基于海量车牌识别数据的相似轨迹查询方法

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

清华大学辅仁网/2017-07-07

基于海量车牌识别数据的相似轨迹查询方法

赵卓峰, 卢帅, 韩燕波

北方工业大学大规模流数据集成与分析技术北京市重点实验室, 北京 100144

Similar trajectory query method based on massive vehicle license plate recognition data

ZHAO Zhuofeng, LU Shuai, HAN Yanbo

Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data, North China University of Technology, Beijing 100144, China

摘要:

输出: BibTeX | EndNote (RIS)

摘要车牌识别数据是一种具有数据量大、时空相关、位置可测等特征的车辆监测数据，基于此类数据的相似轨迹查询面临着诸多问题。该文给出一种基于“点伴随关系”的车辆相似轨迹定义，提出了一种多级任务并行的相似轨迹查询方法，并给出了基于MapReduce迭代计算模型的方法实现，可支持在海量车牌识别数据集中利用分布计算环境高效地完成相似轨迹查询。基于近千万条真实车牌识别数据的实验表明，相对于传统方法，该方法在保证相似轨迹查询结果准确的前提下具有更好的查询性能。

关键词 ：相似轨迹,车牌识别数据,点伴随,多级任务并行

Abstract：Vehicle license plate recognition data provides a kind of traffic monitoring data that is a large spatial-temporal stream with fixed positions. Similar trajectory queries of such data face several problems. This paper presents a similar trajectory query method based on site companions with multistage task parallelization based on the MapReduce computing model. This method gives more efficient similar trajectory queries in a distributed computing environment for massive license plate recognition data. Tests show that this method can correctly query similar trajectories more efficiently than traditional stand-alone methods based on tests with almost ten million real vehicle license plate data points.

收稿日期: 2016-06-28 出版日期: 2017-02-21

ZTFLH:

TP319

引用本文:

赵卓峰, 卢帅, 韩燕波. 基于海量车牌识别数据的相似轨迹查询方法[J]. 清华大学学报（自然科学版）, 2017, 57(2): 220-224.
ZHAO Zhuofeng, LU Shuai, HAN Yanbo. Similar trajectory query method based on massive vehicle license plate recognition data. Journal of Tsinghua University(Science and Technology), 2017, 57(2): 220-224.

链接本文:

http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2017.22.018或 http://jst.tsinghuajournals.com/CN/Y2017/V57/I2/220

图表:

图1 点伴随关系判定伪码

图2 点伴随次数统计伪码

表1 不同时间范围的数据规模下查询耗时对比

表2 不同时间范围的数据规模下查询得到的相似轨迹数量对比

图3 不同阈值下的查询性能变化^[14]

参考文献:

[1]	柴华骏, 李瑞敏, 郭敏. 基于车牌识别数据的城市道路旅行时间分布规律及估计方法研究[J]. 交通运输系统工程与信息, 2012, 12(6):41-47.CHAI Huajun, LI Ruimin, GUO Min. Travel time distribution and estimation of urban traffic using vehicle identification data[J]. Journal of Transportation Systems Engineering and Information Technology, 2012, 12(6):41-47. (in Chinese)
[2]	姜桂艳, 常安德, 牛世峰. 基于车牌识别数据的交通拥堵识别方法[J]. 哈尔滨工业大学学报, 2011, 43(4):131-135.JIANG Guiyan, CHANG Ande, NIU Shifeng. Traffic congestion identification method based on license plate recognition data[J]. Journal of Harbin Institute of Technology, 2011, 43(4):131-135. (in Chinese)
[3]	丁锐, 孟小峰, 杨楠. 一种高效的移动对象相似轨迹查询方法[J]. 计算机科学, 2003, 30(10):386-403.DING Rui, MENG Xiaofeng, YANG Nan. An efficient solution about similarity queries for moving object trajectories[J]. Computer Science, 2003, 30(10):386-403. (in Chinese)
[4]	Jensen C S, Lin D, Ooi B C. Continuous clustering of moving objects[J]. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2007, 19(9):1161-1174.
[5]	Yang D, Rundensteiner E A, Ward M O. Neighbor-based pattern detection for windows over streaming data[C]//Proceedings of the 12th International Conference on Extending Database Technology (EDBT09). Saint Petersburg, Russia, 2009:529-540.
[6]	Jeung H, Yiu M, Zhou X. Discovery of convoys in trajectory databases[C]//Proceedings of the 36th International Conference on Very Large Data Bases (VLDB08). Auckland, New Zealand, 2008:1068-1080.
[7]	Xiong Y, Zhu Y. Mining peculiarity groups in day-by-day behavioral dataset[C]//Proceedings of the 9th International Conference on Data Mining (ICDM09). Miami, FL, USA, 2009:578-587.
[8]	Chang J, Song M, Um J. TMN-tree:New trajectory index structure for moving objects in spatial networks[C]//Proceedings of the 10th IEEE International Conference on Computer and Information Technology. Bradford, UK, 2010:1633-1638.
[9]	赵新勇, 安实. 伴随车检测技术应用研究[J]. 交通运输系统工程与信息, 2012, 12(3):36-40.ZHAO Xinyong, AN Shi. Research on accompanying cars recognition in practical application[J]. Journal of Transportation Systems Engineering and Information Technology, 2012, 12(3):36-40. (in Chinese)
[10]	Tang L, Zheng Y, Yuan J, et al. On discovery of traveling companions from streaming trajectories[C]//Proceedings of the 28th IEEE International Conference on Data Engineering (ICDE12). Arlington, VI, USA, 2012:186-197.
[11]	Tang L, Zheng Y, Yuan J, et al. A framework of traveling companion discovery on trajectory data streams[J]. ACM Transactions on Intelligent Systems and Technology, 2013, 5(1):3-1-3-34.
[12]	Zheng K, Zheng Y, Yuan J, et al. Online discovery of gathering patterns over trajectories[J]. IEEE Transactions on Data and Knowledge Engineering, 2014, 26(8):1-14.
[13]	Ekanayake J, Li H, Zhang B, et al. Twister:A runtime for iterative MapReduce[C]//Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing. Chicago, IL, USA, 2010:810-818.
[14]	赵卓峰,丁维龙,韩燕波. 基于云架构的交通感知数据集成处理平台[J]. 计算机研究与发展, 2016, 53(6):1332-1341.ZHAO Zhuofeng, DING Weilong, HAN Yanbo. An intergrated processing platform for traffic sensor data based on cloud architecture[J]. Journal of Computer Research and Development, 2016, 53(6):1332-1341. (in Chinese)

[1]	兰超, 张勇, 邢春晓. 分布式Top-k子图匹配技术[J]. 清华大学学报（自然科学版）, 2016, 56(8): 871-877.