CN110287917A - The security management and control system and method in capital construction building site - Google Patents
The security management and control system and method in capital construction building site Download PDFInfo
- Publication number
- CN110287917A CN110287917A CN201910577950.3A CN201910577950A CN110287917A CN 110287917 A CN110287917 A CN 110287917A CN 201910577950 A CN201910577950 A CN 201910577950A CN 110287917 A CN110287917 A CN 110287917A
- Authority
- CN
- China
- Prior art keywords
- image
- monitoring image
- abnormal conditions
- capital construction
- building site
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012544 monitoring process Methods 0.000 claims abstract description 101
- 230000002159 abnormal effect Effects 0.000 claims abstract description 74
- 230000006399 behavior Effects 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 239000000428 dust Substances 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 230000002045 lasting effect Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000009172 bursting Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a kind of security management and control systems in capital construction building site, the monitoring image of captured in real-time capital construction building site predeterminable area is used for including photographic device, if and present frame monitoring image and pre-stored image there are it is different when, the monitoring image of subsequent shooting is uploaded to operation gateway;Operation gateway is used to the monitoring image received carrying out image recognition, obtains the abnormal conditions information in predeterminable area, and abnormal conditions information is uploaded to background server;Background server issues alarm prompt according to abnormal conditions information.Device structure is simple in security management and control system of the invention, is easy to configure and install, and operation use cost is low, and can reuse in multiple capital construction building sites, largely reduces the security maintenance cost in capital construction building site, is conducive to urbanization.A kind of security control method in capital construction building site is additionally provided in the present invention, and there is above-mentioned beneficial effect.
Description
Technical field
The present invention relates to capital construction building site peace pipes to manage technical field, more particularly to a kind of security management and control system in capital construction building site
System and method.
Background technique
With the high speed development of China's economic level, various subways, office block, overpass, City complex building etc.
Etc. technical equipment construction it is also more and more.And the safety in capital construction building site just become unit in charge of construction emphatically it should be noted that the problem of it
One.
Complicated for the installation of the security management and control system in capital construction building site at present and higher operating costs, and for it is certain
The architectural engineering come into operation, if necessary to which it is extended or is safeguarded, the duration is often shorter, using high-cost bursting tube
Control system necessarily will increase the cost of entire extension project.
Summary of the invention
The object of the present invention is to provide the security management and control systems and method in a kind of capital construction building site, solve the peace in capital construction building site
The high problem of full control operating cost.
In order to solve the above technical problems, the present invention provides a kind of security management and control system in capital construction building site, including distribution setting
Multiple photographic devices in capital construction building site;It is communicated to connect with the photographic device and the operation gateway that capital construction building site is arranged in is set
It is standby;And the background server with the communication connection of operation gateway strange land;
Wherein, the photographic device is used for the monitoring image of captured in real-time capital construction building site predeterminable area, and if present frame
Monitoring image and pre-stored image there are it is different when, then the monitoring image of subsequent shooting is uploaded to the operation gateway;
The operation gateway is used to the monitoring image received carrying out image recognition, obtains in predeterminable area
Abnormal conditions information, and the abnormal conditions information is uploaded to background server;
The background server issues alarm prompt according to the abnormal conditions information.
Wherein, the operation gateway is specifically used for according to the abnormal conditions identification model being pre-created, to the prison
Altimetric image carries out image recognition.
Wherein, the background server is also used to the pre- monitoring figure for first passing through the photographic device and acquiring the predeterminable area
Decent;And study is trained according to the monitoring image sample, the abnormal conditions identification model is obtained, so as to will be described
Abnormal conditions identification model is built in the operation gateway.
Wherein, the abnormal conditions identification model, for identification behavior of hurdling of predeterminable area, identification safe wearing cap insignia
Chapter, identification target person enter danger zone behavior, identification fire conditions and identification predeterminable area fugitive dust situation.
Wherein, the photographic device is specifically also used to, if the monitoring image and the pre-stored image of the present frame of shooting are not
When having differences, then the frame pre-stored image that shooting time is earliest in the pre-stored image is deleted;And the monitoring image is made
It is stored for new pre-stored image;
Wherein, pre-stored image described in multiframe is stored in the photographic device.
