CN106096522A - A kind of swarm and jostlement method for early warning based on stress and strain model and device - Google Patents
A kind of swarm and jostlement method for early warning based on stress and strain model and device Download PDFInfo
- Publication number
- CN106096522A CN106096522A CN201610388644.1A CN201610388644A CN106096522A CN 106096522 A CN106096522 A CN 106096522A CN 201610388644 A CN201610388644 A CN 201610388644A CN 106096522 A CN106096522 A CN 106096522A
- Authority
- CN
- China
- Prior art keywords
- inclination angle
- grid
- body gesture
- target area
- gesture inclination
- 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
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of swarm and jostlement method for early warning based on stress and strain model and device.The method comprises steps of determining that target area to be monitored；According to default stress and strain model rule, described target area is carried out stress and strain model；Determine the body gesture inclination angle warning value of each grid；During monitoring described target area, it is judged that the magnitude relationship of the body gesture inclination angle warning value of the body gesture inclination angle of personnel and this grid in each grid；According to judged result, it is determined whether export crowded early warning information.The technical scheme that the application embodiment of the present invention is provided, can in time, accurately make swarm and jostlement early warning, it is to avoid the generation of swarm and jostlement event.
Description
Technical field
The present invention relates to monitoring technical field, particularly relate to a kind of swarm and jostlement method for early warning based on stress and strain model and
Device.
Background technology
During the large-scale activities such as congratulation activity in red-letter day, competitive sports, religious activities, so many people close quarters, because of visitor
Flow is big, intensity of passenger flow is high, it is easy to swarm and jostlement event occurs, causes casualties.
Such as, on December 31st, 2014, a large amount of visitors, citizen are gathered in region, outbeach, Huangpu District, Shanghai and meet New Year, due to
Chen Yi square liquidates towards the ladder entrance of two, north and south, path and the artificial abortion exited of sightseeing platform, causes someone to fall down, occurs
Swarm and jostlement accident, causes that 36 people are dead, 49 people are injured.On February 5th, 2004, on the sweet dumplings in the close rainbow park of Beijing's Miyun County
In lantern festival, because visitor explodes, overcrowding, there is personnel's tread event on Bifrost, cause 37 people's death, 15 people injured.
At present, for densely populated place region, mainly by the artificial personnel amount estimating whole region, according to estimating roughly
The personnel amount in the whole region of meter determines whether to carry out swarm and jostlement early warning.
This method is that the personnel amount to whole region is added up, and is difficult to accurately make swarm and jostlement early warning, because
For a region, the personnel that the part that this region has is accommodated may be the most overcrowding, but because of whole region
Personnel amount not up to threshold value and do not make swarm and jostlement early warning, it is likely that cause the generation of swarm and jostlement event.
Summary of the invention
For solving above-mentioned technical problem, the present invention provides a kind of swarm and jostlement method for early warning based on stress and strain model and dress
Put, can in time, accurately make swarm and jostlement early warning, it is to avoid the generation of swarm and jostlement event.
A kind of swarm and jostlement method for early warning based on stress and strain model, including:
Determine target area to be monitored；
According to default stress and strain model rule, described target area is carried out stress and strain model；
Determine the body gesture inclination angle warning value of each grid；
During monitoring described target area, it is judged that the body gesture inclination angle of personnel and the body of this grid in each grid
The magnitude relationship of body posture inclination angle warning value；
According to judged result, it is determined whether export crowded early warning information.
In a kind of detailed description of the invention of the present invention, the stress and strain model rule that described basis is preset, to described target area
Territory carries out stress and strain model, including:
Obtain the Site characteristic of described target area；
According to described Site characteristic, described target area is carried out stress and strain model.
In a kind of detailed description of the invention of the present invention, the described body gesture inclination angle warning value determining each grid, bag
Include:
The history crowding data being obtained ahead of time are carried out machine learning, it is thus achieved that body gesture inclination angle training pattern；
According to described body gesture inclination angle training pattern, determine the body gesture inclination angle of each grid of described target area
Warning value.
In a kind of detailed description of the invention of the present invention, described during monitoring described target area, it is judged that each net
The magnitude relationship of the body gesture inclination angle warning value of the body gesture inclination angle of personnel and this grid in lattice, including:
During monitoring described target area, obtain the video image of described target area in real time；
According to described video image, determine the body gesture inclination angle of personnel in each grid of described target area；
For each grid, it is judged that in this grid, the body gesture inclination angle of personnel is guarded against with the body gesture inclination angle of this grid
The magnitude relationship of value.
In a kind of detailed description of the invention of the present invention, described according to judged result, it is determined whether to export crowded early warning letter
Breath, including:
For each grid, if body gesture inclination angle is more than the body gesture inclination angle warning value of this grid in this grid
Personnel ratios reaches preset first threshold value, then export crowded early warning information；
Or,
Reach to preset Second Threshold more than the personnel ratios of corresponding body gesture inclination angle warning value according to body gesture inclination angle
Grid scale, it is determined whether export crowded early warning information.
A kind of swarm and jostlement prior-warning device based on stress and strain model, including:
Target area determines module, for determining target area to be monitored；
Stress and strain model module, for according to the stress and strain model rule preset, carrying out stress and strain model to described target area；
Warning value determines module, for determining the body gesture inclination angle warning value of each grid；
Monitoring modular, for during monitoring described target area, it is judged that in each grid, the body gesture of personnel is inclined
The magnitude relationship of the body gesture inclination angle warning value of angle and this grid；
Warning module, for the judged result according to described monitoring modular, it is determined whether export crowded early warning information.
In a kind of detailed description of the invention of the present invention, described stress and strain model module, specifically for:
Obtain the Site characteristic of described target area；
According to described Site characteristic, described target area is carried out stress and strain model.
In a kind of detailed description of the invention of the present invention, described warning value determines module, specifically for:
The history crowding data being obtained ahead of time are carried out machine learning, it is thus achieved that body gesture inclination angle training pattern；
According to described body gesture inclination angle training pattern, determine the body gesture inclination angle of each grid of described target area
Warning value.
In a kind of detailed description of the invention of the present invention, described monitoring modular, specifically for:
During monitoring described target area, obtain the video image of described target area in real time；
According to described video image, determine the body gesture inclination angle of personnel in each grid of described target area；
For each grid, it is judged that in this grid, the body gesture inclination angle of personnel is guarded against with the body gesture inclination angle of this grid
The magnitude relationship of value.
In a kind of detailed description of the invention of the present invention, described warning module, specifically for:
For each grid, if body gesture inclination angle is more than the body gesture inclination angle warning value of this grid in this grid
Personnel ratios reaches preset first threshold value, then export crowded early warning information；
Or,
Reach to preset Second Threshold more than the personnel ratios of corresponding body gesture inclination angle warning value according to body gesture inclination angle
Grid scale, it is determined whether export crowded early warning information.
The technical scheme that the application embodiment of the present invention is provided, carries out stress and strain model to target area to be monitored, determines
Go out the body gesture inclination angle warning value of each grid, during this target area is monitored, according to people in each grid
The body gesture inclination angle of member and the magnitude relationship of the body gesture inclination angle warning value of this grid, it is determined whether export crowded early warning letter
Breath, accuracy is high, ageing by force, can at utmost avoid the generation of swarm and jostlement event.
Accompanying drawing explanation
For the clearer explanation embodiment of the present invention or the technical scheme of prior art, below will be to embodiment or existing
In technology description, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to root
Other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 is the implementing procedure figure of a kind of swarm and jostlement method for early warning based on stress and strain model in the embodiment of the present invention；
Fig. 2 is the structural representation of a kind of swarm and jostlement prior-warning device based on stress and strain model in the embodiment of the present invention.
Detailed description of the invention
The core of the present invention is to provide a kind of swarm and jostlement method for early warning based on stress and strain model and device, with for monitoring
Target area, in time, accurately export crowded early warning information, it is to avoid the generation of swarm and jostlement event.
In order to make those skilled in the art be more fully understood that the present invention program, below in conjunction with the accompanying drawings and detailed description of the invention
The present invention is described in further detail.Obviously, described embodiment be only a part of embodiment of the present invention rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, broadly falls into the scope of protection of the invention.
Shown in Figure 1, by the one of the swarm and jostlement method for early warning based on stress and strain model that the embodiment of the present invention is provided
Planting implementing procedure figure, the method may comprise steps of:
S110: determine target area to be monitored.
It is understood that swarm and jostlement event mostly occurs in personnel's highly dense place, such as large-scale square, stadium
Shop, subway station transferring passage or gateway etc..For these places, the technology that the embodiment of the present invention is provided can be applied
Scheme, is monitored it, to determine whether to export swarm and jostlement early warning information.
Target area to be monitored determined by the embodiment of the present invention, can be whole districts of being comprised, these places above-mentioned
Territory or subregion.As a example by large-scale square, if to broadly fall into personnel the closeest in the whole region that this large-scale square is comprised
Collection region, then can be defined as target area to be monitored by the Zone Full on this large-scale square；If this large-scale square is wrapped
The subregion contained belongs to personnel's highly dense region, then the subregion on this large-scale square can be defined as mesh to be monitored
Mark region.
After determining target area to be monitored, the operation of step S120 can be continued executing with.
S120: according to default stress and strain model rule, target area is carried out stress and strain model.
The basic thought of stress and strain model is by structural separation, and continuum i.e. carries out discretization, utilizes and simplifies geometry list
Unit carrys out close approximation continuum, then comprehensively solves according to deformation compatibility condition.
After step S110 determines target area to be monitored, can be according to default stress and strain model rule, to this target
Region carries out stress and strain model.
In actual applications, different stress and strain model rule can be set for different types of region in advance by technical staff
Then.Such as, for the region of open type, set a kind of stress and strain model rule, for the region of closed type, set another
A kind of stress and strain model rule.So, after determining target area to be monitored, can select according to the type of this target area
The stress and strain model rule corresponding with the type, carries out stress and strain model to this target area.
Certainly, identical stress and strain model rule can also be set for different types of region.So, determine to be monitored
Target area after, can according to stress and strain model set in advance rule, this target area is carried out stress and strain model.
Concrete stress and strain model rule can be set according to practical situation.As the marginal portion in target area sets
Bigger grid, the core in target area sets less grid, or sets formed objects for target area
Grid etc..Concrete sizing grid can also be set according to practical situation, as each grid accounts for a square meter.
In actual applications, those skilled in the art can select prior art according to default stress and strain model rule
One or more Meshing Methods carry out stress and strain model to target area.In the prior art, there is more stress and strain model side
Method, can classify according to the cell type produced, the dimension of signal generating unit, automaticity etc..Relatively common grid
Division methods mainly has reflection method, Grid Method, node even unit's method, topology decomposition method, geometric decomposition method, scanning method, artificial division
Method and the finite element analysis stress and strain model method etc. being widely used in various engineering fields in recent years.
In a kind of detailed description of the invention of the present invention, step S120 may comprise steps of:
Step one: obtain the Site characteristic of target area；
Step 2: according to Site characteristic, target area is carried out stress and strain model.
For convenience of describing, above-mentioned two step is combined and illustrates.
After determining target area to be monitored, it is possible to obtain the Site characteristic of this target area.Site characteristic can include
One or more in the extra exit number of this target area, the open degree in place, structure structure, size.
According to the Site characteristic of target area, automatically target area can be carried out stress and strain model, or by technical staff
Manually divide.Such as, if the extra exit number of target area is less, then can be divided into less grid, strengthen
Monitoring dynamics, if the open degree in the place of target area is relatively big, then can be divided into bigger grid, if target area is
Multiple structure, then can carry out stress and strain model respectively, if the area of target area is less, then can be divided into relatively for every layer
Little grid.
In short, more suitably mode can be selected to carry out stress and strain model according to the Site characteristic of target area.
S130: determine the body gesture inclination angle warning value of each grid.
Body gesture inclination angle, refers to an angle maximum in two angles between human body and horizontal plane.It is understood that
The angle that human body is tilted under different congestion states is different, and, everyone health has one can support oneself balance
Inclination maximum, once more than this inclination angle, human body may be fallen down.
Can body gesture inclination angle warning value be the important evidence judging occur swarm and jostlement event, as personnel in grid
When body gesture inclination angle is more than the body gesture inclination angle warning value of this grid, it is possible to swarm and jostlement event occurs.
In step S120, after target area is carried out stress and strain model, it may be determined that the body gesture inclination angle of each grid is alert
Ring value, concrete, the body gesture inclination angle warning value of each grid can be set according to experiment or experience, and by this health appearance
Gesture inclination angle warning value directly applies to this target area.In target area, the body gesture inclination angle warning value of different grids can phase
Same or different.
In a kind of detailed description of the invention of the present invention, step S130 may comprise steps of:
First step: the history crowding data being obtained ahead of time are carried out machine learning, it is thus achieved that body gesture inclination angle is instructed
Practice model；
Second step: according to body gesture inclination angle training pattern, determine the body gesture of each grid of target area
Inclination angle warning value.
For convenience of describing, above-mentioned two step is combined and illustrates.
Before target area is monitored, can first obtain the history crowding in this target area or other regions
Data, other regions can be to have the region of identical Site characteristic with target area, or be same type with target area
Region.
The history crowding data being obtained ahead of time carry out machine learning, and the body gesture training different crowding corresponding is inclined
Angle, it is thus achieved that body gesture inclination angle training pattern.According to body gesture inclination angle training pattern, it may be determined that each net of target area
The body gesture inclination angle warning value of lattice.Concrete, this grid can be determined according to the concrete condition of each grid of target area
Body gesture inclination angle warning value.
In embodiments of the present invention, it is possible to use degree of depth learning algorithm carries out machine to the history crowding data being obtained ahead of time
Device learns.Degree of depth learning algorithm is the one of machine learning algorithm, is a kind of emerging multilayer neural network dimension-reduction algorithm.Pass through
Set up the neutral net Deep model containing multiple hidden layers, the high dimensional data of input is successively extracted feature, to find data
Low-dimensional nested structure, forms the most abstract effective high-rise expression.It is simultaneously based on neural network simulation human brain analysis, study
Model, imitate people's brain mechanism identification target, perception information.
S140: in monitoring objective region process, it is judged that the body gesture inclination angle of personnel and this grid in each grid
The magnitude relationship of body gesture inclination angle warning value.
Operation by step S110 to step S130, it is determined that target area to be monitored, is carried out this target area
Stress and strain model, and determine the body gesture inclination angle warning value of each grid.So far, complete target area is monitored
Preparation.The operation that this target area is monitored can be continued executing with.
In monitoring objective region process, it is possible to obtain the body gesture inclination angle of personnel in each grid.At current time,
For each grid, can be by the body gesture inclination angle warning value at the body gesture inclination angle of each personnel in this grid Yu this grid
Compare, it is also possible to the body gesture inclination angle of a certain proportion of personnel in this grid is alert with the body gesture inclination angle of this grid
Ring value compares.
In a kind of detailed description of the invention of the present invention, step S140 may comprise steps of:
Step one: in monitoring objective region process, obtains the video image of target area in real time；
Step 2: according to video image, determines the body gesture inclination angle of personnel in each grid of target area；
Step 3: for each grid, it is judged that the body gesture inclination angle of personnel and the body gesture of this grid in this grid
The magnitude relationship of inclination angle warning value.
For ease of describing, above three step is combined and illustrates.
In embodiments of the present invention, it is possible to use Video Analysis Technology determines the body of personnel in each grid of target area
Body posture inclination angle.
Video Analysis Technology, refers to utilize computer picture Visual analysis techniques, by background in scene and target being divided
From so analyze and follow the trail of the target in camera scene.Different non-regulations can be preset in the scene of different cameras
Then, the target occurring to violate the behavior of predefined rule is identified.
In actual applications, several video image acquisition devices can be installed in target area, make these video images
The coverage of harvester is not less than the scope of target area.If there is multiple video image acquisition devices, can be for
The video image that the multiple video image acquisition devices received send carries out Data Fusion, it is thus achieved that the video of target area
Image, thus according to this video image, it may be determined that the body gesture inclination angle of personnel in each grid of this target area.
During target area is monitored, the video image of target area can be obtained in real time.According to obtain
Video image, it may be determined that the body gesture inclination angle of personnel in each grid of target area.Such that it is able to for each grid,
Judge the magnitude relationship at the body gesture inclination angle of personnel and the body gesture inclination angle warning value of this grid in this grid.
S150: according to judged result, it is determined whether export crowded early warning information.
In step S140, for each grid, it can be determined that the body gesture inclination angle of personnel and this grid in this grid
Body gesture inclination angle warning value between magnitude relationship, according to judged result, it may be determined that whether export early warning information.
In a kind of detailed description of the invention of the present invention, for each grid, if body gesture inclination angle is big in this grid
Personnel ratios in the body gesture inclination angle warning value of this grid reaches preset first threshold value, then can export crowded early warning letter
Breath.
It is understood that in actual scene, it is possible that the situation that individual persons's imprudence is fallen down, for getting rid of this
The situation of kind, for each grid, if body gesture inclination angle is more than the body gesture inclination angle warning value of this grid in this grid
Personnel ratios reaches preset first threshold value, then it is assumed that current it may happen that swarm and jostlement event, can export crowded early warning letter
Breath.First threshold can be set according to practical situation and adjust, and the embodiment of the present invention is without limitation.
In the another kind of detailed description of the invention of the present invention, can incline more than corresponding body gesture according to body gesture inclination angle
The personnel ratios of angle warning value reaches to preset the grid scale of Second Threshold, it is determined whether output early warning information.
In actual applications, if grid arranges less, then in single grid, body gesture inclination angle is more than body gesture
The personnel ratios of inclination angle warning value is less, and the probability causing swarm and jostlement event can be less.If it is determined that health in multiple grids
Posture inclination angle reaches to preset Second Threshold more than the personnel ratios of corresponding body gesture inclination angle warning value, and such grid
When quantity accounting reaches default grid scale, show that the probability causing swarm and jostlement event is relatively big, now can export crowded
Early warning information, this crowded early warning information can be the early warning information for target area, it is also possible to be pre-for specifiable lattice
Alarming information.Second Threshold and the grid scale preset can be set according to practical situation and adjust.
Export crowded early warning information, on the one hand can send alarm in target area, to remind the masses on the scene to take care,
On the other hand crowded early warning information can be exported to the police or other related personnel, so that the police or related personnel are timely
Target area is intervened, such as takes current limiting measures or evacuation measure, it is to avoid the generation of swarm and jostlement event.
The method that the application embodiment of the present invention is provided, carries out stress and strain model to target area to be monitored, determines every
The body gesture inclination angle warning value of individual grid, during being monitored this target area, according to personnel in each grid
The magnitude relationship of the body gesture inclination angle warning value of body gesture inclination angle and this grid, it is determined whether export crowded early warning information,
Accuracy is high, ageing by force, can at utmost avoid the generation of swarm and jostlement event.
A kind of based on stress and strain model the swarm and jostlement prior-warning device provided the embodiment of the present invention below is introduced, under
A kind of based on stress and strain model the swarm and jostlement prior-warning device that literary composition describes is a kind of based on stress and strain model crowded with above-described
Trampling method for early warning can be mutually to should refer to.
A kind of based on stress and strain model swarm and jostlement prior-warning device shown in Figure 2, that provided by the embodiment of the present invention
Structural representation, this device can include with lower module:
Target area determines module 210, for determining target area to be monitored；
Stress and strain model module 220, for according to the stress and strain model rule preset, carrying out grid to described target area and draw
Point；
Warning value determines module 230, for determining the body gesture inclination angle warning value of each grid；
Monitoring modular 240, for during monitoring described target area, it is judged that the body gesture of personnel in each grid
The magnitude relationship of the body gesture inclination angle warning value of inclination angle and this grid；
Warning module 250, for the judged result according to described monitoring modular 240, it is determined whether export crowded early warning letter
Breath.
The device that the application embodiment of the present invention is provided, carries out stress and strain model to target area to be monitored, determines every
The body gesture inclination angle warning value of individual grid, during being monitored this target area, according to personnel in each grid
The magnitude relationship of the body gesture inclination angle warning value of body gesture inclination angle and this grid, it is determined whether export crowded early warning information,
Accuracy is high, ageing by force, can at utmost avoid the generation of swarm and jostlement event.
In a kind of detailed description of the invention of the present invention, described stress and strain model module 220, can be specifically for:
Obtain the Site characteristic of described target area；
According to described Site characteristic, described target area is carried out stress and strain model.
In a kind of detailed description of the invention of the present invention, described warning value determines module 230, can be specifically for:
The history crowding data being obtained ahead of time are carried out machine learning, it is thus achieved that body gesture inclination angle training pattern；
According to described body gesture inclination angle training pattern, determine the body gesture inclination angle of each grid of described target area
Warning value.
In a kind of detailed description of the invention of the present invention, described monitoring modular 240, can be specifically for:
During monitoring described target area, obtain the video image of described target area in real time；
According to described video image, determine the body gesture inclination angle of personnel in each grid of described target area；
For each grid, it is judged that in this grid, the body gesture inclination angle of personnel is guarded against with the body gesture inclination angle of this grid
The magnitude relationship of value.
In a kind of detailed description of the invention of the present invention, described warning module 250, can be specifically for:
For each grid, if body gesture inclination angle is more than the body gesture inclination angle warning value of this grid in this grid
Personnel ratios reaches preset first threshold value, then export crowded early warning information；
Or,
Reach to preset Second Threshold more than the personnel ratios of corresponding body gesture inclination angle warning value according to body gesture inclination angle
Grid scale, it is determined whether export crowded early warning information.
In this specification, each embodiment uses the mode gone forward one by one to describe, and what each embodiment stressed is and other
The difference of embodiment, between each embodiment, same or similar part sees mutually.For filling disclosed in embodiment
For putting, owing to it corresponds to the method disclosed in Example, so describe is fairly simple, relevant part sees method part
Illustrate.
Professional further appreciates that, in conjunction with the unit of each example that the embodiments described herein describes
And algorithm steps, it is possible to electronic hardware, computer software or the two be implemented in combination in, in order to clearly demonstrate hardware and
The interchangeability of software, the most generally describes composition and the step of each example according to function.These
Function performs with hardware or software mode actually, depends on application-specific and the design constraint of technical scheme.Specialty
Technical staff specifically should can be used for using different methods to realize described function to each, but this realization should not
Think beyond the scope of this invention.
The method described in conjunction with the embodiments described herein or the step of algorithm can direct hardware, processor be held
The software module of row, or the combination of the two implements.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, depositor, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Above a kind of swarm and jostlement method for early warning based on stress and strain model provided by the present invention and device are carried out in detail
Thin introduction.Principle and the embodiment of the present invention are set forth by specific case used herein, saying of above example
Bright method and the core concept thereof being only intended to help to understand the present invention.It should be pointed out that, the ordinary skill for the art
For personnel, under the premise without departing from the principles of the invention, it is also possible to the present invention is carried out some improvement and modification, these improve
Also fall in the protection domain of the claims in the present invention with modifying.
Claims (10)
1. a swarm and jostlement method for early warning based on stress and strain model, it is characterised in that including:
Determine target area to be monitored；
According to default stress and strain model rule, described target area is carried out stress and strain model；
Determine the body gesture inclination angle warning value of each grid；
During monitoring described target area, it is judged that the body gesture inclination angle of personnel and the health appearance of this grid in each grid
The magnitude relationship of gesture inclination angle warning value；
According to judged result, it is determined whether export crowded early warning information.
Method the most according to claim 1, it is characterised in that the stress and strain model rule that described basis is preset, to described mesh
Mark region carries out stress and strain model, including:
Obtain the Site characteristic of described target area；
According to described Site characteristic, described target area is carried out stress and strain model.
Method the most according to claim 1 and 2, it is characterised in that the described body gesture inclination angle police determining each grid
Ring value, including:
The history crowding data being obtained ahead of time are carried out machine learning, it is thus achieved that body gesture inclination angle training pattern；
According to described body gesture inclination angle training pattern, determine the body gesture inclination angle warning of each grid of described target area
Value.
Method the most according to claim 3, it is characterised in that described during monitoring described target area, it is judged that every
The magnitude relationship of the body gesture inclination angle warning value of the body gesture inclination angle of personnel and this grid in individual grid, including:
During monitoring described target area, obtain the video image of described target area in real time；
According to described video image, determine the body gesture inclination angle of personnel in each grid of described target area；
For each grid, it is judged that the body gesture inclination angle warning value of the body gesture inclination angle of personnel and this grid in this grid
Magnitude relationship.
Method the most according to claim 4, it is characterised in that described according to judged result, it is determined whether export crowded pre-
Alarming information, including:
For each grid, if body gesture inclination angle is more than the personnel of the body gesture inclination angle warning value of this grid in this grid
Ratio reaches preset first threshold value, then export crowded early warning information；
Or,
Reach the net of default Second Threshold more than the personnel ratios of corresponding body gesture inclination angle warning value according to body gesture inclination angle
Lattice ratio, it is determined whether export crowded early warning information.
6. a swarm and jostlement prior-warning device based on stress and strain model, it is characterised in that including:
Target area determines module, for determining target area to be monitored；
Stress and strain model module, for according to the stress and strain model rule preset, carrying out stress and strain model to described target area；
Warning value determines module, for determining the body gesture inclination angle warning value of each grid；
Monitoring modular, for monitoring during described target area, it is judged that in each grid the body gesture inclination angle of personnel with
The magnitude relationship of the body gesture inclination angle warning value of this grid；
Warning module, for the judged result according to described monitoring modular, it is determined whether export crowded early warning information.
Device the most according to claim 6, it is characterised in that described stress and strain model module, specifically for:
Obtain the Site characteristic of described target area；
According to described Site characteristic, described target area is carried out stress and strain model.
8. according to the device described in claim 6 or 7, it is characterised in that described warning value determines module, specifically for:
The history crowding data being obtained ahead of time are carried out machine learning, it is thus achieved that body gesture inclination angle training pattern；
According to described body gesture inclination angle training pattern, determine the body gesture inclination angle warning of each grid of described target area
Value.
Device the most according to claim 8, it is characterised in that described monitoring modular, specifically for:
During monitoring described target area, obtain the video image of described target area in real time；
According to described video image, determine the body gesture inclination angle of personnel in each grid of described target area；
For each grid, it is judged that the body gesture inclination angle warning value of the body gesture inclination angle of personnel and this grid in this grid
Magnitude relationship.
Device the most according to claim 9, it is characterised in that described warning module, specifically for:
For each grid, if body gesture inclination angle is more than the personnel of the body gesture inclination angle warning value of this grid in this grid
Ratio reaches preset first threshold value, then export crowded early warning information；
Or,
Reach the net of default Second Threshold more than the personnel ratios of corresponding body gesture inclination angle warning value according to body gesture inclination angle
Lattice ratio, it is determined whether export crowded early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610388644.1A CN106096522A (en) | 2016-06-02 | 2016-06-02 | A kind of swarm and jostlement method for early warning based on stress and strain model and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610388644.1A CN106096522A (en) | 2016-06-02 | 2016-06-02 | A kind of swarm and jostlement method for early warning based on stress and strain model and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106096522A true CN106096522A (en) | 2016-11-09 |
Family
ID=57447244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610388644.1A Pending CN106096522A (en) | 2016-06-02 | 2016-06-02 | A kind of swarm and jostlement method for early warning based on stress and strain model and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106096522A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844531A (en) * | 2016-12-29 | 2017-06-13 | 福建四创软件有限公司 | A kind of flood control command based on grid studies and judges system |
| CN109087478A (en) * | 2018-08-22 | 2018-12-25 | 徐自远 | A kind of early warning of the anti-swarm and jostlement of intelligence and method of river diversion and system |
| CN110166789A (en) * | 2019-05-15 | 2019-08-23 | 上海哔哩哔哩科技有限公司 | Monitor method, computer equipment and the readable storage medium storing program for executing of net cast sensitive information |
| CN115797864A (en) * | 2022-12-02 | 2023-03-14 | 孙力 | Safety management system applied to smart community |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101386395A (en) * | 2007-09-13 | 2009-03-18 | 三菱电机株式会社 | Safety device for escalator |
| CN102930248A (en) * | 2012-10-22 | 2013-02-13 | 中国计量学院 | Crowd abnormal behavior detection method based on machine learning |
| US20150160035A1 (en) * | 2013-12-09 | 2015-06-11 | Nec Europe Ltd. | Method and computer system for detecting crowds in a location tracking system |
| CN105261148A (en) * | 2015-10-14 | 2016-01-20 | 广州医科大学 | Trample event early warning evacuation method based on skynet monitoring system |
| CN105561492A (en) * | 2014-11-07 | 2016-05-11 | 开利公司 | Dynamic acquisition terminal for behavior statistical information of humans as well as evacuation system and method |
-
2016
- 2016-06-02 CN CN201610388644.1A patent/CN106096522A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101386395A (en) * | 2007-09-13 | 2009-03-18 | 三菱电机株式会社 | Safety device for escalator |
| CN102930248A (en) * | 2012-10-22 | 2013-02-13 | 中国计量学院 | Crowd abnormal behavior detection method based on machine learning |
| US20150160035A1 (en) * | 2013-12-09 | 2015-06-11 | Nec Europe Ltd. | Method and computer system for detecting crowds in a location tracking system |
| CN105561492A (en) * | 2014-11-07 | 2016-05-11 | 开利公司 | Dynamic acquisition terminal for behavior statistical information of humans as well as evacuation system and method |
| CN105261148A (en) * | 2015-10-14 | 2016-01-20 | 广州医科大学 | Trample event early warning evacuation method based on skynet monitoring system |
Non-Patent Citations (2)
| Title |
|---|
| 布鲁斯•帕克: "《海洋的力量》", 31 January 2014, 北京：海洋出版社 * |
| 柴俊勇: "《城市大人流风险管理》", 31 October 2015, 上海人民出版社 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844531A (en) * | 2016-12-29 | 2017-06-13 | 福建四创软件有限公司 | A kind of flood control command based on grid studies and judges system |
| CN106844531B (en) * | 2016-12-29 | 2020-05-05 | 四创科技有限公司 | Flood prevention command research and judgment system based on grids |
| CN109087478A (en) * | 2018-08-22 | 2018-12-25 | 徐自远 | A kind of early warning of the anti-swarm and jostlement of intelligence and method of river diversion and system |
| CN110166789A (en) * | 2019-05-15 | 2019-08-23 | 上海哔哩哔哩科技有限公司 | Monitor method, computer equipment and the readable storage medium storing program for executing of net cast sensitive information |
| CN110166789B (en) * | 2019-05-15 | 2021-10-22 | 上海哔哩哔哩科技有限公司 | Method for monitoring video live broadcast sensitive information, computer equipment and readable storage medium |
| CN115797864A (en) * | 2022-12-02 | 2023-03-14 | 孙力 | Safety management system applied to smart community |
| CN115797864B (en) * | 2022-12-02 | 2024-02-06 | 深圳市兴海物联科技有限公司 | Security management system applied to intelligent community |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106096521A (en) | A kind of swarm and jostlement method for early warning based on stress and strain model and device | |
| CN109886241A (en) | Driver fatigue detection based on shot and long term memory network | |
| CN106096522A (en) | A kind of swarm and jostlement method for early warning based on stress and strain model and device | |
| CN109117749A (en) | A kind of abnormal object monitoring and managing method and system based on unmanned plane inspection image | |
| CN109271888A (en) | Personal identification method, device, electronic equipment based on gait | |
| CN107679503A (en) | A kind of crowd's counting algorithm based on deep learning | |
| CN107844797A (en) | A kind of method of the milking sow posture automatic identification based on depth image | |
| CN109241871A (en) | A kind of public domain stream of people's tracking based on video data | |
| CN107463919A (en) | A kind of method that human facial expression recognition is carried out based on depth 3D convolutional neural networks | |
| CN100565557C (en) | System for tracking infrared human body target based on corpuscle dynamic sampling model | |
| CN108154110A (en) | A kind of intensive people flow amount statistical method based on the detection of the deep learning number of people | |
| CN105868707A (en) | Method for real-time detection of falling from bed behaviors based on depth image information | |
| CN104796667A (en) | Campus night-vision three-dimensional virtual monitoring system and method | |
| CN107330973A (en) | A kind of single-view method for reconstructing based on various visual angles supervision | |
| CN109815813A (en) | Image processing method and Related product | |
| CN108830225A (en) | The detection method of target object, device, equipment and medium in terahertz image | |
| CN109935080A (en) | The monitoring system and method that a kind of vehicle flowrate on traffic route calculates in real time | |
| CN109117717A (en) | A kind of city pedestrian detection method | |
| CN108875482A (en) | Object detecting method and device, neural network training method and device | |
| CN106101857B (en) | A kind of display methods and device of video pictures | |
| CN108280398A (en) | A kind of gait recognition method and system based on various visual angles fusion | |
| CN107481260A (en) | A kind of region crowd is detained detection method, device and storage medium | |
| CN112036267A (en) | Target detection method, device, equipment and computer readable storage medium | |
| Peissig et al. | The pigeon's perception of depth-rotated shapes | |
| CN109831634A (en) | The density information of target object determines method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20161109 |