CN109284706A - Hot spot grid agglomeration of industries area recognizing method based on Multi-sensor satellite remote sensing - Google Patents
Hot spot grid agglomeration of industries area recognizing method based on Multi-sensor satellite remote sensing Download PDFInfo
- Publication number
- CN109284706A CN109284706A CN201811059933.2A CN201811059933A CN109284706A CN 109284706 A CN109284706 A CN 109284706A CN 201811059933 A CN201811059933 A CN 201811059933A CN 109284706 A CN109284706 A CN 109284706A
- Authority
- CN
- China
- Prior art keywords
- subregion
- data
- remote sensing
- agglomeration
- monitoring
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002776 aggregation Effects 0.000 title claims abstract description 45
- 238000005054 agglomeration Methods 0.000 title claims abstract description 42
- 238000012544 monitoring process Methods 0.000 claims abstract description 53
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 18
- 231100000719 pollutant Toxicity 0.000 claims abstract description 18
- 241001269238 Data Species 0.000 claims abstract description 6
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- 238000001228 spectrum Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 description 8
- 239000000284 extract Substances 0.000 description 5
- 238000011835 investigation Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of hot spot grid agglomeration of industries area recognizing method based on Multi-sensor satellite remote sensing, comprising: obtain the Multi-sensor satellite remote sensing in pollution monitoring region；Multi-sensor satellite remote sensing is divided into multiple subregion remotely-sensed datas；Potential industrial premises information is identified based on multidimensional region feature；Pollution monitoring region is divided into multiple first monitoring subregions and multiple second monitoring subregions according to predetermined manner；Potential industrial premises concentration class, industry POI concentration class and the pollutant concentration in each subregion are integrated, industrial enterprise's distributed data of each first monitoring subregion is obtained；Generate the agglomeration of industries degree characteristic information of each first monitoring subregion；Sample set is identified according to potential industrial premises aggregation characteristic, agglomeration of industries degree feature and pollutant concentration information structuring；Depth characteristic study is carried out using identification sample set, obtains identification model；The agglomeration of industries region in multiple second monitoring subregions is identified using identification model.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of hot spot grids based on Multi-sensor satellite remote sensing
Agglomeration of industries area recognizing method.
Background technique
Remote sensing images identification, which refers to, passes through the spectral information and space letter to atural objects all kinds of in remote sensing images using computer
Breath is analyzed, and feature is selected, and feature space is divided into the subspace not overlapped with certain means, then by image
In each pixel incorporate into the corresponding atural object classification of each sub-spaces and go.With the development of remote sensing technology, optics, thermal infrared and
The application of a large amount of different satellite sensor earth observations such as microwave, a variety of remote sensing image datas of the areal of acquisition are (when more
Phase, multispectral, multisensor, multi-platform and multiresolution) it is more and more, here it is multi-source remote sensings.With single source remote sensing image number
According to comparing, information provided by multi- source Remote Sensing Data data has redundancy, complementarity and cooperative.
2016, Chinese Ministry of Environmental Protection cooperated with science-and-technology enterprise, by Jing-jin-ji region and the city periphery key area " 2+26 " (2 fingers
Beijing and Tianjin, 26 refer to Shijiazhuang City, Hebei Province, Tangshan, Baoding, Langfang, Cangzhou, Hengshui, Handan, Xingtai, and Shanxi Province is too
Original, Yangquan, Changzhi, Jincheng, Jinan City, Shandong Province, Zibo, Liaocheng, Dezhou, Binzhou, Jining, Heze, Zhengzhou, Henan Province, Xinxiang, crane
26 wall, Anyang, Jiaozhuo, Puyang, Kaifeng cities) according to 3km × 3km grid division, amount to 36793.According to what is be divided into
Grid, encryption distribution air monitoring places.The higher grid cell of atmospheric pollution level is periodically filtered out by big data, is sent
To related local government and environmental protection administration, pushes and implement precisely law enforcement.
The pollution control emphasis in national 2+26 city has been put into the net of 36793 3km × 3km division by grid cell
On lattice, the step focusing to pollution is realized.But 3km × 3km is still not careful enough for micro, need into
One step orients the gridding agglomeration of industries region for needing emphasis to implement environmental protection supervision investigation, and therefore, it is necessary to one kind to be based on multi-source
The agglomeration of industries region recognition solution of remotely-sensed data.
Summary of the invention
It is a kind of based on Multi-sensor satellite remote sensing the purpose of the present invention is in view of the deficiencies in the prior art, providing
Hot spot grid agglomeration of industries area recognizing method.
To achieve the above object, in a first aspect, the present invention provides a kind of hot spot net based on Multi-sensor satellite remote sensing
Lattice agglomeration of industries area recognizing method, comprising:
Obtain the Multi-sensor satellite remote sensing in pollution monitoring region；
The Multi-sensor satellite remote sensing is divided into multiple subregion remotely-sensed datas；
The area characteristic information of the subregion remotely-sensed data is extracted, the area characteristic information includes textural characteristics, ash
Spend feature, shape feature, position feature；
Potential industrial premises Classification and Identification is carried out to the subregion remotely-sensed data according to the area characteristic information, is obtained
The potential industrial premises information of subregion calculates the potential industrial premises concentration class feature of subregion；
Every one kind subregion remotely-sensed data is layered, the remote sensing features of each sub-regions remotely-sensed data are extracted
Information；
The pollution monitoring region is divided into multiple first monitoring subregions and multiple second monitorings according to predetermined manner
Subregion；
Industrial enterprise's distributed data of each first monitoring subregion is obtained, industrial enterprise's distributed data includes
Industrial information point POI assembles data, pollutant data；
Assemble data according to the industry POI, pollutant data generate the industry that each described first monitors subregion and gather
Intensity characteristic information；
According to the potential industrial premises concentration class characteristic information in the domain and the agglomeration of industries degree characteristic information conformation identification
Sample set；
Depth characteristic study is carried out using the identification sample set, obtains identification model；
The agglomeration of industries region in the multiple second monitoring subregion is identified using the identification model.
Further, the Multi-sensor satellite remote sensing for obtaining pollution monitoring region specifically includes:
The polar orbiting meteorological satellite remotely-sensed data, static in the pollution monitoring region is extracted from Multi-sensor satellite remote sensing library
Remote sensing data, high-spectrum remote-sensing satellite data.
Further, after the Multi-sensor satellite remote sensing for obtaining pollution monitoring region, the method also includes:
The multi- source Remote Sensing Data data is pre-processed, the pretreatment includes geometric correction, information enhancement, smooth filter
Wave, information fusion.
Further, described that potential industrial premises is carried out to the subregion remotely-sensed data according to the area characteristic information
Classification and Identification obtains the potential industrial premises information of subregion and specifically includes:
The subregion remotely-sensed data is divided into multiple polygon image data according to the shape feature information；
The characteristic information of the polygon image data is extracted, and potential industrial premises point is carried out according to the characteristic information
Class identification.
Further, described that data, each first monitoring of pollutant data generation are assembled according to the industry POI
The agglomeration of industries degree characteristic information in region specifically includes:
Assemble the industrial POI concentration class that data calculate the first monitoring subregion according to the industry POI；
The pollutant concentration value of the first monitoring subregion within a preset period of time is calculated according to the pollutant data；
The industry POI concentration class and the pollutant concentration value are subjected to Spatial Overlap Analysis, it is poly- to generate the industry
Intensity characteristic information.
Further, described according to the potential industrial premises concentration class characteristic information in the domain and the agglomeration of industries degree feature
Information structuring identification sample set specifically includes:
Multiple fisrt feature parameters are extracted from the potential industrial premises concentration class characteristic information；
Multiple second feature parameters are extracted from the agglomeration of industries degree characteristic information；
Utilize the fisrt feature parameter, second feature parametric configuration multidimensional characteristic vectors；
Multiple multidimensional characteristic vectors are generated into the identification sample set.
Second aspect, the present invention provides a kind of equipment, including memory and processor, the memory is for storing journey
Sequence, the processor are used to execute the method in the various implementations of first aspect and first aspect.
The third aspect, the present invention provides a kind of computer program products comprising instruction, when the computer program produces
When product are run on computers, so that the computer executes the side in the various implementations of first aspect and first aspect
Method.
Fourth aspect, the present invention provides a kind of computer readable storage medium, on the computer readable storage medium
It is stored with computer program, the various realizations of first aspect and first aspect are realized when the computer program is executed by processor
Method in mode.
Hot spot grid agglomeration of industries area recognizing method provided by the invention based on Multi-sensor satellite remote sensing, by multi-source
Satellite remote sensing date and industrial enterprise's distributed data carry out data fusion, extract the potential industrial premises number of multi-source satellite remote sensing respectively
According to the characteristic information of, industrial enterprise's distributed data, conformation identification sample set carries out depth characteristic study using identification sample set,
Identification model is trained, identifies agglomeration of industries region using identification model.Method provided by the invention is based on multi-source satellite remote sensing
Data carry out agglomeration of industries region recognition, can precise positioning go out need emphasis implement environmental protection supervision investigation agglomeration of industries area
Domain improves the validity of pollution monitoring.
Detailed description of the invention
Fig. 1 is that the hot spot grid agglomeration of industries region based on Multi-sensor satellite remote sensing that the embodiment of the present invention one provides is known
Other method flow diagram；
Fig. 2 is the schematic diagram for being divided into grid cell for region is monitored that the embodiment of the present invention one provides.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that the described embodiments are only some of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
The technical scheme is that carrying out the identification of hot spot grid based on Multi-sensor satellite remote sensing, that is, for needs
The gridding agglomeration of industries region that emphasis implements environmental protection supervision investigation is identified, it is intended that improves the validity of pollution monitoring.
Fig. 1 is that the hot spot grid agglomeration of industries region based on Multi-sensor satellite remote sensing that the embodiment of the present invention one is related to is known
Other method flow diagram.As shown in Figure 1, specifically comprising the following steps:
Step 101, the Multi-sensor satellite remote sensing in pollution monitoring region is obtained.
Polar orbiting meteorological satellite remotely-sensed data, the static meteorology in pollution monitoring region are extracted from Multi-sensor satellite remote sensing library
Satellite remote sensing date, high-spectrum remote-sensing satellite data.
The image that polar orbiting meteorological satellite obtains includes: cloud, the system of cloud, cold and hot cutting edge of a knife or a sword, typhoon, lake, forest, mountain range, ice
The image data of snow, fire, smog, greasy dirt etc..Stationary weather satellite carries various meteorological remote sensing instruments, can receive and survey
Visible light, the infrared and microwave radiation of the earth and its atmosphere are measured, and is converted into electric signal and is transmitted to ground.Earth station
It stands and the electric signal recovery that satellite is sent is depicted as various cloud layers, earth's surface and ocean surface picture.High-spectrum remote-sensing satellite image data
Including the visible light of electromagnetic spectrum, near-infrared, within the scope of infrared and Thermal infrared bands, obtain many very narrow spectrum and connect
Continuous image data.
Before step 101, the corresponding Multi-sensor satellite remote sensing library in pollution monitoring region is pre-established.
After step 101, multi- source Remote Sensing Data data is pre-processed, pretreatment includes geometric correction, information enhancement, puts down
Sliding filtering, information fusion.Multi- source Remote Sensing Data data carries out to pretreated purpose is easy for subsequent progress image segmentation and feature mentions
It takes.
Wherein, geometric correction, which refers to through a series of mathematical model, corrects and eliminates when remote sensing image is imaged because of photography
It is each on original image caused by the factors such as material deformation, object lens distortion, Atmosphere Refraction, earth curvature, earth rotation, hypsography
The change that the features such as geometric position, shape, size, the orientation of atural object generate when requiring inconsistent with the expression in reference system
Shape.
Information enhancement refers to the processing for improving image visual effect.When analyzing remote sensing images, in order to enable analyst to hold
Easily definitely identify picture material, it is necessary to process according to analysis purpose to image data, it is therefore an objective to improve sentencing for image
The property read.Information enhancement includes gray scale exchange, colored synthesis etc..
The purpose of smothing filtering is to carry out denoising to image, specifically includes linear filtering and nonlinear filtering.Linearly
Filtering such as neighbor smoothing filters, and restores to the image degenerated by noise pollution.Nonlinear filter such as median filtering,
It can overcome problem of image blurring brought by linear filtering, while filtering out noise, preferably retain to a certain extent
The marginal information of image.
Information fusion refers to that the data obtained to different remote sensors merge, and can be divided into the spatial registration and image of image
Merge two steps.The spatial registration of image refers to the spatial registration to two width images, generally a wherein width is called referring to image, with
On the basis of it, another piece image is corrected.Visual fusion refers to intelligently to be selected to close according to fusion purpose and fusion PCR
The remote sensing image data of spatial registration is carried out organic synthesis, obtains the more acurrate expression or estimation of target by suitable blending algorithm.
Step 102, Multi-sensor satellite remote sensing is divided into multiple subregion remotely-sensed datas；
Since Multi-sensor satellite remote sensing size is larger, need to carry out just to can be carried out subsequent processing after image segmentation.Figure
As segmentation is the process that digital picture is divided into mutually disjoint region.
Multi-sensor satellite remote sensing is divided into the subregion remotely-sensed data of multiple units, specific dividing method includes being based on
The dividing method of threshold value, the dividing method based on region, the dividing method based on edge and the segmentation side based on specific theory
Method etc..
The multiple subregion remotely-sensed datas obtained after image segmentation are marked, and assign each subregion to unique area
Domain coding.Corresponding unique region can be inquired according to regional code.
Step 103, the area characteristic information of subregion remotely-sensed data is extracted；
Wherein, area characteristic information includes textural characteristics, gray feature, shape feature, position feature etc..Provincial characteristics letter
Breath is that the subregion is different from the corresponding feature of other subregions or the set of characteristic or these features and characteristic.Provincial characteristics
It is to be extracted by measuring or handling.Every piece image all has the unique characteristics that can be different from other class images, some
It is the physical feature that can be perceive intuitively that, such as brightness, edge, texture and color；Some then be need by transformation or
Processing is just getable, such as square, histogram and main composition.
Textural characteristics needs carry out statistics calculating in the region comprising multiple pixels.The extracting method packet of textural characteristics
Include statistical method, geometric method, modelling and signal processing method.
Gray feature includes gray average, gray scale intermediate value etc..Gray average refers to the average value of all pixels in region；Ash
Degree intermediate value refers to the sequence intermediate value of all pixels in region.
Shape feature includes contour feature and provincial characteristics.Contour feature uses the outer boundary of object, provincial characteristics relationship
To entire shape area.The extracting method of shape feature includes boundary characteristic method, Fourier's shape description symbols method, geometry parameter method
Deng.
Position feature refers to that mutual spatial position or relative direction between the multiple targets split in image are closed
System.Extracting picture position feature can be there are two types of method: a kind of method is to be divided automatically to image first, marks off image
Included in object or color region, then according to these extracted region images features, and establish index；Another method is then
Several regular sub-blocks simply by image uniform are divided into, feature then are extracted to each image subblock, and establish index.
Step 104, potential industrial premises classification is carried out to the subregion remotely-sensed data according to the area characteristic information
Identification obtains the potential industrial premises information of subregion, calculates the potential industrial premises concentration class feature of subregion；
By sub-zone dividing it is different classifications according to different characteristic informations, obtains subregion potential industrial premises letter
Breath, and calculate the potential industrial premises concentration class feature of subregion.
Optionally, subregion remotely-sensed data is divided by multiple polygon image data according to shape feature information；It extracts
The characteristic information of polygon image data, and potential industrial premises Classification and Identification is carried out according to characteristic information.
For example, the residential block in each subregion is divided into " square " according to shape feature, river is divided into " square
School is divided into " circle " by shape ", " square " in all subregions is then divided into residential block one kind, by all " squares
Shape " is divided into river one kind, and all " circles " is divided into school's one kind.
Step 105, every a kind of subregion remotely-sensed data is layered, extracts the remote sensing of each sub-regions remotely-sensed data
Characteristic information；
Specifically, every a kind of subregion remotely-sensed data is further refined, it is layered, and extracts the feature letter after layering
Breath.For example, a residential block includes more buildings, then it is layered each building of a residential block as one, corresponding extraction is distant
Feel characteristic information.According to different dimensions, different remote sensing features information can be extracted.
Step 106, pollution monitoring region is divided into multiple first monitoring subregions and multiple second according to predetermined manner
Monitor subregion；
It is multiple grid cells by contamination monitoring region division, for example, by the pollution control emphasis in national 2+26 city,
It has been put on the grid of 36793 3km × 3km division, in order to further refine, the grid of each 3km × 3km has been drawn again
It is divided into multiple 100 meters × 100 meters of grid cell.As shown in Figure 2.One is assigned uniquely for each grid cell after division
Grid coding, corresponding grid cell, the corresponding sub-district of a portion grid cell can be inquired according to grid coding
Domain is as the first monitoring subregion, and the corresponding subregion of another part grid cell is as the second monitoring subregion, the first monitoring
Subregion and the second monitoring subregion do not have common grid cell.
Step 107, industrial enterprise's distributed data of each first monitoring subregion is obtained；
Wherein, industrial enterprise's distributed data includes industrial information point (Point of Interest, POI) aggregation data, dirt
Contaminate object data etc..
Specifically, the record by departments such as industry and commerce, quality supervision, environmental protection obtains enterprises registration distributed intelligence, pass through map number
It obtains area map data according to library and examines on the spot the modes such as enterprise object and obtain industrial enterprise's distributed data.
Step 108, data are assembled according to industrial POI, pollutant data generate the industry that each first monitors subregion and gather
Intensity characteristic information；
Assemble the industrial POI concentration class that data calculate the first monitoring subregion according to industrial POI；According to pollutant data meter
Calculate the pollutant concentration value of the first monitoring subregion within a preset period of time；By industrial POI concentration class and pollutant concentration value into
Row Spatial Overlap Analysis generates agglomeration of industries degree characteristic information.
For example, according to industrial enterprise's quantity of the industrial POI aggregation zone area of a certain subregion and the region clustering come
Industrial enterprise's concentration class of unit of account area；Being calculated according to the PM2.5 concentration data in the past 1 year of a certain subregion should
Subregion PM2.5 annual mean；Industrial enterprise's concentration class of a certain subregion and PM2.5 annual mean are subjected to Spatial Overlap point
Analysis, obtains the agglomeration of industries degree characteristic information of the subregion.
Step 109, according to potential industrial premises concentration class characteristic information and agglomeration of industries degree characteristic information conformation identification sample
This collection；
Specifically, extracting multiple fisrt feature parameters from potential industrial premises concentration class characteristic information；From agglomeration of industries
Multiple second feature parameters are extracted in degree characteristic information；Using fisrt feature parameter, second feature parametric configuration multidimensional characteristic to
Amount；Multiple multidimensional characteristic vectors are generated into identification sample set.Different parameters is selected, then the multidimensional characteristic vectors constructed are different.
Step 110, depth characteristic study is carried out using identification sample set, obtains identification model；
Feature learning, cognitive learning, deep learning are carried out using identification sample set, trains identification model parameter, according to
Identification model parameter determines that identification model, identification model are able to reflect out the pass between satellite remote sensing date and industrial enterprise's distribution
System.Identify that the data sample in sample set is more, obtained identification model is more effective.
Step 111, the agglomeration of industries region in multiple second monitoring subregions is identified using identification model.
Specifically, obtaining the Multi-sensor satellite remote sensing of the second monitoring subregion, carried out using the identification model trained
Identification sample set is constantly iterated and is optimized, obtains the agglomeration of industries region of the second monitoring subregion by identification, that is, the
Emphasis is needed to implement the agglomeration of industries region of environmental protection supervision investigation in two monitoring subregions.
Hot spot grid agglomeration of industries area recognizing method provided by the invention based on Multi-sensor satellite remote sensing, by multi-source
Satellite remote sensing date and industrial enterprise's distributed data carry out data fusion, extract the potential industrial premises number of multi-source satellite remote sensing respectively
According to the characteristic information of, industrial enterprise's distributed data, conformation identification sample set carries out depth characteristic study using identification sample set,
Identification model is trained, identifies agglomeration of industries region using identification model.Method provided by the invention is based on multi-source satellite remote sensing
Data carry out agglomeration of industries region recognition, can precise positioning go out need emphasis implement environmental protection supervision investigation agglomeration of industries area
Domain improves the validity of pollution monitoring.
Second embodiment of the present invention provides a kind of equipment, including memory and processor, memory is deposited for storing program
Reservoir can be connect by bus with processor.Memory can be nonvolatile storage, such as hard disk drive and flash memory, storage
Software program and device driver are stored in device.Software program is able to carry out the above method provided in an embodiment of the present invention
Various functions；Device driver can be network and interface drive program.Processor is for executing software program, the software journey
Sequence is performed, and can be realized method provided in an embodiment of the present invention.
The embodiment of the present invention three provides a kind of computer program product comprising instruction, when computer program product is being counted
When being run on calculation machine, so that computer executes the method that the embodiment of the present invention one provides.
The embodiment of the present invention four provides a kind of computer readable storage medium, is stored on computer readable storage medium
Computer program realizes the method that the embodiment of the present invention one provides when computer program is executed by processor.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, processor
The combination of software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only memory
(ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field
In any other form of storage medium well known to interior.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (9)
1. a kind of hot spot grid agglomeration of industries area recognizing method based on Multi-sensor satellite remote sensing, which is characterized in that described
Method includes:
Obtain the Multi-sensor satellite remote sensing in pollution monitoring region；
The Multi-sensor satellite remote sensing is divided into multiple subregion remotely-sensed datas；
The area characteristic information of the subregion remotely-sensed data is extracted, the area characteristic information includes textural characteristics, gray scale spy
Sign, shape feature, position feature；
Potential industrial premises Classification and Identification is carried out to the subregion remotely-sensed data according to the area characteristic information, obtains sub-district
The potential industrial premises information in domain calculates the potential industrial premises concentration class feature of subregion；
Every one kind subregion remotely-sensed data is layered, the remote sensing features letter of each sub-regions remotely-sensed data is extracted
Breath；
The pollution monitoring region is divided into multiple first monitoring subregions and multiple second monitoring sub-districts according to predetermined manner
Domain；
Industrial enterprise's distributed data of each first monitoring subregion is obtained, industrial enterprise's distributed data includes industry
Information point POI assembles data, pollutant data；
Assemble data according to the industry POI, pollutant data generate each described first agglomeration of industries degree for monitoring subregion
Characteristic information；
According to the potential industrial premises concentration class characteristic information and the agglomeration of industries degree characteristic information conformation identification sample set；
Depth characteristic study is carried out using the identification sample set, obtains identification model；
The agglomeration of industries region in the multiple second monitoring subregion is identified using the identification model.
2. the method according to claim 1, wherein the multi-source satellite remote sensing number for obtaining pollution monitoring region
According to specifically including:
Polar orbiting meteorological satellite remotely-sensed data, the static meteorology in the pollution monitoring region are extracted from Multi-sensor satellite remote sensing library
Satellite remote sensing date, high-spectrum remote-sensing satellite data.
3. the method according to claim 1, wherein in the Multi-sensor satellite remote sensing for obtaining pollution monitoring region
Later, the method also includes:
The multi- source Remote Sensing Data data is pre-processed, the pretreatment includes geometric correction, information enhancement, smothing filtering, letter
Breath fusion.
4. the method according to claim 1, wherein it is described according to the area characteristic information to the subregion
Remotely-sensed data carries out potential industrial premises Classification and Identification, obtains the potential industrial premises information of subregion and specifically includes:
The subregion remotely-sensed data is divided into multiple polygon image data according to the shape feature information；
The characteristic information of the polygon image data is extracted, and potential industrial premises classification is carried out according to the characteristic information and is known
Not.
5. the method according to claim 1, wherein described assemble data, pollutant number according to the industry POI
It is specifically included according to the agglomeration of industries degree characteristic information for generating each first monitoring subregion:
Assemble the industrial POI concentration class that data calculate the first monitoring subregion according to the industry POI；
The pollutant concentration value of the first monitoring subregion within a preset period of time is calculated according to the pollutant data；
The industry POI concentration class and the pollutant concentration value are subjected to Spatial Overlap Analysis, generate the agglomeration of industries degree
Characteristic information.
6. the method according to claim 1, wherein described believe according to the potential industrial premises concentration class feature
Breath and the agglomeration of industries degree characteristic information conformation identification sample set specifically include:
Multiple fisrt feature parameters are extracted from the potential industrial premises concentration class characteristic information；
Multiple second feature parameters are extracted from the agglomeration of industries degree characteristic information；
Utilize the fisrt feature parameter, second feature parametric configuration multidimensional characteristic vectors；
Multiple multidimensional characteristic vectors are generated into the identification sample set.
7. a kind of equipment, including memory and processor, which is characterized in that the memory is for storing program, the processing
Device is used to execute the method as described in claim 1-6 is any.
8. a kind of computer program product comprising instruction, which is characterized in that when the computer program product on computers
When operation, so that the computer executes the method as described in claim 1-6 any claim.
9. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the method as described in claim 1-6 any claim when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811059933.2A CN109284706B (en) | 2018-09-12 | 2018-09-12 | Hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811059933.2A CN109284706B (en) | 2018-09-12 | 2018-09-12 | Hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109284706A true CN109284706A (en) | 2019-01-29 |
| CN109284706B CN109284706B (en) | 2023-12-01 |
Family
ID=65180698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811059933.2A Active CN109284706B (en) | 2018-09-12 | 2018-09-12 | Hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109284706B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110954482A (en) * | 2019-12-02 | 2020-04-03 | 生态环境部卫星环境应用中心 | Atmospheric pollution gridding monitoring method based on static satellite and polar orbit satellite |
| CN112148823A (en) * | 2020-09-04 | 2020-12-29 | 国家卫星气象中心(国家空间天气监测预警中心) | Geometric correction parallel method and device for remote sensing data and computer equipment |
| CN112800993A (en) * | 2021-02-03 | 2021-05-14 | 北华航天工业学院 | Regional scale industrial factory building information enhancement method based on discrete wavelet transform |
| CN112883251A (en) * | 2021-01-09 | 2021-06-01 | 重庆市农业科学院 | Agricultural auxiliary system based on multi-satellite combination |
| CN113176216A (en) * | 2021-01-12 | 2021-07-27 | 生态环境部卫星环境应用中心 | Ozone precursor VOCs high-value area satellite remote sensing identification method |
| WO2022048196A1 (en) * | 2020-09-03 | 2022-03-10 | 深圳前海微众银行股份有限公司 | Method and device for monitoring industrial production index |
| CN115132290A (en) * | 2022-09-02 | 2022-09-30 | 北京市生态环境监测中心 | Method for identifying VOCs fixed source emission area based on multi-source satellite remote sensing |
| CN115272854A (en) * | 2022-07-27 | 2022-11-01 | 清华大学 | Palm area identification method and product based on multi-source information analysis |
| CN117237647A (en) * | 2023-11-15 | 2023-12-15 | 成都嘉德数源环保科技有限公司 | Atmospheric pollution monitoring system and method |
| CN117591619A (en) * | 2023-11-23 | 2024-02-23 | 北京英视宇辰科技有限公司 | Method, system, equipment and medium for identifying double high-temperature hot spot grids of polluted carbon |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101777125A (en) * | 2010-02-03 | 2010-07-14 | 武汉大学 | Method for supervising and classifying complex class of high-resolution remote sensing image |
| CN103776540A (en) * | 2013-12-30 | 2014-05-07 | 华中科技大学 | Multiband common-optical-path spectrum combined remote sensing measurement system and method thereof |
| CN103984310A (en) * | 2014-05-12 | 2014-08-13 | 华迪计算机集团有限公司 | Chemical industry park environment pollution detection method and device based on multi-source remote sensing data |
| KR20160021528A (en) * | 2014-08-18 | 2016-02-26 | 한국과학기술연구원 | Air Pollution Monitor Method |
| CN105493109A (en) * | 2013-06-05 | 2016-04-13 | 微软技术许可有限责任公司 | Air quality inference using multiple data sources |
| CN105740643A (en) * | 2016-03-15 | 2016-07-06 | 杭州电子科技大学 | Self-adaptive PM<2.5>concentration speculating method based on city region grid |
| CN106124374A (en) * | 2016-07-22 | 2016-11-16 | 中科宇图科技股份有限公司 | Atmospheric particulates remote-sensing monitoring method based on data fusion |
| CN106611090A (en) * | 2016-12-31 | 2017-05-03 | 中国科学技术大学 | Roadside air pollutant concentration prediction method based on reconstruction deep learning |
| US20170124116A1 (en) * | 2015-11-02 | 2017-05-04 | Mda Information Systems Llc | System and method for aggregating multi-source data and identifying geographic areas for data acquisition |
| CN107688818A (en) * | 2016-08-05 | 2018-02-13 | 中国电力科学研究院 | A kind of path intelligent selecting method and system based on satellite remote-sensing image signature analysis |
-
2018
- 2018-09-12 CN CN201811059933.2A patent/CN109284706B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101777125A (en) * | 2010-02-03 | 2010-07-14 | 武汉大学 | Method for supervising and classifying complex class of high-resolution remote sensing image |
| CN105493109A (en) * | 2013-06-05 | 2016-04-13 | 微软技术许可有限责任公司 | Air quality inference using multiple data sources |
| CN103776540A (en) * | 2013-12-30 | 2014-05-07 | 华中科技大学 | Multiband common-optical-path spectrum combined remote sensing measurement system and method thereof |
| CN103984310A (en) * | 2014-05-12 | 2014-08-13 | 华迪计算机集团有限公司 | Chemical industry park environment pollution detection method and device based on multi-source remote sensing data |
| KR20160021528A (en) * | 2014-08-18 | 2016-02-26 | 한국과학기술연구원 | Air Pollution Monitor Method |
| US20170124116A1 (en) * | 2015-11-02 | 2017-05-04 | Mda Information Systems Llc | System and method for aggregating multi-source data and identifying geographic areas for data acquisition |
| CN105740643A (en) * | 2016-03-15 | 2016-07-06 | 杭州电子科技大学 | Self-adaptive PM<2.5>concentration speculating method based on city region grid |
| CN106124374A (en) * | 2016-07-22 | 2016-11-16 | 中科宇图科技股份有限公司 | Atmospheric particulates remote-sensing monitoring method based on data fusion |
| CN107688818A (en) * | 2016-08-05 | 2018-02-13 | 中国电力科学研究院 | A kind of path intelligent selecting method and system based on satellite remote-sensing image signature analysis |
| CN106611090A (en) * | 2016-12-31 | 2017-05-03 | 中国科学技术大学 | Roadside air pollutant concentration prediction method based on reconstruction deep learning |
Non-Patent Citations (3)
| Title |
|---|
| YIN, Q ET AL.: "Views on Chinese remote sensing development", 《JOURNAL OF INFRARED AND MILLIMETER WAVES》, vol. 26, no. 3, pages 225 - 231 * |
| 白永亮 等,: "大气污染的空间关联与区域间防控协作———基于全国 ２８８ 个地市工业 ＳＯ２ 污染数据的空间统计分析", 《中国地质大学学报（社会科学版）》, vol. 16, no. 3, pages 63 - 72 * |
| 黄祚继等: "新兴信息技术在大气环境治理中的研究与应用", 中国科学技术大学出版社 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110954482B (en) * | 2019-12-02 | 2020-12-15 | 生态环境部卫星环境应用中心 | Atmospheric pollution gridding monitoring method based on static satellite and polar orbit satellite |
| CN110954482A (en) * | 2019-12-02 | 2020-04-03 | 生态环境部卫星环境应用中心 | Atmospheric pollution gridding monitoring method based on static satellite and polar orbit satellite |
| WO2022048196A1 (en) * | 2020-09-03 | 2022-03-10 | 深圳前海微众银行股份有限公司 | Method and device for monitoring industrial production index |
| CN112148823A (en) * | 2020-09-04 | 2020-12-29 | 国家卫星气象中心(国家空间天气监测预警中心) | Geometric correction parallel method and device for remote sensing data and computer equipment |
| CN112148823B (en) * | 2020-09-04 | 2023-12-26 | 国家卫星气象中心(国家空间天气监测预警中心) | Remote sensing data geometric correction parallel method and device and computer equipment |
| CN112883251A (en) * | 2021-01-09 | 2021-06-01 | 重庆市农业科学院 | Agricultural auxiliary system based on multi-satellite combination |
| CN113176216A (en) * | 2021-01-12 | 2021-07-27 | 生态环境部卫星环境应用中心 | Ozone precursor VOCs high-value area satellite remote sensing identification method |
| CN113176216B (en) * | 2021-01-12 | 2022-03-15 | 生态环境部卫星环境应用中心 | Ozone precursor VOCs high-value area satellite remote sensing identification method |
| CN112800993A (en) * | 2021-02-03 | 2021-05-14 | 北华航天工业学院 | Regional scale industrial factory building information enhancement method based on discrete wavelet transform |
| CN115272854B (en) * | 2022-07-27 | 2023-08-15 | 清华大学 | Palm land identification method and product based on multi-source information analysis |
| CN115272854A (en) * | 2022-07-27 | 2022-11-01 | 清华大学 | Palm area identification method and product based on multi-source information analysis |
| CN115132290A (en) * | 2022-09-02 | 2022-09-30 | 北京市生态环境监测中心 | Method for identifying VOCs fixed source emission area based on multi-source satellite remote sensing |
| CN115132290B (en) * | 2022-09-02 | 2022-12-02 | 北京市生态环境监测中心 | Method for identifying VOCs fixed source emission area based on multi-source satellite remote sensing |
| CN117237647A (en) * | 2023-11-15 | 2023-12-15 | 成都嘉德数源环保科技有限公司 | Atmospheric pollution monitoring system and method |
| CN117237647B (en) * | 2023-11-15 | 2024-01-26 | 成都嘉德数源环保科技有限公司 | Atmospheric pollution monitoring system and method |
| CN117591619A (en) * | 2023-11-23 | 2024-02-23 | 北京英视宇辰科技有限公司 | Method, system, equipment and medium for identifying double high-temperature hot spot grids of polluted carbon |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109284706B (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284706A (en) | Hot spot grid agglomeration of industries area recognizing method based on Multi-sensor satellite remote sensing | |
| Melgani | Contextual reconstruction of cloud-contaminated multitemporal multispectral images | |
| Kim et al. | Deep-hurricane-tracker: Tracking and forecasting extreme climate events | |
| CN109101955A (en) | Industrial heat anomaly area recognizing method based on Multi-sensor satellite remote sensing | |
| CN111598098B (en) | Water gauge water line detection and effectiveness identification method based on full convolution neural network | |
| CN103413151A (en) | Hyperspectral image classification method based on image regular low-rank expression dimensionality reduction | |
| CN108805050A (en) | Electric wire detection method based on local binary patterns | |
| CN109146974A (en) | A kind of readings of pointer type meters recognition methods and system | |
| CN103605171A (en) | All-sky imaging instrument and cloud layer characteristic analysis method based on all-sky imaging instrument | |
| Hu et al. | What you get is not always what you see—pitfalls in solar array assessment using overhead imagery | |
| Lee et al. | Pre-trained feature aggregated deep learning-based monitoring of overshooting tops using multi-spectral channels of GeoKompsat-2A advanced meteorological imagery | |
| Aruna et al. | Visualization and Prediction of Rainfall Using Deep Learning and Machine Learning Techniques | |
| Larsen et al. | Automatic system for operational traffic monitoring using very-high-resolution satellite imagery | |
| Yang et al. | An Improved Method for Individual Tree Segmentation in Complex Urban Scene Based on Using Multispectral LiDAR by Deep Learning | |
| Li et al. | Evaluating the ability of NOAA-20 monthly composite data for socioeconomic indicators estimation and urban area extraction | |
| CN117152637A (en) | Strong convection cloud identification method based on FY-4A satellite cloud image prediction sequence | |
| CN110175638B (en) | Raise dust source monitoring method | |
| CN104123569A (en) | Video person number information statistics method based on supervised learning | |
| Sadouki et al. | Classification of radar echoes with a textural–fuzzy approach: an application for the removal of ground clutter observed in Sétif (Algeria) and Bordeaux (France) sites | |
| Storch et al. | Detecting historical terrain anomalies with UAV-LiDAR data using spline-approximation and support vector machines | |
| Bouchahma et al. | Optical-flow-based approach for the detection of shoreline changes using remote sensing data | |
| Romano et al. | Morphological operators for polarimetric anomaly detection | |
| Rawshan Habib et al. | Study on Advanced Image Processing Techniques for Remote Sensor Data Analysis | |
| Ding et al. | Roadside Unit Visibility Prediction Method Based on SVR. | |
| Moctezuma-Flores et al. | Synthetic aperture radar analysis of floating ice at Terra Nova Bay—an application to ice eddy parameter extraction |
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 | ||
| CB02 | Change of applicant information |
Address after: 100070 Beijing Fengtai Auto Museum West Road No. 8 Courtyard 1 Building 6 Floor 606 Applicant after: Beijing Yingshi Ruida Technology Co.,Ltd. Address before: 1202, No. 18, Yumin Middle Road, Xicheng District, Beijing 100029 Applicant before: BEIJING INSIGHTS VALUE TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230407 Address after: Unit 02, 12th Floor, 501, Building 3, Yard 20, Jinhe East Road, Chaoyang District, Beijing, 100020 Applicant after: IBM (CHINA) INVESTMENT CO.,LTD. Address before: 100070 Beijing Fengtai Auto Museum West Road No. 8 Courtyard 1 Building 6 Floor 606 Applicant before: Beijing Yingshi Ruida Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231222 Address after: Armank, New York, USA Patentee after: International Business Machines Corp. Address before: Unit 02, 12th Floor, 501, Building 3, Yard 20, Jinhe East Road, Chaoyang District, Beijing, 100020 Patentee before: IBM (CHINA) INVESTMENT CO.,LTD. |
|
| TR01 | Transfer of patent right |