海量车牌识别数据集上基于时空划分的旅行时间计算方法

doi:10.3969/j.issn.0372-2112.2016.05.031

电子学报 ›› 2016, Vol. 44 ›› Issue (5): 1227-1233.DOI: 10.3969/j.issn.0372-2112.2016.05.031

海量车牌识别数据集上基于时空划分的旅行时间计算方法

赵卓峰^1,2, 丁维龙^1,2, 张帅¹

1. 北方工业大学云计算研究中心, 北京 100144;
2. 大规模流数据集成与分析技术北京市重点实验室, 北京 100144

收稿日期:2014-11-24 修回日期:2015-10-19 出版日期:2016-05-25
- 作者简介:
- 赵卓峰 男,1977年5月出生,山东济南人.博士,现为北方工业大学云计算研究中心副研究员、副主任.研究方向为云计算、流数据处理、服务计算、智能交通.E-mail:edzhao@ncut.edu.cn;丁维龙 男,1983年3月出生,山东泰安人.博士,现为北方工业大学云计算研究中心助理研究员.主要研究方向为流数据处理、流计算及分布式系统.E-mail:dingweilong@ncut.edu.cn
- 基金资助:
- 北京市自然科学基金 (No.4131001,No.4162021); 北京市属高等学校创新团队建设项目 (No.IDHT20130502); 北方工业大学校科研基金

A Travel Time Calculation Method Based on Spatio-Temporal Data Partition of Large-Scale License Plate Recognition Data Set

ZHAO Zhuo-feng^1,2, DING Wei-long^1,2, ZHANG Shuai¹

1. Cloud Computing Research Center, North China University of Technology, Beijing 100144, China;
2. Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data, Beijing 100144, China

Received:2014-11-24 Revised:2015-10-19 Online:2016-05-25 Published:2016-05-25
- Supported by:
- National Natural Science Foundation of Beijing Municipality, China (No.4131001, No.4162021); Innovation Team Construction Project of Beijing Municipal Universities (No.IDHT20130502); Science and Technology Foundation of North China University of Technology

摘要/Abstract

摘要：

城市路段旅行时间计算是智能交通领域的一个研究热点.车牌识别数据作为近年来新兴的一种针对城市道路行驶车辆的实时监测数据,具有持续生成且数据量大、时间空间相关等特性.为了利用车牌识别数据集进行高效、准确的旅行时间计算,给出了基于车牌识别数据集的旅行时间计算定义,在此基础上提出一种基于时空划分的流水线式并行计算模型,并给出了该模型基于实时MapReduce的实现.通过一组基于海量真实车牌识别数据集的实验表明,本文方法在亿级车牌识别数据集上的旅行时间计算性能方面相对于直接基于Hadoop的实现可以提高3倍以上,同时具有适合细粒度划分及受路网规模影响小的特点.

关键词: 旅行时间, 时空划分, 流水线并行, 实时MapReduce, 车牌识别数据

Abstract:

The calculation of travel time of city roads is an important issue in the domain of the intelligent transportation system research.License plate recognition data is one kind of monitoring data for vehicles running on urban roads, which has some new features, such as high volume, high velocity and spatio-temporal correlation.In order to achieve travel time calculations on massive license plate recognition data collection, we present the formal definition of travel time calculation based on license plate recognition data set, and propose a pipelined parallel computing model based on spatio-temporal data partition.Moreover, the implementation of the computing model is given based on a real-time MapReduce computing system.The corresponding experiments based on real license plate recognition data set show that, the computing performance on million-level data sets of our method can achieve three times increasing compared to traditional travel time calculation methods.Meanwhile our method is more suitable for fine-grained partition and large scale traffic network.

Key words: travel time, spatio-temporal partition, parallel pipeline, real-time mapreduce, large-scale license plate recognition data

中图分类号:

TP301

赵卓峰, 丁维龙, 张帅. 海量车牌识别数据集上基于时空划分的旅行时间计算方法[J]. 电子学报, 2016, 44(5): 1227-1233.

ZHAO Zhuo-feng, DING Wei-long, ZHANG Shuai . A Travel Time Calculation Method Based on Spatio-Temporal Data Partition of Large-Scale License Plate Recognition Data Set[J]. Acta Electronica Sinica, 2016, 44(5): 1227-1233.

参考文献

[1] 朱爱华.基于浮动车数据的路段旅行时间预测研究[D].北京:北京交通大学,2008. Zhu Aihua.Research on link travel time prediction method based on data collected by floating car[D].Beijing Jiaotong University,2008.(in Chinese)
[2] 廖律超,等.一种支持轨迹大数据潜在语义相关性挖掘的谱聚类方法[J].电子学报,2015,43(5):956-964. Liao Lvchao,et al.A spectral clustering method for big trajectory data mining with latent semantic correlation[J].Acta Electronica Sinica,2015,43(5):956-964.(in Chinese)
[3] 姜桂艳,等.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. Jang Jiayan,et al.Traffic congestion identification method based on license plate recognition data[J].Journal of Harbin Institute of Technology,2011,43(4):131-135.(in Chinese)
[4] 刘好德.基于浮动车数据的城市交通状态判别与行程时间计算[R].同济大学,博士后出站报告,2010. Liu Haode.Estimation of urban traffic status and prediction of travel time based on floating car data[R].Research Report for Post-Doctor,Tongji University,2010.(in Chinese)
[5] 朱定局.并行时空模型[M].北京:科学出版社,2009. Zhu Dingjun.Parallel Space-Time Model[M].Beijing,Science Press,2009.(in Chinese)
[6] 亓开元,赵卓峰,房俊,马强.针对高速数据流的大规模数据实时处理方法[J].计算机学报,2012,35(3):477-490. Qi Kaiyuan,Zhao Zhuofeng,Fang Jun.Real-time processing for high speed data stream over large scale data[J].Chinese Journal of Computers,2012,35(3):477-490.(in Chinese)
[7] 亓开元,韩燕波,赵卓峰,等.支持高并发数据流处理的MapReduce中间结果缓存.计算机研究与发展,2013,50(1):111-121. Qi Kaiyuan,Han Yanbo,Zhao Zhuofeng,et al.MapReduce intermediate result cache for concurrent data stream processing[J].Journal of Computer Research and Development,2013,50(1):111-121.(in Chinese)
[8] 张帅,赵卓峰,丁维龙.基于MapReduce的城市道路旅行时间实测计算[J].计算机与数字工程,2014,42(9):1542-1546. Zhang Shuai,Zhao Zhuofeng,Ding Weilong.Urban road trip time measured calculation based on mapReduce[J].Computer & Digital Engineering,2014,42(9):1542-1546. (in Chinese)
[9] 廖飞,黄晟,龚德俊.基于Hadoop的城市道路交通流量数据分布式存储与挖掘分析研究[J].公路与汽运,2013,27(5):82-86. Liao Fei,Huang Sheng,Gong Dejun.Distributed storage and data mining analysis of urban road traffic based on hadoop[J].Highways & Automotive Applications,2013,27(5):82-86.(in Chinese)
[10] Lizhe Wang,et al.G-Hadoop:MapReduce across distributed data centers for data-intensive computing[J].Future Generation Computer Systems,2013,29(3):739-750.
[11] Yingyi Bu,Bill Howe,Magdalena Balazinska,et al.The haLoop approach to large-scale iterative data analysis[J].VLDB Journal,2012,21(2):169-190.
[12] 张鹏,刘庆云,谭建龙,等.流水行云:支持可扩展的并行分布式流处理系统[J].电子学报,2015,43(4):639-646. Zhang Peng,Liu Qingyun,Tan Jianlong,et al.SPSPS:A scalable parallel-distributed stream processing system[J].Acta Electronica Sinica,2015,43(4):639-646.(in Chinese)
[13] Yanfeng Zhang,et al.iMapReduce:A distributed computing framework for iterative computation[J].Journal of Grid Computing,2012,10:47-68.
[14] Matei Zaharia.An Architecture for fast and general data processing on large clusters[R].University of California,Berkeley,Technical Report No.UCB/EECS-2014-12,2014.

[1]	刘景森, 李浩然, 李煜, 周欢. 一种面向大规模复杂全局优化的流场吸引动态涡流搜索算法[J]. 电子学报, 2023, (): 1-7.
[2]	黄鹤, 李文龙, 吴琨, 杨澜, 王会峰, 王萍. 动态自适应特征融合的MFOPA跟踪器[J]. 电子学报, 2023, (): 1-10.
[3]	张淑军, 彭中, 李辉. SAU-Net：基于U-Net和自注意力机制的医学图像分割方法[J]. 电子学报, 2022, 50(10): 2433-2442.
[4]	陇盛, 陶蔚, 张泽东, 陶卿. 非光滑强凸情形Adam型算法的最优收敛速率[J]. 电子学报, 2022, 50(9): 2049-2059.
[5]	张长胜, 张健忠, 钱斌, 胡蓉. 多策略融合的改进天鹰优化算法[J]. 电子学报, 2022, (): 1-11.
[6]	邓海刚, 王传旭, 李成伟, 林晓萌. 深度学习框架下群组行为识别算法综述[J]. 电子学报, 2022, 50(8): 2018-2036.
[7]	穆磊, 王鹏. 量子启发式优化算法的尺度动态调速机制[J]. 电子学报, 2022, 50(7): 1664-1673.
[8]	李凯, 张可心. 结构α-熵的加权高斯混合模型的子空间聚类[J]. 电子学报, 2022, 50(3): 718-725.
[9]	于娟, 杨琼, 鲁剑锋, 韩建民, 彭浩. 高级地图匹配算法：研究现状和趋势[J]. 电子学报, 2021, 49(9): 1818-1829.
[10]	周鹏, 董朝轶, 陈晓艳, 齐咏生, 赵肖懿, 王启来. 基于阶梯式Tent混沌和模拟退火的樽海鞘群算法[J]. 电子学报, 2021, 49(9): 1724-1735.
[11]	李彦苍, 巩翔宇. 基于信息熵的改进狮群算法及其在组合优化中的应用[J]. 电子学报, 2021, 49(8): 1577-1585.
[12]	林运国. 一维离散时间量子行走的路径分析法、概率分布与对称性[J]. 电子学报, 2021, 49(7): 1323-1330.
[13]	刘景森, 马义想, 李煜. 改进蝴蝶算法求解多维复杂函数优化问题[J]. 电子学报, 2021, 49(6): 1068-1076.
[14]	廖彬, 黄静莱, 王鑫, 孙瑞娜, 葛晓燕, 国冰磊. SCEA:一种适应高维海量数据的并行聚类集成算法[J]. 电子学报, 2021, 49(6): 1077-1087.
[15]	董海, 齐新娜. 基于改进细菌觅食算法的自动化立体仓库集成优化[J]. 电子学报, 2021, 49(5): 1001-1012.

海量车牌识别数据集上基于时空划分的旅行时间计算方法

A Travel Time Calculation Method Based on Spatio-Temporal Data Partition of Large-Scale License Plate Recognition Data Set

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics