基于光流特征描述子的站点限流设施优化方法研究

doi:10.3969/j.issn.0253-2778.2018.04.010

中国科学技术大学学报 ›› 2018, Vol. 48 ›› Issue (4): 341-346.DOI: 10.3969/j.issn.0253-2778.2018.04.010

• 论著 • 上一篇

基于光流特征描述子的站点限流设施优化方法研究

王泽胜，董宝田，罗文慧

北京交通大学交通运输学院，北京 100044

收稿日期:2018-01-08 修回日期:2018-04-11 出版日期:2018-04-30 发布日期:2018-04-30
通讯作者: 董宝田
作者简介:王泽胜，男，1987年生，博士生. 研究方向：机器学习、计算机视觉、智能交通. E-mail：815345591@163.com
基金资助:
国家自然基金（61772065）资助.

Research on flow-limiting facility optimization in rail transit stations based on optical feature descriptor

WANG Zesheng, DONG Baotian,LUO Wenhui

School of Traffic and Transportation，Beijing Jiaotong University，Beijing 100044，China）

Received:2018-01-08 Revised:2018-04-11 Online:2018-04-30 Published:2018-04-30

摘要/Abstract

摘要： 针对现有限流设施与策略智能化程度不高，灵活性较差的问题，提出一种基于光流特征描述子的站点限流设施优化方法.首先，根据枢纽内场景特点，设置感兴趣区域（region of interest，ROI），从而降低后续操作的计算量，提高算法的执行效率；然后，在建立光流特征描述子的基础上，对图片序列进行特征分析；最后，基于人群聚集特征，对经典单分类支持向量机进行调整，并实现超负荷状态的检测.实验结果表明，提出的方法能够对站台人群状态进行准确检测，有效增强限流设施的自动化水平，为轨道交通站点客流组织与管理提供数据支撑和理论依据.

关键词: 智能交通, 状态检测, 特征描述子, 地铁限流, 单分类支持向量机

Abstract: To address the problem of low intelligence and flexibility of existing flow limiting facilities, a new optimization method for flow-limiting facilities in rail transit stations based on optical feature descriptors, is proposed. First, the region of interest (ROI) is set according to the scene characteristics of rail transit stations to reduce the computation of subsequent operation. Then, the features of image sequence are analyzed by establishing optical feature descriptors. Finally, the one-class SVM is adjusted according to the clumped features of pedestrians to make condition detection possible. Experimental results demonstrate that the proposed method can detect the overload status accurately, improve the automatic level of flow-limiting facilities effectively, and provides data support and theoretical basis for organization and management of pedestrians in rail transit stations.

Key words: intelligent transportation, condition detection, feature descriptor, subway flow-limiting, one-class SVM

中图分类号:

U298.2

王泽胜，董宝田，罗文慧. 基于光流特征描述子的站点限流设施优化方法研究[J]. 中国科学技术大学学报, 2018, 48(4): 341-346.

WANG Zesheng, DONG Baotian,LUO Wenhui. Research on flow-limiting facility optimization in rail transit stations based on optical feature descriptor[J]. Journal of University of Science and Technology of China, 2018, 48(4): 341-346.

参考文献

［1］
尹来盛, 张明丽. 我国超大城市交通拥堵及其治理对策研究—以广州市为例[J]. 城市观察, 2017, 1(2): 73-84.
[2] 胡亚楠. 地铁屏蔽门、车门夹人成因分析及防范措施研究[J]. 科技创新与应用, 2017, (10):82-83.
[3] 朱正玲. 城市轨道交通网络高峰时段常态限流问题研究[J]. 铁路通信信号工程技术, 2017, 14(02) :71-74.
[4] 肖慧雅,姚丽亚,曾伟,等. 城市轨道交通站点限流设施优化方法研究[J]. 道路交通与安全, 2016, 16(6): 46-50.
[5] 赵晓旭. 广州地铁换乘车站节假日客流组织与管控研究[J]. 科技资讯, 2015, 13(6): 211-212.
[6] 吴君尚, 张碧纯, 胡湲,等.轨交车站站外限流栏杆设置方案优化研究[J].地下工程与隧道, 2013, (1): 38-41.
[7] 张月坤. 北京地铁客流密度自动检测技术研究[J]. 中国铁路, 2017, (4): 96-100.
[8] 张月坤. 北京地铁视频监测客流告警阈值的针对性和准确性研究[J]. 中国铁路, 2017, (5):78-81.
[9] 赵保锋,邹晓磊,屈晓宜.基于仿真的城市轨道交通站台客流滞留分级预警方法[J].城市轨道交通研究, 2017, 20(9): 107-110,115.
[10] WANG T, SNOUSSI H. Detection of abnormal visual events via global optical flow orientation histogram[J]. IEEE Transactions on Information Forensics and Security, 2014, 9(6): 988-998.
[11] LI A, MIAO Z J, CEN Y G, et al. Histogram of maximal optical flow projection for abnormal events detection in crowded scenes[J]. International Journal of Distributed Sensor Networks, 2015, 11(6): 1-11.
[12] YI Y G, LI X H, ZHAO R, et al. A constrained sparse representation approach for video anomaly detection[C]// Advanced Information Management, Communicates, Electronic and Automation Control Conference. Xi’an, China: IEEE Press, 2016: 45-49.
[13] CHEN L X, GUO H W, WU X Y, et al. Detecting anomaly based on time dependence for large scenes[C]// 2016 IEEE International Conference on Information and Automation. Piscataway, NJ, USA: IEEE Press, 2016: 1376-1381.
[14] ZHAO Y, ZHOU L, FU K, et al. Abnormal event detection using spatio-temporal feature and nonnegative locality-constrained linear coding[C]// International Conference on Image Processing. Piscataway, USA: IEEE Press, 2016: 3354-3358.
[15] WU F, JING X Y, LIU Q, et al. Large-scale image recognition based on parallel kernel supervised and semi-supervised subspace learning[J]. Neural Computing and Applications, 2017, 28(3): 483-498.
[16] XIAN Y, RONG X, YANG X, et al. Evaluation of Low-Level Features for Real-World Surveillance Event Detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(3): 624-634.
[17] 张强,王正林. 精通Matlab图像处理[M]. 电子工业出版社, 2009.
[18] 王爱丽, 董宝田, 王泽胜, 等. 融合光流速度场自适应背景建模的交通场景中运动行人检测算法[J]. 长安大学学报, 2015, 1, 35(S): 184-188.



()
(

基于光流特征描述子的站点限流设施优化方法研究

Research on flow-limiting facility optimization in rail transit stations based on optical feature descriptor

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价