面向视频智能分析的商业街行人交通流预测建模

倪慧荟; 吴波鸿

doi:10.3981/j.issn.1000-7857.2019.16.009

PDF(2936 KB)

科技导报 ›› 2019, Vol. 37 ›› Issue (16) : 74-82. DOI: 10.3981/j.issn.1000-7857.2019.16.009

专题：现代应急管理

面向视频智能分析的商业街行人交通流预测建模

作者信息 -

1. 北京市劳动保护科学研究所安全与应急管理研究室, 北京 100054;
2. 中国科学院科技战略咨询研究院, 北京 100190;
3. 中国科学院大学, 北京 100049

作者简介:

倪慧荟,助理研究员,研究方向为安全与应急管理,电子信箱:nihuihui@kingehs.com

Forecast models for commercial street pedestrian traffic flow data based on intelligent video analysis

Author information -

1. Research Laboratory of Safety and Emergency Management, Beijing Municipal Institute of Labour Protection, Beijing 100054, China;
2. Institutes of Science and Development, Chinese Academy of Sciences, Beijing 100190, China;
3. University of Chinese Academy of Sciences, Beijing 100049, China

摘要

阐述了利用面向视频智能分析技术，对商业区行人交通流数据进行样本提取、预处理和建模分析的方法全过程。以北京西单商业区为例，构建了包含不同类型监测点、不同时间点的日期分组式纵向时间序列，并完成了预测建模和效果对比。研究表明，所有序列均为平稳非白噪声序列，具有相似的自回归移动平均（ARMA）模型形式，能较好地实现对行人流量的预测。

Abstract

The sampling, the preprocessing, and the modeling for the commercial street pedestrian traffic flow data based on the intelligent video analysis are presented in this paper. The Xidan mall is taken as an example, the by-date grouping-style vertical time series are established, consisting of multi surveillance points and different points-in-time. The modeling and forecast results show that all vertical time series are stationary and of non-white noise with similar ARMA expression formulas, which can be well applied to the forecast of pedestrian traffic flow data.

导出引用

倪慧荟, 吴波鸿. 面向视频智能分析的商业街行人交通流预测建模[J]. 科技导报, 2019, 37(16): 74-82 https://doi.org/10.3981/j.issn.1000-7857.2019.16.009

NI Huihui, WU Bohong. Forecast models for commercial street pedestrian traffic flow data based on intelligent video analysis[J]. Science & Technology Review, 2019, 37(16): 74-82 https://doi.org/10.3981/j.issn.1000-7857.2019.16.009

参考文献

[1] 唐明, 贾洪飞, 杨丽丽. 城市轨道交通车站站台行人交通特性[J]. 城市交通, 2010, 8(4):47-51. Tang Ming, Jia Hongfei, Yang Lili. Characteristics of riders' behavior at urban rail transit stations[J]. Urban Transport of China, 2010, 8(4):47-51.
[2] 金晓琼, 韩萍, 左忠义, 等. 大连市西安路商业区行人交通特性分析[J]. 大连交通大学学报, 2008, 29(2):27-31. Jin Xiaoqiong, Han Ping, Zuo Zhongyi, et al. Pedestrian traffic characteristics of Xi'an commercial in Dalian[J]. Journal of Dalian Jiaotong University, 2008, 29(2):27-31.
[3] 王秋平, 张译, 孙皓. 历史街区行人交通特性研究[J]. 公路工程, 2016, 41(6):53-58. Wang Qiuping, Zhang Yi, Sun Hao. Research on the historical block pedestrian traffic characteristics[J]. Highway Engineering, 2016, 41(6):53-58.
[4] 叶建红, 陈小鸿. 行人交通流三参数基本关系式适用性研究[J]. 西南交通大学学报, 2016, 51(1):138-144. Ye Jianhong, Chen Xiaohong. Applicability analysis of triparametric fundamental equations for pedestrian traffic flow[J]. Journal of Southwest Jiaotong University, 2016, 51(1):138-144.
[5] 倪慧荟. 城市人群聚集风险预警及客流安全管理[J]. 现代职业安全, 2015, 165:30-33. Ni Huihui. Urban overcrowding forecast and pedestrian safety management[J]. Modern Occupational Safety, 2015, 165:30-33.
[6] 胡成. 人员密集场所预警系统研究[J]. 安全, 2009, 30(11):57-58. Hu Cheng. Research on the early warning system for assembly occupancies[J]. Safety, 2009, 30(11):57-58.
[7] Blue V J, Adler J L. cellular automata microsimulation for modeling bi-directional pedestrian walkways[J]. Transportation Research, Part B, 2001(35):293-312.
[8] Okazaki S. A study of pedestrian movement in architectural space, part 1:Pedestrian movement by the application on of magnetic models[J]. Journal of Architecture and Planning, 1979, 283(3):111-119.
[9] Helbing D, Molnar P. Social force model for pedestrian dynamics[J].Physical Review E, 1995, 51:4282-4286.
[10] 迟菲, 胡成, 李凤, 等. 密集人群流动规律与模拟技术[M]. 北京:化学工业出版社, 2012. Chi Fei, Hu Cheng, Li Feng, et al. Mass crowd flow and simulation technology[M]. Beijing:Chemical Industry Press, 2012.
[11] 张亚运. 基于客流短时预测的城市轨道交通运营组织[D]. 西安:长安大学, 2016. Zhang Yayun. Operation organization of urban rail transit based on the passenger flow short-term prediction[D]. Xi'an:Chang'an University, 2016.
[12] 郭文, 肖为周, 秦菲菲. 基于支持向量机模型的地铁进站客流量预测[J]. 河北工业科技, 2019, 36(1):31-35. Guo Wen, Xiao Weizhou, Qin Feifei. Prediction of subway entry flow based on support vector machine model[J]. Hebei Journal of Industrial Science & Technology, 2019, 36(1):31-35.
[13] 付保明, 王健, 张宁, 等. 基于云模型的城市轨道交通短时客流预测[J]. 城市轨道交通研究, 2018, 21(4):61-65. Fu Baoming, Wang Jian, Zhang Ning, et al. Forecast of short-term passenger flow in urban rail transit based on cloud model[J]. Urban Mass Transit, 2018, 21(4):61-65.
[14] 北京市劳动保护科学研究所. 基于组合多步预测的行人交通拥堵预警方法及系统:ZL 201110109527.4[P]. 2014-05-28. Beijing Municipal Institute of Labour Protection. An overcrowding forecast method and system based on the combined multi-step prediction:ZL 201110109527.4[P]. 2014-05-28.
[15] 张朝雄, 沈旻, 张慧. 缺失数据插补方法比较研究[J]. 市场研究, 2007(9):33-35. Zhang Chaoxiong, Shen Min, Zhang Hui. Missing data's interpolation method[J]. Marketing Research, 2007(9):33-35.
[16] 谭克平. 极端值判断方法简介[J]. 台东大学教育学报, 2008, 19(1):131-150. Tam Hakping. Introduction to the identification of extreme value[J]. NTTU Educational Research Journal, 2008, 19(1):131-150.
[17] 王燕. 应用时间序列分析[M]. 2版. 北京:中国人民大学出版社, 2005. Wang Yan. Applied time series analysis[M]. 2nd ed. Beijing:China Renmin University Press, 2005.