CN109711348A - Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel - Google Patents
Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel Download PDFInfo
- Publication number
- CN109711348A CN109711348A CN201811619560.XA CN201811619560A CN109711348A CN 109711348 A CN109711348 A CN 109711348A CN 201811619560 A CN201811619560 A CN 201811619560A CN 109711348 A CN109711348 A CN 109711348A
- Authority
- CN
- China
- Prior art keywords
- against regulations
- architecture against
- information
- architecture
- regulations
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000007774 longterm Effects 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 11
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 claims abstract description 11
- 238000003860 storage Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000003825 pressing Methods 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 description 14
- 238000010276 construction Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 10
- 238000001514 detection method Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 4
- 208000004350 Strabismus Diseases 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004873 anchoring Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of intelligent monitoring methods and system based on the long-term real-time architecture against regulations in hollow panel, wherein monitoring system includes: to stay hollow panel for a long time；Photoelectric nacelle: for periodically carrying out region-wide Image Acquisition to periphery atural object automatically；Ground monitoring equipment: for acquiring the image information of photoelectric nacelle blind area；Information database: for receiving, storing and handle acquired image data；And for Architectural drawing region of variation to be pushed to supervising platform；Supervising platform: for receiving Architectural drawing region of variation information and judging whether it is the architecture against regulations, architecture against regulations position and corresponding image information are pushed into law enfrocement official's terminal；Architecture against regulations information is stored in architecture against regulations sample database；For completing the training to artificial intelligence recognizer when sample data reaches setting value in architecture against regulations sample database.The present invention provides the discovery means of the continuous and effective of the architecture against regulations, solve the problems, such as the missing evidence in enforcing law；Timeliness is high.
Description
Technical field
The present invention is more particularly directed to a kind of intelligent monitoring methods and system based on the long-term real-time architecture against regulations in hollow panel.
Background technique
Currently, generalling use artificial inspection, unmanned aerial vehicle remote sensing and satellite remote sensing etc. for the city architecture against regulations and completing image
Suspicious building artificial screening, judgement again is found in monitoring；Such as table 1 of problem condition existing for existing monitoring means.
The existing architecture against regulations of table 1 monitor discovery means there are the problem of
There is certain timeliness and accuracy problem during actual implementation in all kinds of monitoring means.Work is disobeyed currently, prohibiting
The development of work mainly uses the scheme based on daily artificial inspection, supplemented by regular unmanned plane, and the program has following problems:
(1) supervision scope is limited, and timeliness is poor.Architecture against regulations monitoring requirements coverage area is wider, either manually patrols
It looks into or unmanned plane all can not disposably cover whole region, generally can all be pre-designed fixed route and period, make
Residents are obtained illegally to be built using inspection gap.
(2) lack history comparison data, difficulty is defined to the architecture against regulations.Once the architecture against regulations completes, how to go to define
Its construction-time, illegal, often lack sufficient evidence, this carrys out very big puzzlement to work belt of demolishing squatter buildings.
Summary of the invention
It is an object of the present invention in view of the above shortcomings of the prior art, provide a kind of based on the long-term reality for staying hollow panel
When the architecture against regulations intelligent monitoring method and system.
In order to solve the above technical problems, the technical scheme adopted by the invention is that:
A kind of intelligent monitoring method based on the long-term real-time architecture against regulations in hollow panel, its main feature is that including following step
It is rapid:
Step 1, the long-term photoelectric nacelle of carrying in hollow panel is to certain height；
Step 2, photoelectric nacelle is periodically automatic right by scanning angle, scan period, the setting value for scanning stepping rate
Periphery atural object carries out region-wide Image Acquisition；
Step 3, by the storage of photoelectric nacelle acquired image data into information database；Wherein, image data is being believed
Cease the storage mode in database are as follows: building state, acquisition time, location information correspond storage；
Step 4, information database carries out data processing to image data will be built with finding Architectural drawing region of variation
Image change region pushes to supervising platform；
Step 5, artificial to be sentenced according to the Architectural drawing region of variation information received in the human-computer interaction interface of supervising platform
Whether corresponding building of breaking is the architecture against regulations, if then going to step 6, if otherwise repeating step 2~5；
Step 6, architecture against regulations position and corresponding image information are pushed to law enfrocement official's terminal by supervising platform；Simultaneously will
Architecture against regulations information is stored in architecture against regulations sample database；Repeat step 2~6；
Step 7, it when sample data reaches setting value in architecture against regulations sample database, completes to artificial intelligence recognizer
Training；Step 1~6 are repeated, and in steps of 5, using artificial intelligence approach according to the Architectural drawing region of variation information received
Judge whether corresponding building is the architecture against regulations.
Further, in step 2 further include: lay ground monitoring equipment on the shaft tower of monitoring blind area ground in the sky；
It further include storing ground monitoring equipment acquired image data into information database in the step 3.
Further, further includes:
Step 8, according to law enforcement information, law enfrocement official obtains evidence and enforces the law from law enfrocement official's terminal, and returns and feed back to
Supervising platform.
Based on the same inventive concept, the present invention also provides a kind of based on the long-term real-time architecture against regulations in hollow panel
Intelligent monitor system, its main feature is that including:
Hollow panel is stayed for a long time: for carrying photoelectric nacelle to certain height；
Photoelectric nacelle: periodically automatic right for pressing scanning angle, scan period, the setting value for scanning stepping rate
Periphery atural object carries out region-wide Image Acquisition；
Information database: for receiving, storing and handle photoelectric nacelle acquired image data, wherein image data
Storage mode in information database are as follows: building state, acquisition time, location information correspond storage；And it is used for
When searching out Architectural drawing region of variation, Architectural drawing region of variation is pushed into supervising platform；
Supervising platform: for receiving the Architectural drawing region of variation information of information database transmission and judging corresponding building
Whether it is the architecture against regulations, and pushes to architecture against regulations position and corresponding image information when corresponding building is the architecture against regulations
Law enfrocement official's terminal；Architecture against regulations information is stored in architecture against regulations sample database simultaneously；For the sample in architecture against regulations sample database
When data reach setting value, the training to artificial intelligence recognizer is completed.
Further, further includes:
Ground monitoring equipment: for acquiring the image information of photoelectric nacelle blind area and being sent to information database；
Information database is also used to receive, store and handles ground monitoring equipment acquired image data.
Compared with prior art, the present invention provides the supervision of the architecture against regulations for urban construction a set of new, strong
Solution, not only provide continuing, effectively finding means for the architecture against regulations, also solve evidence in enforcing law and lack
Mistake problem；By high-altitude visual angle overall situation video image high frequency time monitoring mode, the dynamic image letter of building different cycles is obtained
Breath, instead of work of manually patrolling；And a large amount of repeatability is replaced to manually check work to change the processing techniques such as detection, image mosaic
Make；It is very short that line law enfrocement official's time is pushed to from the monitoring discovery architecture against regulations to law enforcement commander and evident information, solves it
The problem of its monitoring means timeliness deficiency provides strong information backman for the municipal administration supervision in urban construction process
Tool.
Detailed description of the invention
Fig. 1 is present system composition figure.
Fig. 2 is working-flow figure.
Fig. 3 is information database topology diagram.
Fig. 4 is change detection techniques route map.
Wherein, 1 is stays hollow panel for a long time, and 2 be photoelectric nacelle, and 3 be ground monitoring equipment, and 4 be information database, and 5 be prison
Pipe platform.
Specific embodiment
The case where quick rush construction can be frequently encountered in separated work due to prohibiting at present, (can assault in 2 hours and build completion
Steel frame type building), therefore to accomplish effectively to supervise, it is necessary to high frequency time is carried out to neighboring buildings situation, is continued to monitor；Therewith
The problem of be --- the image information data amount of high frequency time is big, if using manually search video image by the way of look for building
The changed region of state, workload can be very big, so the present invention has been devised for the image data of this high frequency time
Automatically (automated graphics changes in contrast detection technique) is detected in the processing mode of effect --- construction status image change region.Also hold
Method personnel in enforcing law without effective enforcement evidence, so the present invention corresponds to repository (construction status figure by image
Picture-time-situation of building information is corresponding to be stored) effective enforcement evidence library is provided for law enfrocement official.In order to reduce artificial inspection
With manual retrieval's video data workload, in the monitoring system work process, be determined as the architecture against regulations image be added to it is separated
Zhang Jianzhu sample database carries out learning training (depth learning technology) to AI, final to realize that AI intelligent recognition determines architecture against regulations generation
For most of artificial.
The present invention (including near space aerostatics, Auto-control airship, is tethered at using empty aerial platform aerostatics is stayed for a long time
Ship/ball) or unmanned plane is tethered at as monitoring platform in sky, cooperate the photoelectric nacelle with Image Acquisition and target positioning function,
24 hours real-time monitorings of whole day in region are monitored, monitoring video image is counted using image comparison change detection techniques
According to processing state change region is found by computer automatically and marked, manually determine whether the architecture against regulations, be determined as breaking rules and regulations
The image pattern of building is stored in AI deep learning sample database, completes AI recognition training when sample number reaches certain amount, realizes intelligence
Energyization monitoring；Aerial core as the architecture against regulations supervises strength, realizes to squatter building, rush construction, effective strike that Construction Bank is steathily, entirely
Face promotes law enforcement to the ability to supervise of the architecture against regulations in region.
Major part data source is the orthography image of unmanned plane and satellite etc. at present, and the data source that this system uses for
Multi-source data (data from aerial platform, ground monitoring camera), therefore have a large amount of strabismus data processing technique.
The present invention is able to solve following technical problem:
First, space geometry information and the space point of neighboring buildings are obtained with lasting, high frequency time and the operating mode of the overall situation
The image data (real-time for ensuring monitoring data) of cloth information.
Second, super amount real-time monitoring image data is passed through into data processing timely, appropriate, and processing result is turned
Turn to data information required for the architecture against regulations (timeliness for ensuring monitoring data information).
Enforcement evidence is pushed to related law enfrocement official's (timeliness for ensuring law enforcement information) by third in time.
4th, replacing a large amount of repeatability, uncontrollable manual working with aptitude manner, (AI replacement is simply duplicate manually to look into
Figure work, reducing to enforce the law caused by human factor influences).
As shown in Figure 1, the present invention monitor system with aerostatics or be tethered at unmanned plane etc. and stay for a long time absolutely empty platform (be tethered at ship/
Ball, dirigible, near space aerostatics are tethered at unmanned plane), carrying photoelectric nacelle, (photoelectric nacelle includes visible light camera/micro-
Light night vision device, thermal infrared imager, laser range finder, gyro-stabilized platform and video tracker) lift-off work to periphery atural object shape
State carries out high frequency imaging acquisition in 24 hours；Monitoring blind area construction status information is supplemented by ground monitoring equipment；Information data
It is unified in information database and uniformly does image real time transfer；Architecture against regulations policing services are completed by comprehensive supervision platform.
It stays hollow panel for a long time to connect using mechanical fastener with photoelectric nacelle, the visible light camera in photoelectric nacelle is realized
Daytime, the imaging of target scene was investigated, and thermal infrared imager realizes adverse weather on daytime and the imaging investigation of night target scene, the two
It is combined with each other, realizes continual area monitoring task for 24 hours, there are also GPS positioning modules, IMU inertia component, laser ranging for gondola
Machine triplicity completes target using aviation location technology and positions work.
The collected video image data of photoelectric nacelle by main push-towing rope rope in floating plateform system (including load hawser and
Communication optical fiber) it is transmitted to ground display panel control, including computer, display, display and control software etc. in ground anchoring equipment, for supervising
Display, the splicing of video were controlled, and detection processing is changed to monitoring image, by the construction status of realtime graphic and a upper period
Image Database compares；When finding region of variation, label is shown in the software interface of information database by manually sentencing
Whether fixed is the architecture against regulations.The image information for being confirmed as the architecture against regulations is added to AI intelligence learning sample database, and training AI is finally real
Existing AI is intelligently found and the work of the identification architecture against regulations, while the position of the architecture against regulations, image-temporal information are by comprehensive supervision
Platform pushes to law enfrocement official's terminal.
Each module major function is as follows:
Hollow panel is stayed for a long time: for carrying photoelectric nacelle to certain height.
Photoelectric nacelle: periodically automatic right for pressing scanning angle, scan period, the setting value for scanning stepping rate
Periphery atural object carries out one week per hour region-wide Image Acquisition.
Information database: for receiving, storing and handling photoelectric nacelle acquired image data, for receiving, storing
And handle ground monitoring equipment acquired image data, wherein storage mode of the image data in information database are as follows: build
It builds object state, acquisition time, location information and corresponds storage；And for will build when searching out Architectural drawing region of variation
It builds image change region and pushes to supervising platform；Wherein the data topology structure chart of information database is as shown in Figure 2.
Supervising platform: for receiving the Architectural drawing region of variation information of information database transmission and judging corresponding building
Whether it is the architecture against regulations, and pushes to architecture against regulations position and corresponding image information when corresponding building is the architecture against regulations
Law enfrocement official's terminal；Architecture against regulations information is stored in architecture against regulations sample database simultaneously；For the sample in architecture against regulations sample database
When data reach setting value, the training to artificial intelligence recognizer is completed.
Ground monitoring equipment: for acquiring the image information of photoelectric nacelle blind area and being sent to information database.
As shown in figure 3, the intelligent monitoring method based on the long-term real-time architecture against regulations in hollow panel the following steps are included:
Step 1, hollow panel (such as aerostatics or being tethered at unmanned plane) is stayed for a long time carry photoelectric nacelle to certain height；
Step 2, photoelectric nacelle is periodically automatic right by scanning angle, scan period, the setting value for scanning stepping rate
Periphery atural object carries out one week per hour region-wide Image Acquisition；
Step 3, data processing is done into the storage of photoelectric nacelle acquired image data into information database, as evidence
And back up data；Wherein, storage mode of the image data in information database are as follows: building state, acquisition time, position letter
Breath corresponds storage；
Step 4, information database uses image mosaic technology, base map modeling technique, image affine transformation technology, image certainly
The technologies such as dynamic comparison carry out data processing to image data, to find Architectural drawing region of variation, by Architectural drawing region of variation
Push to supervising platform；
Step 5, in the human-computer interaction interface of supervising platform, staff is manually according to the Architectural drawing variation zone received
Domain information judges whether corresponding building is the architecture against regulations, if then going to step 6, if otherwise repeating step 2~5；
Step 6, architecture against regulations position and corresponding image information are pushed to law enfrocement official's terminal by supervising platform；Simultaneously will
Architecture against regulations information is stored in architecture against regulations sample database, the learning sample as artificial intelligence recognizer；Repeat step 2~6；
Step 7, it when sample data reaches setting value in architecture against regulations sample database, completes to artificial intelligence recognizer
Training, it is final to replace artificial searching and determine architecture against regulations work；Step 1~6 are repeated, and in steps of 5, using artificial intelligence
Method judges whether corresponding building is the architecture against regulations according to the Architectural drawing region of variation information received.
In step 2 further include: ground monitoring equipment is laid on the shaft tower of monitoring blind area ground, in the sky to fill up aerial prison
Survey blind area data；
It further include storing ground monitoring equipment acquired image data into information database in the step 3.
It further include step 8, according to law enforcement information, law enfrocement official obtains evidence and enforces the law from law enfrocement official's terminal, using floating
State image information after the photoelectric nacelle admission law enforcement that pocket carries, and return and feed back to supervising platform.
The present invention has following technical characteristic:
1. (inside having visible light/low-light, red using staying hollow panel (aerostatics/be tethered at unmanned plane) for a long time and carrying photoelectric nacelle
Outer video camera) high resolution video image acquisition was carried out to periphery atural object, building in whole day 24 hours；
2. being patrolled according to designed scan pattern and scanning speed control photoelectric nacelle and sweeping full monitoring region；
3. carrying out the modeling of panorama base map to neighboring buildings status image by panoramic mosaic technology, benchmark is detected as variation
Base map regard base map as detection benchmark and enforcement evidence library into information database with time, corresponding store of location information；
4. using change detection algorithm, the region of variation in image and label are found out by computer self, are shown in letter
It ceases on database work interface, the architecture against regulations is determine whether by staff；
5. region of variation pixel threshold can manually change setting and improve effective discovery rate；
6. the base map after discovery variation automatically updates, again image comparison benchmark of the modeling as next period；
7. the image pattern that constantly will determine as the architecture against regulations is added to AI learning database in the system operation, lead to
Depth learning technology is crossed, training AI image recognition algorithm is finally reached computational screening automatic identification and determines the architecture against regulations.
The invention has the characteristics that:
1. monitoring mode is in real time, efficiently
Using long-term in hollow panel the carryings video surveillance devices of aerostatics/be tethered at unmanned plane etc., pinpointed for a long time (due to pinpointing
Monitoring data are conducive to the modeling of base map benchmark model, but data are mostly strabismus data) whole day 24 hours, high frequency time monitoring periphery
Construction status (monitoring cycle is less than the artificial rush construction period at present) can efficiently find neighboring buildings state change.(compare unmanned plane
It is long, higher than the satellite monitoring frequency and image resolution ratio to continue to monitor the time, than unmanned plane, artificial inspection, satellite monitoring timeliness
It is good)
2. multi-data source merges
Data source not only includes airborne video monitoring data, has also merged ground shaft tower monitoring camera video data, people,
The operation behaviour video data of engineering truck, multi-data source comprehensive analysis processing realize the architecture against regulations all standing monitoring in region.
3. possessing building status image-time-position archives evidence library
By the corresponding storage of building state image information and time, location information, base map time file store is established, the bottom of as
Figure benchmark model provides evident information simultaneously for law enforcement agency；Image data base base map model real-time update according to the actual situation,
Guarantee the timeliness of image data；
4. automatically retrieval image change region, which mitigates, manually looks into figure workload
Base map and real-time construction status image carry out automatic variation by image comparison algorithm and detect, and complete construction status and become
The real-time monitoring of change works；
5. monitoring system intelligent
Manually it is determined as that the image of the architecture against regulations is added to architecture against regulations identification learning library, as AI deep learning sample,
System AI is constantly trained, it is final to realize that automatic identification determines architecture against regulations function.
In the present invention:
Selection is tethered at 500 meters of ship height；Load 80kg；Wind loading rating: anti-strong gale.
O-E Payload type selecting:
As shown in figure 4, change detection techniques route process of the present invention is generally summarized as following 3 step:
(1) it pre-processes: carrying out the registration and radiant correction of data by pre-treatment step, weaken strabismus, be tethered at ship shaking
It influences to simplify variation test problems Deng extraneous imaging circumstances.
(2) variation detection: it is strong to extract variation for the spectrum of atural object, space, Texture eigenvalue difference in analysis multi-temporal data
The information such as degree or change type.
(3) precision evaluation: the precision of variation testing result comprehensively, is accurately evaluated.
The neural network of depth learning technology includes that a large amount of unknown parameter is learnt, therefore largely has multiplicity
Property distribution sample be that training can succeed convergent premise.The present invention trains neural network by the way of supervised learning.
Usual training sample set will at least reach 2000~3000 or so magnitude, and trained model is just effective.
A. sample training
In training process, in conjunction with historical data, all pixels for being included by handmarking's target.Meanwhile further
It is extended for the obtained sample of label, including rotating, translating, simulating different degrees of exposure into row stochastic to sample image
Light and a degree of affine transformation of progress, so that the scale of enlarged sample, is conducive to the stability being trained.
B. recognizer
The present invention carries out the target of remote sensing images using the newest identification framework based on encoding and decoding deep neural network
Identification can make full use of the image information of different scale to carry out classification and feature extraction, improve the precision of identification.
C. behavioural analysis
Means are interpreted by visual observation, are collected in typical squatter building action process, typical building, builder's temporary shed and mound etc. are fixedly
The changing rule of the mobile atural object such as object and oversize vehicle, aggregation crowd, night pedestrian, constructs target dynamic variation model, uses
Doubtful squatter building behavior is obtained in analysis.
On the basis of being detected, being classified and being tracked to target, the behavior understanding of higher level pedestrian can be carried out
And description, to analyze specific behavior type.Behavior understanding and analysis are the analysis and identification by the behavior pattern to people, are obtained
The relevant description of the behaviors such as movement, state, event out assists the behavior it is found that abnormal, to make intelligent decision.It is involved
And high-rise motion-visual analysis be mainly the loading of engineering truck, unloading, repeat dealing etc., personnel's unusual checking, such as
The abnormal behaviour phenomenon of phenomena such as personnel area is hovered, personnel's night concentrates and crowd, such as abnormal poly- scattered, speed cataclysm are lived
Dynamic and event.
After target identification center finds target, in order to determine the geographical location of suspicious object, need to carry out target
It is accurately positioned, conventional location technology is to come in such a way that GPS/ Beidou directly positions since this system adopts remote sensing techniques
Monitoring objective is not suitable for conventional direct location mode, and therefore, present invention introduces aerial survey location technologies to ask to solve this
Topic.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than limitation, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, within these are all belonged to the scope of protection of the present invention.
Claims (5)
1. a kind of intelligent monitoring method based on the long-term real-time architecture against regulations in hollow panel, which is characterized in that including following step
It is rapid:
Step 1, the long-term photoelectric nacelle of carrying in hollow panel is to certain height；
Step 2, photoelectric nacelle is by scanning angle, scan period, the setting value for scanning stepping rate, periodically automatically to periphery
Atural object carries out region-wide Image Acquisition；
Step 3, by the storage of photoelectric nacelle acquired image data into information database；Wherein, image data is in Information Number
According to the storage mode in library are as follows: building state, acquisition time, location information correspond storage；
Step 4, information database carries out data processing to image data, to find Architectural drawing region of variation, by Architectural drawing
Region of variation pushes to supervising platform；
Step 5, artificial according to the Architectural drawing region of variation information received judgement pair in the human-computer interaction interface of supervising platform
Whether the building answered is the architecture against regulations, if then going to step 6, if otherwise repeating step 2 ~ 5；
Step 6, architecture against regulations position and corresponding image information are pushed to law enfrocement official's terminal by supervising platform；It will break rules and regulations simultaneously
Architecture information is stored in architecture against regulations sample database；Repeat step 2 ~ 6；
Step 7, when sample data reaches setting value in architecture against regulations sample database, the instruction to artificial intelligence recognizer is completed
Practice；Step 1 ~ 6 are repeated, and in steps of 5, is judged using artificial intelligence approach according to the Architectural drawing region of variation information received
Whether corresponding building is the architecture against regulations.
2. the intelligent monitoring method of the long-term real-time architecture against regulations in hollow panel as described in claim 1, which is characterized in that
In step 2 further include: lay ground monitoring equipment on the shaft tower of monitoring blind area ground in the sky；
It further include storing ground monitoring equipment acquired image data into information database in the step 3.
3. the intelligent monitoring method of the long-term real-time architecture against regulations in hollow panel as claimed in claim 1 or 2, feature exist
In, further includes:
Step 8, according to law enforcement information, law enfrocement official obtains evidence and enforces the law from law enfrocement official's terminal, and returns and feed back to supervision
Platform.
4. a kind of intelligent monitor system based on the long-term real-time architecture against regulations in hollow panel characterized by comprising
Hollow panel is stayed for a long time: for carrying photoelectric nacelle to certain height；
Photoelectric nacelle: for pressing scanning angle, scan period, the setting value for scanning stepping rate, periodically automatically to periphery
Atural object carries out region-wide Image Acquisition；
Information database: for receiving, storing and handle photoelectric nacelle acquired image data, wherein image data is being believed
Cease the storage mode in database are as follows: building state, acquisition time, location information correspond storage；And for finding
When to Architectural drawing region of variation, Architectural drawing region of variation is pushed into supervising platform；
Supervising platform: for receiving the Architectural drawing region of variation information of information database transmission and whether judging corresponding building
For the architecture against regulations, and architecture against regulations position and corresponding image information are pushed into law enforcement when corresponding building is the architecture against regulations
Staff terminal；Architecture against regulations information is stored in architecture against regulations sample database simultaneously；For the sample data in architecture against regulations sample database
When reaching setting value, the training to artificial intelligence recognizer is completed.
5. the intelligent monitor system as claimed in claim 4 based on the long-term real-time architecture against regulations in hollow panel, feature exist
In, further includes:
Ground monitoring equipment: for acquiring the image information of photoelectric nacelle blind area and being sent to information database；
Information database is also used to receive, store and handles ground monitoring equipment acquired image data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811619560.XA CN109711348A (en) | 2018-12-28 | 2018-12-28 | Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811619560.XA CN109711348A (en) | 2018-12-28 | 2018-12-28 | Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109711348A true CN109711348A (en) | 2019-05-03 |
Family
ID=66257906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811619560.XA Pending CN109711348A (en) | 2018-12-28 | 2018-12-28 | Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711348A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288262A (en) * | 2019-07-03 | 2019-09-27 | 韶关市创驰科技技术发展有限公司 | A kind of task delivery system based on GPS image |
| CN110765900A (en) * | 2019-10-10 | 2020-02-07 | 安徽磐众信息科技有限公司 | DSSD-based automatic illegal building detection method and system |
| CN110855952A (en) * | 2019-12-04 | 2020-02-28 | 中国特种飞行器研究所 | Remote image monitoring system and method for small and medium-sized unmanned airship |
| CN111369495A (en) * | 2020-02-17 | 2020-07-03 | 珀乐(北京)信息科技有限公司 | Video-based panoramic image change detection method |
| CN111523392A (en) * | 2020-03-26 | 2020-08-11 | 北京航天自动控制研究所 | Deep learning sample preparation method and recognition method based on satellite ortho-image full-attitude |
| CN112241659A (en) * | 2019-07-17 | 2021-01-19 | 杭州海康威视数字技术股份有限公司 | Detection device and detection method for illegal building and terminal equipment |
| CN112414374A (en) * | 2020-10-27 | 2021-02-26 | 江苏科博空间信息科技有限公司 | Illegal land surveying system based on unmanned aerial vehicle |
| CN115100536A (en) * | 2022-06-01 | 2022-09-23 | 中科星睿科技(北京)有限公司 | Building identification method, building identification device, electronic equipment and computer readable medium |
| CN115797775A (en) * | 2022-12-14 | 2023-03-14 | 中国铁塔股份有限公司重庆市分公司 | Intelligent illegal building identification method and system based on near-earth video image |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105513247A (en) * | 2015-11-25 | 2016-04-20 | 北京环境特性研究所 | Floating-mooring-airship-based fire monitoring and positioning system and method |
| WO2018045731A1 (en) * | 2016-09-07 | 2018-03-15 | 东南大学 | Expressway emergency lane occupation supervision and punishment method and system |
| CN207251817U (en) * | 2017-09-27 | 2018-04-17 | 湖南航天远望科技有限公司 | A kind of regional monitoring system |
| CN108009507A (en) * | 2017-12-08 | 2018-05-08 | 杨川 | Unmanned plane identifying system for the supervision of city illegal building |
| CN108052917A (en) * | 2017-12-25 | 2018-05-18 | 东南大学 | A kind of method of the architecture against regulations automatic identification found based on new and old Temporal variation |
| CN108052887A (en) * | 2017-12-07 | 2018-05-18 | 东南大学 | A kind of doubtful illegal land automatic recognition system and method for merging SLAM/GNSS information |
| CN207976923U (en) * | 2018-01-12 | 2018-10-16 | 东莞前沿技术研究院 | It is a kind of based on the three-dimensional modeling apparatus for being tethered at aerostatics |
-
2018
- 2018-12-28 CN CN201811619560.XA patent/CN109711348A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105513247A (en) * | 2015-11-25 | 2016-04-20 | 北京环境特性研究所 | Floating-mooring-airship-based fire monitoring and positioning system and method |
| WO2018045731A1 (en) * | 2016-09-07 | 2018-03-15 | 东南大学 | Expressway emergency lane occupation supervision and punishment method and system |
| CN207251817U (en) * | 2017-09-27 | 2018-04-17 | 湖南航天远望科技有限公司 | A kind of regional monitoring system |
| CN108052887A (en) * | 2017-12-07 | 2018-05-18 | 东南大学 | A kind of doubtful illegal land automatic recognition system and method for merging SLAM/GNSS information |
| CN108009507A (en) * | 2017-12-08 | 2018-05-08 | 杨川 | Unmanned plane identifying system for the supervision of city illegal building |
| CN108052917A (en) * | 2017-12-25 | 2018-05-18 | 东南大学 | A kind of method of the architecture against regulations automatic identification found based on new and old Temporal variation |
| CN207976923U (en) * | 2018-01-12 | 2018-10-16 | 东莞前沿技术研究院 | It is a kind of based on the three-dimensional modeling apparatus for being tethered at aerostatics |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288262A (en) * | 2019-07-03 | 2019-09-27 | 韶关市创驰科技技术发展有限公司 | A kind of task delivery system based on GPS image |
| CN112241659B (en) * | 2019-07-17 | 2024-05-17 | 杭州海康威视数字技术股份有限公司 | Detection device and detection method for illegal building and terminal equipment |
| CN112241659A (en) * | 2019-07-17 | 2021-01-19 | 杭州海康威视数字技术股份有限公司 | Detection device and detection method for illegal building and terminal equipment |
| CN110765900A (en) * | 2019-10-10 | 2020-02-07 | 安徽磐众信息科技有限公司 | DSSD-based automatic illegal building detection method and system |
| CN110765900B (en) * | 2019-10-10 | 2023-09-05 | 安徽磐众信息科技有限公司 | Automatic detection illegal building method and system based on DSSD |
| CN110855952A (en) * | 2019-12-04 | 2020-02-28 | 中国特种飞行器研究所 | Remote image monitoring system and method for small and medium-sized unmanned airship |
| CN111369495A (en) * | 2020-02-17 | 2020-07-03 | 珀乐(北京)信息科技有限公司 | Video-based panoramic image change detection method |
| CN111369495B (en) * | 2020-02-17 | 2024-02-02 | 珀乐(北京)信息科技有限公司 | Panoramic image change detection method based on video |
| CN111523392B (en) * | 2020-03-26 | 2023-06-06 | 北京航天自动控制研究所 | Deep learning sample preparation method and recognition method based on satellite orthographic image full gesture |
| CN111523392A (en) * | 2020-03-26 | 2020-08-11 | 北京航天自动控制研究所 | Deep learning sample preparation method and recognition method based on satellite ortho-image full-attitude |
| CN112414374A (en) * | 2020-10-27 | 2021-02-26 | 江苏科博空间信息科技有限公司 | Illegal land surveying system based on unmanned aerial vehicle |
| CN115100536A (en) * | 2022-06-01 | 2022-09-23 | 中科星睿科技(北京)有限公司 | Building identification method, building identification device, electronic equipment and computer readable medium |
| CN115797775A (en) * | 2022-12-14 | 2023-03-14 | 中国铁塔股份有限公司重庆市分公司 | Intelligent illegal building identification method and system based on near-earth video image |
| CN115797775B (en) * | 2022-12-14 | 2024-04-26 | 中国铁塔股份有限公司重庆市分公司 | Intelligent illegal building identification method and system based on near-to-ground video image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711348A (en) | Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel | |
| CN112422783B (en) | Unmanned aerial vehicle intelligent patrol system based on parking apron cluster | |
| CN108037770B (en) | Unmanned aerial vehicle power transmission line inspection system and method based on artificial intelligence | |
| CN111241959B (en) | Method for detecting personnel not wearing safety helmet through construction site video stream | |
| CN101872526B (en) | Smoke and fire intelligent identification method based on programmable photographing technology | |
| CN108710126A (en) | Automation detection expulsion goal approach and its system | |
| CN113240688A (en) | Integrated flood disaster accurate monitoring and early warning method | |
| CN114419825B (en) | High-speed rail perimeter intrusion monitoring device and method based on millimeter wave radar and camera | |
| CN111191586A (en) | Method and system for inspecting wearing condition of safety helmet of personnel in construction site | |
| CN113903081A (en) | Visual identification artificial intelligence alarm method and device for images of hydraulic power plant | |
| CN114240868A (en) | Unmanned aerial vehicle-based inspection analysis system and method | |
| CN109255286A (en) | A kind of quick detection recognition method of unmanned plane optics based on YOLO deep learning network frame | |
| CN113240249B (en) | Urban engineering quality intelligent evaluation method and system based on unmanned aerial vehicle augmented reality | |
| CN108688805A (en) | The unmanned plane detected safely applied to restricted clearance | |
| CN110163184A (en) | Intelligent video monitoring system and method | |
| CN110209196A (en) | A kind of unmanned plane garden night watching method and system | |
| CN116846059A (en) | Edge detection system for power grid inspection and monitoring | |
| CN112434828A (en) | Intelligent identification method for safety protection in 5T operation and maintenance | |
| CN112434827A (en) | Safety protection identification unit in 5T fortune dimension | |
| CN116993665A (en) | Intelligent detection method for construction progress of construction engineering working face based on computer vision | |
| Fiorillo et al. | Automated Mapping of the roof damage in historic buildings in seismic areas with UAV photogrammetry | |
| CN112785564A (en) | Pedestrian detection tracking system and method based on mechanical arm | |
| CN109902647B (en) | Portable online bird nest intelligent identification method and system | |
| CN208544425U (en) | The unmanned plane detected safely applied to restricted clearance | |
| CN114663818B (en) | Airport operation core area monitoring and early warning system and method based on vision self-supervision learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190503 |