WO2018014873A1 - 一种基于mac码和人脸识别的人流预警方法 - Google Patents

一种基于mac码和人脸识别的人流预警方法 Download PDF

Info

Publication number
WO2018014873A1
WO2018014873A1 PCT/CN2017/093937 CN2017093937W WO2018014873A1 WO 2018014873 A1 WO2018014873 A1 WO 2018014873A1 CN 2017093937 W CN2017093937 W CN 2017093937W WO 2018014873 A1 WO2018014873 A1 WO 2018014873A1
Authority
WO
WIPO (PCT)
Prior art keywords
flow
people
migration
time
information
Prior art date
Application number
PCT/CN2017/093937
Other languages
English (en)
French (fr)
Inventor
傅东生
Original Assignee
深圳奇迹智慧网络有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳奇迹智慧网络有限公司 filed Critical 深圳奇迹智慧网络有限公司
Publication of WO2018014873A1 publication Critical patent/WO2018014873A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02Alarms for ensuring the safety of persons

Definitions

  • the invention relates to a human flow early warning method, and more particularly to a human flow early warning method based on MAC code and face recognition.
  • an object of the present invention is to provide a human flow early warning method based on MAC code and face recognition.
  • the present invention provides the following technical solution: a method for alerting a person flow based on MAC code and face recognition, which specifically includes the following steps:
  • the camera collects the face of the key crowd appearing within the specified range through video surveillance, and performs an alarm
  • the probe detects the hardware related information of the client mobile phone (the field strength, time, latitude and longitude (space) dimension);
  • the camera uploads the alarm information to the cloud
  • the probe uploads the hardware information of the detection ethical client to the cloud
  • the cloud constructs machine learning according to the alarm information of the camera and the ethics information collected by the probe in the time, distance, and historical retention dimension, and the associated face and the hardware information are matched and proofread;
  • the sixth step is to push the results of the cloud push to the visualization platform and the big data integration platform;
  • the visualization platform and the big data integration platform display the thermal status of the whole system in a minute-level refresh manner according to the real-time view, the sudden increase of the situation, the road condition, the status of the population, the frequency of the population visits, and the migration status of the crowd;
  • the crowd-related warning and alarm messages are reported to the platform administrator, and the message is automatically pushed to the outdoor large screen and the client mobile phone of the monitoring area to provide an early warning effect.
  • the seventh step is as follows:
  • the heat map mainly displays two aspects of information. Based on the big data, the flow of people collected by the equipment in the project is analyzed. According to the intensity of the flow of different devices, the map is displayed in real time with different colors combined with the map.
  • the system can display the real-time number and peak of different single-point devices, and support the detailed page of the single-point device to view the detailed monitoring status of the single-point device. For ease of use, the real-time number of single-point devices is displayed below the heat map.
  • the sudden increase chart shows the growth of the number of different single-point devices in the system compared with the previous period, and the degree of growth of the person flow is marked by different colors: the growth level of the green representative does not reach the sudden increase warning value set by the administrator, and the flow of people is relatively normal. Yellow indicates that the number of surges has reached the warning threshold and needs to pay attention to the growth of people. Red represents a sudden increase in the number of people reaching the alert threshold, and needs to focus on the growth of people.
  • the hedging map based on big data, analyzes the changes in the flow density of a specific monitoring point in the detection area and the flow direction of the person, and combines the map to obtain the flow situation of each collision point that is prone to danger. If there is a dangerous collision point, there is a commercial building. Narrow roads, elevators and other crowded or narrow cornices will also highlight the information on the mouth, so that the relevant departments can take different mitigation measures according to the condition of the mouth.
  • the blue road segment represents normal flow of people, the yellow road segment represents denser flow of people, and the red road segment represents dense crowds, which is prone to collision;
  • Migration map Urban planners sometimes need to know the flow of people who are concerned about the migration center throughout the business district at different times. After the user sets up the migration center in the system, the system can show the migration of people between different migration centers. At the same time, the following details can be displayed:
  • the system displays the following three information:
  • Hottest route show the hottest migration routes at different times according to the flow situation of different migration centers
  • Moving out of the hot spot real-time display of the migration center with a large number of people moving out;
  • the migration and removal information of the migration center is displayed;
  • the proportion of occurrence the number of days / the total number of days so far, the proportion of people who appear more than 40%, less than 80%;
  • First visitor The first person to appear within 90 days.
  • Alert water level Shows the flow of blocks and APs that are prone to danger, but does not show information about all blocks and equipment in the system.
  • the warning water level shows the real-time flow status of all blocks and single-point devices in the system.
  • People flow forecast Based on historical flow data of the entire business circle and different regions of interest, establish a flow forecasting model to predict the hourly flow and peak time of each block in the next 48 hours, so that relevant personnel can deal with risks ahead of time.
  • the system first displays the peak flow information of tomorrow's people in different blocks of interest in the entire project. Clicking on the block will show the flow of people in the system block at different times of the day and tomorrow.
