为缓解大型客运枢纽因诱导服务不到位而产生的人流拥堵问题，采用室内WiFi 定位技术和Mysql获取行人交通流分布热力图，通过百度地图坐标拾取系统识别人流聚集区的具体位置。通过定义迷路人群的交通特征参数，提出“人群迷路区”概念；应用视频识别追踪技术，分析行人速度与加速度的方差，于人流密集区运用视频识别技术寻找“人群迷路区”。最后以北京南站为例进行实地调研，利用调研数据识别北京南站的“人群迷路区”。基于人群速度与加速度方差，“人群迷路区”被分为四类：单纯人流聚集区、因标识不足而产生的人群迷路区、因标识过于复杂而产生的人群迷路区、因商业设施或障碍物遮挡而产生的人群迷路区。同时提出加大商业活动监管力度、简化部分引导标识、增加其他交通方式换乘区域标识等优化方法，可使人群行进效率提高约25%。
Abstract
To alleviate the problem of pedestrian congestion caused by inadequate guidance service in large passenger hubs, the indoor WiFi positioning technology and Mysql were used to obtain the thermo-dynamic chart of pedestrian traffic flow distribution. The specific locations of pedestrian aggregation areas were identified through Baidu map coordinate picking system. By defining the traffic characteristic parameters of the lost pedestrians, the concept of "crowd lost area" was put forward. The video recognition and tracking technology was applied to analyze the variances of pedestrian speed and speed acceleration to find out the "crowd lost areas" in pedestrians′ high-density areas. Finally, Beijing South Railway Station was taken as an example to conduct the on-the-spot investigation. The "crowd lost areas" were distinguished via survey data analysis. Based on the variance of crowd speed and speed acceleration, the "crowd lost areas" were divided into four categories, which were simple pedestrian aggregation areas, crowd lost areas caused by insufficient identification, crowd lost areas caused by over-complicated logos, crowd lost areas caused by commercial facilities or obstacle occlusion. Optimization methods were proposed such as increasing the supervision of commercial activities, simplifying some of the guiding signs and increasing the transfering signage to other transportation modes. It could improve the operation efficiency of the crowd by about 25%.
关键词
客运枢纽 /
人群迷路区 /
客流组织 /
WiFi数据 /
视频识别
Key words
passenger transportation hub /
crowd lost area /
passenger flow organization /
WiFi data /
video identification
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 刘栋栋，赵斌，李磊，等. 北京南站行人特征参数的调查与分析[J]. 建筑科学，2011，27（5）：61-66.
[2] 薛艳青，张喜. 基于Anylogic 仿真技术的北京南站客流组织优化分析[J]. 铁路计算机应用，2012，21（2）：5-8.
[3] 孙明正，潘昭宇，高胜庆. 北京南站高铁旅客特征与接驳交通体系改善[J]. 城市交通，2012（3）：23-32.
[4] 李晓英. 北京南站客流组织动态仿真分析方法研究[D]. 北京：北京交通大学，2009.
[5] 王英男. 大型综合交通枢纽站客流预测及组织优化方法研究[D]. 北京：北京交通大学，2008.
[6] 李田田，胡昌龙，刘宇祺. 基于WiFi 的交通枢纽室内定位导航系统设计[J]. 商情，2017（4）：140-141.
[7] 夏英，万建斌，刘素彤，等. 基于Wi-Fi 和基站信号强度的室内定位系统设计与实现[J]. 数字通信，2012，39（6）：21-25.
[8] 孙立山，任福田. 客运交通枢纽换乘客流的组织优化[J]. 道路交通与安全，2007，7（3）：18-21.
[9] 刘小明，沈龙利，杨孝宽. 城市客运枢纽综合评价指标体系研究[J]. 中国公路学报，1995（S1）：97-102.
[10] WANG J Q, CHEN K, YANG S, et al. Region Proposal by Guided Anchoring[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE, 2019: 2965-2974.
[11] ZHU C C, HE Y H, SAVVIDES M. Feature Selective Anchor-Free Module for Single- Shot Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach, USA: IEEE, 2019: 840-849.
[12] KARLINSKY L, SHTOK J, HARARY S, et al. RepMet: Representative- Based Metric Learning for Classification and Few- Shot Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach, USA: IEEE, 2019: 5197-5206.
[13] LI P L, CHEN X Z, SHEN S J. Stereo R-CNN Based 3D Object Detection for Autonomous Driving[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach, USA: IEEE, 2019: 7644-7652.
[14] JIANG B R, LUO R X, MAO J Y, et al. Acquisition of Localization Confidence for Accurate Object Detection[C]// Proceedings of the European Conference on Computer Vision (ECCV). Munich, Germany: the official ECCV 2018, 2018: 784-799.
[15] 赵东拂，宿宇. 综合交通枢纽行人交通导向标志指示效率研究[J]. 城市轨道交通研究，2014，17（4）：43-46.
基金
中国博士后科学基金项目（2018M641138）；北京自然科学基金项目（L181001）；北京自然科学基金重点项目（4181002）；北京市交通运输委员会科技项目（201825JNBJ2）
PDF(1910 KB)
京公网安备 11010102003417号
京ICP备17006742号-3
