Exclusive: Intelligent Transport

Applications of traffic video big data

  • ZHAO Ying ,
  • WANG Yatao ,
  • HUANG Gang
Expand
  • 1. Beijing Tongfang Software Co., Ltd., Beijing 100083, China;
    2. Tongfang Co., Ltd., Beijing 100083, China

Received date: 2018-09-18

  Revised date: 2018-11-30

  Online published: 2019-04-09

Abstract

The real-time perception of the road network operation in a low-cost way is the key factor to gurantee the transportation safety and the unblocked operation. The rapid and accurate detection of traffic incidents and the collection of traffic data are often difficult. The traditional method is not visual, real-time and cost-effective. In recent years, the development of video big data and artificial intelligence provides a new way to solve these problems. This paper reviews the research history and application limitations of the intelligent video analysis in the field of transportation, as well as the characteristic connotation of video big data, the design of an artificial intelligence platform driven by video big data, and the solution and the application for highway traffic.

Cite this article

ZHAO Ying , WANG Yatao , HUANG Gang . Applications of traffic video big data[J]. Science & Technology Review, 2019 , 37(6) : 73 -83 . DOI: 10.3981/j.issn.1000-7857.2019.06.010

References

[1] Cameron M. World report on road traffic injury prevention[M]//World report on road traffic injury prevention. Geneva:World Health Organization, 2004:270-275.
[2] Kissi S, Fournier L, How N K. Road traffic accidents:A pictorial review[J]. Emergency Radiology, 2018, 25(4):425-433.
[3] Von H H, Al E. Reducing the severity of road injuries through post impact care[J]. European Journal of Emergency Medicine. 1999, 6:271-274.
[4] 杨惠敏, 陈雨人, 方守恩, 等. 高速公路交通事故救援时间与生存率关系模型研究[J]. 交通信息与安全, 2015(4):82-86. Yang Huimin, Chen Yuren, Fang Shouen, et al. A Study of the relationship between rescue time and survival rate of traffic accidents on freeways using a cox regression model[J]. Transport Information and Safety, 2015(4):82-86.
[5] 寒金. 美国高速公路管理革新[J]. 交通企业管理, 2006, 21(9):68-69. Han Jin. American highway management innovation[J]. Transportation Enterprise Management, 2006, 21(9):68-69.
[6] Haddon W. The changing approach to the epidemiology, prevention, and amelioration of trauma:The transition to approaches etiologically rather than descriptively based[J]. American Journal of Public Health and the Nations Health, 1968, 58(8):1431-1438.
[7] Leduc G. Road traffic data:Collection methods and applications[Z/OL]. Working Papers on Energy, Transport and Climate Change, 2008, https://www.researchgate.net/profile/Guillaume_Leduc2/publication/254424803_Road_Traffic_Data_Collection_Methods_and_Applications/links/55645bf008ae6f4dcc99951f.pdf.
[8] 邵春福, 赵熠, 吴戈. 道路交通数据采集技术研究展望[J]. 现代交通技术, 2006(6):66-70. Shao Chunfu, Zhao Yi, Wu Ge. Review of road traffic data collection technology[J]. Modern Transportation Technology, 2006(6):66-70.
[9] Sun Z, Bebis G, Miller R. On-road vehicle detection:A review[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2006, 28(5):694-711.
[10] 赵英, 江龙, 王亚涛, 等. 视频大数据采集分析技术在高速路网安全畅通中的应用[J]. 中国交通信息化, 2017(增刊1):143-147. Zhao Ying, Jiang Long, Wang Yatao, et al. Application of video big data acquisition and analysis technology in safety and unblocked of highway network[J]. China ITS Journal, 2017(Suppl 1):143-147.
[11] 张敬磊, 王晓原. 交通事件检测算法研究进展[J]. 武汉理工大学学报(交通科学与工程版), 2005, 29(2):215-218. Zhang Jinglei, Wang Xiaoyuan. Research progress of traffic incident detection algorithms[J]. Wuhan University of Technology (Transportation Science & Engineering), 2005, 29(2):215-218.
[12] Dogru N, Subasi A. Traffic accident detection by using machine learning methods[C/OL]. International Symposium on Sustainable Development, 2012, https://www.researchgate.net/publication/288511790_TRAFFIC_ACCIDENT_DETECTION_BY_USING_MACHINE_LEARNING_METHODS.
[13] 武林芝, 陈淑燕, 郑小花. 基于PCA和SVM的交通事件自动检测算法[J]. 微计算机信息, 2010, 26(13):220-222. Wu Linzhi, Chen Shuyan, Zheng Xiaohua. Automatic incident detection algorithm based on PCA and SVM[J]. Microcomputer Information, 2010, 26(13):220-222.
[14] Liu C, Lu J, Chen S Y. Yesign and analysis of traffic incident detection based on random forest[J]. Journal of Southeast University (English Edition), 2014(1):88-95.
[15] 姜紫峰, 刘小坤. 基于神经网络的交通事件检测算法[J]. 长安大学学报(自然科学版), 2000, 20(3):67-69. Jiang Zifeng, Liu Xiaokun. Artificial neural network(ANN) algorithm for traffic incidents detection[J]. Journal of Chang'an University (Natural Science Edition), 2000, 20(3):67-69.
[16] Gupte S, Masoud O, Martin R F K, et al. Detection and classification of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2002, 3(1):37-47.
[17] Cheng H Y, Jeng B S, Tseng P T, et al. Lane detection with moving vehicles in the traffic scenes[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(4):571-582.
[18] Karmann K P. Moving object recognition using an adaptive background memory[J]. Time-Varying Image Processing and Moving Object Recognition, 1990, 2:289-296.
[19] Lipton A J, Fujiyoshi H, Patil R S. Moving target classification and tracking from real-time video[C]//IEEE Workshop on Applications of Computer Vision. Piscataway, NJ:IEEE, 1998:8-14.
[20] 王潮, 宣国荣. 基于计算机视觉的实时交通流检测[J]. 计算机工程, 1997(增刊1):276-278. Wang Chao, Xuan Guorong. Real-time traffic flow detection based on computer vision[J]. Computer Engineering, 1997(suppl 1):276-278.
[21] 彭甜. 三个关键检测技术:目标检测、目标跟踪和多摄像头协同[D]. 上海:上海交通大学, 2010. Peng Tian. Three key technologies:Target detecting, multi-targets tracking and multi-cameras coordination[D]. Shanghai Jiao Tong University, 2010.
[22] 刘安安, 苏育挺. 跨摄像头的多运动目标跟踪方法:102156863 B[P]. 2011-08-17. Liu Anan, Sun Yuting. Multi-moving target tracking method across cameras:102156863 B[P]. 2012-08-17.
[23] Beymer D, Mclauchlan P, Coifman B, et al. A real-time computer vision system for measuring traffic parameters[C]. Proceedings of IEEE Computer Society Computer Vision & Pattern Recognition, 1997:495-501.
[24] Buch N, Velastin S A, Orwell J. A review of computer vision techniques for the analysis of urban traffic[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(3):920-939.
[25] Hu W M, Xiao X J, Xie D, et al. Traffic accident prediction using 3-D model-based vehicle tracking[J]. IEEE Transactions on Vehicular Technology, 2004, 53(3):677-694.
[26] 罗浩. 基于深度学习的行人重识别研究综述[EB/OL]. (2017-12-10)[2018-9-12]. https://blog.csdn.net/baidu_18891025/article/details/79202249. Luo Hao. Review of pedestrian recognition based on deep learning[EB/OL]. (2017-12-10)[2018-9-12]. https://blog.csdn.net/baidu_18891025/article/details/79202249.
[27] Zapletal D, Herout A. Vehicle re-identification for automatic video traffic surveillance[C]//Computer Vision and Pattern Recognition Workshops. Piscataway, New Jencey:IEEE, 2016:1568-1574.
[28] Liu X C, Liu W, Mei T, et al. A deep learning-based approach to progressive vehicle re-identification for urban surveillance[C]//European Conference on Computer Vision. Cham:Springer, 2016:869-884.
[29] Zhou Y, Shao L. Vehicle re-identification by adversarial bidirectional LSTM network[C]//IEEE Winter Conference on Applications of Computer Vision. Piscataway, New Jencey:IEEE, 2018:653-662.
[30] 自动驾驶计算机视觉研究综述:难题、数据集与前沿成果[EB/OL]. (2017-09-13)[2018-9-12]. http://www.sohu.com/a/191792533_465591. Research summary of computer vision for autonomous vehicle:Difficulties, data sets and forefront achievements[EB/OL]. (2017-09-13)[2018-9-12]. http://www.sohu.com/a/191792533_465591.
[31] "十三五"末全国高速公路通车里程将达16.9万公里[EB/OL]. (2016-04-15)[2018-09-02]. http://finance.sina.com.cn/roll/2016-04-15/doc-ifxrizpp1181339.shtml. By the end of the 13th Five-Year Plan, the mileage of national expressway will reach 169,000 kilometers[EB/OL]. (2016-04-15)[2018-09-02]. http://finance.sina.com.cn/roll/2016-04-15/doc-ifxrizpp1181339.shtml.
[32] 何明. 智能交通基于视频、图像的大数据分析应用[J]. 智能城市, 2016(10):112. He Ming. Big data analysis and application of intelligent transportation based on video and image[J]. Intelligent City, 2016(10):112.
[33] 何志涛, 田铁红, 孙世臻, 等. 基于大数据技术的视频监控应用研究与探索[J]. 数字技术与应用, 2017(1):95-96. He Zhitao, Tian Tiehong, Sun Shizhen, et al. Research and application of video surveillance based on big data technology[J]. Digital Technology & Application,2017(1):95-96.
[34] 赵英. 智慧城市与视频大数据[M]. 北京:科学出版社, 2018:86. Zhao Ying. Smart city and video big data[M]. Beijing:Science Press, 2018:86.
[35] 黄海军. 浅谈安防大数据的应用[J]. 中国安防, 2016(5):60-62. Huang Haijun. Talking about the application of big security data[J]. China Security & Protection, 2016(5):60-62.
[36] 何遥. 安防大数据的发展趋势[J]. 中国公共安全, 2015(22):84-86. He Yao. Development trend of security big data[J]. China Public Security, 2015(22):84-86.
[37] 赵晟, 姜进磊. 典型大数据计算框架分析[J]. 中兴通讯技术, 2016, 22(2):14-18. Zhao Sheng, Jiang Jinlei. Analysis of typical big data computing framework[J]. ZTE Technology Journal, 2016, 22(2):14-18.
[38] 海康视频云存储介绍[EB/OL]. (2014-9-11)[2017-11-25]. https://wenku.baidu.com/view/a6c4c841a300a6c30d229f0f.html. Haikang video cloud storage introduce[EB/OL]. (2014-9-11)[2017-11-25]. https://wenku.baidu.com/view/a6c4c841a300a6c30d229f0f.html.
[39] 舒文琼. 大视频元年已来服务质量评估需同步跟进[J]. 通信世界, 2016(30):30. Shu Wenqiong. Big video year has come, service quality assessment needs to be followed up synchronously[J]. Telecom World, 2016(30):30.
[40] 韩怿冰, 宋文军, 尚展垒. 云存储环境下的用户数据安全机制研究[J]. 网络安全技术与应用, 2016(4):63-64. Han Yibing, Song Wenjun, Shang Zhanlei. Research on user data security mechanism in cloud storage environmen[J]. Practical Network Security Technology, 2016(4):63-64.
[41] Bertozzi M, Broggi A. GOLD:a parallel real-time stereo vision system for generic obstacle and lane detection[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 1998, 7(1):62.
Outlines

/