  • the elapsed time is indicated by the solid line
  • the predicted time is indicated by the dotted line, which is convenient for the user to view the difference between the predicted and actual flow of people.
  • the invention has the following advantages: the invention monitors the distribution of people flow, personnel identity information, migration trend of human flow in a designated area in real time, and conducts flow flow prediction and early warning analysis and notification to the area, and when the situation occurs in the area, the situation can be predicted in advance and given Prepare a plan to avoid accidents.
  • Figure 1 is a block diagram showing the structure of the present invention.
  • a method for alerting a person flow based on MAC code and face recognition includes the following steps:
  • the camera collects the face of the key crowd appearing within the specified range through video surveillance, and performs an alarm
  • the probe detects the hardware related information of the client mobile phone (the field strength, time, latitude and longitude (space) dimension);
  • the camera uploads the alarm information to the cloud
  • the probe uploads the hardware information of the detection ethical client to the cloud
  • the cloud constructs machine learning according to the alarm information of the camera and the ethics information collected by the probe in the time, distance, and historical retention dimension, and the associated face and the hardware information are matched and proofread;
  • the sixth step is to push the results of the cloud push to the visualization platform and the big data integration platform;
  • the visualization platform and the big data integration platform display the thermal status of the whole system in a minute-level refresh manner according to the real-time view, the sudden increase of the situation, the road condition, the status of the population, the frequency of the population visits, and the migration status of the crowd;
  • the crowd-related warning and alarm messages are reported to the platform administrator, and the message is automatically pushed to the outdoor large screen and the client mobile phone of the monitoring area to provide an early warning effect.
  • the seventh step is as follows:
  • the heat map mainly displays two aspects of information, based on big data, analyzes the flow of people collected by the equipment in the project, and combines the maps with different colors according to the intensity of the different devices.
  • the system presents a crowded situation.
  • the system can display the real-time number and peak value of different single-point devices, and support the detailed monitoring status of single-point devices by entering the single-point device detailed page. For ease of use, the real-time number of single-point devices is displayed below the heat map.
  • the sudden increase chart shows the growth of the number of different single-point devices in the system compared with the previous period, and the degree of growth of the person flow is marked by different colors: the growth level of the green representative does not reach the sudden increase warning value set by the administrator, and the flow of people is relatively normal. Yellow indicates that the number of surges has reached the warning threshold and needs to pay attention to the growth of people. Red represents a sudden increase in the number of people reaching the alert threshold, and needs to focus on the growth of people.
  • the hedging map based on big data, analyzes the changes in the flow density of a specific monitoring point in the detection area and the flow direction of the person, and combines the map to obtain the flow situation of each collision point that is prone to danger. If there is a dangerous collision point, there is a commercial building. Narrow roads, elevators and other crowded or narrow cornices will also highlight the information on the mouth, so that the relevant departments can take different mitigation measures according to the condition of the mouth.
  • Path icon The blue road segment represents normal flow of people, the yellow road segment represents denser flow of people, and the red road segment represents dense crowds, which is prone to collision.
  • Migration map Urban planners sometimes need to know the flow of people who are concerned about the migration center throughout the business district at different times. After the user sets up the migration center in the system, the system can show the migration of people between different migration centers. At the same time, the following details can be displayed:
  • the system displays the following three information:
  • Hottest route show the hottest migration routes at different times according to the flow situation of different migration centers
  • Moving out of the hot spot real-time display of the migration center with a large amount of people moving out
  • the migration and removal information of the migration center is displayed.
  • the proportion of occurrence the number of days / the total number of days so far, the proportion of people greater than 40%, less than 80%
  • the proportion the number of days / the total number of days so far, the proportion of people greater than 0%, less than 40%
  • Alert water level Shows the flow of blocks and APs that are prone to danger, but does not show information about all blocks and equipment in the system.
  • the warning water level shows the real-time flow status of all blocks and single-point devices in the system.
  • People flow forecast Based on historical flow data of the entire business circle and different regions of interest, establish a flow forecasting model to predict the hourly flow and peak time of each block in the next 48 hours, so that relevant personnel can deal with risks ahead of time.
  • the system first displays the peak flow information of tomorrow's people in different blocks of interest in the entire project. Clicking on the block will show the flow of people in the system block at different times of the day and tomorrow.
  • the elapsed time is indicated by the solid line
  • the predicted time is indicated by the dotted line, which is convenient for the user to view the difference between the predicted and actual flow of people.

Landscapes

  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Alarm Systems (AREA)

Abstract

本发明公开了一种基于MAC码和人脸识别的人流预警方法,其具体包括以下步骤:第一步,采集指定范围内出现的关键人群人脸,并进行告警;第二步,探测客户端手机硬件信息;第三步,将告警信息上传到云端;第四步,将探测到的客户端硬件信息上传到云端;第五步,关联人脸与硬件信息打通匹配校对;第六步,云端推送打通的结果到可视化平台与大数据整合平台;第七步,可视化平台和大数据整合平台按照实时视图以分钟级别刷新的方式展示整个系统;第八步,将人群相关的预警和报警消息报告给平台管理员,并自动将消息推送到监测区域的室外大屏幕和客户端手机,起到预警效果。

Description

一种基于MAC码和人脸识别的人流预警方法 技术领域
本发明涉及一种人流预警方法,更具体的说,它涉及一种基于MAC码和人脸识别的人流预警方法。
背景技术
随着现在我国人口的不断骤增,由于人流拥挤发生的突发事故不断加多,特别是在节假日,人们出去旅游的加多,在某些旅游景点内会出现人流拥挤、爆棚的现象,如果不能做好很好的疏导、分流,很容易出现事故。
发明内容
针对现有技术存在的不足,本发明的目的在于提供一种基于MAC码和人脸识别的人流预警方法。
为实现上述目的,本发明提供了如下技术方案:一种基于MAC码和人脸识别的人流预警方法,其具体包括以下步骤:
第一步,摄像头通过视频监控采集指定范围内出现的关键人群人脸,并进行告警;
第二步,探针探测到客户端手机硬件相关信息(分场强、时间、经纬度(空间)维度);
第三步,摄像头将告警信息上传到云端;
第四步,探针将探测道德客户端硬件信息上传到云端;
第五步,云端根据摄像头的告警信息及探针采集道德信息在时间、距离、历史存留维度下构建机器学习,关联人脸与硬件信息打通匹配校对;
第六步,云端推送打通的结果到可视化平台与大数据整合平台;
第七步,可视化平台和大数据整合平台按照实时视图以分钟级别刷新的方式展示整个系统的热力状况,骤增状况,道路状况、关注人群身份状况、人群造访频次状况以及人群迁徙状况;
第八步,将人群相关的预警和报警消息报告给平台管理员,并自动将消息推送到监测区域的室外大屏幕和客户端手机,起到预警效果。
优选为,第七步具体如下:
热力图主要展示两方面信息,基于大数据对项目内设备采集到的人流进行分析,根据不同设备人流密集程度以不同的颜色结合地图实时呈现系统人流密集状况。系统能够展示不同单点设备的实时人数和峰值,并且支持进入单点设备详细页面查看单点设备的详细监测状况,为了易用性,热力图下方展示单点设备的实时人数。
骤增图体现系统不同单点设备近一段时间相对前一段时间的人数增长状况,并以不同颜色标识人流增长程度:绿色代表增长程度没有达到管理员设定的骤增预警值,人流状况比较正常,黄色代表骤增人数达到预警阈值、需要关注人流增长状况。红色代表骤增人数达到警戒阈值,需要重点关注人流增长状况。
对冲图,基于大数据对探测区域内特定监控点人流密度变化及人流动向进行分析并结合地图,得出各个容易发生危险的对撞点的人流状况,如果容易发生危险的对撞点附件有商厦,窄路,电梯等拥挤或者狭窄的隘口,也会突出展示隘口信息,方便有关部门根据隘口状况采取不同的缓解措施。
路径图示:蓝色路段代表人流正常,黄色路段代表人流比较密集、红色路段代表人流密集,容易发生对撞;
迁徙图:城市规划者有时需要知道不同时间整个商圈内关注迁徙中心的人群流向。用户在系统内设定迁徙中心后,系统就可以展示不同迁徙中心之间的人流迁徙状况。同时能够展示如下细节信息:
用户不选中任何迁徙中心时,系统展示如下三个信息:
最热线路:根据不同迁徙中心的人流状况,展示不同时间的最热迁徙线路;
迁入热点:实时展示人群迁入量比较大的迁徙中心;
迁出热点:实时展示人群迁出量比较大的迁徙中心;
当用户选中某一个迁徙中心时,展示该迁徙中心的迁入迁出信息;
迁入:展示其他迁徙中心迁入到本中心的人流状况;
迁出:展示本迁徙中心迁出到其他中心的人流状况;
人群分析:根据不同人群停留时间特征,系统分为如下四类人群。固定人群:90天内出现比例>80%,小于等于100%的人。(出现比例=出现天数/到目前为止总天数)。
重度访客:90天内,出现比例=出现天数/到目前为止总天数,出现比例大于40%,小于80%的人;
偶尔访客:90天内,出现比例=出现天数/到目前为止总天数,出现比例大于0%,小于40%的人;
初次访客:90天内,首次出现的人。
警戒水位:展示容易发生危险的区块和AP的人流状况,但不会展示系统全部区块和设备的信息。警戒水位展示系统内全部区块和单点设备的实时人流状况。
人流预测:基于整个商圈及不同关注区域的历史人流数据,建立人流预测模型,预测未来48小时各个区块内每小时人流量及峰值出现的时间,以便相关人员提前处理风险,防患未然。
系统首先展示整个项目不同关注区块的明天的人流峰值信息,点击区块,能够展示系统区块今明两天不同时段的人流状况。已经经过的时间用实线表示,预测的用虚线表示,方便用户查看预测和实际已经发生的人流差异情况。
本发明具有下述优点:本发明实时监测指定区域的人流分布、人员身份信息、人流迁徙动向,并对该区域进行人流预测和预警分析通报,当该区域出现人群骤增情况能提前预测并给出预案,避免事故的发生。
附图说明
图1为本发明的结构框图。
具体实施方式
参照图1所示,本实施例的一种基于MAC码和人脸识别的人流预警方法,其具体包括以下步骤:
第一步,摄像头通过视频监控采集指定范围内出现的关键人群人脸,并进行告警;
第二步,探针探测到客户端手机硬件相关信息(分场强、时间、经纬度(空间)维度);
第三步,摄像头将告警信息上传到云端;
第四步,探针将探测道德客户端硬件信息上传到云端;
第五步,云端根据摄像头的告警信息及探针采集道德信息在时间、距离、历史存留维度下构建机器学习,关联人脸与硬件信息打通匹配校对;
第六步,云端推送打通的结果到可视化平台与大数据整合平台;
第七步,可视化平台和大数据整合平台按照实时视图以分钟级别刷新的方式展示整个系统的热力状况,骤增状况,道路状况、关注人群身份状况、人群造访频次状况以及人群迁徙状况;
第八步,将人群相关的预警和报警消息报告给平台管理员,并自动将消息推送到监测区域的室外大屏幕和客户端手机,起到预警效果。
优选为,第七步具体如下:
热力图主要展示两方面信息,基于大数据对项目内设备采集到的人流进行分析,根据不同设备人流密集程度以不同的颜色结合地图实 时呈现系统人流密集状况。系统能够展示不同单点设备的实时人数和峰值,并且支持进入单点设备详细页面查看单点设备的详细监测状况,为了易用性,热力图下方展示单点设备的实时人数
骤增图体现系统不同单点设备近一段时间相对前一段时间的人数增长状况,并以不同颜色标识人流增长程度:绿色代表增长程度没有达到管理员设定的骤增预警值,人流状况比较正常,黄色代表骤增人数达到预警阈值、需要关注人流增长状况。红色代表骤增人数达到警戒阈值,需要重点关注人流增长状况。
对冲图,基于大数据对探测区域内特定监控点人流密度变化及人流动向进行分析并结合地图,得出各个容易发生危险的对撞点的人流状况,如果容易发生危险的对撞点附件有商厦,窄路,电梯等拥挤或者狭窄的隘口,也会突出展示隘口信息,方便有关部门根据隘口状况采取不同的缓解措施。
路径图示:蓝色路段代表人流正常,黄色路段代表人流比较密集、红色路段代表人流密集,容易发生对撞。
迁徙图:城市规划者有时需要知道不同时间整个商圈内关注迁徙中心的人群流向。用户在系统内设定迁徙中心后,系统就可以展示不同迁徙中心之间的人流迁徙状况。同时能够展示如下细节信息:
用户不选中任何迁徙中心时,系统展示如下三个信息:
最热线路:根据不同迁徙中心的人流状况,展示不同时间的最热迁徙线路
迁入热点:实时展示人群迁入量比较大的迁徙中心
迁出热点:实时展示人群迁出量比较大的迁徙中心
当用户选中某一个迁徙中心时,展示该迁徙中心的迁入迁出信息
迁入:展示其他迁徙中心迁入到本中心的人流状况。
迁出:展示本迁徙中心迁出到其他中心的人流状况
人群分析:根据不同人群停留时间特征,系统分为如下四类人群。固定人群:90天内出现比例>80%,小于等于100%的人。(出现比例=出现天数/到目前为止总天数)
重度访客:90天内,出现比例=出现天数/到目前为止总天数,出现比例大于40%,小于80%的人
偶尔访客:90天内,出现比例=出现天数/到目前为止总天数,出现比例大于0%,小于40%的人
初次访客:90天内,首次出现的人
警戒水位:展示容易发生危险的区块和AP的人流状况,但不会展示系统全部区块和设备的信息。警戒水位展示系统内全部区块和单点设备的实时人流状况。
人流预测:基于整个商圈及不同关注区域的历史人流数据,建立人流预测模型,预测未来48小时各个区块内每小时人流量及峰值出现的时间,以便相关人员提前处理风险,防患未然。
系统首先展示整个项目不同关注区块的明天的人流峰值信息,点击区块,能够展示系统区块今明两天不同时段的人流状况。已经经过的时间用实线表示,预测的用虚线表示,方便用户查看预测和实际已经发生的人流差异情况。
以上所述仅是本发明的优选实施方式,本发明的保护范围并不仅局限于上述实施例,凡属于本发明思路下的技术方案均属于本发明的保护范围。应当指出,对于本技术领域的普通技术人员来说,在不脱离本发明原理前提下的若干改进和润饰,这些改进和润饰也应视为本发明的保护范围。

Claims (2)

  1. 一种基于MAC码和人脸识别的人流预警方法,其具体包括以下步骤:
    第一步,摄像头通过视频监控采集指定范围内出现的关键人群人脸,并进行告警;
    第二步,探针探测到客户端手机硬件相关信息(分场强、时间、经纬度(空间)维度);
    第三步,摄像头将告警信息上传到云端;
    第四步,探针将探测道德客户端硬件信息上传到云端;
    第五步,云端根据摄像头的告警信息及探针采集道德信息在时间、距离、历史存留维度下构建机器学习,关联人脸与硬件信息打通匹配校对;
    第六步,云端推送打通的结果到可视化平台与大数据整合平台;
    第七步,可视化平台和大数据整合平台按照实时视图以分钟级别刷新的方式展示整个系统的热力状况,骤增状况,道路状况、关注人群身份状况、人群造访频次状况以及人群迁徙状况;
    第八步,将人群相关的预警和报警消息报告给平台管理员,并自动将消息推送到监测区域的室外大屏幕和客户端手机,起到预警效果。
  2. 根据权利要求1所述的一种基于MAC码和人脸识别的人流预警方法,其特征在于,所述第七步具体如下:
    热力图主要展示两方面信息
    基于大数据对项目内设备采集到的人流进行分析,根据不同设备人流密集程度以不同的颜色结合地图实时呈现系统人流密集状况。系统能够展示不同单点设备的实时人数和峰值,并且支持进入单点设备详细页面查看单点设备的详细监测状况;
    为了易用性,热力图下方展示单点设备的实时人数;
    骤增图
    骤增图体现系统不同单点设备近一段时间相对前一段时间的人数增长状况,并以不同颜色标识人流增长程度:绿色代表增长程度没有达到管理员设定的骤增预警值,人流状况比较正常,黄色代表骤增人数达到预警阈值、需要关注人流增长状况。红色代表骤增人数达到警戒阈值,需要重点关注人流增长状况;
    对冲图
    基于大数据对探测区域内特定监控点人流密度变化及人流动向进行分析并结合地图,得出各个容易发生危险的对撞点的人流状况,如果容易发生危险的对撞点附件有商厦,窄路,电梯等拥挤或者狭窄的隘口,也会突出展示隘口信息,方便有关部门根据隘口状况采取不同的缓解措施;
    路径图示:蓝色路段代表人流正常,黄色路段代表人流比较密集、红色路段代表人流密集,容易发生对撞;
    迁徙图
    城市规划者有时需要知道不同时间整个商圈内关注迁徙中心的人群流向。用户在系统内设定迁徙中心后,系统就可以展示不同迁徙中心之间的人流迁徙状况。同时能够展示如下细节信息:
    用户不选中任何迁徙中心时,系统展示如下三个信息:
    最热线路:根据不同迁徙中心的人流状况,展示不同时间的最热迁徙线路
    迁入热点:实时展示人群迁入量比较大的迁徙中心;
    迁出热点:实时展示人群迁出量比较大的迁徙中心;
    当用户选中某一个迁徙中心时,展示该迁徙中心的迁入迁出信息;
    迁入:展示其他迁徙中心迁入到本中心的人流状况;
    迁出:展示本迁徙中心迁出到其他中心的人流状况;
    人群分析
    根据不同人群停留时间特征,系统分为如下四类人群;
    固定人群:90天内出现比例>80%,小于等于100%的人;(出现比例=出现天数/到目前为止总天数);
    重度访客:90天内,出现比例=出现天数/到目前为止总天数,出现比例大于40%,小于80%的人;
    偶尔访客:90天内,出现比例=出现天数/到目前为止总天数,出现比例大于0%,小于40%的人;
    初次访客:90天内,首次出现的人;
    警戒水位
    展示容易发生危险的区块和AP的人流状况,但不会展示系统全部区块和设备的信息。警戒水位展示系统内全部区块和单点设备的实时人流状况;
    人流预测
    基于整个商圈及不同关注区域的历史人流数据,建立人流预测模型,预测未来48小时各个区块内每小时人流量及峰值出现的时间,以便相关人员提前处理风险,防患未然;
    系统首先展示整个项目不同关注区块的明天的人流峰值信息,点击区块,能够展示系统区块今明两天不同时段的人流状况;
    已经经过的时间用实线表示,预测的用虚线表示,方便用户查看预测和实际已经发生的人流差异情况。
PCT/CN2017/093937 2016-07-21 2017-07-21 一种基于mac码和人脸识别的人流预警方法 WO2018014873A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610577231.8A CN106128028B (zh) 2016-07-21 2016-07-21 一种基于mac码和人脸识别的人流预警方法
CN201610577231.8 2016-07-21

Publications (1)

Publication Number Publication Date
WO2018014873A1 true WO2018014873A1 (zh) 2018-01-25

Family

ID=57289910

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/093937 WO2018014873A1 (zh) 2016-07-21 2017-07-21 一种基于mac码和人脸识别的人流预警方法

Country Status (2)

Country Link
CN (1) CN106128028B (zh)
WO (1) WO2018014873A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110322049A (zh) * 2019-06-03 2019-10-11 浙江图灵软件技术有限公司 一种公安大数据预警方法
CN110674750A (zh) * 2019-09-25 2020-01-10 浪潮软件集团有限公司 一种智慧城市人员预警及引导系统
CN116977934A (zh) * 2023-08-02 2023-10-31 无锡八英里电子科技有限公司 一种云边结合的人流量预警控制方法及系统
CN117612243A (zh) * 2023-08-18 2024-02-27 全景智联(武汉)科技有限公司 一种基于多层注意力的重点人员行为预警方法及服务器

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106128028B (zh) * 2016-07-21 2018-11-20 深圳奇迹智慧网络有限公司 一种基于mac码和人脸识别的人流预警方法
CN106603747A (zh) * 2016-12-30 2017-04-26 广东创我科技发展有限公司 一种mac地址采集功能的摄像机、系统及数据处理方法
CN106952289B (zh) * 2017-03-03 2019-06-07 中国民航大学 结合深度视频分析的WiFi目标定位方法
CN106927324A (zh) * 2017-04-13 2017-07-07 安徽省沃瑞网络科技有限公司 一种基于人脸识别的售楼管理方法
CN107066978A (zh) * 2017-04-18 2017-08-18 云熠信息科技有限公司 一种人群信息采集分析方法和系统
CN107358314B (zh) * 2017-06-20 2021-03-16 深圳中兴网信科技有限公司 一种热力图的处理方法及系统
CN108024207B (zh) * 2017-12-06 2020-12-01 南京华苏科技有限公司 基于三层防控圈的人流量监控方法
CN108358002B (zh) * 2018-01-25 2019-09-20 揭阳市聆讯软件有限公司 防止电梯救援系统被恶意呼叫的方法、装置及智能设备
CN109640249B (zh) * 2018-11-27 2020-08-11 佛山科学技术学院 一种基于大数据的商场人流量预测系统
CN109856979B (zh) * 2018-12-21 2022-03-25 深圳云天励飞技术有限公司 环境调节方法、系统、终端及介质
CN109919066B (zh) * 2019-02-27 2021-05-25 湖南信达通信息技术有限公司 一种检测轨道交通车厢内乘客密度异常的方法和装置
CN110163083A (zh) * 2019-04-03 2019-08-23 深圳奇迹智慧网络有限公司 用户信息的匹配方法、装置及终端设备
CN110950197B (zh) * 2019-12-12 2022-04-01 中国联合网络通信集团有限公司 一种智能电梯的选择方法及智能电梯控制装置
CN111147620A (zh) * 2019-12-25 2020-05-12 北京天翔睿翼科技有限公司 一种人脸识别FaceID匹配无线接入点中某个MAC地址方法
CN111866736A (zh) * 2020-06-12 2020-10-30 深圳市元征科技股份有限公司 一种风险提醒方法、风险提醒装置及服务器
CN112188478B (zh) * 2020-09-29 2023-04-07 浙江新再灵科技股份有限公司 基于大数据分析的常驻人口数据采集方法
CN112866919B (zh) * 2021-01-05 2022-02-11 西安交通大学 基于室内人员定位和行为感知的非入侵安防方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005039181A1 (ja) * 2003-10-21 2005-04-28 Matsushita Electric Industrial Co., Ltd. 監視装置
CN204348028U (zh) * 2015-01-22 2015-05-20 曾钰之 一种楼梯间人流量管理装置
CN105246033A (zh) * 2015-09-14 2016-01-13 百度在线网络技术(北京)有限公司 一种基于终端定位的人群状态监测方法和监测装置
CN105282523A (zh) * 2015-11-23 2016-01-27 上海赢谊电子设备有限公司 一种人流量估计电子设备及其在公交站亭的使用方法
CN105681768A (zh) * 2016-03-29 2016-06-15 浪潮通信信息系统有限公司 一种通过通信数据实现人流实时监控的方法
CN106128028A (zh) * 2016-07-21 2016-11-16 深圳奇迹智慧网络有限公司 一种基于mac码和人脸识别的人流预警方法

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101174298A (zh) * 2006-11-02 2008-05-07 上海银晨智能识别科技有限公司 分散点大流量的人脸识别系统及识别方法
CN104683995B (zh) * 2013-11-27 2018-04-13 北京易汇众盟网络技术有限公司 一种访客信息处理系统及方法
CN104811894B (zh) * 2015-03-09 2018-08-21 安徽云之迹信息技术有限公司 一种人流分布的统计方法、装置及服务器
CN105160321A (zh) * 2015-09-05 2015-12-16 深圳市飞思未来云媒体科技有限公司 一种基于视觉与无线定位的移动终端身份确认方法
CN105512772B (zh) * 2015-12-22 2020-09-15 重庆邮电大学 一种基于移动网络信令数据的动态人流量预警方法
CN105611492A (zh) * 2016-02-29 2016-05-25 京信通信技术(广州)有限公司 一种定位信息的处理方法、装置及系统
CN105791313A (zh) * 2016-04-22 2016-07-20 上海良相智能化工程有限公司 无线网络信息侦讯平台

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005039181A1 (ja) * 2003-10-21 2005-04-28 Matsushita Electric Industrial Co., Ltd. 監視装置
CN204348028U (zh) * 2015-01-22 2015-05-20 曾钰之 一种楼梯间人流量管理装置
CN105246033A (zh) * 2015-09-14 2016-01-13 百度在线网络技术(北京)有限公司 一种基于终端定位的人群状态监测方法和监测装置
CN105282523A (zh) * 2015-11-23 2016-01-27 上海赢谊电子设备有限公司 一种人流量估计电子设备及其在公交站亭的使用方法
CN105681768A (zh) * 2016-03-29 2016-06-15 浪潮通信信息系统有限公司 一种通过通信数据实现人流实时监控的方法
CN106128028A (zh) * 2016-07-21 2016-11-16 深圳奇迹智慧网络有限公司 一种基于mac码和人脸识别的人流预警方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110322049A (zh) * 2019-06-03 2019-10-11 浙江图灵软件技术有限公司 一种公安大数据预警方法
CN110674750A (zh) * 2019-09-25 2020-01-10 浪潮软件集团有限公司 一种智慧城市人员预警及引导系统
CN116977934A (zh) * 2023-08-02 2023-10-31 无锡八英里电子科技有限公司 一种云边结合的人流量预警控制方法及系统
CN117612243A (zh) * 2023-08-18 2024-02-27 全景智联(武汉)科技有限公司 一种基于多层注意力的重点人员行为预警方法及服务器

Also Published As

Publication number Publication date
CN106128028B (zh) 2018-11-20
CN106128028A (zh) 2016-11-16

Similar Documents

Publication Publication Date Title
WO2018014873A1 (zh) 一种基于mac码和人脸识别的人流预警方法
WO2018032938A1 (zh) 基于探针的人流预警分析方法和系统
CN105512772B (zh) 一种基于移动网络信令数据的动态人流量预警方法
Petrovska et al. Traffic congestion analysis visualisation tool
Ye et al. Methodology and its application for community-scale evacuation planning against earthquake disaster
CN108198416A (zh) 一种手机信令与路网大数据的融合方法及其应用与系统
CN110555381A (zh) 人员疏导系统及人员疏导方法
KR20180129500A (ko) 위성 영상을 이용한 재해 및 재난 경보 방법 및 그 방법을 수행하는 재해 및 재난 경보 서버
CN105741486A (zh) 基于手机定位数据的城市公共空间踩踏事故实时预警方法
CN105303831A (zh) 一种基于通信数据判断高速路拥堵情况的方法
KR101722989B1 (ko) 기지국 유동인구 정보를 활용한 재난 관리 장치 및 방법
CN113744108B (zh) 基于大数据的智慧消防控制方法和系统
Yabe et al. Estimating Evacuation Hotspots using GPS data: What happened after the large earthquakes in Kumamoto, Japan
CN104157141A (zh) 基于物联网的智能交通监管系统
CN112330066A (zh) 一种基于地理信息的台风期间出行风险预警的方法
JP2002334184A (ja) リアルタイム状況収集システム
Song et al. Using mobile sensing technology for capturing people mobility information
Ali et al. The Importance of Google Maps for Traffic in Calculating the Level of Service for the Road and Traffic Delay
US10368037B2 (en) Public safety camera monitoring system and method
KR20080021225A (ko) 교통/재난 및 지리적 현황에 대한 지리적 감시시스템
CN110523041A (zh) 一种智能化的消火栓流速监测系统、方法及存储介质
Liu et al. A spatial analysis approach to evacuation management: shelter assignment and routing
November et al. Inquiry In Control Rooms–An Analysis Through The Lenses of Space, Time and Practice
Asgary et al. Emergency Calls in the City of Vaughan (Canada) During the COVID-19 Pandemic: A Spatiotemporal Analysis
Traganmaturapot et al. Foot Traffic Analysis Using Wi-Fi Sensor During the Tokyo 2020 Olympics and Paralympics

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17830507

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 04.07.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17830507

Country of ref document: EP

Kind code of ref document: A1