城市轨道交通站突发事件实时检测与应急响应模型研究
详细信息 查看官网全文
- 英文论文题名：Research on Model for Real-time Detection and Response of Emergency in Urban Rail Transit Station
- 论文作者：王敏 ; 赵凌 ; 姜良维
- 英文论文作者：WANG Min ; ZHAO Ling ; JIANG Liang-wei ; Traffic Management Research Institute of Ministry of Public Security ; Rail Transit Security Department ; Railway Police College
- 年：2017
- 作者机构：公安部交通管理科学研究所;铁道警察学院轨道交通安全保卫系;
- 论文关键词：突发事件 ; 视频分析 ; 应急响应模型 ; 轨道交通
- 英文论文关键词：Emergency ; Video Analysis ; Emergency Response Model ; Railway Transit
- 会议召开时间：2017-07-03
- 会议录名称：第五届中国指挥控制大会论文集
- 语种：中文
- 分类号：TP391.41;U298
- 学会代码：ZHKZ
- 会议名称：第五届中国指挥控制大会
- 会议地点：中国北京
- 主办单位：中国指挥与控制学会
- 学会名称：中国指挥与控制学会
- 页数：6
- 文件大小：653k
- 原文格式：D
- 会议级别：全国
摘要
针对当前城市轨道交通站等公共场所人员流动聚集变化快、突发事件发生概率大、安全监控智能化低、运营管理风险高的隐患,本文对突发事件的响应机制进行了梳理,提出了一种基于多源信息融合的突发事件检测和应急响应模型。该模型基于自上而下的人工引导机制,对系统前端设备的信息感知、关键特征提取、识别结果决策等进行多层次、人工监督的全面融合。本文对该模型系统中各个模块、各个阶段所应用到的信息处理、图像识别、状态估计、系统集成等技术以及应急响应后台指挥及现场人员组成进行了阐述和建议,对我国公共交通车站等人员聚集公共场所突发事件应急响应应用具有积极的意义。
In view of the hidden troubles of the current rail transit stations and other public places, such as quick change flow of gathered people, high probability of emergency, low intelligence of security monitoring, high risk of operation management, this paper generalizes the emergency response mechanism and presents a emergency detection-response model of multi-source information fusion. Based on the top-down artificial experience, system learning and other transcendental guidance mechanism, the model constructs a multi-layer structure and realizes the comprehensive integration with human supervision by the information awareness from front-end equipment, key feature extraction and recognition result decision. This paper introduces emergency response command, field staff composition and the technologies of each module and stage: information processing, image recognition, state estimation, system integration. In a word, the paper has positive significance for the public transportation station and other personnel assembled public places to for emergency response.
In view of the hidden troubles of the current rail transit stations and other public places, such as quick change flow of gathered people, high probability of emergency, low intelligence of security monitoring, high risk of operation management, this paper generalizes the emergency response mechanism and presents a emergency detection-response model of multi-source information fusion. Based on the top-down artificial experience, system learning and other transcendental guidance mechanism, the model constructs a multi-layer structure and realizes the comprehensive integration with human supervision by the information awareness from front-end equipment, key feature extraction and recognition result decision. This paper introduces emergency response command, field staff composition and the technologies of each module and stage: information processing, image recognition, state estimation, system integration. In a word, the paper has positive significance for the public transportation station and other personnel assembled public places to for emergency response.
引文
[1]张起贵,张妮.基于地铁复杂场景下异常行为的视频分析研究[J].电视技术,2014(3):163-166.
[2]何晔,奉泽熙.安防和乘客异动在途监测系统设计[J].机车电传动,2013(4):77-84.
[3]张振江,辛跃.基于物联网的城市轨道交通环境监测系统研究[J].都市快轨交通,2013,25(4):63-66.
[4]沈海燕,冯云梅,史宏.基于信息融合的客运站人体异常行为识别研究[J].公路交通科技,2009,26(S1):58-61.
[5]P Viola,M Jones.Robust Real-time Face Detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[6]T Ahonen,A Hadid,M Pietikainen.Face Recognition with Local Binary Patterns[C].European Conference on Computer Vision,2006,28(12):469-481.
[7]E Osuna,R Freund,F Girosi.Training Support Vector Machines:an Application to Face Detection[C].IEEE Conference on Computer Vision&Pattern Recognition,1997:130-136.
[8]H A Rowley,S Baluja,T Kanade.Neural Network-Based Face Detection[C].IEEE Conference on Computer Vision&Pattern Recognition,1996:203-208.
[9]G E Hinton,R R Salakhutdinov.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[10]黄何.应急处置中公安机关内外联动机制研究[D].安徽大学,2016.
[2]何晔,奉泽熙.安防和乘客异动在途监测系统设计[J].机车电传动,2013(4):77-84.
[3]张振江,辛跃.基于物联网的城市轨道交通环境监测系统研究[J].都市快轨交通,2013,25(4):63-66.
[4]沈海燕,冯云梅,史宏.基于信息融合的客运站人体异常行为识别研究[J].公路交通科技,2009,26(S1):58-61.
[5]P Viola,M Jones.Robust Real-time Face Detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[6]T Ahonen,A Hadid,M Pietikainen.Face Recognition with Local Binary Patterns[C].European Conference on Computer Vision,2006,28(12):469-481.
[7]E Osuna,R Freund,F Girosi.Training Support Vector Machines:an Application to Face Detection[C].IEEE Conference on Computer Vision&Pattern Recognition,1997:130-136.
[8]H A Rowley,S Baluja,T Kanade.Neural Network-Based Face Detection[C].IEEE Conference on Computer Vision&Pattern Recognition,1996:203-208.
[9]G E Hinton,R R Salakhutdinov.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[10]黄何.应急处置中公安机关内外联动机制研究[D].安徽大学,2016.