CN109284706B - Hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data - Google Patents
Hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data Download PDFInfo
- Publication number
- CN109284706B CN109284706B CN201811059933.2A CN201811059933A CN109284706B CN 109284706 B CN109284706 B CN 109284706B CN 201811059933 A CN201811059933 A CN 201811059933A CN 109284706 B CN109284706 B CN 109284706B
- Authority
- CN
- China
- Prior art keywords
- industrial
- remote sensing
- aggregation
- data
- sensing data
- 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.)
- Active
Links
- 230000002776 aggregation Effects 0.000 title claims abstract description 76
- 238000004220 aggregation Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012544 monitoring process Methods 0.000 claims abstract description 62
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 18
- 231100000719 pollutant Toxicity 0.000 claims abstract description 18
- 230000004927 fusion Effects 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 3
- 238000011109 contamination Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 description 8
- 238000011835 investigation Methods 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 5
- 238000003709 image segmentation Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect 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
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect 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 invention relates to a hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data, which comprises the following steps: acquiring multi-source satellite remote sensing data of a pollution monitoring area; dividing multi-source satellite remote sensing data into a plurality of sub-region remote sensing data; identifying potential industrial plant information based on the multi-dimensional regional features; dividing the pollution monitoring area into a plurality of first monitoring subareas and a plurality of second monitoring subareas according to a preset mode; integrating the potential industrial factory building aggregation degree, the industrial POI aggregation degree and the pollutant concentration in each subarea to acquire industrial enterprise distribution data of each first monitoring subarea; generating industrial aggregation characteristic information of each first monitoring subarea; constructing an identification sample set according to the aggregation characteristics of the potential industrial factory buildings, the industrial aggregation characteristics and the pollutant concentration information; deep feature learning is carried out by utilizing the identification sample set, and an identification model is obtained; an industrial aggregation area in the plurality of second monitoring sub-areas is identified using the identification model.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data.
Background
The remote sensing image identification means that a computer is used for analyzing the spectrum information and the space information of various ground objects in the remote sensing image, selecting characteristics, dividing the characteristic space into subspaces which are not overlapped with each other by a certain means, and dividing each pixel in the image into the ground object categories corresponding to each subspace. With the development of remote sensing technology, a large number of different satellite sensors such as optical, thermal infrared and microwave are applied to earth observation, and multiple remote sensing image data (multi-temporal, multi-spectrum, multi-sensor, multi-platform and multi-resolution) of the same region are acquired more and more, which is multi-source remote sensing. Compared with single-source remote sensing image data, the information provided by the multi-source remote sensing data has redundancy, complementarity and cooperation.
In 2016, the Ministry of environmental protection cooperates with scientific and technological enterprises to divide the Beijing Ji and the surrounding key areas of "2+26" cities (2 refers to Beijing city and Tianjin city, 26 refers to Hebei Jizhuang, tangshan, baoding, jifang, cangzhou, heshui, zhuang, chen, shanxi Taiyuan, yangquan, changzhi, jincheng, shandong Jinan, bobo, chacheng, texas, binzhou, jining, ganzze, henan Zheng, new county, henan Jibi, anyang, jiang, puyang and Kakai 26 cities) into grids according to 3km×3km, and 36793 in total. And according to the divided grids, encrypting and distributing the atmospheric monitoring points. Grid cells with higher atmospheric pollution degree are regularly screened out through big data and sent to relevant local governments and environmental protection departments, so that accurate law enforcement is promoted to be implemented.
The grid unit focuses on pollution control of 2+26 cities nationwide, and places the pollution control focus on 36793 grids divided by 3km multiplied by 3km, so that one-step focusing on pollution is realized. However, 3km×3km is still not fine enough for the micro-environment, and it is necessary to further locate the grid-type industrial aggregation area where the environmental monitoring and investigation needs to be performed, and thus, an industrial aggregation area identification solution based on multi-source remote sensing data is needed.
Disclosure of Invention
The invention aims at overcoming the defects in the prior art and provides a hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data.
In order to achieve the above object, in a first aspect, the present invention provides a method for identifying a hotspot grid industrial aggregation area based on multi-source satellite remote sensing data, including:
acquiring multi-source satellite remote sensing data of a pollution monitoring area;
dividing the multi-source satellite remote sensing data into a plurality of sub-region remote sensing data;
extracting regional characteristic information of the sub-region remote sensing data, wherein the regional characteristic information comprises texture characteristics, gray level characteristics, shape characteristics and position characteristics;
carrying out potential industrial factory building classification and identification on the subarea remote sensing data according to the area characteristic information to obtain subarea potential industrial factory building information, and calculating subarea potential industrial factory building aggregation characteristics;
layering the sub-region remote sensing data of each type, and extracting the remote sensing characteristic information of the sub-region remote sensing data of each layer;
dividing the pollution monitoring area into a plurality of first monitoring subareas and a plurality of second monitoring subareas according to a preset mode;
acquiring industrial enterprise distribution data of each first monitoring subarea, wherein the industrial enterprise distribution data comprise industrial information point POI aggregation data and pollutant data;
generating industrial aggregation degree characteristic information of each first monitoring subarea according to the industrial POI aggregation data and the pollutant data;
constructing an identification sample set according to the regional potential industrial factory building aggregation characteristic information and the industrial aggregation characteristic information;
deep feature learning is carried out by utilizing the identification sample set, so that an identification model is obtained;
an industrial aggregation area in the plurality of second monitoring sub-areas is identified using the identification model.
Further, the acquiring the multi-source satellite remote sensing data of the pollution monitoring area specifically includes:
and extracting polar orbit meteorological satellite remote sensing data, static meteorological satellite remote sensing data and hyperspectral remote sensing satellite data of the pollution monitoring area from a multisource satellite remote sensing database.
Further, after acquiring the multi-source satellite remote sensing data of the pollution monitoring area, the method further comprises:
preprocessing the multi-source remote sensing data, wherein the preprocessing comprises geometric correction, information enhancement, smooth filtering and information fusion.
Further, the step of classifying and identifying the sub-region remote sensing data according to the region characteristic information to obtain sub-region potential industrial factory building information specifically includes:
dividing the sub-region remote sensing data into a plurality of polygon image data according to the shape characteristic information;
and extracting characteristic information of the polygon image data, and carrying out potential industrial factory building classification identification according to the characteristic information.
Further, the generating the industrial aggregation degree characteristic information of each first monitoring subarea according to the industrial POI aggregation data and the pollutant data specifically includes:
calculating the industrial POI aggregation degree of the first monitoring subarea according to the industrial POI aggregation data;
calculating a pollutant concentration value of the first monitoring subarea in a preset time period according to the pollutant data;
and carrying out space superposition analysis on the industrial POI aggregation level and the pollutant concentration value to generate the industrial aggregation level characteristic information.
Further, the constructing an identification sample set according to the domain potential industrial factory building aggregation characteristic information and the industrial aggregation characteristic information specifically includes:
extracting a plurality of first characteristic parameters from the potential industrial plant aggregation characteristic information;
extracting a plurality of second characteristic parameters from the industrial aggregation characteristic information;
constructing a multidimensional feature vector by utilizing the first feature parameter and the second feature parameter;
generating the identification sample set from a plurality of the multi-dimensional feature vectors.
In a second aspect, the present invention provides an apparatus comprising a memory for storing a program and a processor for performing the method of the first aspect and various implementations of the first aspect.
In a third aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of the first aspect and the various implementations of the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of the first aspect and the various implementations of the first aspect.
According to the identification method for the hot spot grid industrial aggregation area based on the multi-source satellite remote sensing data, the multi-source satellite remote sensing data and the industrial enterprise distribution data are subjected to data fusion, characteristic information of the multi-source satellite remote sensing potential industrial factory building data and the industrial enterprise distribution data is respectively extracted, an identification sample set is constructed, deep characteristic learning is conducted by using the identification sample set, an identification model is trained, and the industrial aggregation area is identified by using the identification model. According to the method provided by the invention, the industrial aggregation area is identified based on the multi-source satellite remote sensing data, so that the industrial aggregation area needing to be subjected to the environmental protection monitoring and investigation can be accurately positioned, and the effectiveness of pollution monitoring is improved.
Drawings
FIG. 1 is a flowchart of a method for identifying a hot spot grid industrial aggregation area based on multi-source satellite remote sensing data according to an embodiment of the present invention;
fig. 2 is a schematic diagram of dividing a monitoring area into grid cells according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is to identify the hot spot grids based on multi-source satellite remote sensing data, namely identify the grid industrial aggregation areas which need to be subjected to the environmental protection monitoring and investigation, and aim to improve the effectiveness of pollution monitoring.
Fig. 1 is a flowchart of a method for identifying a hotspot grid industrial aggregation area based on multi-source satellite remote sensing data according to an embodiment of the present invention. As shown in fig. 1, the method specifically comprises the following steps:
step 101, multi-source satellite remote sensing data of a pollution monitoring area is obtained.
And extracting polar orbit meteorological satellite remote sensing data, static meteorological satellite remote sensing data and hyperspectral remote sensing satellite data of the pollution monitoring area from a multisource satellite remote sensing database.
The images obtained by the polar orbit meteorological satellites include: cloud, cloud systems, cold and hot fronts, typhoons, lakes, forests, mountains, ice and snow, fire, smoke, oil stains, and the like. The stationary weather satellites carry various weather remote sensing instruments capable of receiving and measuring visible light, infrared and microwave radiation of the earth and its atmosphere and converting them into electrical signals for transmission to the ground. The ground station recovers and draws the electric signals sent by the satellites into various cloud layers, ground surfaces and ocean surface pictures. The hyperspectral remote sensing satellite image data includes image data acquired in a very narrow spectrum of succession in the visible, near infrared, mid infrared and thermal infrared bands of the electromagnetic spectrum.
Before step 101, a multi-source satellite remote sensing database corresponding to the pollution monitoring area is pre-established.
After step 101, the multi-source remote sensing data is preprocessed, where the preprocessing includes geometric correction, information enhancement, smoothing filtering, and information fusion. The purpose of preprocessing the multi-source remote sensing data is to facilitate the subsequent image segmentation and feature extraction.
The geometric correction is to correct and eliminate deformation generated when the characteristics of geometric position, shape, size, azimuth and the like of each feature on the original image caused by factors such as photographic material deformation, objective lens distortion, atmospheric refraction, earth curvature, earth rotation, topography fluctuation and the like are inconsistent with the expression requirements in a reference system when the remote sensing image is imaged through a series of mathematical models.
Information enhancement refers to a process of improving the visual effect of an image. When analyzing a remote sensing image, in order for an analyst to easily and accurately identify the image content, the image data must be processed for analysis purposes in order to improve the interpretability of the image. Information enhancement includes gray scale interchange, color synthesis, etc.
The purpose of smoothing filtering is to denoise the image, including in particular linear filtering and nonlinear filtering. Linear filtering, such as neighborhood smoothing filtering, recovers images that are degraded by noise contamination. The nonlinear filter such as median filtering can overcome the problem of image blurring caused by linear filtering to a certain extent, and the edge information of the image is well reserved while noise is filtered.
The information fusion refers to the fusion of data acquired by different remote sensors, and can be divided into two steps of spatial registration and image fusion of images. The spatial registration of images refers to spatial registration of two images, one of which is generally referred to as a reference image, and the other image is corrected based on the reference image. The image fusion is to intelligently select a proper fusion algorithm according to the fusion purpose and the fusion level, and organically synthesize the remote sensing image data with spatial registration to obtain more accurate representation or estimation of the target.
102, dividing multi-source satellite remote sensing data into a plurality of sub-region remote sensing data;
because the remote sensing data of the multi-source satellite has larger size, the subsequent processing can be performed after the image segmentation. Image segmentation is the process of dividing a digital image into mutually disjoint regions.
The multi-source satellite remote sensing data is segmented into sub-region remote sensing data of a plurality of units, and specific segmentation methods comprise a segmentation method based on a threshold value, a segmentation method based on a region, a segmentation method based on an edge, a segmentation method based on a specific theory and the like.
And marking a plurality of sub-region remote sensing data obtained after image segmentation, and endowing each sub-region with a unique region code. The corresponding unique region can be queried according to the region code.
Step 103, extracting regional characteristic information of the remote sensing data of the subareas;
wherein the region characteristic information includes texture characteristics, gray level characteristics, shape characteristics, position characteristics, and the like. The region characteristic information is a corresponding feature or characteristic of the sub-region that is distinct from other sub-regions, or a set of such features and characteristics. The regional characteristics are extracted by measurement or processing. Each image has its own characteristics which can be distinguished from other types of images, some are intuitively perceived natural characteristics such as brightness, edges, textures, colors, etc.; some are obtained by transformation or processing, such as moments, histograms, principal components, etc.
The texture feature requires statistical computation in an area containing a plurality of pixels. The extraction method of the texture features comprises a statistical method, a geometric method, a model method and a signal processing method.
The gray scale features include a gray scale average, a gray scale median, etc. The gray average value refers to the average value of all pixels in the area; the median gray level refers to the median of the order of all pixels in the region.
Shape features include contour features and region features. The contour features are used to the outer boundary of the object and the region features relate to the entire shape region. The extraction method of the shape features comprises a boundary feature method, a Fourier shape descriptor method, a geometric parameter method and the like.
The position feature refers to a mutual spatial position or a relative direction relation between a plurality of objects segmented in the image. There are two methods for extracting the image position features: one method is that firstly, an image is automatically segmented, an object or a color region contained in the image is segmented, then image characteristics are extracted according to the regions, and an index is established; another approach simply divides the image uniformly into regular sub-blocks, then extracts features for each image sub-block, and builds an index.
Step 104, classifying and identifying the potential industrial factory buildings according to the regional characteristic information, obtaining the information of the potential industrial factory buildings of the subregions, and calculating the aggregation characteristics of the potential industrial factory buildings of the subregions;
dividing the subareas into different categories according to different characteristic information to obtain subarea potential industrial factory building information, and calculating the subarea potential industrial factory building aggregation characteristics.
Optionally, dividing the sub-region remote sensing data into a plurality of polygon image data according to the shape characteristic information; and extracting characteristic information of the polygon image data, and carrying out potential industrial factory building classification identification according to the characteristic information.
For example, the residential area in each sub-area is divided into "squares", the river is divided into "rectangles", the school is divided into "circles", then the "squares" in all sub-areas are divided into the residential area class, all "rectangles" are divided into the river class, and all "circles" are divided into the school class according to the shape characteristics.
Step 105, layering each type of sub-region remote sensing data, and extracting the remote sensing characteristic information of each layer of sub-region remote sensing data;
specifically, each type of sub-region remote sensing data is further refined, layering is carried out, and feature information after layering is extracted. For example, if a residential area includes a plurality of buildings, each building of the residential area is used as a hierarchy, and remote sensing characteristic information is correspondingly extracted. According to different dimensions, different remote sensing characteristic information can be extracted.
Step 106, dividing the pollution monitoring area into a plurality of first monitoring subareas and a plurality of second monitoring subareas according to a preset mode;
the pollution monitoring area is divided into a plurality of grid cells, for example, the pollution control emphasis of 2+26 cities in the whole country is put on 36793 grids divided into 3km×3km, and each grid of 3km×3km is divided into a plurality of grid cells of 100 m×100 m again for further refinement. As shown in fig. 2. Each divided grid cell is endowed with a unique grid code, and corresponding grid cells can be inquired according to the grid code, wherein a part of subareas corresponding to the grid cells are used as first monitoring subareas, the other part of subareas corresponding to the grid cells are used as second monitoring subareas, and the first monitoring subareas and the second monitoring subareas do not have common grid cells.
Step 107, acquiring industrial enterprise distribution data of each first monitoring subarea;
among other things, industrial enterprise distribution data includes industrial information point (Point of Interest, POI) aggregate data, contaminant data, and the like.
Specifically, the enterprise registration distribution information is obtained through records of departments such as industry and commerce, quality supervision, environmental protection and the like, and the industrial enterprise distribution data is obtained through the modes such as regional map data acquisition by a map database, and enterprise distribution investigation in the field.
Step 108, generating industrial aggregation degree characteristic information of each first monitoring subarea according to the industrial POI aggregation data and the pollutant data;
calculating the industrial POI aggregation degree of the first monitoring subarea according to the industrial POI aggregation data; calculating a pollutant concentration value of the first monitoring subarea in a preset time period according to the pollutant data; and carrying out space superposition analysis on the industrial POI aggregation level and the pollutant concentration value to generate industrial aggregation level characteristic information.
For example, calculating the industrial enterprise aggregation degree of a unit area according to the industrial POI aggregation area of a certain subarea and the number of industrial enterprises aggregated in the area; calculating PM2.5 annual average value of the subarea according to PM2.5 concentration data in the past year of the subarea; and carrying out space superposition analysis on the industrial enterprise aggregation degree and PM2.5 year average value of a certain subarea to obtain the industrial aggregation degree characteristic information of the subarea.
Step 109, constructing an identification sample set according to the potential industrial factory building aggregation characteristic information and the industrial aggregation characteristic information;
specifically, extracting a plurality of first characteristic parameters from the characteristic information of the aggregation level of the potential industrial factory buildings; extracting a plurality of second characteristic parameters from the industrial aggregation level characteristic information; constructing a multidimensional feature vector by utilizing the first feature parameter and the second feature parameter; a plurality of multi-dimensional feature vectors are generated into a set of recognition samples. Different parameters are selected, and the constructed multidimensional feature vectors are different.
Step 110, performing deep feature learning by using the recognition sample set to obtain a recognition model;
and performing feature learning, cognitive learning and deep learning by using the recognition sample set, training out recognition model parameters, determining a recognition model according to the recognition model parameters, wherein the recognition model can reflect the relationship between satellite remote sensing data and industrial enterprise distribution. The more data samples in the recognition sample set, the more efficient the resulting recognition model.
Step 111, identifying an industrial aggregation area in the plurality of second monitoring sub-areas using the identification model.
Specifically, multi-source satellite remote sensing data of the second monitoring subarea are obtained, the trained identification model is utilized for identification, and the identification sample set is continuously iterated and optimized to obtain an industrial aggregation area of the second monitoring subarea, namely an industrial aggregation area in the second monitoring subarea, wherein the industrial aggregation area needs to be subjected to environmental protection monitoring and investigation.
According to the identification method for the hot spot grid industrial aggregation area based on the multi-source satellite remote sensing data, the multi-source satellite remote sensing data and the industrial enterprise distribution data are subjected to data fusion, characteristic information of the multi-source satellite remote sensing potential industrial factory building data and the industrial enterprise distribution data is respectively extracted, an identification sample set is constructed, deep characteristic learning is conducted by using the identification sample set, an identification model is trained, and the industrial aggregation area is identified by using the identification model. According to the method provided by the invention, the industrial aggregation area is identified based on the multi-source satellite remote sensing data, so that the industrial aggregation area needing to be subjected to the environmental protection monitoring and investigation can be accurately positioned, and the effectiveness of pollution monitoring is improved.
The second embodiment of the invention provides a device, which comprises a memory and a processor, wherein the memory is used for storing programs, and the memory can be connected with the processor through a bus. The memory may be non-volatile memory, such as a hard disk drive and flash memory, in which software programs and device drivers are stored. The software program can execute various functions of the method provided by the embodiment of the invention; the device driver may be a network and interface driver. The processor is configured to execute a software program, where the software program is executed to implement the method provided by the embodiment of the present invention.
A third embodiment of the present invention provides a computer program product containing instructions, which when executed on a computer, cause the computer to perform the method provided by the first embodiment of the present invention.
The fourth embodiment of the present invention provides a computer readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method provided in the first embodiment of the present invention is implemented.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of function in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A method for identifying a hotspot grid industrial aggregation area based on multi-source satellite remote sensing data, the method comprising:
acquiring multi-source satellite remote sensing data of a pollution monitoring area;
dividing the multi-source satellite remote sensing data into a plurality of sub-region remote sensing data;
extracting regional characteristic information of the sub-region remote sensing data, wherein the regional characteristic information comprises texture characteristics, gray level characteristics, shape characteristics and position characteristics;
carrying out potential industrial factory building classification and identification on the subarea remote sensing data according to the area characteristic information to obtain subarea potential industrial factory building information, and calculating subarea potential industrial factory building aggregation characteristics;
dividing the pollution monitoring area into a plurality of first monitoring subareas and a plurality of second monitoring subareas according to a preset mode;
acquiring industrial enterprise distribution data of each first monitoring subarea, wherein the industrial enterprise distribution data comprise industrial information point POI aggregation data and pollutant data;
generating industrial aggregation degree characteristic information of each first monitoring subarea according to the industrial POI aggregation data and the pollutant data;
constructing an identification sample set according to the potential industrial factory building aggregation characteristic information and the industrial aggregation characteristic information;
deep feature learning is carried out by utilizing the identification sample set, so that an identification model is obtained;
an industrial aggregation area in the plurality of second monitoring sub-areas is identified using the identification model.
2. The method of claim 1, wherein the acquiring multi-source satellite remote sensing data of the pollution monitoring area specifically comprises:
and extracting polar orbit meteorological satellite remote sensing data, static meteorological satellite remote sensing data and hyperspectral remote sensing satellite data of the pollution monitoring area from a multisource satellite remote sensing database.
3. The method of claim 1, wherein after acquiring the multi-source satellite telemetry data of the contamination monitoring area, the method further comprises:
preprocessing the multi-source satellite remote sensing data, wherein the preprocessing comprises geometric correction, information enhancement, smooth filtering and information fusion.
4. The method of claim 1, wherein the performing the classification and identification of the potential industrial factory building on the sub-region remote sensing data according to the region characteristic information, to obtain the sub-region potential industrial factory building information specifically includes:
dividing the sub-region remote sensing data into a plurality of polygon image data according to the shape characteristic information;
and extracting characteristic information of the polygon image data, and carrying out potential industrial factory building classification identification according to the characteristic information.
5. The method according to claim 1, wherein the generating the industrial concentration characteristic information of each of the first monitoring subareas according to the industrial POI concentration data and the pollutant data specifically comprises:
calculating the industrial POI aggregation degree of the first monitoring subarea according to the industrial POI aggregation data;
calculating a pollutant concentration value of the first monitoring subarea in a preset time period according to the pollutant data;
and carrying out space superposition analysis on the industrial POI aggregation level and the pollutant concentration value to generate the industrial aggregation level characteristic information.
6. The method of claim 1, wherein constructing an identification sample set from the potential industrial plant concentration profile information and the industrial concentration profile information comprises:
extracting a plurality of first characteristic parameters from the potential industrial plant aggregation characteristic information;
extracting a plurality of second characteristic parameters from the industrial aggregation characteristic information;
constructing a multidimensional feature vector by utilizing the first feature parameter and the second feature parameter;
generating the identification sample set from a plurality of the multi-dimensional feature vectors.
7. An apparatus comprising a memory for storing a program and a processor for performing the method of any of claims 1-6.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the method according to any of claims 1-6.
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 CN109284706A (en) | 2019-01-29 |
| CN109284706B true 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) |
Families Citing this family (10)
| 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 |
| CN112183218A (en) * | 2020-09-03 | 2021-01-05 | 深圳前海微众银行股份有限公司 | Method and device for monitoring industrial production index |
| 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 |
| CN112883251B (en) * | 2021-01-09 | 2023-01-10 | 重庆市农业科学院 | Agricultural auxiliary system based on multi-satellite combination |
| 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 |
| 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 |
| 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 |
Citations (9)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10346446B2 (en) * | 2015-11-02 | 2019-07-09 | Radiant Geospatial Solutions Llc | System and method for aggregating multi-source data and identifying geographic areas for data acquisition |
-
2018
- 2018-09-12 CN CN201811059933.2A patent/CN109284706B/en active Active
Patent Citations (9)
| 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 |
| 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 (4)
| Title |
|---|
| Views on Chinese remote sensing development;Yin, Q et al.;《JOURNAL OF INFRARED AND MILLIMETER WAVES》;第26卷(第3期);第225-231页 * |
| 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;白永亮 等,;《中国地质大学学报（社会科学版）》;第16卷(第3期);第63-72页 * |
| 胡昊等.新兴信息技术在大气环境治理中的研究与应用.中国环境科学出版社,2014,第80页，第82-83页，第86-89页，图7-11，图7-14. * |
| 黄祚继等.多源遥感数据目标地物的分类与优化.中国科学技术大学出版社,2017,第25页，第29页，第31页，第33页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109284706A (en) | 2019-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284706B (en) | Hot spot grid industrial aggregation area identification method based on multi-source satellite remote sensing data | |
| Liu et al. | Object-based shadow extraction and correction of high-resolution optical satellite images | |
| Jiang et al. | Advancing opportunistic sensing in hydrology: A novel approach to measuring rainfall with ordinary surveillance cameras | |
| CN109101955A (en) | Industrial heat anomaly area recognizing method based on Multi-sensor satellite remote sensing | |
| Dihkan et al. | Evaluation of surface urban heat island (SUHI) effect on coastal zone: The case of Istanbul Megacity | |
| CN111598098A (en) | Water gauge water line detection and effectiveness identification method based on full convolution neural network | |
| Chen et al. | Extraction of bridges over water from high-resolution optical remote-sensing images based on mathematical morphology | |
| CN114898097B (en) | Image recognition method and system | |
| Grigillo et al. | Automated building extraction from IKONOS images in suburban areas | |
| Akshay et al. | Satellite image classification for detecting unused landscape using CNN | |
| CN113887472A (en) | Remote sensing image cloud detection method based on cascade color and texture feature attention | |
| Al-Lashi et al. | Automated processing of oceanic bubble images for measuring bubble size distributions underneath breaking waves | |
| CN110569733B (en) | Lake long time sequence continuous water area change reconstruction method based on remote sensing big data platform | |
| Khatriker et al. | Building footprint extraction from high resolution satellite imagery using segmentation | |
| Mostafa et al. | Corresponding regions for shadow restoration in satellite high-resolution images | |
| Mohamed et al. | Change detection techniques using optical remote sensing: a survey | |
| Li et al. | Hybrid cloud detection algorithm based on intelligent scene recognition | |
| CN112946643B (en) | Offshore wind power extraction method and system based on time sequence radar remote sensing | |
| Marchesoni-Acland et al. | Deep learning methods for intra-day cloudiness prediction using geostationary satellite images in a solar forecasting framework | |
| CN110175638B (en) | Raise dust source monitoring method | |
| CN112036246B (en) | Construction method of remote sensing image classification model, remote sensing image classification method and system | |
| Subhashini et al. | A review on road extraction based on neural and non-neural networks | |
| Tan et al. | Automatic extraction of built-up area based on deep convolution neural network | |
| CN108563674B (en) | Sea area geographic element measurement method, system and device based on RS and GIS | |
| Bouchahma et al. | Optical-flow-based approach for the detection of shoreline changes using remote sensing data |
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 |