s driving preferences.
First, a driving preference model in the dynamic road traffic network is proposed. Based on this model, a two-stage map-matching
algorithm is developed. While local matching searches multiple local likely Skyline paths, a global matching dynamic programming
algorithm is designed and the most probable k global paths are selected as the matching result. Experiments show that the proposed
method is eff ecti ve and eff ici ent .
∗ 基金项目: 国家自然科学基金(61402449, 91546111); 中国科学院战略性科技先导专项课题(XDA06010600); 北京市教委重点
项目(KZ201610005009)
Foundation it em: National Natural Science Foundation of China (61402449, 91546111); Strategic Priority Res earch Program of the
Chinese Academy of Sciences (XDA06010600); Key Project of Beijing Municipal Education Commission (KZ201610005009)
收稿时间: 2017-01-25; 修改时间: 2 017-03-12; 采用时间: 2017-04-12; jos 在线出版时间: 2018-04-16
CNKI 网络优先出版: 2018-04-16 10:59:45, http://kns.cnki.net/kcms/d etail/11.2560.TP.20180416.1059.004.html
评论