CN106412507A - Intelligent monitoring method and system of personnel flow - Google Patents
Intelligent monitoring method and system of personnel flow Download PDFInfo
- Publication number
- CN106412507A CN106412507A CN201610873481.6A CN201610873481A CN106412507A CN 106412507 A CN106412507 A CN 106412507A CN 201610873481 A CN201610873481 A CN 201610873481A CN 106412507 A CN106412507 A CN 106412507A
- Authority
- CN
- China
- Prior art keywords
- personnel
- information
- flow
- video monitoring
- real
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 138
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004458 analytical method Methods 0.000 claims description 32
- 239000000284 extract Substances 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 13
- 238000012546 transfer Methods 0.000 claims description 12
- 238000011217 control strategy Methods 0.000 claims description 10
- 230000008447 perception Effects 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000003556 assay Methods 0.000 claims description 2
- 239000003550 marker Substances 0.000 claims description 2
- 230000004907 flux Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 7
- 206010000210 abortion Diseases 0.000 description 5
- 231100000176 abortion Toxicity 0.000 description 5
- 239000002609 medium Substances 0.000 description 5
- 238000004590 computer program Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000002730 additional effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000012120 mounting media Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an intelligent monitoring method and system of personnel flow. The problem that the personnel flow cannot be monitored in real time by the video monitoring mode in the prior art is solved. The intelligent monitoring method of personnel flow comprises the following steps: collecting video monitoring data in real time; extracting a target facility in the video monitoring data collected in real time; counting the personnel flow information of personnel occurring in the target facility in the video monitoring data in real time; and determining personnel flow management and control information of a monitoring scene corresponding to the video monitoring data according to the personnel flow information counted in real time.
Description
Technical field
The present invention relates to technical field of video monitoring is and in particular to a kind of intelligent control method of personnel's flow and system.
Background technology
With the raising of the popularization of broadband network, the development of computer technology and image processing techniquess, video monitoring skill
Art is just penetrating into the various field such as education, government, amusement, medical treatment, hotel more and more widely.Especially in safety-security area, video
Monitoring is the important means assisting public safety department to fight crime, maintain social stability.But the analysis of existing video monitoring
Method can only carry out manual analyses afterwards based on the monitor video being gathered it is impossible to according to public place personnel's traffic conditions
Monitor in real time and take corresponding management and control measures in real time.Therefore, it is badly in need of a kind of intelligence prison being capable of monitor in real time personnel's flow
Prosecutor formula.
Content of the invention
In view of this, embodiments provide a kind of intelligent control method of personnel's flow and system, solve existing
Have video monitoring mode in technology cannot monitor in real time personnel's flow problem.
A kind of intelligent control method of personnel's flow provided in an embodiment of the present invention, including：Real-time Collection video monitoring number
According to；Extract the target facility in the video monitoring data of Real-time Collection；Mesh is occurred in video monitoring data described in real-time statistics
Personnel's flow information of personnel in mark facility-wide；And described video is determined according to personnel's flow information of described real-time statistics
Personnel's traffic management and control information of the monitoring scene corresponding to monitoring data.
A kind of intelligent monitor system of personnel's flow provided in an embodiment of the present invention, including：Environmental perception device, for reality
When gather video monitoring data；Geographical sign analytical equipment, the video for extracting described environmental perception device Real-time Collection is supervised
Target facility in control data；Statistic device, for occurring in described target facility in video monitoring data described in real-time statistics
In the range of personnel personnel's flow information；And decision making device, for the personnel's flow according to described statistic device real-time statistics
Information determines personnel's traffic management and control information of the monitoring scene corresponding to described video monitoring data.
Personnel's flux monitoring method provided in an embodiment of the present invention and system, by the video monitoring data to Real-time Collection
The extraction of middle target facility, and to occurring in the more accurately real of personnel's flow information of personnel in this target facility-wide
Shi Tongji is it is achieved that monitor in real time to personnel's flow, and can determine that video according to personnel's flow information of this real-time statistics
Personnel's traffic management and control information of the monitoring scene corresponding to monitoring data, in order to take corresponding personnel's traffic management and control to arrange in time
Apply, in addition, when personnel's flow information of this real-time statistics corresponds to the inlet/outlet of public place, it may also be used for estimate this public affairs
Daily personnel's flow in place altogether.
Brief description
The flow chart that Fig. 1 show a kind of intelligent control method of personnel's flow of one embodiment of the invention offer.
The flow chart that Fig. 2 show a kind of intelligent control method of personnel's flow of another embodiment of the present invention offer.
The flow chart that Fig. 3 show a kind of intelligent control method of personnel's flow of another embodiment of the present invention offer.
Fig. 4 show a kind of structural representation of the intelligent monitor system of personnel's flow of one embodiment of the invention offer.
The monitoring that is based on of intelligent monitor system that Fig. 5 show a kind of personnel's flow of one embodiment of the invention offer regards
Frequency intelligent information illustraton of model.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.Based on this
Embodiment in invention, the every other reality that those of ordinary skill in the art are obtained under the premise of not making creative work
Apply example, broadly fall into the scope of protection of the invention.
Fig. 1 show a kind of schematic flow sheet of the intelligent control method of personnel's flow of one embodiment of the invention offer.
As shown in figure 1, the intelligent control method of this personnel's flow includes：
Step 101：Real-time Collection video monitoring data.
Some essential informations that this video monitoring data directly collects for head end video collecting device, directly as rear
The continuous basic resources data carrying out further real-time intelligent analysis.In an embodiment of the present invention, the video monitoring of Real-time Collection
The monitoring personnel that data also can directly issue Surveillance center is checked so that monitoring personnel being capable of real-time oversight whole personnel flow intelligence
Automatically carrying out of process can be monitored.
In an embodiment of the present invention, the video monitoring data of this Real-time Collection may include monitor video and following items
One or more of：Video acquisition positional information and video acquisition temporal information.Wherein monitor video is subsequently to enter administrative staff
The resource data that flow information/personnel's body dynamics information extracts, video acquisition positional information and video acquisition temporal information can
It is used for the when and where of clear and definite current persons' traffic monitoring scene as additional attribute information.
Step 102：Extract the target facility in the video monitoring data of Real-time Collection.
This target facility is scene facility to be monitored, can be set according to actual monitoring demand by developer, for example,
If the monitoring personnel situation for certain railway station floor ladder crowd's congestion of interest, target facility can be set to this train
Stand this floor ladder；If monitoring personnel wants to monitor/count daily artificial abortion's situation of certain large-scale public place (as amusement park), can be by
Target facility is set to entrance or the outlet of this large-scale public place.For the target facility of this setting, image pair can be based on
As extractive technique directly extracts from video image.
Step 103：Personnel's flow information of personnel in target facility-wide is occurred in real-time statistics video monitoring data.
This target facility-wide monitors the difference of demand and does different set also dependent on target facility and monitoring personnel,
For example, if monitoring personnel is wanted to monitor the situation of certain railway station floor ladder crowd's congestion, flood stair can be set to target
Facility-wide, if the entrance of large-scale public place is set to target facility by monitoring personnel, target facility-wide can enter from this
Mouth carries out the expansion of certain area to surrounding or side, and the concrete scope expanding sets also dependent on the demand of monitoring personnel
Fixed.The labelling of this target facility-wide can be realized by setting detection graticule around target facility, and for example monitoring personnel can
The surrounding target facility setting true graticule of non-physical on the video image of the video monitoring data of Real-time Collection, also can be in video
Pre-set the true graticule of physics in monitoring scene corresponding to monitoring data, occur in this target facility-wide for statistics
Personnel's flow.
Target facility based on extraction and the target facility-wide determining, whenever personnel occur in this target facility
In the range of just the quantity of personnel is added one.It should be appreciated that personnel's flow information is not simple digital information, due to video prison
Control data possesses time shafts, and this personnel's flow information should also be based on the propulsion of time shafts and changes, i.e. this personnel
Contain all time points in flow information or under the time period, occur in the personnel amount in target facility-wide.
Step 104：Monitoring scene corresponding to video monitoring data is determined according to personnel's flow information of real-time statistics
Personnel's traffic management and control information.
Specifically, the determination process of this personnel's traffic management and control information can be based on personnel's flow under different personnel's flow status
The pre-training gained model realization of the machine description of management and control strategy.For example, the maximum personnel's stream being allowed under current monitoring scene
Measure as 200 people beat/min, and personnel's flow that monitor in real time is drawn has reached 160 people beat/min, now suggestion is taken
Slight personnel's traffic management and control strategy；And when personnel's flow that monitor in real time is drawn reaches 280 people beat/min, illustrate current
Personnel's flow in target facility-wide under monitoring scene, seriously beyond the traffic capacity, may interfere with public safety (such as：
It may happen that the security incident such as trampling) it is proposed that taking strict personnel's traffic management and control strategies such as orderly evacuation.It should be appreciated that people
Concrete corresponding relation between member's traffic management and control information and personnel's flow information of monitor in real time can be by monitoring personnel according to reality
Need and adjust, but adjust in any case, this corresponding relation all can be based on pre-training gained model and sets up,
The present invention does not limit to this specific corresponding to relation.
In an embodiment of the present invention, when target facility is set to entrance or the outlet of public place, this personnel's flow
Intelligent control method further include：Estimate daily personnel's stream of this public place according to personnel's flow information of real-time statistics
Amount.
Personnel's flux monitoring method provided in an embodiment of the present invention and system, by the video monitoring data to Real-time Collection
The extraction of middle target facility, and to occurring in the more accurately real of personnel's flow information of personnel in this target facility-wide
Shi Tongji is it is achieved that monitor in real time to personnel's flow, and can determine that video according to personnel's flow information of this real-time statistics
Personnel's traffic management and control information of the monitoring scene corresponding to monitoring data, in order to take corresponding personnel's traffic management and control to arrange in time
Apply, in addition, when personnel's flow information of this real-time statistics corresponds to the inlet/outlet of public place, it may also be used for estimate this public affairs
Daily personnel's flow in place altogether.
Fig. 2 show a kind of schematic flow sheet of personnel's flux monitoring method of one embodiment of the invention offer.With Fig. 1 institute
The personnel's flux monitoring method showing is different, and the method shown in Fig. 2 further includes：
Step 201：Personnel's motion feature of personnel in target facility-wide is occurred in extract real-time video monitoring data
Information.
In an embodiment of the present invention, the body dynamics information of personnel may include one or more of following items：People
Member's movement locus, personnel's direction of motion and personnel's movement velocity, for clearly occurring in the people in target facility-wide further
Personnel's motion feature of member.
It should be appreciated that more diversified personnel's traffic management and control strategy be can achieve based on diversified body dynamics information, this
A little characteristic informations can comprehensively determine personnel's traffic management and control information with personnel's flow information.For example, when personnel's body dynamics information institute
Including personnel motion trail almost identical, and movement velocity is slower, and personnel's flow information has shown beyond current monitor
During the handling capacity of scene, setting artificial abortion can be taken to dredge personnel's traffic management and control strategy of box stall.For another example, when motion feature is believed
The included personnel's direction of motion of breath includes contrary both direction, and personnel's flow information has shown beyond current monitor field
The handling capacity of scape, then can take by the artificial abortion of this both direction separately, such as guide one of direction artificial abortion and lead to another
Personnel's traffic management and control strategy in road.As it was previously stated, personnel's flow information of personnel's traffic management and control information and monitor in real time and real-time
Concrete corresponding relation between the body dynamics information extracting also can be adjusted by monitoring personnel according to actual needs, the present invention couple
This specific corresponding to relation does not equally limit.
Step 202：Personnel's body dynamics information of the personnel's flow information based on real-time statistics and extract real-time generates language
Adopted analysis result.
For example, this semantic analysis result is represented by：Personnel's flow under current monitoring scene is 280 people beat/min, its
The track of middle personnel's motion is almost identical, and movement velocity is slower.
Step 203：Right based on this semantic analysis result and different personnel's flow information and personnel's body dynamics information institute
Answer the pre-training gained model of the machine description of personnel's traffic management and control strategy, determine the monitoring corresponding to video monitoring data in real time
Personnel's traffic management and control information of scene.
For example, based on semantic analysis result above-mentioned it may be determined that personnel's traffic management and control information can be：Current state
For personnel's congestion, may interfere with public safety (such as：It may happen that the security incident such as trampling) it is proposed that setting artificial abortion dredges box stall
Evacuated in order.
In an embodiment of the present invention, personnel's motion feature of personnel's flow information of this real-time statistics and extract real-time
Information can be saved.By receiving with personnel's body dynamics information, video monitoring period or personnel's flow information for inquiry
The query statement of condition, to transfer and to occur in target under all video monitoring time periods corresponding with personnel's body dynamics information and set
Personnel's flow information of the personnel in the range of applying, or transfer all personnel body dynamics information corresponding with the video monitoring period and
Occur in personnel's flow information of the personnel in target facility-wide, or transfer all video prison corresponding with personnel's flow information
Personnel's body dynamics information under the control time period.
Fig. 3 show a kind of schematic flow sheet of personnel's flux monitoring method of another embodiment of the present invention offer.With Fig. 2
Shown method is different, and the personnel's flux monitoring method shown in Fig. 3 further includes：
Step 301：The region in the region residing for personnel occurring in target facility-wide is intercepted from video monitoring data
Video monitoring data.
Step 302：From this area video monitoring data, extract real-time occurs in the personnel of personnel in target facility-wide
Body dynamics information.
By from video monitoring data intercept area video monitoring data, eliminate with current monitor occur in target
The video monitoring data in the unrelated region of the personnel in facility-wide, decreases the calculating of subsequent extracted personnel's body dynamics information
Amount, mitigates the computation burden of hardware analysis resource.
It should be noted that the number of steps in the method for the invention is used only as the reference of this step, it is not offered as holding
Row order, because some actions can occur according to order different that is described herein and indicating, application claims are protected
The not execution sequence institute by these actions is limited by the subject content of shield.In addition, the description of abovementioned steps is not excluded for the method also
Can include obtaining the additional step of additional effect.It is also understood that described in different embodiments or flow process
Method and step can be mutually combined or replace.
Fig. 4 show a kind of structural representation of the intelligent monitor system of personnel's flow of one embodiment of the invention offer.
As shown in figure 4, the intelligent monitor system of this personnel's flow includes：
Environmental perception device 401, for Real-time Collection video monitoring data；
Geographical sign analytical equipment 402, the mesh in the video monitoring data being gathered for extraction environment sensing device 401
Mark facility；
Statistic device, for occurring in personnel's flow of personnel in target facility-wide in real-time statistics video monitoring data
Information；And
Decision making device 403, for determining video monitoring data institute according to personnel's flow information of statistic device real-time statistics
Personnel's traffic management and control information of corresponding monitoring scene.
In an embodiment of the present invention, when the target facility that geographical MARKER ASSAYS device 402 extracts is entering of public place
When mouth or outlet, decision making device 403 is further used for：
Estimate daily personnel's flow of this public place according to personnel's flow information of statistic device real-time statistics.
In an embodiment of the present invention, the intelligent monitor system of this personnel's flow further includes：
Characteristics of objects analytical equipment 404, occurs in people in target facility-wide in extract real-time video monitoring data
Personnel's body dynamics information of member.
In an embodiment of the present invention, the intelligent monitor system of this personnel's flow further includes：
Semantic analysis device 405, for the personnel's flow information based on statistic device real-time statistics and characteristics of objects analysis
Personnel's body dynamics information generative semantics analysis result of device 404 extract real-time；
Wherein, decision making device 403 is further used for：
The semantic analysis result being generated based on semantic analysis device 405 and different personnel's flow information and personnel's motion
The pre-training gained model of the machine description of personnel's traffic management and control strategy corresponding to characteristic information, determines video monitoring data in real time
Personnel's traffic management and control information of corresponding monitoring scene.
In an embodiment of the present invention, decision making device 403 is further used for：
Receive and referred to personnel's body dynamics information, the inquiry as querying condition of video monitoring period or personnel's flow information
Order；And transfer and occur in target facility-wide under all video monitoring time periods corresponding with personnel's body dynamics information
Personnel's flow information of personnel, or transfer all personnel body dynamics information corresponding with the video monitoring period and occur in target
Personnel's flow information of the personnel in facility-wide, or transfer under all video monitoring time period corresponding with personnel's flow information
Personnel's body dynamics information.
In an embodiment of the present invention, the intelligent monitor system of this personnel's flow further includes：
Subject area extraction element 406, for intercepting the people occurring in target facility-wide from video monitoring data
The area video monitoring data in region residing for member；
Wherein, characteristics of objects analytical equipment 404 is further used for extract real-time from area video monitoring data and occurs in
Personnel's body dynamics information of personnel in target facility-wide.
As can be seen here, personnel's flux monitoring system that the embodiment of the present invention is provided is based on a kind of monitor video intelligence in fact
Energy information model is realized.Flow of information in this monitor video intelligent information model can be divided into different aspects to extract, Er Qiexiang
There is certain dependence, as shown in Figure 5 between adjacent aspect.Gather video monitoring data in environmental perception device 401
During, by video with live perception data (such as：Sound, time, the geographical position of camera, temperature, meteorology, camera pose etc.)
It is stored in environment sensing layer, these information are the fundamentals that traditional video surveillance and intelligent video monitoring provide monitoring scene, are
Top layer decision-making provides necessary support.During front-end processing, the video monitoring data of acquired original is carried out preliminary treatment
(include conventional pretreatment, and the front end intellectual analysis based on statistical learning method etc.), and the result of preliminary treatment is stored in
Characteristic layer, geographical sign layer and object layer, the mistake of corresponding objects feature analyzing apparatus 404 extraction personnel's body dynamics information respectively
Journey, geographical sign analytical equipment 402 extract process and subject area extraction element 406 the regarding from acquired original of target facility
The process of area video monitoring data is intercepted in frequency monitoring data.In back-end processing procedures, by according to different application needs,
Comprehensive aforesaid accordingly each layer, is analyzed using machine learning techniques and processes, related result is stored in semantic layer,
The process of corresponding semantic analysis device 405 generative semantics analysis result.For the semantic analysis knot in semantic analysis device 405
Really, different decision recommendations can be provided using the judgment models of machine learning techniques training and supply monitoring personnel reference；Meanwhile, supervise
Control personnel can also send instruction to system, and with content corresponding in query monitor data, these belong to decision-making/understand layer.Its
In judgment models and the decision recommendation that obtains is judged by it, belong to decision-making category.Monitoring personnel observe during, to
Monitoring system sends certain instruction to inquire about in a certain event, possesses the target of certain category feature, and system is instructed to be construed to accord with
Close the describing mode of this structural model, the data that it is grasped enters line retrieval, belongs to and understands category.
It should be appreciated that when personnel's flux monitoring system includes head end video collecting device and rear end video analysis equipment,
Environmental perception device 401 may be provided in head end video collecting device, and geographical sign analytical equipment 402, subject area are extracted
Device 406, characteristics of objects analytical equipment 404, semantic analysis device 405, decision making device 403 can be separately positioned on head end video and adopt
In collection equipment or be arranged in the video analysis equipment of rear end.As long as all devices in personnel's flux monitoring system are capable of respectively
From analysis abstraction function and flow of information progressively extraction, to be finally reached the purpose of semantic decision-making.The present invention is to people
Device in member's flux monitoring system is specifically located at head end video collecting device or rear end video analysis equipment does not limit
Fixed.
The teachings of the present invention is also implemented as a kind of computer program of computer-readable recording medium, including meter
Calculation machine program code, when computer program code is by computing device, it enables a processor to according to embodiment party of the present invention
The method of formula is realizing personnel's flux monitoring method as the embodiment described herein.Computer-readable storage medium can have for any
Shape medium, such as floppy disk, CD-ROM, DVD, hard disk drive, even network medium etc..
It should be understood that although a kind of way of realization the foregoing describing embodiment of the present invention can be computer program product
Product, but the method or apparatus of embodiments of the present invention can be come in fact by the combination according to software, hardware or software and hardware
Existing.Hardware components can be realized using special logic；Software section can store in memory, by suitable instruction execution
System, such as microprocessor or special designs hardware are executing.It will be understood by those skilled in the art that above-mentioned side
Method and equipment can be realized in processor control routine using computer executable instructions and/or be included in, such as such as
Disk, the mounting medium of CD or DVD-ROM, such as the programmable memory of read only memory (firmware) or such as optics or
Such code is provided on the data medium of electrical signal carrier.Methods and apparatus of the present invention can be by such as ultra-large
The quasiconductor of integrated circuit OR gate array, logic chip, transistor etc. or such as field programmable gate array, can compile
The hardware circuit of the programmable hardware device of journey logical device etc. is realized it is also possible to soft by various types of computing devices
Part is realized it is also possible to be realized by the combination such as firmware of above-mentioned hardware circuit and software.
It will be appreciated that though be referred to some modules or the unit of device in detailed descriptions above, but this stroke
Divide and be merely exemplary rather than enforceable.In fact, according to an illustrative embodiment of the invention, above-described two or
The more feature of multimode/unit and function can be realized in a module/unit, conversely, an above-described module/mono-
The feature of unit and function can be to be realized by multiple module/units with Further Division.Additionally, above-described certain module/
Unit can be omitted under some application scenarios.For example when the computing capability of hardware computing resource is unrestricted, also can not wrap
Include subject area extraction element.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all essences in the present invention
Within god and principle, any modification of being made, equivalent etc., should be included within the scope of the present invention.
Claims (15)
1. a kind of intelligent control method of personnel's flow is it is characterised in that include：
Real-time Collection video monitoring data；
Extract the target facility in the video monitoring data of Real-time Collection；
Personnel's flow information of personnel in target facility-wide is occurred in video monitoring data described in real-time statistics；And
Determine the personnel of the monitoring scene corresponding to described video monitoring data according to personnel's flow information of described real-time statistics
Traffic management and control information.
2. the intelligent control method of personnel's flow according to claim 1 is it is characterised in that the target facility working as extraction is
When the entrance of public place or outlet, further include：
Personnel's flow information according to described real-time statistics estimates daily personnel's flow of described public place.
3. the intelligent control method of personnel's flow according to claim 1 is it is characterised in that further include：
Personnel's body dynamics information of personnel in described target facility-wide is occurred in video monitoring data described in extract real-time.
4. the intelligent control method of personnel's flow according to claim 3 is it is characterised in that further include：
Personnel's body dynamics information generative semantics of the personnel's flow information based on described real-time statistics and described extract real-time divides
Analysis result；
Wherein, described personnel's flow information according to described real-time statistics determines the monitoring field corresponding to described video monitoring data
Personnel's traffic management and control information of scape includes：
Based on described semantic analysis result and different personnel's flow information and personnel's flow corresponding to personnel's body dynamics information
The pre-training gained model of the machine description of management and control strategy, the monitoring scene corresponding to the described video monitoring data of real-time determination
Personnel's traffic management and control information.
5. the intelligent control method of personnel's flow according to claim 3 is it is characterised in that in video described in extract real-time
Before occurring in personnel's body dynamics information of personnel in described target facility-wide in monitoring data, further include：
The area video in the region residing for personnel occurring in described target facility-wide is intercepted from described video monitoring data
Monitoring data；
Wherein, occur in personnel's motion of personnel in described target facility-wide in video monitoring data described in described extract real-time
Characteristic information includes：
From described area video monitoring data, extract real-time occurs in the personnel motion spy of personnel in described target facility-wide
Reference ceases.
6. the intelligent control method of personnel's flow according to claim 3 is it is characterised in that further include：
Preserve personnel's flow information of described real-time statistics and personnel's body dynamics information of described extract real-time.
7. the intelligent control method of personnel's flow according to claim 6 is it is characterised in that further include：
Receive and referred to described personnel's body dynamics information, the inquiry as querying condition of video monitoring period or personnel's flow information
Order；And
Transfer and under all video monitoring time periods corresponding with described personnel's body dynamics information, occur in described target facility model
Personnel's flow information of the personnel in enclosing, or transfer all described personnel motion feature letter corresponding with the described video monitoring period
Breath and the personnel's flow information occurring in the personnel in described target facility-wide, or transfer corresponding with described personnel's flow information
All video monitoring time periods under described personnel's body dynamics information.
8. the intelligent control method according to the arbitrary described personnel's flow of claim 3 to 7 is it is characterised in that described video is supervised
Control data includes one or more of monitor video and following items：Video acquisition positional information and video acquisition time letter
Breath；And/or,
Described personnel's body dynamics information includes one or more of following items：Personnel motion trail, personnel's direction of motion
With personnel's movement velocity.
9. a kind of intelligent monitor system of personnel's flow is it is characterised in that include：
Environmental perception device, for Real-time Collection video monitoring data；
Geographical sign analytical equipment, sets for extracting the target in the video monitoring data of described environmental perception device Real-time Collection
Apply；
Statistic device, for occurring in the personnel of personnel in described target facility-wide in video monitoring data described in real-time statistics
Flow information；And
Decision making device, for determining described video monitoring data institute according to personnel's flow information of described statistic device real-time statistics
Personnel's traffic management and control information of corresponding monitoring scene.
10. the intelligent monitor system of personnel's flow according to claim 9 is it is characterised in that work as geographical MARKER ASSAYS dress
Put extraction target facility be public place entrance or outlet when, described decision making device is further used for：
Personnel's flow information according to described statistic device real-time statistics estimates daily personnel's flow of described public place.
The intelligent monitor system of 11. personnel's flows according to claim 9 is it is characterised in that further include：
Characteristics of objects analytical equipment, for occurring in people in described target facility-wide in video monitoring data described in extract real-time
Personnel's body dynamics information of member.
The intelligent monitor system of 12. personnel's flows according to claim 11 is it is characterised in that further include：
Semantic analysis device, for the personnel's flow information based on described statistic device real-time statistics and characteristics of objects analytical equipment
Personnel's body dynamics information generative semantics analysis result of extract real-time；
Wherein, described decision making device is further used for：
The semantic analysis result being generated based on described semantic analysis device and different personnel's flow information and personnel motion spy
The pre-training gained model of the machine description of personnel's traffic management and control strategy corresponding to reference breath, determines described video monitoring number in real time
Personnel's traffic management and control information according to corresponding monitoring scene.
The intelligent monitor system of 13. personnel's flows according to claim 12 is it is characterised in that further include：
Subject area extraction element, for intercepting the people occurring in described target facility-wide from described video monitoring data
The area video monitoring data in region residing for member；
Wherein, described characteristics of objects analytical equipment is further used for extract real-time from described area video monitoring data and occurs in
Personnel's body dynamics information of personnel in described target facility-wide.
The intelligent monitor system of 14. personnel's flows according to claim 11 is it is characterised in that described decision making device enters one
Walk and be used for：
Receive and referred to described personnel's body dynamics information, the inquiry as querying condition of video monitoring period or personnel's flow information
Order；And
Transfer and under all video monitoring time periods corresponding with described personnel's body dynamics information, occur in described target facility model
Personnel's flow information of the personnel in enclosing, or transfer all described personnel motion feature letter corresponding with the described video monitoring period
Breath and the personnel's flow information occurring in the personnel in described target facility-wide, or transfer corresponding with described personnel's flow information
All video monitoring time periods under described personnel's body dynamics information.
The intelligent monitor system of 15. personnel's flows according to claim 13 is it is characterised in that described system includes front end
Video capture device and rear end video analysis equipment；
Wherein, described environmental perception device is arranged in described head end video collecting device；
Described geographical sign analytical equipment, subject area extraction element, characteristics of objects analytical equipment, semantic analysis device, decision-making
Device is separately positioned in described head end video collecting device or is arranged in the video analysis equipment of described rear end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610873481.6A CN106412507A (en) | 2016-09-30 | 2016-09-30 | Intelligent monitoring method and system of personnel flow |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610873481.6A CN106412507A (en) | 2016-09-30 | 2016-09-30 | Intelligent monitoring method and system of personnel flow |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106412507A true CN106412507A (en) | 2017-02-15 |
Family
ID=59227991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610873481.6A Pending CN106412507A (en) | 2016-09-30 | 2016-09-30 | Intelligent monitoring method and system of personnel flow |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106412507A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108132708A (en) * | 2017-12-21 | 2018-06-08 | 清华大学 | The collecting method and device of indoor evacuation system of behavior based on virtual reality |
| CN108665691A (en) * | 2018-08-22 | 2018-10-16 | 张菁菁 | A kind of system and method for the early warning and water conservancy diversion of the anti-swarm and jostlement of intelligence |
| CN109508632A (en) * | 2018-09-30 | 2019-03-22 | 百度在线网络技术（北京）有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN110324572A (en) * | 2018-03-28 | 2019-10-11 | 佳能株式会社 | Monitoring system, monitoring method and non-transitory computer-readable storage media |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101795395A (en) * | 2009-02-04 | 2010-08-04 | 深圳市先进智能技术研究所 | System and method for monitoring crowd situation |
| US20120033854A1 (en) * | 2010-08-06 | 2012-02-09 | Samsung Techwin Co., Ltd. | Image processing apparatus |
| CN103440491A (en) * | 2013-06-24 | 2013-12-11 | 中国科学院上海微系统与信息技术研究所 | Intensive pedestrian flow rate real-time detection method based on color feature |
| CN103871082A (en) * | 2014-03-31 | 2014-06-18 | 百年金海科技有限公司 | Method for counting people stream based on security and protection video image |
| US20160019698A1 (en) * | 2014-07-21 | 2016-01-21 | Florida Atlantic University | Systems and methods for people counting in sequential images |
| CN105787853A (en) * | 2016-04-14 | 2016-07-20 | 北京中电万联科技股份有限公司 | Public area congestion and stampede emergency early-warning system |
-
2016
- 2016-09-30 CN CN201610873481.6A patent/CN106412507A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101795395A (en) * | 2009-02-04 | 2010-08-04 | 深圳市先进智能技术研究所 | System and method for monitoring crowd situation |
| US20120033854A1 (en) * | 2010-08-06 | 2012-02-09 | Samsung Techwin Co., Ltd. | Image processing apparatus |
| CN103440491A (en) * | 2013-06-24 | 2013-12-11 | 中国科学院上海微系统与信息技术研究所 | Intensive pedestrian flow rate real-time detection method based on color feature |
| CN103871082A (en) * | 2014-03-31 | 2014-06-18 | 百年金海科技有限公司 | Method for counting people stream based on security and protection video image |
| US20160019698A1 (en) * | 2014-07-21 | 2016-01-21 | Florida Atlantic University | Systems and methods for people counting in sequential images |
| CN105787853A (en) * | 2016-04-14 | 2016-07-20 | 北京中电万联科技股份有限公司 | Public area congestion and stampede emergency early-warning system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108132708A (en) * | 2017-12-21 | 2018-06-08 | 清华大学 | The collecting method and device of indoor evacuation system of behavior based on virtual reality |
| CN110324572A (en) * | 2018-03-28 | 2019-10-11 | 佳能株式会社 | Monitoring system, monitoring method and non-transitory computer-readable storage media |
| CN110324572B (en) * | 2018-03-28 | 2021-11-30 | 佳能株式会社 | Monitoring system, monitoring method, and non-transitory computer-readable storage medium |
| CN108665691A (en) * | 2018-08-22 | 2018-10-16 | 张菁菁 | A kind of system and method for the early warning and water conservancy diversion of the anti-swarm and jostlement of intelligence |
| CN109508632A (en) * | 2018-09-30 | 2019-03-22 | 百度在线网络技术（北京）有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN109508632B (en) * | 2018-09-30 | 2023-04-07 | 百度在线网络技术（北京）有限公司 | Image processing method, device, equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106096577B (en) | A kind of target tracking method in camera distribution map | |
| Seer et al. | Kinects and human kinetics: A new approach for studying pedestrian behavior | |
| CN109684916B (en) | Method, system, equipment and storage medium for detecting data abnormity based on path track | |
| EP2913798B1 (en) | Method, device and system for obtaining the number of persons | |
| CN106412507A (en) | Intelligent monitoring method and system of personnel flow | |
| CN107256386A (en) | Human behavior analysis method based on deep learning | |
| CN112668525B (en) | People flow counting method and device, electronic equipment and storage medium | |
| CN108764167A (en) | A kind of target of space time correlation recognition methods and system again | |
| CN106446002A (en) | Moving target-based video retrieval method for track in map | |
| CN109743547A (en) | A kind of artificial intelligence security monitoring management system | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN106355604A (en) | Target image tracking method and system | |
| CN110032947A (en) | A kind of method and device that monitor event occurs | |
| CN109934074A (en) | Movement track determines method and device | |
| CN103456168A (en) | System and method for monitoring behaviors of pedestrians at traffic intersection | |
| CN106454233A (en) | Intelligent crowd-gathering monitoring method and system | |
| Pi et al. | Deep learning for visual analytics of the spread of COVID-19 infection in crowded urban environments | |
| CN109977796A (en) | Trail current detection method and device | |
| Iyer et al. | Adaptive real time traffic prediction using deep neural networks | |
| CN106507037A (en) | Intelligent control method and system that personnel invade/cross the border | |
| CN104200231B (en) | A kind of efficient traffic behavior mask method | |
| Bazo et al. | Baptizo: A sensor fusion based model for tracking the identity of human poses | |
| CN109977884B (en) | Target following method and device | |
| CN113469150B (en) | Method and system for identifying risk behaviors | |
| Nelikanti et al. | An optimization based deep lstm predictive analysis for decision making in cricket |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20171207 Address after: 519000 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant after: Zhongxing Technology Co., Ltd. Address before: 100083 Haidian District, Xueyuan Road, No. 35, the world building, the second floor of the building on the ground floor, No. 16 Applicant before: Beijing Vimicro Corporation |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant after: Mid Star Technology Limited by Share Ltd Address before: 519000 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant before: Zhongxing Technology Co., Ltd. |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |