CN116051398B - Construction method and device for multi-source multi-mode remote sensing data investigation monitoring feature library - Google Patents
Construction method and device for multi-source multi-mode remote sensing data investigation monitoring feature library Download PDFInfo
- Publication number
- CN116051398B CN116051398B CN202211476611.4A CN202211476611A CN116051398B CN 116051398 B CN116051398 B CN 116051398B CN 202211476611 A CN202211476611 A CN 202211476611A CN 116051398 B CN116051398 B CN 116051398B
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- image
- feature library
- features
- source
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000010276 construction Methods 0.000 title claims description 19
- 238000011835 investigation Methods 0.000 title claims description 11
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 27
- 230000003287 optical effect Effects 0.000 claims abstract description 13
- 238000012937 correction Methods 0.000 claims description 18
- 230000005855 radiation Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 15
- 230000003595 spectral effect Effects 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000010287 polarization Effects 0.000 claims description 7
- 208000027066 STING-associated vasculopathy with onset in infancy Diseases 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000000443 aerosol Substances 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a device for constructing a survey and monitoring feature library for multi-source multi-mode remote sensing data. The invention is suitable for multi-source multi-mode data, integrates more than ten sensors related to optical remote sensing and radar remote sensing data, and uniformly processes and utilizes the data; meanwhile, relevant characteristic index calculation of each sensor is collected for autonomous selection, so that the comprehensiveness of a characteristic library is ensured; the invention builds the multi-source multi-mode data to build the monitoring feature library, which makes the build process very convenient and avoids the error and complexity generated in the process of cross-platform environment configuration and result integration.
Description
Technical Field
The invention relates to remote sensing data processing, in particular to a method and a device for constructing a survey monitoring feature library for multi-source multi-mode remote sensing data.
Background
The remote sensing data is very important, and is an important foundation support for different fields of services such as forestry, agriculture, water resources, construction, traffic, urban planning, disaster emergency and the like. However, the remote sensing data is complicated in category, and the multi-source remote sensing data is difficult to use due to the wide variety of different types of re-circulation periods, image conditions and the like. In particular to the field of feature use and feature library construction, the current use and processing of remote sensing data depend on mature software, the processing of the remote sensing images by the software is too scattered, the consistent generation of the feature library cannot be carried out on the images in a targeted manner, the features of the multi-source data cannot be cooperatively applied under a unified framework due to the influence of different processes on the generation of the feature library, and a process method capable of providing a data basis for the collaborative inversion of the multi-source sensor data under a unified environment is designed.
In recent years, some students further acquire quantitative relations among multi-source remote sensing parameters through complex mathematical models, so that mixed use of multi-source remote sensing data in remote sensing earth observation is possible, but different remote sensing data comprise different optical remote sensing images and radar image modes, and the same-mode data such as the optical remote sensing images also comprise a plurality of sensors such as Sentinel-2 and Landsat8, when the use of the multi-source multi-mode data is involved, feature extraction of the different data often comprises different processing flows, software operation platforms and calculation methods required for completing the flows are different, the calculable features are limited, remote sensing image information cannot be fully mined, and the final feature extraction results cannot be compared under a unified frame.
Disclosure of Invention
The invention aims at solving the disadvantages of different processing flows and multiple platforms of the existing multi-source multi-mode remote sensing data feature construction, and provides a remote sensing data feature library construction method integrating sensors and platforms.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
in a first aspect, the present invention provides a method for constructing a survey monitoring feature library for multi-source and multi-mode remote sensing data, the method comprising:
performing radiation correction on an original multi-source multi-mode remote sensing image to obtain a corrected multi-source multi-mode remote sensing image, wherein the multi-source multi-mode remote sensing image comprises an optical remote sensing image and a radar polarization image;
constructing spectral features based on the optical remote sensing image after radiation correction;
constructing radar features based on the radar polarization image after radiation correction;
constructing texture features based on the multi-source multi-mode remote sensing image after radiation correction;
forming an image feature library based on the constructed spectrum features, radar features and texture features;
cutting an image feature library by using a sample vector range to obtain an image monitoring sample feature set, and carrying out statistical calculation on pixel values in the sample feature set to obtain corresponding sample statistical features; the sample feature set and the sample statistical features together form a monitoring sample feature library.
The image feature library and the monitoring sample feature library together form a final investigation monitoring feature library for image feature analysis and sample feature analysis.
Further, the spectral features include NDVI, NDWI, SAVI.
Further, the radar features include including a radar vegetation index RVI dp 。
Further, the spectrum characteristics NDVI, NDWI, SAVI are calculated as follows:
wherein NIR is near infrared band, RED is RED band, and GREEN is GREEN band.
Further, the radar vegetation index RVI dp The calculation mode of (2) is as follows:
wherein ,to polarize the cross-polarized backscatter intensity in SAR, and (2)>Is the co-polarized backscatter intensity in polarized SAR.
Further, the calculation of the texture feature uses a gray level co-occurrence matrix, which is defined as taking any point (x, y) in the image (n×n) and the other point (x+a, y+b) deviated from the point, setting the gray level value of the point pair as (g 1, g 2), making the point (x, y) move on the whole image, obtaining various (g 1, g 2) values, setting the number of gray level values as k, and setting the combination of (g 1, g 2) to share k square; counting the occurrence times of each (g 1, g 2) value for the whole picture, then arranging the values into a square matrix, and normalizing the occurrence times into occurrence probability P (g 1, g 2) by the total occurrence times of the (g 1, g 2);
the calculation involves texture features as follows:
Energy＝∑ i,j g(i,j) 2
wherein g (i, j) is the frequency of the ith row and j columns in the gray level co-occurrence matrix, namely the frequency of the pairing of the pixel values i and j in the direction, mu is the mean value, and sigma is the standard deviation.
Further, the calculation formula of the sample statistical feature is as follows:
in the above formula: mu is the mean value, sigma is the standard deviation, E is the desired operator, mu 3 Is the third central moment, k t Is the accumulated quantity of the order t.
Further, the original multi-source multi-mode remote sensing image is subjected to radiation correction by using a 6s model in the atmospheric radiation transmission model.
In a second aspect, the present invention provides a device for constructing a survey monitoring feature library for multi-source and multi-modal remote sensing data, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any of the methods described above when executing the computer program.
In a third aspect, the present invention provides a computer readable storage medium storing a computer program which when executed by a processor performs the steps of any of the methods described above.
Compared with the prior art, the invention has the beneficial effects that:
the construction of the existing remote sensing data investigation monitoring feature library is based on single data, or the feature library is constructed by simply superposing wave band information of different images. The invention is suitable for multi-source multi-mode data, integrates more than ten sensors related to optical remote sensing and radar remote sensing data, and uniformly processes and utilizes the data; meanwhile, relevant characteristic index calculation of each sensor is collected for autonomous selection, so that the comprehensiveness of a characteristic library is ensured; the invention builds the multi-source multi-mode data to build the monitoring feature library, which makes the build process very convenient and avoids the error and complexity generated in the process of cross-platform environment configuration and result integration.
Drawings
Fig. 1 is a flowchart of a method for constructing a survey monitoring feature library for multi-source multi-mode remote sensing data provided in embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of a gray level co-occurrence matrix p calculation method;
fig. 3 is a software operation interface diagram of the method for constructing the survey monitoring feature library for multi-source and multi-mode remote sensing data provided in embodiment 1 of the present invention;
fig. 4 is a schematic diagram of the construction device of the investigation monitoring feature library for multi-source multi-mode remote sensing data provided in embodiment 2 of the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
The multi-source multi-mode related to the invention is from the perspective of remote sensing data sources, namely the remote sensing data sources comprise platforms such as Sentinel-2 and Landsat series which are both optical images, and the multi-mode data are different from the sensors, and comprise not only optical remote sensing but also radar remote sensing images.
Example 1:
referring to fig. 1, the method for constructing a survey monitoring feature library for multi-source multi-mode remote sensing data provided in this embodiment includes the following steps:
and the original multi-source multi-mode remote sensing image is subjected to radiation correction, so that the accurate image characteristics can be extracted later. The method comprises the steps of performing corresponding image atmosphere correction pretreatment on an applicable original multispectral remote sensing image by using a 6s model in an atmosphere transmission model to obtain a corrected multisource multimode remote sensing image, wherein the corrected multisource multimode remote sensing image comprises a multisource optical remote sensing image and various radar image data.
The atmospheric radiation transmission model is a model serving remote sensing atmospheric correction, and the 6S model used in this embodiment is an excellent representative thereof. The 6S model uses a state of the art and successive scatter SOS (successive orders of scattering) algorithm to calculate scatter and absorption, taking into account the non-lambertian nature of the earth' S surface. When the model is used, the original image is subjected to atmospheric radiation correction according to parameters such as geometric conditions of the image, an atmospheric mode, an aerosol mode, a wavelength range, surface reflectivity and the like.
And constructing spectral features based on the optical remote sensing image after the radiation correction. For different spectral images, corresponding computable spectral feature indexes are adaptively enumerated according to the specific wave bands of the spectral images for manual selection. The spectrum features can be freely combined and selected, then the selected features are calculated according to the pixel values of each wave band of the remote sensing image and a feature calculation formula, each feature is used as a new wave band of the image, and feature names are attached to wave band description information to show and distinguish, so that calculated spectrum features are obtained;
based on the radar polarization images after radiation correction, constructing radar features, and adaptively enumerating corresponding calculated radar feature indexes for manual selection according to polarization modes and polarization wave bands of different radar images. The radar characteristic indexes can be freely combined and selected, selected characteristics are calculated according to each polarized wave band value and a characteristic calculation formula of the remote sensing image, each characteristic is used as a new wave band of the image, and calculated radar characteristics are obtained;
based on the multi-source and multi-mode image (both optical and radar) after radiation correction, texture features are constructed, information such as a selected wave band, a pixel range, a direction, a step length and the like is designated for the selected image, and a texture feature analysis mode is selected to obtain corresponding texture features;
forming an image feature library based on the constructed spectrum features, radar features and texture features;
cutting an image feature library by using a sample vector range to obtain an image monitoring sample feature set, and carrying out statistical calculation on pixel values in the sample feature set to obtain corresponding sample statistical features; the sample feature set and the sample statistical features together form a monitoring sample feature library.
The image feature library and the monitoring sample feature library together form a final investigation monitoring feature library for image feature analysis and sample feature analysis.
In one embodiment, the spectral features include NDVI, NDWI, SAVI and other tens of spectral features, and the radar features include RVI dp And a plurality of texture features, namely tens of texture features, and more than hundred features in total. The spectral features NDVI, NDWI, SAVI are calculated as follows:
wherein NIR is near infrared band, RED is RED band, and GREEN is GREEN band.
Radar vegetation index RVI dp The calculation mode of (2) is as follows:
wherein ,to polarize the cross-polarized backscatter intensity in SAR, and (2)>Is the co-polarized backscatter intensity in polarized SAR.
The texture feature is calculated using a gray level co-occurrence matrix defined by taking any point (x, y) in the image (n×n) and the other point (x+a, y+b) offset from it, and setting the gray level value of the point pair to (g 1, g 2). When the points (x, y) are moved over the entire screen, various values (g 1, g 2) are obtained, and when the number of gray scale levels is k, the combination of the values (g 1, g 2) has k square types; counting the occurrence times of each (g 1, g 2) value for the whole picture, then arranging the values into a square matrix, and normalizing the occurrence times into occurrence probability P (g 1, g 2) by the total occurrence times of the (g 1, g 2);
the calculation involves texture features as follows:
Energy＝∑ i,j g(i,j) 2
wherein g (i, j) is the frequency of the ith row and j columns in the gray level co-occurrence matrix, namely the frequency of the pairing of the pixel values i and j in the direction, mu is the mean value, and sigma is the standard deviation.
Thus, the texture features can be accurately and efficiently calculated by the calculation mode.
The method includes the steps of obtaining sample statistical characteristics, namely counting sample pixel values, obtaining sample characteristic information formed by various integral statistical characteristics of sample units such as skew values, kurtosis peaks and the like, describing the samples to obtain the sample statistical characteristics, and forming a monitoring sample characteristic library together with an extracted sample characteristic set. Wherein the statistical characteristic part has the following calculation formula:
in the above formula: mu is the mean value, sigma is the standard deviation, E is the desired operator, mu 3 Is the third central moment, k t Is the accumulated quantity of the order t.
The following equation shows the positive and negative value of the skewness with respect to the normal distribution.
In the above formula: mu (mu) 4 The fourth moment, σ, is the standard deviation.
The method is further described in connection with an application scenario example:
step 1: and acquiring original multispectral remote sensing images, such as Sentinel-2L1C data, from related websites, and performing corresponding atmosphere correction pretreatment of corresponding sensors to obtain L1A products.
Step 2: and providing available calculation features of Sentinel-2, so as to select the required spectral features and texture features, and obtaining the calculation features by simply setting parameters or default parameters (calculation formulas of the corresponding features), wherein the calculation features of the images form part of a feature library for investigation and monitoring.
Step 3: based on the vector range of the sample, outputting the original image with each feature as an image sample with a clipping range of each feature, and carrying out statistical feature calculation on pixel features such as NDVI and the like in each sample unit to obtain sample feature information such as skewness, kurtosis and the like of the features in the sample unit, and forming a final investigation and monitoring feature library together with the features of the whole image.
In particular, the software program operation interface is shown in fig. 3.
Example 2:
referring to fig. 4, the device for constructing a survey feature library for multi-source multi-mode remote sensing data according to the present embodiment includes a processor 41, a memory 42, and a computer program 43 stored in the memory 42 and capable of running on the processor 41, for example, a survey feature library construction program for multi-source multi-mode remote sensing data. The processor 41 implements the steps of embodiment 1 described above, such as the steps shown in fig. 1, when executing the computer program 43.
Illustratively, the computer program 43 may be partitioned into one or more modules/units that are stored in the memory 42 and executed by the processor 41 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program 43 in the multi-source multi-modal remote sensing data oriented survey monitoring feature library construction apparatus. For example, the computer program 43 may be divided into a conversion module and a matching operation module.
The survey and monitoring feature library construction device for the multi-source multi-mode remote sensing data can be computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud server. The device for constructing the investigation and monitoring feature library for the multi-source multi-mode remote sensing data can comprise, but is not limited to, a processor 41 and a memory 42. It will be appreciated by those skilled in the art that fig. 4 is merely an example of a multi-source multi-mode remote sensing data oriented survey feature library construction apparatus, and does not constitute a limitation of the multi-source multi-mode remote sensing data oriented survey feature library construction apparatus, and may include more or less components than illustrated, or may combine certain components, or different components, for example, the multi-source multi-mode remote sensing data oriented survey feature library construction apparatus may further include an input/output device, a network access device, a bus, and the like.
The processor 41 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (FieldProgrammable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 42 may be an internal storage element of the survey feature library construction apparatus for multi-source multi-mode remote sensing data, such as a hard disk or a memory of the survey feature library construction apparatus for multi-source multi-mode remote sensing data. The memory 42 may also be an external storage device of the survey and monitoring feature library construction apparatus for multi-source and multi-mode remote sensing data, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like. Further, the memory 42 may further include an internal storage unit and an external storage device of the survey monitoring feature library construction apparatus for multi-source multi-mode remote sensing data. The memory 42 is used for storing the computer program and other programs and data required by the survey monitoring feature library construction device for multi-source multi-mode remote sensing data. The memory 42 may also be used to temporarily store data that has been output or is to be output.
Example 3:
the present embodiment provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method described in embodiment 1.
The computer readable medium can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer readable medium may even be paper or another suitable medium upon which the program is printed, such as by optically scanning the paper or other medium, then editing, interpreting, or otherwise processing as necessary, and electronically obtaining the program, which is then stored in a computer memory.
The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement the same, and are not intended to limit the scope of the present invention. All equivalent changes or modifications made in accordance with the essence of the present invention are intended to be included within the scope of the present invention.
Claims (5)
1. A method for constructing a survey monitoring feature library for multi-source and multi-mode remote sensing data is characterized by comprising the following steps:
performing radiation correction on an original multi-source multi-mode remote sensing image to obtain a corrected multi-source multi-mode remote sensing image, wherein the multi-source multi-mode remote sensing image comprises an optical remote sensing image and a radar polarization image;
constructing spectral features based on the optical remote sensing image after radiation correction;
constructing radar features based on the radar polarization image after radiation correction;
constructing texture features based on the multi-source multi-mode remote sensing image after radiation correction;
forming an image feature library based on the constructed spectral features, radar features and texture features;
cutting an image feature library by using a sample vector range to obtain an image monitoring sample feature set, and carrying out statistical calculation on pixel values in the sample feature set to obtain corresponding sample statistical features; the sample feature set and the sample statistical features together form a monitoring sample feature library;
the image feature library and the monitoring sample feature library together form a final investigation monitoring feature library for image feature analysis and sample feature analysis;
the calculation of the texture features uses a gray level co-occurrence matrix, which is defined as taking any point (x, y) in an image (N multiplied by N) and the other point (x+a, y+b) deviating from the point, setting the gray level value of the point pair as (g 1, g 2), enabling the point (x, y) to move on the whole picture, obtaining various (g 1, g 2) values, setting the number of the gray level values as k, and enabling the combination of the (g 1, g 2) to share the square of k; counting the occurrence times of each (g 1, g 2) value for the whole picture, then arranging the values into a square matrix, and normalizing the occurrence times into occurrence probability P (g 1, g 2) by the total occurrence times of the (g 1, g 2);
the calculation involves texture features as follows:
Energy＝∑ i,j g(i,j) 2
wherein g (i, j) is the frequency of the ith row and j columns in the gray level co-occurrence matrix, namely the frequency of pairing the pixel values i and j in the direction, mu is the mean value, and sigma is the standard deviation;
performing radiation correction on the original multi-source multi-mode remote sensing image by using a 6s model in the atmospheric radiation transmission model;
the radar features include a radar vegetation index RVI dp The method comprises the steps of carrying out a first treatment on the surface of the The radar vegetation index RVI dp The calculation mode of (2) is as follows:
wherein ,to polarize the cross-polarized backscatter intensity in SAR, and (2)>The same polarized backward scattering intensity in polarized SAR;
the calculation formula of the sample statistical characteristics is as follows:
in the above formula: mu is the mean value, sigma is the standard deviation, E is the desired operator, mu 3 Is the third central moment, k t Is the accumulated quantity of the order t.
2. The method of claim 1, wherein the spectral features comprise NDVI, NDWI, SAVI.
3. The method for constructing the investigation and monitoring feature library for multi-source and multi-mode remote sensing data according to claim 2, wherein the calculation modes of the spectrum features NDVI, NDWI, SAVI are as follows:
wherein NIR is near infrared band, RED is RED band, and GREEN is GREEN band.
4. A multi-source multi-modal remote sensing data oriented survey monitoring feature library construction apparatus comprising a memory, a processor and a computer program stored in said memory and executable on said processor, wherein said processor when executing said computer program implements the steps of the method according to any one of claims 1 to 3.
5. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211476611.4A CN116051398B (en) | 2022-11-23 | 2022-11-23 | Construction method and device for multi-source multi-mode remote sensing data investigation monitoring feature library |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211476611.4A CN116051398B (en) | 2022-11-23 | 2022-11-23 | Construction method and device for multi-source multi-mode remote sensing data investigation monitoring feature library |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116051398A CN116051398A (en) | 2023-05-02 |
| CN116051398B true CN116051398B (en) | 2023-09-22 |
Family
ID=86128424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211476611.4A Active CN116051398B (en) | 2022-11-23 | 2022-11-23 | Construction method and device for multi-source multi-mode remote sensing data investigation monitoring feature library |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116051398B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108257123A (en) * | 2018-01-11 | 2018-07-06 | 西京学院 | Multiband radar image change detection method based on higher order statistical theory |
| CN112183209A (en) * | 2020-08-27 | 2021-01-05 | 中国农业大学 | Regional crop classification method and system based on multi-dimensional feature fusion |
| CN112395914A (en) * | 2019-08-15 | 2021-02-23 | 中国科学院遥感与数字地球研究所 | Method for identifying land parcel crops by fusing remote sensing image time sequence and textural features |
| CN114594476A (en) * | 2022-03-15 | 2022-06-07 | 中国自然资源航空物探遥感中心 | Pi/4 simple-polarization synthetic aperture radar building area extraction method |
| CN115170979A (en) * | 2022-06-30 | 2022-10-11 | 国家能源投资集团有限责任公司 | Mining area fine land classification method based on multi-source data fusion |
-
2022
- 2022-11-23 CN CN202211476611.4A patent/CN116051398B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108257123A (en) * | 2018-01-11 | 2018-07-06 | 西京学院 | Multiband radar image change detection method based on higher order statistical theory |
| CN112395914A (en) * | 2019-08-15 | 2021-02-23 | 中国科学院遥感与数字地球研究所 | Method for identifying land parcel crops by fusing remote sensing image time sequence and textural features |
| CN112183209A (en) * | 2020-08-27 | 2021-01-05 | 中国农业大学 | Regional crop classification method and system based on multi-dimensional feature fusion |
| CN114594476A (en) * | 2022-03-15 | 2022-06-07 | 中国自然资源航空物探遥感中心 | Pi/4 simple-polarization synthetic aperture radar building area extraction method |
| CN115170979A (en) * | 2022-06-30 | 2022-10-11 | 国家能源投资集团有限责任公司 | Mining area fine land classification method based on multi-source data fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116051398A (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Seo et al. | Fusion of SAR and multispectral images using random forest regression for change detection | |
| Rivera et al. | On the semi-automatic retrieval of biophysical parameters based on spectral index optimization | |
| Waller et al. | Diagnosing horizontal and inter-channel observation error correlations for SEVIRI observations using observation-minus-background and observation-minus-analysis statistics | |
| Rivera et al. | Multiple cost functions and regularization options for improved retrieval of leaf chlorophyll content and LAI through inversion of the PROSAIL model | |
| BR112021015232A2 (en) | SHADOW AND CLOUD MASKING FOR REMOTE SENSING IMAGES IN AGRICULTURE APPLICATIONS USING MULTI-LAYER PERCEPTRON | |
| Eckardt et al. | Removal of optically thick clouds from multi-spectral satellite images using multi-frequency SAR data | |
| Polychronaki et al. | Evaluation of ALOS PALSAR imagery for burned area mapping in Greece using object-based classification | |
| Xu et al. | A correlated multi-pixel inversion approach for aerosol remote sensing | |
| Hasanlou et al. | Earthquake damage region detection by multitemporal coherence map analysis of radar and multispectral imagery | |
| Sun et al. | Improving the retrieval of crop canopy chlorophyll content using vegetation index combinations | |
| Ma et al. | Uncertainty analysis for topographic correction of hyperspectral remote sensing images | |
| Sabater et al. | Impact of atmospheric inversion effects on solar-induced chlorophyll fluorescence: Exploitation of the apparent reflectance as a quality indicator | |
| CN107680081B (en) | Hyperspectral image unmixing method based on convolutional neural network | |
| Annala et al. | Chlorophyll concentration retrieval by training convolutional neural network for stochastic model of leaf optical properties (SLOP) inversion | |
| Zheng et al. | Sparse unmixing for hyperspectral image with nonlocal low-rank prior | |
| Kazakeviciute-Januskeviciene et al. | Assessment of the segmentation of RGB remote sensing images: a subjective approach | |
| Hua et al. | Multi-Model Estimation of Forest Canopy Closure by Using Red Edge Bands Based on Sentinel-2 Images | |
| Banić et al. | Green stability assumption: Unsupervised learning for statistics-based illumination estimation | |
| Gao et al. | Smartphone–Camera–Based Water Reflectance Measurement and Typical Water Quality Parameter Inversion | |
| Chen et al. | Evaluation of the accuracy of the field quadrat survey of alpine grassland fractional vegetation cover based on the satellite remote sensing pixel scale | |
| Hu et al. | A deconvolution technology of microwave radiometer data using convolutional neural networks | |
| Manohar Kumar et al. | Benchmark studies on pixel-level spectral unmixing of multi-resolution hyperspectral imagery | |
| Amziane et al. | Reflectance estimation from multispectral linescan acquisitions under varying illumination—application to outdoor weed identification | |
| US11610284B2 (en) | Enhancing generative adversarial networks using combined inputs | |
| Brook et al. | Supervised vicarious calibration (SVC) of multi-source hyperspectral 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |