CN104616432B - A kind of density of stream of people Intelligent Recognition and control method and system - Google Patents
A kind of density of stream of people Intelligent Recognition and control method and system Download PDFInfo
- Publication number
- CN104616432B CN104616432B CN201510057810.5A CN201510057810A CN104616432B CN 104616432 B CN104616432 B CN 104616432B CN 201510057810 A CN201510057810 A CN 201510057810A CN 104616432 B CN104616432 B CN 104616432B
- Authority
- CN
- China
- Prior art keywords
- people
- stream
- density
- index
- early warning
- Prior art date
- Legal status (The legal status 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 status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/002—Generating a prealarm to the central station
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Alarm Systems (AREA)
Abstract
A kind of density of stream of people Intelligent Recognition and control method and system.By digital high-definition camera Real-time Collection to crowded passage a certain transverse section on dynamic people's stream picture, by IP network system transfers to computer, the intellectual analysis software people's stream picture of seizure per second that installs on computer, identify the number on selected channel cross-section, and real-time density of stream of people index is calculated according to specific mathematical model, then early warning signal is sent to artificial abortion's control platform.After artificial abortion's control platform is connected to early warning signal, alert messages are issued externally, while taking corresponding control measure.The method can artificial abortion's close quarters such as effective control market, square, tourist attractions personnel amount, the security incident such as prevent congestion, trample, to stablizing traffic, public security order, it is ensured that safety is significant.
Description
Technical field
The present invention relates to the field such as traffic administration, public place management, tourist attraction management, and in particular to a kind of artificial abortion is close
Degree Intelligent Recognition and control method and system.
Background technology
In recent years, the tread event that the artificial abortion's congestion on market, square, tourist attractions and recreation ground and other places is caused has repeatly to be sent out
Raw, some even cause serious casualties.For the generation for effectively preventing artificial abortion's congestion, trampling accident, it is necessary in real time
Density of stream of people on monitoring main thoroughfare, and density of stream of people and safe early warning letter is issued to channel management unit and surrounding area
Breath.
Content of the invention
It is an object of the invention to provide artificial abortion's close quarters such as a kind of energy effective control market, square, tourist attractions
Personnel amount, the security incident such as prevents congestion, tramples, to stablizing traffic, public security order, it is ensured that safety has important
The density of stream of people Intelligent Recognition of meaning and control method and system.
For reaching above-mentioned purpose, the system of the present invention includes that image acquisition units, image acquisition units are passed by IP network
The image result that the image transmitting for gathering will be analyzed by defeated unit to computer intelligence analytic unit, computer intelligence analytic unit
Artificial abortion's control platform is sent to by signal conversion unit.
The image acquisition units of the present invention include some digital high-definition cameras of real-time image acquisition data, and numeral is high
The shooting mouth of clear video camera shoots the vertical view picture of road or passage perpendicular to road or passage.
Described computer intelligence analytic unit is made up of computer and the intellectual analysis software that installs on computers.
Described artificial abortion's control platform is to the field erected electronic display of passage, media releasing platform, channel management list
Position or passage access management system real-time release density of stream of people information, while issue according to density of stream of people information different grades of pre-
Alarming information.
The identification and control method of the present invention is as follows：
1) the digital high-definition camera Real-time Collection during artificial abortion's dynamic menu is by image acquisition units, and passed by IP network
Defeated unit is transmitted to computer intelligence analytic unit；
2) computer intelligence analytic unit is per second catches people's stream picture, is identified in image by intellectual analysis software
Number, and calculate density of stream of people index K and safety index G；
3) then intellectual analysis software by density of stream of people index K and safety index G by signal conversion unit to artificial abortion control
Platform real-time release density of stream of people index K and safety index G processed；
4) artificial abortion's control platform to the field erected electronic display of passage, media releasing platform, channel management unit or
Passage goes out to enter a profession management system real-time release K, G-value, while according to safety index G-value size, issuing different grades of early warning letter
Breath.
Described intellectual analysis software is identified to the dynamic artificial abortion's picture transmitted to computer and analyzes, and recognizes and divides
Analysis process is as follows：
The first step：The overhead view image of some transverse section of the passage for needing monitoring is selected in dynamic menu, per second is caught
An image is caught, adopts the method for Identification of Images to identify the number in image for n.
Second step：Density of stream of people index K and the channel security index that people's stream picture reflects is calculated using formula 1 and 2
G：
K=n/N (formula 1)
K channel cross section density of stream of people indexes, dimensionless；
The number that n is recognized from the artificial abortion's picture for capturing per second, individual；
The safe number allowed in N channel cross sections, individual.
G=t/T (formula 2)
G channel security indexes, dimensionless；
Cumulative time when K values are more than or equal to 1 in the t management times, s；
T manages time, s.
The cross-sectional length of the overhead view image of some transverse section of described passage is less than or equal to 10 meters, and transverse section is bowed
Width is regarded as 200～300mm.
Described artificial abortion's control platform is to the field erected electronic display of passage, media releasing platform, channel management list
Position or passage access management system real-time release density of stream of people index K and safety index G-value, while big according to safety index G-value
Little issue different grades of early warning information, specially：
When G-value is 0.9～1.0, it is red early warning, represents highly dangerous；
When G-value is 0.8～0.9, it is orange early warning, represents dangerous；
When G-value is 0.6～0.8, it is yellow early warning, represents dangerous；
When G-value is 0.4～0.6, it is blue early warning, represents safer；
When G-value is less than 0.4, it is green early warning, represents safety.
Early warning information proposed by the present invention is issued towards specific region and personnel, to promoting the civilization trip of the whole society and protecting
The life security of the barrier masses is significant.
Description of the drawings
Fig. 1 is principle of the invention figure.
Specific embodiment
Below in conjunction with the accompanying drawings the present invention is described in further detail.
Referring to Fig. 1, the system of the present invention includes the figure of the composition of some digital high-definition cameras 6 of real-time image acquisition data
As collecting unit 1, the shooting mouth of digital high-definition camera 6 shoots the vertical view picture of road or passage perpendicular to road or passage,
Image acquisition units 1 are by IP network transmission unit 2 by the image transmitting for gathering to computer intelligence analytic unit 3, computer
Intellectual analysis unit 3 is made up of computer 7 and the intellectual analysis software 8 that installs on computers, computer intelligence analytic unit 3
The result that analysis is obtained is sent to artificial abortion's control platform 5 by signal conversion unit 4, and artificial abortion's control platform 5 is to passage scene
The electronic display 9 of installation, media releasing platform 10,11 real-time release artificial abortion of channel management unit or passage access management system
Density information, while issue different grades of early warning information according to density of stream of people information.
The density of stream of people Intelligent Recognition and control method of the present invention, comprises the following steps：
1) artificial abortion's dynamic menu is by 6 Real-time Collection of digital high-definition camera in image acquisition units 1, and passes through IP network
Transmission unit 2 is transmitted to computer intelligence analytic unit 3；
2) computer intelligence analytic unit 3 is per second catches people's stream picture, is identified in image by intellectual analysis software 8
Number, and calculate density of stream of people index K and safety index G；
Its detailed process is as follows：
The first step：In dynamic menu, (cross-sectional length is less than the overhead view image of the monitored specific transverse section of passage of selection
Or 10 meters are equal to, and the vertical view width of transverse section is 200～300mm), image of seizure per second is known using intellectual analysis software 8
The number not gone out in image is n.
Second step：Density of stream of people index K and the channel security index that people's stream picture reflects is calculated using formula 1 and 2
G：
K=n/N (formula 1)
K channel cross section density of stream of people indexes, dimensionless；
The number that n is recognized from the artificial abortion's picture for capturing, individual；
The safe number allowed in N channel cross sections, individual.
G=t/T (formula 2)
G channel security indexes, dimensionless；
Cumulative time when K values are more than or equal to 1 in the t management times, s；
T manages time, s.
3) then intellectual analysis software 8 by density of stream of people index K and safety index G by signal conversion unit 4 to artificial abortion
Control platform 5 real-time release density of stream of people index K and safety index G；
4) artificial abortion's control platform 5 is to the field erected electronic display 9 of passage, media releasing platform 10, channel management list
Position or 11 real-time release K of passage access management system, G-value, while according to safety index G-value size, issue different grades of pre-
Alarming information is specially：
When G-value is 0.9～1.0, it is red early warning, represents highly dangerous；
When G-value is 0.8～0.9, it is orange early warning, represents dangerous；
When G-value is 0.6～0.8, it is yellow early warning, represents dangerous；
When G-value is 0.4～0.6, it is blue early warning, represents safer；
When G-value is less than 0.4, it is green early warning, represents safety.
During the vacation, famous tourist attractions the Forbidden City welcomes rush hour to National Day length, in order to prevent density of stream of people excessive, causes
Artificial abortion's congestion, tramples accident then, and Security Administration Department can be on the main thoroughfares such as the trip major trunk roads in the Forbidden City, stone bridge
Configuration artificial abortion image acquisition units 1.Artificial abortion's image acquisition units 1 by the overhead view image of channel cross-section, by IP network system 2
Transmit to computer intelligence analytic unit 3.Computer intelligence analytic unit 3 passes through intelligence software operation on computers, from
Select to be about 3～10 meters of monitored space in the overhead view image of channel cross-section, and per second catch the once area image, identify
Number is n, calculates density of stream of people index K and channel security early warning index G, and result of calculation is passed through signal conversion unit 4
Send the pure man flow control platform 5.Artificial abortion's control platform 5 can issue different grades of early warning information according to the size of K, G-value, make trip
People's autonomy selects the travel time, and notes safety, makes Security Administration Department take corresponding safety measure in time, with true
Protect visitor's safety.
For example on National Day one morning 10:00～10:In 05 this 5 minutes, i.e. 300s, the passage that 1s is captured is horizontal
Number on section in the overhead view image of 5 meters of long monitor areas is 10 people, and according to the Forbidden City Security Administration or management warp
From the point of view of testing, the safe number of this 5 meters of monitor areas should be 7 people.The artificial abortion that so software can calculate this second according to formula 1 is close
Degree index K=10/7=1.4.Afterwards, at the 2nd second, until the 300th second, K values are becoming always according to the number difference of monitor area
Change, but the time cumulation more than 1 reaches 260 seconds, then software can calculate the channel security index in this 300s according to formula 2
G=260/300=0.87, and G-value is sent by the pure man flow control platform 5 by signal conversion unit 4.Artificial abortion's control platform 5 is by G
Value and early warning information are issued in the electronic display in the region such as the Forbidden City major trunk roads and stone bridge, are issued and are being had subscribed to the message
In common people's SMS or wechat, issue on the media such as associated television, network.The numerous common people, including just in the Forbidden City, preparation
The visitor of the Forbidden City is entered, K, G-value and early warning information can be known in time.Such as someone is just prepared to enter on the Forbidden City doorway, is passed through
Handset Wechat message learns 10:The 05 channel security index that issues is 0.87, and artificial abortion's control platform 5 has been sent from orange early warning letter
Number, passage is dangerous.In this case, the visitor may be selected to enter.And just after the people of the Forbidden City learns this message, just can be from
Hold observation surrounding enviroment, autonomy ground notes the current safety of personnel or withdraws calmly the Forbidden City.At the same time, artificial abortion's control platform 5
The very first time sends the message to the Forbidden City Security Administration Department, and the mechanism can take corresponding evacuation according to urgent prediction scheme at once
The measure that crowd and postponement personnel pass through, to reduce G-value, and guarantees visitor's safety.
Claims (3)
1. a kind of density of stream of people Intelligent Recognition and control method, it is characterised in that：
1) artificial abortion's dynamic menu is by digital high-definition camera (6) Real-time Collection in image acquisition units (1), and passes through IP network
Transmission unit (2) is transmitted to computer intelligence analytic unit (3)；
2) computer intelligence analytic unit (3) is per second catches people's stream picture, is identified in image by intellectual analysis software (8)
Number, and calculate density of stream of people index K and channel security index G；
Described intellectual analysis software (8) is identified to the dynamic artificial abortion's picture transmitted to computer and analyzes, and recognizes and divides
Analysis process is as follows：
The first step：The overhead view image of the specific transverse section of the monitored passage of selection in dynamic menu, image of seizure per second,
Portrait identification method is adopted to identify the number in image for n；
Second step：Density of stream of people index K and the channel security index G that people's stream picture reflects is calculated using formula 1 and 2：
K=n/N (formula 1)
K channel cross section density of stream of people indexes, dimensionless；
The number that n is recognized from the artificial abortion's picture for capturing, individual；
The safe number allowed in N channel cross sections, individual；
G=t/T (formula 2)
G channel security indexes, dimensionless；
Cumulative time when K values are more than or equal to 1 in the t management times, s；
T manages time s；
3) then intellectual analysis software (8) by density of stream of people index K and channel security index G by signal conversion unit (4) to
Artificial abortion's control platform (5) real-time release density of stream of people index K and channel security index G；
4) artificial abortion's control platform (5) is to the field erected electronic display of passage (9), media releasing platform (10), channel management
Unit or passage access management system (11) real-time release K, G-value, while according to channel security index G-value size, issue different
The early warning information of grade.
2. density of stream of people Intelligent Recognition according to claim 1 and control method, it is characterised in that：The spy of described passage
The cross-sectional length of overhead view image of transverse section is determined less than or equal to 10 meters, the vertical view width of transverse section is 200～300mm.
3. density of stream of people Intelligent Recognition according to claim 1 and control method, it is characterised in that：Described people's flow control
Platform (5) comes in and goes out to the field erected electronic display of passage (9), media releasing platform (10), channel management unit or passage
Management system (11) real-time release density of stream of people index K and channel security index G-value, while big according to channel security index G-value
Little issue different grades of early warning information, specially：
When G-value is 0.9～1.0, it is red early warning, represents highly dangerous；
When G-value is 0.8～0.9, it is orange early warning, represents dangerous；
When G-value is 0.6～0.8, it is yellow early warning, represents dangerous；
When G-value is 0.4～0.6, it is blue early warning, represents safer；
When G-value is less than 0.4, it is green early warning, represents safety.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510057810.5A CN104616432B (en) | 2015-02-04 | 2015-02-04 | A kind of density of stream of people Intelligent Recognition and control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510057810.5A CN104616432B (en) | 2015-02-04 | 2015-02-04 | A kind of density of stream of people Intelligent Recognition and control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104616432A CN104616432A (en) | 2015-05-13 |
| CN104616432B true CN104616432B (en) | 2017-03-15 |
Family
ID=53150864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510057810.5A Expired - Fee Related CN104616432B (en) | 2015-02-04 | 2015-02-04 | A kind of density of stream of people Intelligent Recognition and control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104616432B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106548158A (en) * | 2016-11-07 | 2017-03-29 | 华南理工大学 | Crowd density intelligent monitor system and method based on machine vision |
| CN107123234A (en) * | 2017-04-21 | 2017-09-01 | 成都大学 | A kind of automatic monitoring exit region crowd density device and its workflow |
| CN109657625A (en) * | 2018-12-23 | 2019-04-19 | 广东腾晟信息科技有限公司 | A kind of identification of crowd density estimation and method for early warning |
| CN110674750A (en) * | 2019-09-25 | 2020-01-10 | 浪潮软件集团有限公司 | Wisdom city personnel early warning and bootstrap system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202134048U (en) * | 2010-12-29 | 2012-02-01 | 泰安市泰山风景名胜区管理委员会 | Scenic area visitor distribution statistical system |
| CN103049765A (en) * | 2012-12-21 | 2013-04-17 | 武汉经纬视通科技有限公司 | Method for judging crowd density and number of people based on fish eye camera |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3981391B2 (en) * | 2003-10-21 | 2007-09-26 | 松下電器産業株式会社 | Monitoring device |
| US20130101159A1 (en) * | 2011-10-21 | 2013-04-25 | Qualcomm Incorporated | Image and video based pedestrian traffic estimation |
-
2015
- 2015-02-04 CN CN201510057810.5A patent/CN104616432B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202134048U (en) * | 2010-12-29 | 2012-02-01 | 泰安市泰山风景名胜区管理委员会 | Scenic area visitor distribution statistical system |
| CN103049765A (en) * | 2012-12-21 | 2013-04-17 | 武汉经纬视通科技有限公司 | Method for judging crowd density and number of people based on fish eye camera |
Non-Patent Citations (1)
| Title |
|---|
| 旅游景区智能客流统计系统应用研究-以玄武湖为例;马乐等;《中国科技信息》;20130228(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104616432A (en) | 2015-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104616432B (en) | A kind of density of stream of people Intelligent Recognition and control method and system | |
| CN103108159B (en) | Electric power intelligent video analyzing and monitoring system and method | |
| CN102945603B (en) | Method for detecting traffic event and electronic police device | |
| CN101799985B (en) | Highway tunnel traffic identification method | |
| CN201936415U (en) | Automatic forest fire identification and alarm system | |
| WO2009152766A1 (en) | Embedded computer vision warning device for monitoring the flow of passengers on escalator | |
| CN105679043A (en) | 3D radar intelligent bayonet system and processing method thereof | |
| KR101514696B1 (en) | Safety Accident Management System Of Bridge | |
| CN101835032A (en) | Multi-camera crowd-gathered message statistic device and method | |
| CN106530738A (en) | Real-time traffic information generation and service method in tunnel and system thereof | |
| CN104581081A (en) | Passenger-flow analysis method based on video information | |
| CN104680791A (en) | Pedestrian violation information and advertisement networking play device based on video detection | |
| CN109146914B (en) | Drunk driving behavior early warning method for expressway based on video analysis | |
| KR101049758B1 (en) | Method for monitoring total of school zone and system thereof | |
| CN114566056B (en) | Highway tunnel driving safety risk identification, prevention and control method and system | |
| CN105427519A (en) | Intelligent three-in-one alarm system for tunnel | |
| CN109389794A (en) | A kind of Intellectualized Video Monitoring method and system | |
| CN105427618B (en) | Vehicle takes the alarming method for power and system for the band that stops in emergency | |
| CN108012117A (en) | A kind of city based on background modeling is set up a stall detection method | |
| CN110322703A (en) | One kind tests the speed bayonet type intersection safety warning system | |
| CN116597394A (en) | Railway foreign matter intrusion detection system and method based on deep learning | |
| CN106339973A (en) | Guard security system based on data platform and and guard security method thereof | |
| CN110809137A (en) | Campus safety trampling prevention monitoring system and method | |
| CN205584337U (en) | Vehicle event data recorder intelligence video identification system | |
| CN117671918B (en) | Community special area safety identification method and system based on edge server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170315 Termination date: 20180204 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |