CN104616432A - Intelligent identification and control method and system for people flow density - Google Patents
Intelligent identification and control method and system for people flow density Download PDFInfo
- Publication number
- CN104616432A CN104616432A CN201510057810.5A CN201510057810A CN104616432A CN 104616432 A CN104616432 A CN 104616432A CN 201510057810 A CN201510057810 A CN 201510057810A CN 104616432 A CN104616432 A CN 104616432A
- Authority
- CN
- China
- Prior art keywords
- people
- stream
- passage
- early warning
- index
- 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.)
- Granted
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
The invention discloses an intelligent identification and control method and system for people flow density. The intelligent identification and control method includes that transmitting dynamic people flow images on a cross section of a dense people flow passage gathered by a digital high-definition camera to a computer through an IP network system, capturing the people flow images per second through an intelligent analyzing software on the computer, identifying the people number on the cross section of the selected passage, calculating a real-time people flow density index according to a special mathematical model, and sending an early warning signal to a people flow control platform. The people flow control platform publishes a warning message to the outside and adopts corresponding control measures after receiving the early warning signal. The intelligent identification and control method for the people flow density is capable of effectively controlling the people number of the markets, squares, tourist attractions and the like dense people flow regions to avoid crowding, treading and the like accidents; the intelligent identification and control method and system for the people flow density are significant for stabilizing the traffic order and public security order and guaranteeing the travel safety.
Description
Technical field
The present invention relates to the fields such as traffic administration, public place management, tourist attraction management, be specifically related to a kind of people's current density Intelligent Recognition and control method and system.
Background technology
In recent years, in market, square, the ground such as tourist attractions and recreation ground stream of people's tread event caused of blocking up occur repeatedly, some even causes serious casualties.To block up to effectively prevent the stream of people, trampling the generation of accident, must people's current density in real time on monitoring main thoroughfare, and to channel management unit and surrounding area publisher's current density and safe early warning information.
Summary of the invention
The object of the present invention is to provide a kind of personnel amount that effectively can control the crowded regions such as market, square, tourist attractions, prevent security incidents such as blocking up, trample, to stable traffic, public security order, guarantee people's current density Intelligent Recognition that safety is significant and control method and system.
For achieving the above object, system of the present invention comprises image acquisition units, image acquisition units passes through IP network transmission unit by the image transmitting of collection to computer intelligence analytic unit, and the image result of analysis is sent to stream of people's parametric controller by signal conversion unit by computer intelligence analytic unit.
Image acquisition units of the present invention comprises some digital high-definition cameras of real-time image acquisition data, and the shooting mouth of digital high-definition camera is perpendicular to road or passage, shooting road or passage overlook picture.
Described computer intelligence analytic unit is made up of computing machine and the intellectual analysis software installed on computers.
Described stream of people's parametric controller, to the field erected electronic display of passage, media releasing platform, channel management unit or passage access management system real-time release stream of people density information, issues the early warning information of different brackets simultaneously according to stream of people's density information.
Identification of the present invention and control method as follows:
1) stream of people's dynamic menu is by the digital high-definition camera Real-time Collection in image acquisition units, and transfers to computer intelligence analytic unit by IP network transmission unit;
2) computer intelligence analytic unit seizure per second people's stream picture, is identified the number in image by intellectual analysis software, and calculates stream of people dnesity index K and safety index G;
3) then stream of people dnesity index K and safety index G is passed through signal conversion unit to stream of people's parametric controller real-time release stream of people dnesity index K and safety index G by intellectual analysis software;
4) stream of people's parametric controller is to the field erected electronic display of passage, media releasing platform, channel management unit or passage discrepancy row management system real-time release K, G value, simultaneously according to safety index G value size, issues the early warning information of different brackets.
Described intellectual analysis software identifies the dynamic stream of people's picture transferring to computing machine and analyzes, identify and analytic process as follows:
The first step: the overhead view image selecting some transversal section of the passage needing monitoring in dynamic menu, seizure per second image, the method number identified in image adopting Identification of Images is n.
Second step: adopt formula 1 and 2 to calculate stream of people dnesity index K and channel security index G that people's stream picture reflects:
K=n/N (formula 1)
K---channel cross section stream of people dnesity index, dimensionless;
N---the number recognized from the stream of people's picture captured per second, individual;
N---the safe number allowed in channel cross section, individual.
G=t/T (formula 2)
G---channel security index, dimensionless;
T---cumulative time when K value is more than or equal to 1 in administrative time, s;
T---administrative time, s.
The cross-sectional length of the overhead view image of some transversal section of described passage is less than or equal to 10 meters, and the width of overlooking of transversal section is 200 ~ 300mm.
Described stream of people's parametric controller is to the field erected electronic display of passage, media releasing platform, channel management unit or passage access management system real-time release stream of people dnesity index K and safety index G value, issue the early warning information of different brackets simultaneously according to safety index G value size, be specially:
When G value is 0.9 ~ 1.0, be red early warning, represent highly dangerous;
When G value is 0.8 ~ 0.9, be orange early warning, represent dangerous;
When G value is 0.6 ~ 0.8, be yellow early warning, represent dangerous;
When G value is 0.4 ~ 0.6, be blue early warning, represent safer;
When G value is less than 0.4, be green early warning, represent safety.
The early warning information that the present invention proposes is issued towards specific region and personnel, to promoting the trip of the civilization of the whole society and ensureing that the life security of the masses is significant.
Accompanying drawing explanation
Fig. 1 is principle of the invention figure.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
See Fig. 1, the image acquisition units 1 that some digital high-definition cameras 6 that system of the present invention comprises real-time image acquisition data form, the shooting mouth of digital high-definition camera 6 is perpendicular to road or passage, shooting road or passage overlook picture, image acquisition units 1 passes through IP network transmission unit 2 by the image transmitting of collection to computer intelligence analytic unit 3, computer intelligence analytic unit 3 is made up of computing machine 7 and the intellectual analysis software 8 installed on computers, computer intelligence analytic unit 3 is sent to stream of people's parametric controller 5 by analyzing the result obtained by signal conversion unit 4, stream of people's parametric controller 5 is to the field erected electronic display 9 of passage, media releasing platform 10, channel management unit or passage access management system 11 real-time release stream of people density information, issue the early warning information of different brackets according to stream of people's density information simultaneously.
People's current density Intelligent Recognition of the present invention and control method, comprise the following steps:
1) stream of people's dynamic menu is by digital high-definition camera 6 Real-time Collection in image acquisition units 1, and transfers to computer intelligence analytic unit 3 by IP network transmission unit 2;
2) computer intelligence analytic unit 3 seizure per second people's stream picture, is identified the number in image by intellectual analysis software 8, and calculates stream of people dnesity index K and safety index G;
Its detailed process is as follows:
The first step: (cross-sectional length is less than or equal to 10 meters to select the overhead view image of the specific transversal section of monitored passage in dynamic menu, the width of overlooking of transversal section is 200 ~ 300mm), seizure per second image, adopts intellectual analysis software 8 number identified in image to be n.
Second step: adopt formula 1 and 2 to calculate stream of people dnesity index K and channel security index G that people's stream picture reflects:
K=n/N (formula 1)
K---channel cross section stream of people dnesity index, dimensionless;
N---the number recognized from the stream of people's picture captured, individual;
N---the safe number allowed in channel cross section, individual.
G=t/T (formula 2)
G---channel security index, dimensionless;
T---cumulative time when K value is more than or equal to 1 in administrative time, s;
T---administrative time, s.
3) then stream of people dnesity index K and safety index G is passed through signal conversion unit 4 to stream of people's parametric controller 5 real-time release stream of people dnesity index K and safety index G by intellectual analysis software 8;
4) stream of people's parametric controller 5 is to the field erected electronic display 9 of passage, media releasing platform 10, channel management unit or passage access management system 11 real-time release K, G value, simultaneously according to safety index G value size, the early warning information issuing different brackets is specially:
When G value is 0.9 ~ 1.0, be red early warning, represent highly dangerous;
When G value is 0.8 ~ 0.9, be orange early warning, represent dangerous;
When G value is 0.6 ~ 0.8, be yellow early warning, represent dangerous;
When G value is 0.4 ~ 0.6, be blue early warning, represent safer;
When G value is less than 0.4, be green early warning, represent safety.
During long holidays on National Day, famous tourist attractions the Forbidden City welcomes rush hour, in order to prevent people's current density excessive, causes the stream of people to block up, then trample accident, Security Administration Department the main thoroughfare such as trip major trunk roads, stone bridge in the Forbidden City can configure stream of people's image acquisition units 1.Stream of people's image acquisition units 1, by the overhead view image of channel cross-section, transfers to computer intelligence analytic unit 3 by IP network system 2.Computer intelligence analytic unit 3 is by intelligent software operation on computers, the monitored space being about 3 ~ 10 meters is selected from the overhead view image of channel cross-section, and seizure per second once this area image, the number of identifying is n, calculate stream of people dnesity index K and channel security early warning index G, and result of calculation is sent to stream of people's parametric controller 5 by signal conversion unit 4.Stream of people's parametric controller 5 can issue the early warning information of different brackets according to the size of K, G value, make visitor's independence select line time, and note safety, make Security Administration Department take corresponding safety practice in time, to guarantee visitor's safety.
Such as first day on National Day 10:00 ~ 10:05 in the morning these 5 minutes, namely in 300s, on the channel cross-section that 1s captures 5 meters of long guarded regions overhead view image in number be 10 people, and according to the Forbidden City Security Administration or managerial experience, the safe number of these 5 meters of guarded regions should be 7 people.So software can calculate the stream of people dnesity index K=10/7=1.4 of this second according to formula 1.Afterwards, at the 2nd second, until the 300th second, K value is changing according to the number difference of guarded region always, but the time cumulation more than 1 reaches 260 seconds, so software can calculate the channel security index G=260/300=0.87 in this 300s according to formula 2, and by signal conversion unit 4, G value is sent to stream of people's parametric controller 5.G value and early warning information are distributed in the electronic display in the regions such as the Forbidden City major trunk roads and stone bridge by stream of people's parametric controller 5, are distributed in common people's SMS or micro-letter of subscribing to this message, are distributed on the media such as associated television, network.The numerous common people, comprise just in the Forbidden City, prepare to enter the visitor of the Forbidden City, all can know K, G value and early warning information in time.Such as someone is just preparing on the Forbidden City doorway to enter, and learn that the channel security index that 10:05 issues is 0.87 by handset Wechat message, stream of people's parametric controller 5 has sent orange early warning signal, and passage is dangerous.In this case, this visitor can select to enter.And just after the people of the Forbidden City learns this message, just can observe calmly surrounding enviroment, independence ground is noted the current safety of personnel or is withdrawn the Forbidden City calmly.Meanwhile, this message is sent to the Forbidden City Security Administration Department by stream of people's parametric controller 5 very first time, the measure that this mechanism can take corresponding Evacuation and postponement personnel to pass through according to urgent prediction scheme at once, to reduce G value, and guarantees visitor's safety.
Claims (8)
1. people's current density Intelligent Recognition and control system, it is characterized in that: comprise image acquisition units (1), image acquisition units (1) by IP network transmission unit (2) by the image transmitting that gathers to computer intelligence analytic unit (3), the image result analyzed is sent to stream of people's parametric controller (5) by signal conversion unit (4) by computer intelligence analytic unit (3).
2. people's current density Intelligent Recognition according to claim 1 and control system, it is characterized in that: described image acquisition units (1) comprises some digital high-definition cameras (6) of real-time image acquisition data, and the shooting mouth of digital high-definition camera (6) is perpendicular to road or passage, shooting road or passage overlook picture.
3. people's current density Intelligent Recognition according to claim 1 and control system, is characterized in that: described computer intelligence analytic unit (3) is made up of computing machine (7) and the intellectual analysis software (8) installed on computers.
4. people's current density Intelligent Recognition according to claim 1 and control system, it is characterized in that: described stream of people's parametric controller (5), 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 stream of people density information, issues the early warning information of different brackets simultaneously according to stream of people's density information.
5. people's current density Intelligent Recognition and a control method, is characterized in that:
1) stream of people's dynamic menu is by digital high-definition camera (6) Real-time Collection in image acquisition units (1), and transfers to computer intelligence analytic unit (3) by IP network transmission unit (2);
2) computer intelligence analytic unit (3) seizure per second people's stream picture, is identified the number in image by intellectual analysis software (8), and calculates stream of people dnesity index K and safety index G;
3) then stream of people dnesity index K and safety index G is passed through signal conversion unit (4) to stream of people's parametric controller (5) real-time release stream of people dnesity index K and safety index G by intellectual analysis software (8);
4) stream of people's parametric controller (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, simultaneously according to safety index G value size, issue the early warning information of different brackets.
6. people's current density Intelligent Recognition according to claim 5 and control method, is characterized in that: described intellectual analysis software (8) identifies the dynamic stream of people's picture transferring to computing machine and analyzes, and identification and analytic process are divided as follows:
The first step: the overhead view image selecting the specific transversal section of monitored passage in dynamic menu, seizure per second image, adopts the portrait identification method number identified in image to be n;
Second step: adopt formula 1 and 2 to calculate stream of people dnesity index K and channel security index G that people's stream picture reflects:
K=n/N (formula 1)
K---channel cross section stream of people dnesity index, dimensionless;
N---the number recognized from the stream of people's picture captured, individual;
N---the safe number allowed in channel cross section, individual;
G=t/T (formula 2)
G---channel security index, dimensionless;
T---cumulative time when K value is more than or equal to 1 in administrative time, s;
T---administrative time s.
7. people's current density Intelligent Recognition according to claim 6 and control method, is characterized in that: the cross-sectional length of the overhead view image of the specific transversal section of described passage is less than or equal to 10 meters, and the width of overlooking of transversal section is 200 ~ 300mm.
8. people's current density Intelligent Recognition according to claim 5 and control method, it is characterized in that: described stream of people's parametric controller (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 stream of people dnesity index K and safety index G value, issue the early warning information of different brackets simultaneously according to safety index G value size, be specially:
When G value is 0.9 ~ 1.0, be red early warning, represent highly dangerous;
When G value is 0.8 ~ 0.9, be orange early warning, represent dangerous;
When G value is 0.6 ~ 0.8, be yellow early warning, represent dangerous;
When G value is 0.4 ~ 0.6, be blue early warning, represent safer;
When G value is less than 0.4, be green early warning, represent 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 true CN104616432A (en) | 2015-05-13 |
| CN104616432B 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) |
Cited By (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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005039181A1 (en) * | 2003-10-21 | 2005-04-28 | Matsushita Electric Industrial Co., Ltd. | Monitoring device |
| 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 |
| 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 (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005039181A1 (en) * | 2003-10-21 | 2005-04-28 | Matsushita Electric Industrial Co., Ltd. | Monitoring device |
| 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 |
| US20130101159A1 (en) * | 2011-10-21 | 2013-04-25 | Qualcomm Incorporated | Image and video based pedestrian traffic estimation |
| 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 |
|---|
| 马乐等: "旅游景区智能客流统计系统应用研究-以玄武湖为例", 《中国科技信息》 * |
Cited By (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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104616432B (en) | 2017-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104902227B (en) | A kind of substation safety cap wear condition video monitoring system | |
| CN106251578B (en) | Stream of people's early warning analysis method and system based on probe | |
| CN104766086B (en) | The monitoring and managing method and system of a kind of way mark | |
| CN104616432A (en) | Intelligent identification and control method and system for people flow density | |
| CN104680791A (en) | Pedestrian violation information and advertisement networking play device based on video detection | |
| CN104240505B (en) | Method for reading road traffic video image information | |
| CN110769195B (en) | Intelligent monitoring and recognizing system for violation of regulations on power transmission line construction site | |
| CN105117683B (en) | Detection and early warning method for dense crowd in public place | |
| CN104680794A (en) | Vehicle-mounted monitoring terminal as well as bus lane monitoring method and system based on terminal | |
| WO2009152766A1 (en) | Embedded computer vision warning device for monitoring the flow of passengers on escalator | |
| CN104320616A (en) | Video monitoring system based on three-dimensional scene modeling | |
| KR101514696B1 (en) | Safety Accident Management System Of Bridge | |
| CN109979242A (en) | A kind of freeway tunnel lane change, overtake other vehicles prior-warning 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 | |
| CN108012117A (en) | A kind of city based on background modeling is set up a stall detection method | |
| CN109801421A (en) | A kind of subway intelligent and safe detection system and method | |
| CN110322703A (en) | One kind tests the speed bayonet type intersection safety warning system | |
| CN106412127A (en) | IPv6 and IPv4 dual-stack compatible road monitoring video analysis system | |
| CN113588664A (en) | Vehicle-mounted road defect rapid inspection and analysis system | |
| CN115762120A (en) | Holographic sensing early warning system based on whole highway section | |
| CN105427618A (en) | Method and system for warning in case of vehicle's occupation of emergency parking strip | |
| CN203812397U (en) | Urban road video monitor system | |
| CN110809137A (en) | Campus safety trampling prevention monitoring system and method | |
| CN108682154B (en) | Road congestion detection system based on deep learning analysis of traffic flow state change |
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 |