The present invention also provides a kind of security control methods in capital construction building site, are applied to capital construction as described in any one of the above embodiments
The security management and control system in building site, comprising:
Receive the monitoring image that multiple photographic devices upload, wherein the monitoring image is that the photographic device is clapped in real time
The monitoring image of capital construction building site predeterminable area is taken the photograph, and if starting to clap after the monitoring image and pre-stored image presence Bu Tong of present frame
Take the photograph the image of upload;
Image recognition is carried out to the monitoring image, obtains the abnormal conditions information in predeterminable area;
The abnormal conditions information is uploaded to background server, so that the background server issues alarm prompt.
Wherein, described to carry out image recognition to the monitoring image, the abnormal conditions information obtained in predeterminable area includes:
According to the abnormal conditions identification model being pre-created, image recognition is carried out to the detection image, obtains preset areas
Abnormal conditions information in domain.
Wherein, the creation process of the abnormal conditions identification model includes:
The monitoring image sample of the predeterminable area is acquired by the photographic device, wherein the monitoring image sample is
Persistently shoot predeterminable area multiple image obtained;
The detection image sample is shown in human-computer interaction interface, and receives what user inputted the monitoring image sample
Abnormal conditions mark;
It is identified according to the abnormal conditions and carries out learning training, obtain the abnormal conditions identification model;
Abnormal conditions mark include the behavior mark of hurdling of predeterminable area, safety cap badge mark, target person into
Enter danger zone behavior mark, fire conditions mark and predeterminable area fugitive dust situation mark.
Wherein, further includes:
When the monitoring image of photographic device shooting is identical with the pre-set image, then delete in the pre-stored image
The earliest frame pre-stored image of shooting time;And it is stored the monitoring image as new pre-stored image;
Wherein, pre-stored image described in multiframe is stored in the photographic device.
Wherein, further includes:
When background server receives the alarm prompt error message of user's input, then the alarm prompt mistake is recorded
Information;
When the probability that alarm prompt error message occurs reaches predetermined probabilities, then believed according to the alarm prompt mistake of record
Breath is modified the abnormal conditions identification model.
The security management and control system in capital construction building site provided by the present invention is set to multiple camera shootings in capital construction building site including being distributed
Device;The operation gateway in capital construction building site is communicated to connect and is arranged in photographic device;And with operation gateway strange land
The background server of communication connection;Wherein, photographic device is used for the monitoring image of captured in real-time capital construction building site predeterminable area, and if
The monitoring image and pre-stored image of present frame there are it is different when, then the monitoring image of subsequent shooting is uploaded to operation gateway;
Operation gateway is used to the monitoring image received carrying out image recognition, obtains the abnormal conditions information in predeterminable area,
And abnormal conditions information is uploaded to background server;Background server issues alarm prompt according to abnormal conditions information.
By arranging that multiple photographic devices and operation gateway, the photographic device can be right in capital construction building site in the application
The monitoring image of shooting makees simple discriminatory analysis, only changes in the monitoring image taken relative to pre-stored image
When, just upload monitoring image to operation gateway, reduce between photographic device and operation gateway data upload amount with
And operation gateway is to the treating capacity of monitoring image;The abnormal feelings in monitoring image are identified by operation gateway again
Condition, and the result of abnormal conditions is directly sent to background server, secondary analysis is carried out to testing result without staff,
And reduce the data interaction amount between operation gateway and background server;In addition operation gateway and photographic device are all provided with
It is placed in capital construction building site, data transmission difficulty between the two is reduced, thereby reduces to photographic device and operation gateway
Requirement, advantageously reduce system equipment cost.
Device structure is simple in security management and control system of the invention, is easy to configure and install, operation use cost is low, and can
To be reused in multiple capital construction building sites, the security maintenance cost in capital construction building site is largely reduced, city is conducive to
Change.
A kind of security control method in capital construction building site is additionally provided in the present invention, and there is above-mentioned beneficial effect.
Detailed description of the invention
It, below will be to embodiment or existing for the clearer technical solution for illustrating the embodiment of the present invention or the prior art
Attached drawing needed in technical description is briefly described, it should be apparent that, the accompanying drawings in the following description is only this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the block schematic illustration of the security management and control system in capital construction building site provided in an embodiment of the present invention;
Fig. 2 is the flow diagram of the security control method in capital construction building site provided in an embodiment of the present invention;
Fig. 3 is the creation process flow schematic diagram of creation abnormal conditions identification module provided in an embodiment of the present invention;
Fig. 4 is creation process flow block diagram provided in an embodiment of the present invention;
Fig. 5 is the security control method flow diagram in capital construction building site provided in an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiments are only a part of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
As shown in FIG. 1, FIG. 1 is the block schematic illustrations of the security management and control system in capital construction building site provided in an embodiment of the present invention;
The security management and control system may include:
Distribution is set to multiple photographic devices 1 in capital construction building site;It communicates to connect and is arranged in capital construction building site with photographic device 1
Operation gateway 2;And the background server 3 with the communication connection of 2 strange land of operation gateway;
Wherein, photographic device 1 be used for captured in real-time capital construction building site predeterminable area monitoring image, and if present frame monitoring
Image and pre-stored image there are it is different when, then the monitoring image of subsequent shooting is uploaded to operation gateway 2;
Operation gateway 2 is used to the monitoring image received carrying out image recognition, obtains the exception in predeterminable area
Situation information, and abnormal conditions information is uploaded to background server 3;
Background server 3 issues alarm prompt according to abnormal conditions information.
Specifically, which specifically can be the frame for showing abnormal conditions or number frame monitoring image, with
And explanatory note of cooperation either audio alert sound etc., specific abnormal conditions are understood so that staff is clearer.
As shown in Figure 1, the photographic device 1 can specifically be built-in with storage chip, operation chip, communication core in the present embodiment
Piece and camera;The monitoring image in shooting predeterminable area can be monitored in real time by camera.It in practical applications, can be with
Photographic device 1 is respectively set at the several important outposts in capital construction building site according to actual needs, the camera face of photographic device 1 is needed
The region to be shot, after camera takes monitoring image, operation chip just carries out fundamental analysis, and and storage to monitoring image
Stored pre-stored image compares in chip, judges monitoring image and pre-stored image with the presence or absence of difference.
It should be noted that the pre-stored image is also that the photographic device 1 is shot in same predeterminable area, and unmanned nothing
The image of abnormal conditions.In this, as judgment criteria, as long as difference is not present between the monitoring image and pre-stored image that newly shoot,
Then simultaneously nobody situation without exception explanation occurs;Enter shooting area if there is difference, such as someone.Photographic device 1 is opened at this time
Begin to continue to upload the subsequent monitoring image taken to operation gateway 2 by communication chip.
Operation chip in the present embodiment in photographic device 1 only needs to do monitoring image and pre-stored image simple right
Than, operation is simple, and it is low to the operational capability requirement of chip, installation cost can be also reduced to a certain extent.
Operation gateway 2 in the present embodiment can be to the abnormal conditions in the monitoring image after receiving monitoring image
It is identified, and after obtaining specific abnormal conditions information, abnormal conditions information is sent to background server 3, background service
Device 3 can be issued to staff and be alarmed.
Optionally, the operation gateway 2 in the present embodiment is specifically used for according to the abnormal conditions identification mould being pre-created
Type carries out image recognition to the monitoring image.
It, can be first according to capital construction building site in order to reduce the difficulty that operation gateway 2 identifies abnormal conditions in monitoring image
Actual conditions create model, when being analyzed and processed to operation gateway 2 to monitoring image directly according to the exception feelings
Condition identification model, it is purposive to monitoring image to analyze, reduce operation difficulty.
And if after the capital construction building site construction is completed, it is only necessary to which the abnormal conditions identification module is updated to next needs
The model in the capital construction building site of construction, and other equipment still can continue to use, and be conducive to the recycling of whole system.
Security management and control system in conventional capital construction building site at present is typically necessary a variety of detection devices of configuration, for example takes the photograph
As head persistently records image and uploads to background server, by artificial observation capital construction building site with the presence or absence of abnormal conditions, pass through
Face recognition technology judges whether the personnel entered are staff, while also setting up infrared sensor, detect whether someone into
Enter danger zone etc.;A variety of different detecting devices are all directly to be connected with background server, immediately rearward platform server
Uploading detection data, then analyse whether that, there are abnormal conditions, there are upload data volumes by background server or manual identified
Greatly, increasingly complex to the data processing of detection, it is also higher to equipment requirement.
It is filtered in advance in the application using the photographic device with simple operation function and excludes a part of useless monitoring figure
As data, data upload amount is reduced to a certain extent, further through operation gateway to there may be the monitorings of different situation
Image carries out further recognition and verification, final that recognition result is only uploaded to background server, enables background server
The analysis of specific monitoring image is obtained as a result, carrying out manual analysis again by monitoring image without staff, is subtracted simultaneously
The small data volume for uploading background server, and reduce background server to the treating capacity of data.Bursting tube in the application
Control system, equipment is simple, and installation easy to disassemble, use cost is low, advantageously reduces the security management and control cost of infrastructure project, is applicable in
In the construction of short-term infrastructure project.
As previously mentioned, operation gateway is to be tested and analyzed based on abnormal conditions identification module to monitoring image,
In another specific embodiment of the invention, can also further include:
Background server 3 is also used to the pre- monitoring image sample for first passing through photographic device 1 and acquiring predeterminable area;And according to prison
Altimetric image sample is trained study, abnormal conditions identification model is obtained, so that abnormal conditions identification model is built in operation
In gateway 2.
It specifically, can be first by each photographic device 1 in capital construction building site cloth before using the security management and control system in the application
Completion is set, and continues to shoot the monitoring image sample in predeterminable area, it specifically can be with continuous sampling three days or more;Pass through operation again
Gateway 2 uploads to background server 3, and background server 3 can carry out learning training based on the monitoring image sample, obtain
Abnormal conditions identification model.
It should be noted that not necessarily there is background server 3 to complete abnormal conditions identification model in the present embodiment
Creation, can also using other dedicated for creation module server complete, in this present invention with no restrictions.
Optionally, the abnormal conditions identification model in the present embodiment, the behavior of hurdling, identification of predeterminable area are worn for identification
Badge, the identification target person of wearing a safety helmet enter danger zone behavior, identification fire conditions and identification predeterminable area fugitive dust feelings
Condition.
Specifically, the content specifically identified for abnormal conditions identification model, can be according to actual capabilities in capital construction building site
The various of appearance need the case where alarming and set.
Based on above-mentioned any embodiment, in another embodiment of the present invention, can also further include:
Photographic device 2 is specifically also used to, if the monitoring image of the present frame of shooting is identical with pre-stored image, is deleted pre-
Deposit the frame pre-stored image that shooting time is earliest in image;And it is stored monitoring image as new pre-stored image;
Wherein, multiframe pre-stored image is stored in photographic device 2.
When the monitoring image of pre-stored image and current shooting is compared judgement by the operation chip in photographic device 2,
If the shooting time of pre-stored image, in environment there is difference or camera in bright and dark light, weather condition and present case
There are subtle deflections, and the comparison judging result to monitoring image can all be caused to have an impact, so that judging result is inaccurate.
For this purpose, the pre-stored image in the present embodiment in photographic device 2 belongs to the image of real-time update.For example, can be logical with line
It crosses photographic device 2 and shoots 10 images as pre-stored image, then carry out the shooting of subsequent image by camera.When camera is clapped
The monitoring image for the present frame taken the photograph and this 10 pre-stored image comparisons, when having no significant difference, then will clap in 10 pre-stored images
The longest image-erasing of time gap current time is taken the photograph, and the monitoring image of present frame one the most new pre-stored image is carried out
Storage;When camera takes next frame monitoring image, adopts and compares judgement in a like fashion, distinguish if it does not exist,
Then pre-stored image is updated again.
It is more capable in real time to pre-stored image progress using the monitoring image of camera captured in real-time in the present embodiment, and camera
The time interval for being continuously shot multiple image is very short, when carrying out image comparison, environmental change difference base caused by image
Originally it can ignore, avoid when comparing pre-stored image and monitoring image, influence of the environmental factor to image comparison makes
It is more accurate to obtain comparing result.
The security control method in capital construction building site provided in an embodiment of the present invention is introduced below, capital construction described below
The security control method in building site can correspond to each other reference with the security management and control system in above-described capital construction building site.
Fig. 2 is the flow diagram of the security control method in capital construction building site provided in an embodiment of the present invention, referring to this reality of Fig. 2
The security control method for applying the capital construction building site in example may include:
Step S11: the monitoring image that multiple photographic devices upload is received.
Specifically, monitoring image is the monitoring image of photographic device captured in real-time capital construction building site predeterminable area, and if current
The monitoring image of frame starts the image that shooting uploads after existing Bu Tong with pre-stored image, reduce in the image data of photographic device
Biography amount.
Step S12: image recognition is carried out to monitoring image, obtains the abnormal conditions information in predeterminable area.
Step S13: being uploaded to background server for abnormal conditions information, so that background server issues alarm prompt.
Only abnormal conditions information is uploaded, reduces uploading information data amount, and be not necessarily to background server and staff
Secondary analysis.
Security control method in the present embodiment, step is simple, and data operation quantity is small and then reduces to equipment operational capability
Requirement, reduce the operating cost of equipment, and then reduce the cost of infrastructure project security management and control.
Optionally, in another embodiment of the present invention, above-mentioned steps S12 can specifically include:
According to the abnormal conditions identification model being pre-created, image recognition is carried out to the detection image, obtains preset areas
Abnormal conditions information in domain.
Purposive discriminance analysis is carried out to monitoring image by the model that has been pre-created, is conducive to further decrease pair
The analysis difficulty of monitoring image reduces operation difficulty.
Optionally, in another embodiment of the present invention, as shown in figure 3, Fig. 3 is wound provided in an embodiment of the present invention
Build the creation process flow schematic diagram of abnormal conditions identification module;It can specifically include:
Step S21: the monitoring image sample of predeterminable area is acquired by photographic device, wherein monitoring image sample is lasting
Shoot predeterminable area multiple image obtained.
Step S22: the detection image sample is shown in human-computer interaction interface, and it is defeated to monitoring image sample to receive user
The abnormal conditions mark entered.
Step S23: identifying according to abnormal conditions and carry out learning training, obtains abnormal conditions identification model.
Specifically, abnormal conditions mark includes the behavior mark of hurdling of predeterminable area, safety cap badge mark, target person
Into danger zone behavior mark, fire conditions mark and predeterminable area fugitive dust situation mark.
Optionally, in another embodiment of the present invention, can also further include:
When the monitoring image of photographic device shooting is identical with the pre-set image, then delete in the pre-stored image
The earliest frame pre-stored image of shooting time;And it is stored the monitoring image as new pre-stored image;
Wherein, pre-stored image described in multiframe is stored in the photographic device.
Optionally, it can further include in another embodiment of the present invention:
When background server receives the alarm prompt error message of user's input, then the alarm prompt mistake is recorded
Information;
When the probability that alarm prompt error message occurs reaches predetermined probabilities, then believed according to the alarm prompt mistake of record
Breath is modified the abnormal conditions identification model.
As shown in figure 4, Fig. 4 is creation process flow block diagram provided in an embodiment of the present invention.It needs to adopt via photographic device
Monitor set image sample data to GPU server (that is to say background server), GPU server is provided by man-machine interactive system
Demand mark is done to staff, algorithm training is then carried out by GPU server again, is trained knot using monitoring image sample
After calculation, it is again supplied to artificial cognition mark, manually the mode re-optimization algorithm of error correction.When to existing video data differentiate at
After power reaches 100%, that is, it is transferred to encapsulation link, and is sent to operation gateway and edge calculations camera execution burning step,
Then it is run by operation gateway and edge calculations camera.
As shown in figure 5, Fig. 5 is the security control method flow diagram in capital construction building site provided in an embodiment of the present invention, Fig. 5 is
Operation flow after formally implementing after the training in Fig. 4 is complete.At this point, operation gateway and photographic device had compared at
Ripe mathematical algorithm is executing.Video data (i.e. monitoring image) is acquired by camera, and it is next to be divided into both direction progress
Step movement, in the computing module (i.e. level-one operation) of photographic device itself, the image comparison for carrying out the part to video data is transported
It calculates, and result is fed back into operation gateway.
Operation gateway is after receiving video data, the image recognition algorithm that execute encapsulation burning is completed, and feeds back
Calculated result is to GPU server;Operation gateway can forward video data to GPU server simultaneously, be supplied to GPU server
It does sampling and decision differentiates use.GPU server carries out three-stage operational to the calculated result and video data that receive, and herein three
The sampled images identification that video data is done in grade operation calculates, and result and the result of second level operation are fed back in human-computer interaction circle
Face is supplied to artificial progress decision judgement, while result can also be passed through the warp such as wechat small routine by GPU server after three-stage operational
Internet channel feeds back to user hand generator terminal and carries out alarm prompt.And on human-computer interaction interface, it is supplied to staff's progress
Determination decisions, if via after artificial cognition as a result, belong to correctly, three-stage operational module can be fed back to, for artificial
As a result, belonging to erroneous judgement after differentiation, then artificial to need that the point identification is arranged in interactive interface and submits, GPU server can be right
Artificial to determine that result is adjusted (deep learning) algorithm, the sample of adjustment is more, for algorithm encapsulate again burning and after
Continuous I and II calculated result will be more acurrate.The process of so entire Fig. 5 be repeat constantly to be acquired, calculate, determining,
Training optimizes and reburns what record encapsulated.It should be noted that the burning that encapsulates again here is not all can after mark each time
This step is executed, then encapsulating burning is the sample point sum that must work as False Rate and meet or exceed 10%, can just execute this step.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with it is other
The difference of embodiment, same or similar part may refer to each other between each embodiment.For being filled disclosed in embodiment
For setting, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part
Explanation.
Claims (10)
1. a kind of security management and control system in capital construction building site, which is characterized in that be set to multiple camera shootings in capital construction building site including being distributed
Device;The operation gateway in capital construction building site is communicated to connect and is arranged in the photographic device;And with the operation gateway
The background server of equipment strange land communication connection;
Wherein, the photographic device be used for captured in real-time capital construction building site predeterminable area monitoring image, and if present frame monitoring
Image and pre-stored image there are it is different when, then the monitoring image of subsequent shooting is uploaded to the operation gateway;
The operation gateway is used to the monitoring image received carrying out image recognition, obtains different in predeterminable area
Reason condition information, and the abnormal conditions information is uploaded to background server;
The background server issues alarm prompt according to the abnormal conditions information.
2. the security management and control system in capital construction building site as described in claim 1, which is characterized in that the operation gateway is specific
For carrying out image recognition to the monitoring image according to the abnormal conditions identification model being pre-created.
3. the security management and control system in capital construction building site as claimed in claim 2, which is characterized in that the background server is also used to
The monitoring image sample that the photographic device acquires the predeterminable area is first passed through in advance;And it is carried out according to the monitoring image sample
Training study, obtains the abnormal conditions identification model, so that the abnormal conditions identification model is built in the operation net
It closes in equipment.
4. the security management and control system in capital construction building site as claimed in claim 2, which is characterized in that the abnormal conditions identify mould
Type, the behavior of hurdling of predeterminable area, identification safe wearing cap insignia chapter, identification target person enter danger zone row for identification
For, identification fire conditions and identification predeterminable area fugitive dust situation.
5. such as the security management and control system in the described in any item capital construction building sites of Claims 1-4, which is characterized in that the camera shooting dress
It sets and is specifically also used to, if difference is not present in the monitoring image and the pre-stored image of the present frame of shooting, delete described pre-
Deposit the frame pre-stored image that shooting time is earliest in image;And it is stored the monitoring image as new pre-stored image;
Wherein, pre-stored image described in multiframe is stored in the photographic device.
6. a kind of security control method in capital construction building site, which is characterized in that be applied to as described in any one of claim 1 to 5
The security management and control system in capital construction building site, comprising:
Receive the monitoring image that multiple photographic devices upload, wherein the monitoring image is the photographic device captured in real-time base
The monitoring image of building site predeterminable area is built, and if starting in shooting after the monitoring image and pre-stored image presence Bu Tong of present frame
The image of biography;
Image recognition is carried out to the monitoring image, obtains the abnormal conditions information in predeterminable area;
The abnormal conditions information is uploaded to background server, so that the background server issues alarm prompt.
7. the security control method in capital construction building site as claimed in claim 6, which is characterized in that it is described to the monitoring image into
Row image recognition, the abnormal conditions information obtained in predeterminable area include:
According to the abnormal conditions identification model being pre-created, image recognition is carried out to the detection image, is obtained in predeterminable area
Abnormal conditions information.
8. the security control method in capital construction building site as claimed in claim 7, which is characterized in that the abnormal conditions identification model
Creation process include:
The monitoring image sample of the predeterminable area is acquired by the photographic device, wherein the monitoring image sample is lasting
Shoot predeterminable area multiple image obtained;
The detection image sample is shown in human-computer interaction interface, and receives the exception that user inputs the monitoring image sample
Situation mark;
It is identified according to the abnormal conditions and carries out learning training, obtain the abnormal conditions identification model;
The abnormal conditions mark includes the behavior mark of hurdling of predeterminable area, safety cap badge identifies, target person enters danger
Danger zone domain behavior mark, fire conditions mark and predeterminable area fugitive dust situation mark.
9. such as the security control method in the described in any item capital construction building sites of claim 6 to 8, which is characterized in that further include:
When the monitoring image of photographic device shooting is identical with the pre-set image, then deletes and shot in the pre-stored image
The frame pre-stored image of time earliest;And it is stored the monitoring image as new pre-stored image;
Wherein, pre-stored image described in multiframe is stored in the photographic device.
10. the security control method in capital construction building site as claimed in claim 9, which is characterized in that further include:
When background server receives the alarm prompt error message of user's input, then the alarm prompt mistake letter is recorded
Breath;
It is when the probability that the alarm prompt error message occurs reaches predetermined probabilities, then wrong according to the alarm prompt of record
False information is modified the abnormal conditions identification model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910577950.3A CN110287917B (en) | 2019-06-28 | 2019-06-28 | Safety control system and method for construction site |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910577950.3A CN110287917B (en) | 2019-06-28 | 2019-06-28 | Safety control system and method for construction site |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110287917A true CN110287917A (en) | 2019-09-27 |
CN110287917B CN110287917B (en) | 2024-04-05 |
Family
ID=68020150
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910577950.3A Active CN110287917B (en) | 2019-06-28 | 2019-06-28 | Safety control system and method for construction site |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110287917B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111178145A (en) * | 2019-12-06 | 2020-05-19 | 深圳市中电数通智慧安全科技股份有限公司 | Method and device for identifying illegal operation, terminal equipment and computer storage medium |
CN113516383A (en) * | 2021-06-30 | 2021-10-19 | 南通四建集团有限公司 | Building construction safety control method and device |
CN115546677A (en) * | 2022-07-11 | 2022-12-30 | 北京国电通网络技术有限公司 | Capital construction site information processing method, device, equipment and computer readable medium |
CN115953267A (en) * | 2023-03-09 | 2023-04-11 | 中川建投集团有限公司 | Intelligent construction site management system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5627915A (en) * | 1995-01-31 | 1997-05-06 | Princeton Video Image, Inc. | Pattern recognition system employing unlike templates to detect objects having distinctive features in a video field |
CN104333736A (en) * | 2014-10-28 | 2015-02-04 | 山东大学 | Intelligent recognition monitoring system and method for unmanned substation |
CN105128814A (en) * | 2015-07-31 | 2015-12-09 | 小米科技有限责任公司 | Method and apparatus sending alarm information |
CN108133487A (en) * | 2017-12-04 | 2018-06-08 | 王连圭 | The trans-regional single human body attitude target detection extracting method of video |
CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O&M intelligent monitoring system and method |
CN109214299A (en) * | 2018-08-09 | 2019-01-15 | 合肥美的智能科技有限公司 | Article monitoring method, device and the counter of counter |
CN109241897A (en) * | 2018-08-29 | 2019-01-18 | 深圳华远云联数据科技有限公司 | Processing method, device, gateway and the storage medium of monitoring image |
CN109922310A (en) * | 2019-01-24 | 2019-06-21 | 北京明略软件系统有限公司 | The monitoring method of target object, apparatus and system |
-
2019
- 2019-06-28 CN CN201910577950.3A patent/CN110287917B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5627915A (en) * | 1995-01-31 | 1997-05-06 | Princeton Video Image, Inc. | Pattern recognition system employing unlike templates to detect objects having distinctive features in a video field |
CN104333736A (en) * | 2014-10-28 | 2015-02-04 | 山东大学 | Intelligent recognition monitoring system and method for unmanned substation |
CN105128814A (en) * | 2015-07-31 | 2015-12-09 | 小米科技有限责任公司 | Method and apparatus sending alarm information |
CN108133487A (en) * | 2017-12-04 | 2018-06-08 | 王连圭 | The trans-regional single human body attitude target detection extracting method of video |
CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O&M intelligent monitoring system and method |
CN109214299A (en) * | 2018-08-09 | 2019-01-15 | 合肥美的智能科技有限公司 | Article monitoring method, device and the counter of counter |
CN109241897A (en) * | 2018-08-29 | 2019-01-18 | 深圳华远云联数据科技有限公司 | Processing method, device, gateway and the storage medium of monitoring image |
CN109922310A (en) * | 2019-01-24 | 2019-06-21 | 北京明略软件系统有限公司 | The monitoring method of target object, apparatus and system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111178145A (en) * | 2019-12-06 | 2020-05-19 | 深圳市中电数通智慧安全科技股份有限公司 | Method and device for identifying illegal operation, terminal equipment and computer storage medium |
CN113516383A (en) * | 2021-06-30 | 2021-10-19 | 南通四建集团有限公司 | Building construction safety control method and device |
CN113516383B (en) * | 2021-06-30 | 2024-05-03 | 南通四建集团有限公司 | Building construction safety control method and device |
CN115546677A (en) * | 2022-07-11 | 2022-12-30 | 北京国电通网络技术有限公司 | Capital construction site information processing method, device, equipment and computer readable medium |
CN115546677B (en) * | 2022-07-11 | 2023-10-24 | 北京国电通网络技术有限公司 | Method, apparatus, device and computer readable medium for processing information of construction site |
CN115953267A (en) * | 2023-03-09 | 2023-04-11 | 中川建投集团有限公司 | Intelligent construction site management system |
CN115953267B (en) * | 2023-03-09 | 2023-06-16 | 中川建投集团有限公司 | Intelligent building site management system |
Also Published As
Publication number | Publication date |
---|---|
CN110287917B (en) | 2024-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110287917A (en) | The security management and control system and method in capital construction building site | |
CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
CN110996067A (en) | Personnel safety real-time intelligent video monitoring system under high-risk operation environment based on deep learning | |
CN108389359B (en) | Deep learning-based urban fire alarm method | |
CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
CN102917207A (en) | Motion sequence based abnormal motion vision monitoring system | |
CN110012268A (en) | Pipe network AI intelligent control method, system, readable storage medium storing program for executing and equipment | |
CN110490126B (en) | Safe deposit box safety control system based on artificial intelligence | |
CN113012374A (en) | Intelligent park security system and control method thereof | |
KR20200052418A (en) | Automated Violence Detecting System based on Deep Learning | |
CN112434828A (en) | Intelligent identification method for safety protection in 5T operation and maintenance | |
CN112434827A (en) | Safety protection identification unit in 5T fortune dimension | |
CN111325133A (en) | Image processing system based on artificial intelligence recognition | |
CN109635717A (en) | A kind of mining pedestrian detection method based on deep learning | |
CN105933458A (en) | Multilevel cloud monitoring platform | |
CN111222420A (en) | FTP protocol-based low-bandwidth-requirement helmet identification method | |
CN114627388A (en) | Power transmission line foreign matter detection equipment and foreign matter detection method thereof | |
CN110241791A (en) | A kind of intelligent sluice group remote monitoring system based on GIS | |
CN114067396A (en) | Vision learning-based digital management system and method for live-in project field test | |
CN107368825A (en) | Person number detection device, method and system in a kind of danger zone | |
CN209803819U (en) | Face recognition recorder | |
CN103345625B (en) | A kind of three-dimensional image analysis method and system | |
CN116206253A (en) | Method and system for detecting and judging site fire behavior based on deep learning | |
CN206058456U (en) | It is a kind of for fire identification can monitor in real time image processing system | |
CN112343657B (en) | Method for identifying mine underground air door and monitoring abnormal state of mine underground air door |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |