CN112750060A - Intelligent community standardization platform - Google Patents
Intelligent community standardization platform Download PDFInfo
- Publication number
- CN112750060A CN112750060A CN202110019397.9A CN202110019397A CN112750060A CN 112750060 A CN112750060 A CN 112750060A CN 202110019397 A CN202110019397 A CN 202110019397A CN 112750060 A CN112750060 A CN 112750060A
- Authority
- CN
- China
- Prior art keywords
- community
- range
- house
- room
- smart
- 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
- 238000010586 diagram Methods 0.000 claims abstract description 22
- 238000012544 monitoring process Methods 0.000 claims abstract description 9
- 230000014509 gene expression Effects 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 7
- 230000006855 networking Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000006116 polymerization reaction Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000009434 installation Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims 2
- 230000004931 aggregating effect Effects 0.000 claims 1
- 230000002776 aggregation Effects 0.000 claims 1
- 238000004220 aggregation Methods 0.000 claims 1
- 230000008859 change Effects 0.000 claims 1
- 238000004891 communication Methods 0.000 claims 1
- 238000010276 construction Methods 0.000 claims 1
- 238000009987 spinning Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 6
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000280 densification Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012856 packing 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G06T3/06—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/169—Holistic features and representations, i.e. based on the facial image taken as a whole
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/80—Homes; Buildings
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/40—Information sensed or collected by the things relating to personal data, e.g. biometric data, records or preferences
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Abstract
The invention discloses a smart community standardization platform which comprises a plurality of Internet of things sensors, a community management server, a cloud computing system and a smart community holographic large screen, wherein the Internet of things sensors, the community management server and the smart community holographic large screen are respectively in data connection with the cloud computing system. According to the intelligent community, various intelligent technologies and modes are utilized, only the data set of the house data in the intelligent community range is used as input, the volume elements of the data set of the house data in the intelligent community range are converted into the two-dimensional images of the house in the intelligent community range, the multi-scale characteristic diagram of the top view of the house in the intelligent community range is obtained, cross-layer cross combination is carried out, on the premise that the monitoring speed is guaranteed, the abundant context data of the multi-scale characteristic diagram are fully utilized, and errors caused by background points and noise points are reduced.
Description
Technical Field
The invention relates to an intelligent community standardization platform.
Background
The intelligent community integrates various existing service resources of the community by utilizing various intelligent technologies and modes, and provides multiple convenient services such as government affairs, commerce, entertainment, education, medical care, life mutual assistance and the like for the community. From the application direction, wisdom community should realize improving the efficiency of handling affairs with wisdom government affairs, improve people's life with wisdom citizen, make intelligent life with wisdom family, promote the target of community quality with wisdom district, wisdom community can lay thing networking sensor in its spatial domain, so that the platform can monitor inside security state and the building state of community spatial domain, make things convenient for the management of community, utilize the discernment detection of current country's native resource monitoring video to building itself among the prior art, to the community break away the unable detection that this kind of disguise is stronger, accuracy and convenience are not enough.
Disclosure of Invention
The invention aims to overcome the defects and provide an intelligent community standardization platform.
The invention provides a smart community standardization platform which comprises a plurality of internet of things sensors, a community management server, a cloud computing system and a smart community holographic large screen, wherein the internet of things sensors, the community management server and the smart community holographic large screen are respectively in data connection with the cloud computing system, the internet of things sensors collect house data sets in a smart community range and send the house data sets to the cloud computing system, the cloud computing system cuts three-dimensional spaces of the house data sets in the smart community range, house data sets in the smart community range in the preset range are left, three-dimensional spaces of houses in the smart community range are removed, then comparison and identification are carried out, and the community management server counts, compares, identifies illegal management information and puts the management information into the smart community holographic large screen for early warning.
The invention uses various intelligent technologies and modes to only use the data of the data set of the house points in the intelligent community range as input, converts the volume elements of the data set of the house points in the intelligent community range into the two-dimensional image of the house in the intelligent community range which is convenient to process, acquires the multi-scale characteristic diagram of the top view of the house in the intelligent community range, and carries out cross-layer combination, fully utilizes the rich context data of the multi-scale characteristic diagram on the premise of ensuring the monitoring speed, reduces the error caused by background points and noise points, realizes the accurate monitoring of the house in the multi-size intelligent community range, divides the model into two steps for extracting the multi-scale characteristic diagram for obtaining the context data and monitoring the house in the intelligent community range with different sizes, carries out thinning and cross combination on the multi-scale characteristic diagram, and realizes the clear regression of the three-dimensional boundary of the house in the three-dimensional intelligent community range, the three-dimensional target monitoring and target monitoring tasks are remarkably improved.
Detailed Description
The present invention is further illustrated by the following examples.
Example (b):
the invention provides a smart community standardization platform which comprises a plurality of Internet of things sensors, a community management server, a cloud computing system and a smart community holographic large screen, wherein the Internet of things sensors, the community management server and the smart community holographic large screen are respectively in data connection with the cloud computing system, characterized in that the sensor of the Internet of things collects the data set of the house data in the smart community range and sends the data set to the cloud computing system, the cloud computing system cuts the three-dimensional space of the house point data set in the preset intelligent community range, leaves the house point data set in the intelligent community range in the preset range, removes the three-dimensional space of the house in the intelligent community range, and then, comparing and identifying, and counting, comparing and identifying illegal management information by the community management server and putting the illegal management information to the intelligent community holographic large screen for early warning.
And dividing the cut three-dimensional space of the intelligent community in-range room point data set into equal intelligent community in-range room volume elements, and dividing the intelligent community in-range room point data of each space into the intelligent community in-range room volume elements.
Snatch the wisdom community within range room data set that contains in the room volume element of every wisdom community within range, to the wisdom community within range room volume element that quantity is greater than S, pick S point from it wantonly, carry out 0 packing to the wisdom community within range room volume element that quantity is less than S, accomplish the back of snatching to the wisdom community within range room volume element in every wisdom community within range room data set, use average multilayer voxel feature coding as wisdom community within range room volume element feature encoder to every wisdom community within range room volume element, average the data of the S point in every non-empty wisdom community within range room volume element, then regard as the wisdom community within range room volume element' S of this wisdom after averaging characteristic.
The method comprises the steps of processing volume element features obtained by house volume elements in a smart community range through multilayer voxel feature coding as input, firstly converting the house volume element features in the smart community range into a house four-dimensional tensor in the smart community range through a sparse convolution tensor layer, grabbing the four-dimensional tensor through a preset sparse convolution layer and a sub-manifold convolution, carrying out densification processing on the house four-dimensional tensor in the smart community range after grabbing, further reducing the space height by using a sparse convolution layer with the number of channels as a base number after densifying sparse three-dimensional data, and rearranging the sparse convolution layer into a two-dimensional pseudo-top view of the house in the smart community range.
For the obtained two-dimensional pseudo top plan view of the house in the smart community range, a first rotation product is used to obtain a first two-dimensional pseudo top plan view of the house in the smart community range, a second rotation product operation is used to obtain a second two-dimensional pseudo top plan view of the house in the smart community range, the second two-dimensional pseudo top plan view of the house in the smart community range is half of the size of the house in the smart community range, a third rotation product operation is used to obtain a third two-dimensional pseudo top plan view of the house in the smart community range, a reverse rotation product operation is respectively used to obtain three outputs which are the same as the size of the two-dimensional pseudo top plan view of the house in the smart community range, the three outputs are obtained and combined to output the house feature map in the smart community range after polymerization splicing, respectively using two convolution kernels to carry out maximum pooling operation on the house characteristic diagram in the first smart community range, respectively and correspondingly obtaining a new house characteristic diagram in the smart community range with half size of the two-dimensional pseudo top plan of the house in the smart community range and one fourth size of the two-dimensional pseudo top plan of the house in the smart community range, respectively carrying out inverse convolution operation and maximum pooling operation on the house characteristic diagram in the second smart community range, respectively and correspondingly obtaining a new house characteristic diagram in the smart community range with the same size as the two-dimensional pseudo top plan of the house in the smart community range and one fourth size of the two-dimensional pseudo top plan of the house in the smart community range, finally respectively using two preset convolution products on the house characteristic diagram in the third smart community range to carry out operation, respectively and correspondingly obtaining a new house characteristic diagram in the smart community range with the same size as the two-dimensional pseudo top plan of the house in the smart community range and one half size of the two-dimensional pseudo top plan of the house in the smart community range, to room characteristic map in the first wisdom community scope, room characteristic map in the second wisdom community scope and room characteristic map in the third wisdom community scope and six wisdom community within range room characteristic maps of new generation, room characteristic map in the wisdom community scope with the same size carries out polymerization concatenation, make it combine to obtain new and wisdom community within range room two-dimensional pseudo-top plan size the same, the wisdom community within range room two-dimensional pseudo-top plan half size and the wisdom community within range room two-dimensional pseudo-top plan quarter size wisdom community within range room characteristic map, reuse layer carries out the operation of reducing the dimension to these three new wisdom community within range room characteristic maps respectively, after reducing the dimension with wisdom community within range room two-dimensional pseudo-top plan size the same, the wisdom community within range room two-dimensional pseudo-top plan half size and the wisdom community within range room two-dimensional pseudo-top plan quarter size within range room The house characteristic diagram is processed by using three convolution products respectively to obtain high-level characteristic expressions of the house in three smart community ranges, the three high-level characteristic expressions of the house in the smart community ranges are changed into the characteristic diagram of the house in the smart community ranges, the characteristic diagram of the house in the smart community ranges is the same as the two-dimensional pseudo top view of the house in the smart community ranges, the characteristic diagram of the house in the smart community ranges is output, element-by-element superposition is carried out on the characteristic diagram of the house in the smart community ranges, the result of the result is aggregated and spliced to serve as a new output characteristic diagram of the house in the smart community ranges, and the obtained new output characteristic diagram of the house in the smart community ranges is operated by using three convolution products respectively to obtain the three-dimensional profile of the house in the smart community ranges.
And comparing and identifying the three-dimensional outline of the house in the intelligent community range with the preset three-dimensional outline of the house.
Clicking a plurality of internet of things sensor distribution icons of the holographic large screen of the intelligent community, and displaying related information content of the similar equipment: the current equipment is provided with the same equipment number, equipment name, equipment state, whether online and installation address and other contents.
The sensor of the internet of things can collect face images of people, and the cloud computing system can compare people passing conditions every day in the near term, people passing conditions in each time period of the day, accumulated passing data, caring people passing conditions, paying attention to people passing conditions and blacklist passing conditions.
After the crowd face image is collected, carrying out high-resolution processing on the collected crowd face image, and specifically, creating a crowd face image data set, wherein the human face image data set comprises a plurality of paired data of the crowd face images, namely the high-resolution crowd face image and the corresponding low-resolution crowd face image; cutting the human face image pair of the crowd in the human face image data set to obtain a human face image cut block of the crowd;
inputting the obtained crowd face image cutouts into a neural network of the crowd face image with a convolution filter in batches, wherein the neural network of the crowd face image with the convolution filter comprises a crowd face image global memory neural network and a crowd face image local enhancement neural network, namely respectively inputting the crowd face image cutouts into the crowd face image global memory neural network and the crowd face image local enhancement neural network for feature acquisition; in a crowd face image global memory neural network, converting low-resolution crowd face image cutouts from a crowd face image space to a crowd face feature space by utilizing initialized rotation product to obtain original crowd face features, extracting the crowd face features through a plurality of dense residual blocks, gathering the outputs of different residual blocks, modeling the mutual conversion relation between different stages and a space region through a recursion block, and learning the crowd face contour global features from the original crowd face features;
in the local enhancement neural network of the crowd face image, acquiring an input image by a crowd face image acquirer with a set size to obtain a plurality of low-resolution crowd face image cutouts, and in order to obtain proper crowd face image cutouts and keep a certain local structure, performing non-repeated acquisition on the input image by using the crowd face image acquirer with the original input size of 1/m to obtain m low-resolution crowd face image cutouts; in order to strengthen modeling of local feature association, a plurality of multi-line residual errors are used for extracting local human face features of a crowd face, and conversion relations between local cutouts of crowd face images from low-resolution crowd faces to high-resolution crowd faces are learned by combining human face feature information of different lines and stages to obtain feature expressions based on the local cutouts of the crowd face;
inputting the obtained feature expressions of the local cut blocks of the human faces of the crowds into an upper acquisition layer, compiling and rearranging the feature expressions of the local cut blocks of the human faces of the crowds by utilizing sub-pixel convolution, and converting the feature expressions into a global human face space of the crowds to obtain a feature conversion image with the resolution of the original input human face, namely the local features of the whole human faces of the crowds; combining the obtained global features of the human face outline of the crowd and the local features of the whole human face of the crowd by using a plurality of convolution products, inputting the combined features into an upper acquisition layer, performing super-resolution reconstruction by using sub-pixel convolution products, realizing global and local combined expression of the human face features, converting the human face features into an original human face image space of the crowd, outputting a corresponding human residual human face image, superposing the regressed human residual human face image and interpolation data of the human face image of the crowd with low resolution, and outputting to obtain a clear human face image; the method comprises the steps of optimizing a two-line depth combination network of a proposed crowd face image by minimizing cosine similarity of a clear crowd face image obtained by output and an original high-resolution crowd face, and realizing conversion of a low-resolution crowd face image into a high-resolution crowd face image; the optimization specifically comprises the following steps: the clear crowd face image generated by the network is controlled to be as close to the original high-resolution crowd face image as possible based on the super-resolution loss function, and optimization of a method for converting the low-resolution crowd face image combined with the double-line depth into the high-resolution crowd face image is achieved.
The long-range dependence of the global human face features of the human faces of the crowd is jointly learned by adopting a cyclic convolution and residual dense network, so that the modeling of the global contour of the human faces of the crowd is assisted; meanwhile, the additionally arranged local enhancement neural network of the human face image of the crowd learns the conversion relation between the local cut block of the human face of the crowd with low resolution and the local cut block of the human face of the crowd with high resolution, and is used for enhancing the modeling of the local human face characteristics of the crowd, particularly the facial features; moreover, by combining the global feature of the human face profile of the crowd and the local feature of the whole human face of the crowd, the combined representation of the global and local human face features can be realized, and a clear human face image of the crowd is obtained; finally, through the combined expression of the global and local human face features, the global and local features can be effectively obtained and combined, so that the modeling of the human face features is more accurate, and the conversion effect is better.
The internet of things sensor can collect vehicle information, and the cloud computing system can compare the vehicle passing conditions of vehicles every day in the near future, the vehicle passing conditions of vehicles at all time periods on the day, the accumulated passing conditions and blacklist vehicle early warning.
The sensor of the internet of things can collect community alarm information, and community alarm analysis is divided into related contents such as equipment alarm, personnel and vehicle control alarm and the like.
Claims (10)
1. The utility model provides a standardized platform of wisdom community, includes a plurality of thing networking sensors, community management server, cloud computing system and the holographic big screen of wisdom community, and a plurality of thing networking sensors, community management server and the holographic big screen of wisdom community establish data connection with cloud computing system respectively, a serial communication port, thing networking sensors gathers the data set of wisdom community within range room point and sends to cloud computing system, cloud computing system cuts the three-dimensional space of wisdom community within range room point data set of predetermineeing, leaves the wisdom community within range room point data set of predetermineeing, gets rid of the three-dimensional space that does not contain wisdom community within range house, then compares the discernment, the management server statistics is compared and is discerned out the management information of violating the construction and put in to the holographic big screen of wisdom community and early warning.
2. The intelligent community standardization platform of claim 1 wherein the clipped intelligent community in-range room data sets are partitioned into equal intelligent community in-range room volume elements in three dimensions, and the intelligent community in-range room data for each space is partitioned into each intelligent community in-range room volume element.
3. The intelligent community standardization platform of claim 2 wherein intelligent community-wide room point data sets contained in each intelligent community-wide room volume element are captured, for the volume elements of the house in the intelligent community range with the number larger than S, S points are arbitrarily picked from the volume elements, 0 filling is carried out on the intelligent community-range house volume elements with the quantity less than S, after the capture of the intelligent community-range house point data sets in the house volume elements in each intelligent community range is completed, and averaging the data of S points in the room volume elements in each non-empty smart community range, and then taking the averaged data as the characteristics of the room volume elements in the smart community range.
4. The intelligent community standardization platform of claim 3, wherein a plurality of layers of voxel feature codes are used as input to process volume element features of the intelligent community within the range of the house, a sparse convolution tensor layer is used to convert the volume element features of the intelligent community within the range of the house into a four-dimensional tensor of the house within the range of the intelligent community, the four-dimensional tensor is captured eight times by a preset sparse convolution layer and a sub-manifold convolution, the four-dimensional tensor of the house within the range of the intelligent community after the capture is dense and thick, after the sparse three-dimensional data is dense, the sparse convolution layer is used to further reduce the space height by using the number of channels as a radix, and then the sparse convolution layer is rearranged into a two-dimensional pseudo top view of the house within the range of the intelligent community.
5. The standardized platform of claim 4 wherein the two-dimensional pseudo top view of the house within the smart community is obtained by using a first convolution to obtain a first characteristic diagram of the house within the smart community that is the same size as the two-dimensional pseudo top view of the house within the smart community, using a second convolution operation to obtain a second characteristic diagram of the house within the smart community that is a half size of the two-dimensional pseudo top view of the house within the smart community, using a third convolution operation to obtain a third characteristic diagram of the house within the smart community that is a quarter size of the two-dimensional pseudo top view of the house within the smart community, and using a reverse convolution operation to obtain three outputs that are the same size as the two-dimensional pseudo top view of the house within the smart community, carry out polymerization concatenation to it and handle and output wisdom community within range room characteristic map after combining, use two respectively to revolve the product kernel and carry out the operation of maxmizing to room characteristic map in the first wisdom community range, correspond respectively and obtain the false half size of two-dimentional top view of room in the wisdom community range and the false within range room two-dimentional top view quarter size of new wisdom community within range room characteristic map of wisdom community, carry out derotation product operation and maximum pool operation respectively to room characteristic map in the second wisdom community range, correspond respectively and obtain the false within range room characteristic map of room two-dimentional top view the same with the false within range room two-dimentional top view size of wisdom community and the false within range room two-dimentional top view quarter size of wisdom community, use the derotation product of two preset step steps respectively to room characteristic map in the third wisdom community range to operate, correspond respectively and obtain the false within range room size of room two-dimentional top view the same with the wisdom community wis The method comprises the steps of carrying out aggregation splicing on smart community in-range house characteristic graphs with the same size to a new smart community in-range house characteristic graph with the half size of a two-dimensional pseudo top view of a house, a second smart community in-range house characteristic graph, a third smart community in-range house characteristic graph and newly generated six smart community in-range house characteristic graphs, combining the smart community in-range house characteristic graphs with the same size to obtain a new smart community in-range house two-dimensional pseudo top view with the same size as the smart community in-range house two-dimensional pseudo top view, the half size of the smart community in-range house two-dimensional pseudo top view and the quarter size of the smart community in-range house two-dimensional pseudo top view, then respectively carrying out dimensionality reduction operation on the three new smart community in-range house characteristic graphs by using a spinning layer, and carrying out dimensionality reduction operation on the new smart community in-range house characteristic graphs with the same size as the smart community, The method comprises the steps of respectively processing a half size of a two-dimensional pseudo top view of a room in a smart community range and a quarter size of a two-dimensional pseudo top view of the room in the smart community range by using three convolution to obtain three high-level feature expressions of the room in the smart community range, respectively using three inverse convolution with preset step length to change the three high-level feature expressions of the room in the smart community range into a feature view of the room in the smart community range with the same size as the two-dimensional pseudo top view of the room in the smart community range, overlapping the feature views of the room in the smart community range with the output feature view of the room in the smart community one by one, respectively using one convolution operation, aggregating and splicing results to serve as a new output feature view of the room in the smart community range for monitoring, and obtaining a new output feature view of the room in the smart community range for monitoring, and respectively operating by using three convolution products to obtain the three-dimensional outline of the house in the intelligent community range.
6. The intelligent community standardization platform of claim 5, wherein the obtained three-dimensional profile of the house within the intelligent community is compared with a preset three-dimensional profile of the house for identification.
7. The standardized platform of smart community as claimed in claim 1 or 6, wherein the relevant information content of the same kind of equipment can be displayed by clicking the distributed icons of the plurality of internet of things sensors on the smart community holographic large screen: the current equipment is provided with the same equipment number, equipment name, equipment state, whether online and installation address and other contents.
8. The standardized platform for smart communities as claimed in claim 1 or 6, wherein the sensors of internet of things can collect human face information, and the cloud computing system can compare recent daily traffic conditions, traffic conditions of time periods of the day, accumulated traffic data, traffic conditions of caring people, traffic conditions of concerned people and blacklist traffic conditions.
9. The intelligent community standardization platform of claim 1 or 6, wherein the internet of things sensor can collect vehicle information, and the cloud computing system can compare recent daily vehicle passing conditions, vehicle passing conditions in each time period of the day, accumulated passing condition, and blacklist vehicle warning.
10. The intelligent community standardization platform of claim 1 or 6, wherein the internet of things sensor can collect community alarm information, and the community alarm analysis is divided into related contents such as equipment alarm, personnel and vehicle control alarm, and the like.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110019397.9A CN112750060B (en) | 2021-01-07 | 2021-01-07 | Intelligent community standardization platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110019397.9A CN112750060B (en) | 2021-01-07 | 2021-01-07 | Intelligent community standardization platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112750060A true CN112750060A (en) | 2021-05-04 |
| CN112750060B CN112750060B (en) | 2021-09-24 |
Family
ID=75650215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110019397.9A Active CN112750060B (en) | 2021-01-07 | 2021-01-07 | Intelligent community standardization platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112750060B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115147095A (en) * | 2022-09-02 | 2022-10-04 | 山东慧创信息科技有限公司 | Multistage linkage intelligent community open platform system for government affair information management |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170018045A1 (en) * | 2015-07-13 | 2017-01-19 | Geraldine Patricia Hunter | Quality community review (QCR) |
| CN110243354A (en) * | 2019-07-04 | 2019-09-17 | 桂林理工大学 | A kind of city illegal building object dynamic monitoring method and system |
| CN111105330A (en) * | 2019-10-24 | 2020-05-05 | 广脉科技股份有限公司 | Intelligent community management system based on one-stop management platform |
| CN112116502A (en) * | 2020-09-28 | 2020-12-22 | 松立控股集团股份有限公司 | Smart community security management system |
| CN112116503A (en) * | 2020-09-28 | 2020-12-22 | 松立控股集团股份有限公司 | Smart community cloud platform management system |
-
2021
- 2021-01-07 CN CN202110019397.9A patent/CN112750060B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170018045A1 (en) * | 2015-07-13 | 2017-01-19 | Geraldine Patricia Hunter | Quality community review (QCR) |
| CN110243354A (en) * | 2019-07-04 | 2019-09-17 | 桂林理工大学 | A kind of city illegal building object dynamic monitoring method and system |
| CN111105330A (en) * | 2019-10-24 | 2020-05-05 | 广脉科技股份有限公司 | Intelligent community management system based on one-stop management platform |
| CN112116502A (en) * | 2020-09-28 | 2020-12-22 | 松立控股集团股份有限公司 | Smart community security management system |
| CN112116503A (en) * | 2020-09-28 | 2020-12-22 | 松立控股集团股份有限公司 | Smart community cloud platform management system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115147095A (en) * | 2022-09-02 | 2022-10-04 | 山东慧创信息科技有限公司 | Multistage linkage intelligent community open platform system for government affair information management |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112750060B (en) | 2021-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110619282B (en) | Automatic extraction method for unmanned aerial vehicle orthoscopic image building | |
| CN112287940A (en) | Semantic segmentation method of attention mechanism based on deep learning | |
| CN108171701B (en) | Significance detection method based on U network and counterstudy | |
| CN110135319A (en) | A kind of anomaly detection method and its system | |
| CN111928888A (en) | Intelligent monitoring and analyzing method and system for water pollution | |
| CN104239420A (en) | Video fingerprinting-based video similarity matching method | |
| CN110942071A (en) | License plate recognition method based on license plate classification and LSTM | |
| CN112332981B (en) | Data processing method and device | |
| CN112926548A (en) | Lane line detection method and device, electronic equipment and storage medium | |
| CN112541459A (en) | Crowd counting method and system based on multi-scale perception attention network | |
| CN113989681A (en) | Remote sensing image change detection method and device, electronic equipment and storage medium | |
| CN116385902A (en) | Remote sensing big data processing method, system and cloud platform | |
| CN112750060B (en) | Intelligent community standardization platform | |
| CN116030036A (en) | Image difference detection method, model training method, system, equipment and medium | |
| CN115147545A (en) | Scene three-dimensional intelligent reconstruction system and method based on BIM and deep learning | |
| CN114972378A (en) | Brain tumor MRI image segmentation method based on mask attention mechanism | |
| Qiu et al. | Design and development of a web‐based interactive twin platform for watershed management | |
| CN114973057A (en) | Video image detection method based on artificial intelligence and related equipment | |
| CN108875555B (en) | Video interest area and salient object extracting and positioning system based on neural network | |
| CN111968073B (en) | No-reference image quality evaluation method based on texture information statistics | |
| Ouzounis et al. | Interactive collection of training samples from the max-tree structure | |
| CN112668662A (en) | Outdoor mountain forest environment target detection method based on improved YOLOv3 network | |
| CN115423982B (en) | Three-dimensional detection method for desktop curling based on images and depth | |
| CN115601684A (en) | Emergency early warning method and device, electronic equipment and storage medium | |
| CN115690488A (en) | Image identification method and device based on convolutional neural network model and terminal equipment |
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 |