计算机应用 ›› 2017, Vol. 37 ›› Issue (11): 3064-3068.DOI: 10.11772/j.issn.1001-9081.2017.11.3064

• 第十六届中国机器学习会议(CCML 2017) • 上一篇    下一篇

类自动车牌识别轨迹数据的伴随车辆组挖掘

王保全1,2,3, 蒋同海1,3, 周喜1,3, 马博1,3, 赵凡1,3   

  1. 1. 中国科学院 新疆理化技术研究所, 乌鲁木齐 830011;
    2. 中国科学院大学, 北京 100049;
    3. 新疆理化技术研究所 新疆民族语音语言信息处理实验室, 乌鲁木齐 830011
  • 收稿日期:2017-05-16 修回日期:2017-06-05 出版日期:2017-11-10 发布日期:2017-11-11
  • 通讯作者: 蒋同海
  • 作者简介:王保全(1990-),男,新疆昌吉人,博士研究生,主要研究方向:大数据分析、数据挖掘;蒋同海(1963-),男,新疆福海人,研究员,博士生导师,主要研究方向:多语种信息处理、电子政务、多语种文字语音识别;周喜(1978-),男,湖南双峰人,研究员,博士,CCF会员,主要研究方向:物联网、大数据分析;马博(1984-),男,辽宁鞍山人,副研究员,博士,CCF会员,主要研究方向:数据分析与知识发现、机器学习;赵凡(1980-),男,山西介休人,副研究员,博士研究生,CCF会员,主要研究方向:信息安全、大数据分析。
  • 基金资助:
    新疆维吾尔自治区重点实验室项目(2016D03019);新疆维吾尔自治区高技术计划项目(201512103);中国科学院科技服务网络计划(STS计划)项目(KFJ-EW-STS-129)。

Mining of accompanying vehicle group from trajectory data based on analogous automatic number plate recognition

WANG Baoquan1,2,3, JIANG Tonghai1,3, ZHOU Xi1,3, MA Bo1,3, ZHAO Fan1,3   

  1. 1. Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Urumqi Xinjiang 830011, China;
    2. University of the Chinese Academy of Sciences, Beijing 100049, China;
    3. Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi Xinjiang 8300111, China
  • Received:2017-05-16 Revised:2017-06-05 Online:2017-11-10 Published:2017-11-11
  • Supported by:
    This work is partially supported by the Xinjiang Uygur Autonomous Region Key Laboratory Project (2016D03019); the Xinjiang Uygur Autonomous Region High Technology Project (201512103); Chinese Academy of Sciences Science and Technology Service Network (STS) Project (KFJ-EW-STS-129).

摘要: 自动车牌识别(ANPR)数据比私人全球定位系统(GPS)数据更易获得,且包含更有用的信息,但是相对成熟的针对GPS轨迹数据挖掘伴随车辆组方法并不适用于自动车牌识别数据,现有的少量自动车牌识别数据伴随车辆组挖掘算法存在重视轨迹相似而忽视时间因素的缺陷,因此提出一种基于轨迹特征的聚类方法挖掘伴随车辆组。针对自动车牌识别数据中采样点固定而采样时间不定的特点,通过轨迹中共现的次数判定两个对象构成伴随模式。该共现定义引入豪斯多夫距离,综合考虑轨迹的地点、方向和时间特征,旨在挖掘数据中采样点不同但采样点距离近且轨迹相似的伴随车辆组,以此提高伴随车辆组挖掘效率。实验结果表明,所提方法较现有方法更能有效挖掘伴随车辆组,识别非伴随模式数据,效率提升了近两倍。

关键词: 自动车牌识别轨迹数据, 伴随车辆组, 基于密度的空间聚类, 豪斯多夫距离, 共现

Abstract: Automatic Number Plate Recognition (ANPR) data is easier to obtain than private Global Positioning System (GPS) data, and it contains more useful information, but the relatively mature GPS track data mining with vehicle group method did not apply to ANPR data, the existing accompanying vehicle group mining algorithm pays attention to the similarity of the trajectory and ignores the time factor when dealing with small amount of ANPR data. A clustering method based on trajectory feature to excavate the accompanying vehicle group was proposed. Aiming at the fact that the sampling points are fixed and the sampling time is uncertain in the ANPR data, whether two objects were accompanied was determined by the number of co-occurrence in the trajectory. The co-occurrence definition introduced the Hausdorff distance, taking into account the location, direction and time characteristics of the trajectory. The accompanying vehicle group with different but adjacent sampling points and similar trajectories was minned to improve the mining efficiency. The experimental results show that the proposed method is more effective than the existing method to excavate the vehicle group, and improves the efficiency by nearly two times when identifying the non-accompanying mode data.

Key words: Automatic Number Plate Recognition (ANPR) trajectory data, traveling companions, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Hausdorff distance, co-occurrence

中图分类号: