CN110490061A - A kind of uncertainties model and measure of characteristics of remote sensing image - Google Patents
A kind of uncertainties model and measure of characteristics of remote sensing image Download PDFInfo
- Publication number
- CN110490061A CN110490061A CN201910624094.2A CN201910624094A CN110490061A CN 110490061 A CN110490061 A CN 110490061A CN 201910624094 A CN201910624094 A CN 201910624094A CN 110490061 A CN110490061 A CN 110490061A
- Authority
- CN
- China
- Prior art keywords
- uncertainty
- feature
- image
- pixel
- remote sensing
- 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 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 238000000605 extraction Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of uncertainties model of characteristics of remote sensing image and measures.This method is mainly made of characteristics of remote sensing image in the uncertainties model in geographical space domain and the uncertainties model two parts in feature space domain, then geographical space uncertainty is weighted with feature space uncertainty and is combined, obtained a comprehensive feature uncertainty index FUI (Feature Uncertainty Index) and carry out feature uncertainty that is more acurrate, comprehensively measuring remote sensing image.The present invention considers different manifestations feature of the image feature uncertainty under different perspectives, can provide the feature uncertainty quantized result of entire image pixel-by-pixel, and can be minimized manual intervention.Its accuracy and adaptive degree are high, and computational efficiency is fast, strong operability, it is easy to accomplish and entire model scalability is strong.Uncertain quantized result has very high instruction ability to error in classification, and therefore, the present invention has very high practical value.
Description
Technical Field
The invention belongs to the field of remote sensing image processing and statistical modeling, and particularly relates to an uncertainty modeling and measuring method for remote sensing image characteristics.
Background
The remote sensing image classification product has very important application value in aspects of natural disaster monitoring, environmental protection, city planning, decision making and the like. However, the current remote sensing image classification technology still cannot achieve 100% accuracy or a reliable enough and completely convincing precision level. The root cause of errors in the image classification result and low reliability of the classification result is that uncertainty exists in each link of remote sensing image classification, and the uncertainty can be continuously spread and accumulated in the classification process, so that the precision and reliability of the classification result are finally influenced.
The existing method for quantifying the classification uncertainty of the remote sensing image mainly evaluates the uncertainty of a classification result so as to further refine the classification result. The method only focuses on the uncertainty of the classification result, ignores the uncertainty in the image classification process, and the uncertainty in the classification process is the source of the uncertainty in the classification result, so the uncertainty quantification result of the existing method has no obvious improvement effect on the classification result. The feature extraction is one of the most critical links of image classification, and features constructed by the feature extraction are the basis and the premise of the image classification, so that the uncertainty of quantitatively describing the image features is very important for realizing reliable image classification.
Disclosure of Invention
The invention aims to provide an uncertainty modeling and measuring method for remote sensing image characteristics, aiming at the defects in the prior art.
The technical scheme adopted by the invention is as follows: an uncertainty modeling and measuring method for remote sensing image features comprises the following steps:
step 1, extracting the characteristics of an original remote sensing image, and setting the extracted characteristic dimension as n;
step 2, modeling and quantifying the uncertainty of the extracted image features from the perspective of the geospatial domain, the implementation of which comprises the following substeps:
step 2.1, calculating the uncertainty contained in each dimensional feature of the image according to the heterogeneity of the pixels in the image between the geographic space and the surrounding neighborhood pixels;
step 2.2, calculating the information entropy of each pixel in the image in each dimensional feature according to the magnitude of the overall spatial heterogeneity of the neighborhood where the pixel is located in the image;
step 2.3, taking the information entropy obtained in the step 2.2 as a weight, carrying out weighted summation on the uncertainty of each characteristic calculated in the step 2.1, and normalizing the result of the weighted summation to obtain an uncertainty description index of the image characteristic in the geographic space, namely a geographic space uncertainty GSU;
step 3, modeling and quantifying the uncertainty of the extracted image features from the perspective of the feature space domain, and the specific implementation thereof comprises the following substeps:
step 3.1, in the feature space, searching a plurality of points closest to each feature point for each feature point, and calculating the local point density of the target feature point according to the distance between the closest points and the target feature point;
step 3.2, carrying out normalization processing on the local point densities of all the points in the feature space to obtain an uncertainty description index, namely feature space uncertainty FSU, of the image features in the feature space;
and 4, carrying out weighted combination on the geographic space uncertainty GSU and the feature space uncertainty FSU by introducing a weight adjusting coefficient lambda to obtain a comprehensive feature uncertainty index FUI so as to more accurately and comprehensively measure the feature uncertainty of the remote sensing image.
Further, the specific implementation manner of step 2.1 is as follows,
for the nth dimension feature of the image, the j column pixel Pij of any ith row of the image, and the K x K neighborhood of the pixel Pij in the nth dimension feature is represented asUncertainty of its characteristicsThe calculation formula of (2) is as follows:
among them, the simplest is:
wherein the pixel Pxy is a neighborhoodAny x-th row and y-th column of pixels in,andvalues, w, representing the nth dimensional characteristics of the pixels Pij and Pxy, respectivelypxyThe weight of the influence of the pixel Pxy on the target pixel Pij is determined by the distance Pxy from the pixel Pij, and the larger the distance, the smaller the weight.
Further, the specific implementation manner of step 2.2 is as follows,
for the nth dimension feature of the image, let Pij be the pixel in the ith row and jth column of the image, and its K × K neighborhood is expressed asThe information entropy of the pixel PijThe calculation formula of (2) is as follows:
among them, the simplest is:
wherein the pixel Pxy is a neighborhoodAny x row and y column of pixels in,Andrepresenting the values of the nth dimensional features of the pixels Pij and Pxy, respectively.
Further, the weighted sum in step 2.3 is calculated as follows,
wherein,being the characteristic uncertainty of the pixel Pij,is the information entropy of the pixel Pij.
Further, the local point density Φ of the target feature point i in step 3.1iThe expression of (a) is:
Φi=f(dij,m) (7)
among them, the simplest is:
where m is the number of feature points, dijRepresenting the distance of the target feature point i from the neighboring point j.
Further, the expression of FUI in step 4 is:
FUI=(1-λ)·GSU+λ·FSU (9)
the GSU is the geospatial uncertainty, the FSU is the feature space uncertainty, and the lambda is a normal number between 0 and 1, and is used for adjusting the weight of the geospatial space and the feature space.
Further, the features extracted in step 1 include spectra, textures, shape features and spatial relationship features.
The invention has the advantages that:
(1) the invention considers the heterogeneity of the uncertainty contained in different characteristics of the image and treats them differently in the uncertainty quantization process, so as to obtain more accurate quantization result. The method provided by the invention adaptively determines the weights of different pixels in different characteristics by means of the information entropy, and can minimize manual intervention.
(2) The characteristic uncertainty quantification model simultaneously considers the uncertainty of the image characteristics in the geographic space domain and the uncertainty of the image characteristics in the characteristic space domain, and can measure the uncertainty of the image characteristics more comprehensively.
(3) The method provided by the invention has the advantages of high calculation efficiency, strong operability, easy realization and strong expandability of the whole model. Therefore, the invention has high practical value.
In a word, the method provided by the invention can effectively and comprehensively measure the uncertainty of the features extracted from the remote sensing image, provides a pixel-by-pixel feature uncertainty measurement result for the remote sensing image, and is beneficial to improving the accuracy and reliability of the image classification result. The method has high accuracy and self-adaptive degree, is easy to expand and has high practical value.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
In order to facilitate the understanding and implementation of the present invention for those of ordinary skill in the art, the present invention is further described in detail with reference to the accompanying drawings and examples, it is to be understood that the embodiments described herein are merely illustrative and explanatory of the present invention and are not restrictive thereof.
The features extracted from the remote sensing images contain uncertainties of different degrees, and the uncertainties are continuously propagated and accumulated in the image classification process, and finally the accuracy and reliability of the classification result are affected. Only by accurately and effectively modeling and measuring the uncertainty of the image characteristics, the image classification method can effectively control and restrict the image characteristics in the image classification process, and further improve the precision and reliability of the classification result. Therefore, the quantitative uncertainty of the image characteristic is important for the remote sensing image classification.
Referring to fig. 1, the method for modeling and measuring uncertainty of remote sensing image features provided by the invention comprises the following steps:
step 1: feature extraction is performed on the original remote sensing image by using an existing image feature extraction tool or algorithm (such as a GLCM extraction tool in the enii software, a feature extraction tool in the ecognion, and the like) (the extracted features include a spectrum, a texture, a shape feature, a spatial relationship feature, and the like). Let the feature dimension extracted be n. From a geospatial perspective, the n-dimensional feature extracted can be stacked layer-by-layer to form a "feature cube". From the viewpoint of the feature space, the n-dimensional features may constitute a feature space in an n-dimensional coordinate system. Pixels (or feature points) with different degrees of uncertainty have different performance characteristics at these two viewing angles.
Step 2: modeling and quantifying the uncertainty of the extracted image features from the perspective of the geospatial domain, the implementation of which comprises the following sub-steps:
step 2.1: in the geospatial domain, pixels with high uncertainty in the imagery tend to have high heterogeneity with its surrounding neighboring pixels. And calculating the uncertainty contained in each dimensional feature of the image according to the heterogeneity of the pixels between the geographic space and the surrounding neighborhood pixels. In calculating the uncertainty of each dimension feature of each pixel, the influence of surrounding neighborhood pixels on the target pixel should be considered. In the actual calculation process, each neighborhood pixel is given a weight with different size according to the distance between the neighborhood pixel and the target pixel (the weight is inversely proportional to the distance).
For the nth dimension feature of the image, the j column pixel Pij of any i row of the image (the neighborhood of K × K in the nth dimension feature of the pixel Pij is represented as) Characteristic uncertainty ofThe calculation formula of (2) is as follows:
among them, the simplest is:
wherein the pixel Pxy is a neighborhoodAny x-th row and y-th column of pixels in.Andrepresenting the values of the nth dimensional features of the pixels Pij and Pxy, respectively. w is apxyThe weight of the influence of the pixel Pxy on the target pixel Pij is determined by the distance Pxy from the pixel Pij, and the larger the distance, the smaller the weight. In addition, the relation of the formula (1) can be adaptively changed according to the characteristics of the image and the description method of the local heterogeneity of the image.
Step 2.2: the higher the spatial heterogeneity in the neighborhood of a pixel (the greater the degree of uncertainty in the pixel characteristics), the greater its entropy. Calculating the information entropy of each pixel in the image in each dimensional feature according to the magnitude of the overall spatial heterogeneity of the neighborhood where the pixel is located in the image;
for the nth dimension feature of the image, let Pij be the pixel in the ith row and jth column of the image, and its K × K neighborhood is expressed asThe information entropy of the pixel PijThe calculation formula of (2) is as follows:
among them, the simplest is:
wherein the pixel Pxy is a neighborhoodAny x-th row and y-th column of pixels in.Andrepresenting the values of the nth dimensional features of the pixels Pij and Pxy, respectively. In addition, the relationship of the formula (3) can be adaptively changed depending on the measurement method of the information entropy.
Step 2.3: taking the information entropy obtained by calculation in the step 2.2 as weight, and carrying out weighted summation on the uncertainty of each feature calculated in the step 2.1, wherein the expression is as follows:
and normalizing the result of the weighted summation to obtain the geographic space uncertainty GSU (geographic space uncertainty description indicator) of the image characteristics in the geographic space.
And step 3: modeling and quantifying the uncertainty of the extracted image features from the perspective of the feature space domain, the implementation of which comprises the following substeps:
step 3.1: in the feature space, m feature points closest to each feature point i are found for each feature point i, and the distance d between the closest feature points and the target feature point i is used as the basisij(j=1,2,… …, m), calculating the local point density phi of the target characteristic point ii. The expression is as follows:
Φi=f(dij,m) (7)
among them, the simplest is:
the relationship of the formula (7) can be adaptively changed according to the description model of the point distribution density in the feature space of the image.
Step 3.2: the local point density phi of all points in the feature space calculated in step 3.1 is comparediAnd carrying out normalization processing to obtain an uncertainty description index of the image features in the feature space, namely the feature space uncertainty FSU.
And 4, step 4: by introducing a weight adjusting coefficient lambda, the geographic space uncertainty GSU and the feature space uncertainty FSU are subjected to weighted combination to obtain a comprehensive feature uncertainty index FUI, so that the feature uncertainty of the remote sensing image can be measured more accurately and comprehensively. The expression is as follows:
FUI=(1-λ)·GSU+λ·FSU (9)
wherein λ is a normal number between 0 and 1, and is used for adjusting the weight of the geographic space and the feature space.
The invention considers the heterogeneity of the characteristics of different pixels in the image on the geographic space and the density difference of the characteristics distributed in the characteristic space, models and quantifies the uncertainty of the image characteristics from two different angles of the geographic space domain and the characteristic space domain, and finally performs weighted integration on the two angles to obtain a comprehensive characteristic uncertainty index FUI which can more effectively and comprehensively measure the characteristic uncertainty of the remote sensing image, thereby being beneficial to the improvement of the accuracy and the reliability of the image classification result. The method has the advantages of high accuracy, strong operability, high calculation efficiency, strong expandability of the whole model and high application value.
It should be understood that parts of the specification not set forth in detail are well within the prior art.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (7)
1. An uncertainty modeling and measuring method for remote sensing image features is characterized by comprising the following steps:
step 1, extracting the characteristics of an original remote sensing image, and setting the extracted characteristic dimension as n;
step 2, modeling and quantifying the uncertainty of the extracted image features from the perspective of the geospatial domain, the implementation of which comprises the following substeps:
step 2.1, calculating the uncertainty contained in each dimensional feature of the image according to the heterogeneity of the pixels in the image between the geographic space and the surrounding neighborhood pixels;
step 2.2, calculating the information entropy of each pixel in the image in each dimensional feature according to the magnitude of the overall spatial heterogeneity of the neighborhood where the pixel is located in the image;
step 2.3, taking the information entropy obtained in the step 2.2 as a weight, carrying out weighted summation on the uncertainty of each characteristic calculated in the step 2.1, and normalizing the result of the weighted summation to obtain an uncertainty description index of the image characteristic in the geographic space, namely a geographic space uncertainty GSU;
step 3, modeling and quantifying the uncertainty of the extracted image features from the perspective of the feature space domain, and the specific implementation thereof comprises the following substeps:
step 3.1, in the feature space, searching a plurality of points closest to each feature point for each feature point, and calculating the local point density of the target feature point according to the distance between the closest points and the target feature point;
step 3.2, carrying out normalization processing on the local point densities of all the points in the feature space to obtain an uncertainty description index, namely feature space uncertainty FSU, of the image features in the feature space;
and 4, carrying out weighted combination on the geographic space uncertainty GSU and the feature space uncertainty FSU by introducing a weight adjusting coefficient lambda to obtain a comprehensive feature uncertainty index FUI so as to more accurately and comprehensively measure the feature uncertainty of the remote sensing image.
2. The method for modeling and measuring the uncertainty of the characteristics of the remote sensing image according to claim 1, characterized in that: the specific implementation of step 2.1 is as follows,
for the nth dimension feature of the image, the j column pixel Pij of any ith row of the image, and the K x K neighborhood of the pixel Pij in the nth dimension feature is represented asUncertainty of its characteristicsThe calculation formula of (2) is as follows:
among them, the simplest is:
wherein the pixel Pxy is a neighborhoodAny x-th row and y-th column of pixels in,andrespectively representing the nth dimension of the pixels Pij and PxyValue of sign, wpxyThe weight of the influence of the pixel Pxy on the target pixel Pij is determined by the distance Pxy from the pixel Pij, and the larger the distance, the smaller the weight.
3. The method for modeling and measuring the uncertainty of the characteristics of the remote sensing image according to claim 1, characterized in that: the specific implementation of step 2.2 is as follows,
for the nth dimension feature of the image, let Pij be the pixel in the ith row and jth column of the image, and its K × K neighborhood is expressed asThe information entropy of the pixel PijThe calculation formula of (2) is as follows:
among them, the simplest is:
wherein the pixel Pxy is a neighborhoodAny x-th row and y-th column of pixels in,andrepresenting the values of the nth dimensional features of the pixels Pij and Pxy, respectively.
4. The method for modeling and measuring the uncertainty of the characteristics of the remote sensing image according to claims 2 and 3, characterized in that: the weighted sum in step 2.3 is calculated as follows,
wherein,being the characteristic uncertainty of the pixel Pij,is the information entropy of the pixel Pij.
5. The method for modeling and measuring the uncertainty of the characteristics of the remote sensing image according to claim 1, characterized in that: local point density phi of target feature point i in step 3.1iThe expression of (a) is:
Φi=f(dij,m) (7)
among them, the simplest is:
where m is the number of feature points, dijRepresenting the distance of the target feature point i from the neighboring point j.
6. The method for modeling and measuring the uncertainty of the characteristics of the remote sensing image according to claim 1, characterized in that: the expression of FUI in step 4 is:
FUI=(1-λ)·GSU+λ·FSU (9)
the GSU is the geospatial uncertainty, the FSU is the feature space uncertainty, and the lambda is a normal number between 0 and 1, and is used for adjusting the weight of the geospatial space and the feature space.
7. The method for modeling and measuring the uncertainty of the characteristics of the remote sensing image according to claim 1, characterized in that: the features extracted in step 1 include spectra, textures, shape features and spatial relationship features.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910624094.2A CN110490061B (en) | 2019-07-11 | 2019-07-11 | Uncertainty modeling and measuring method for remote sensing image characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910624094.2A CN110490061B (en) | 2019-07-11 | 2019-07-11 | Uncertainty modeling and measuring method for remote sensing image characteristics |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110490061A true CN110490061A (en) | 2019-11-22 |
CN110490061B CN110490061B (en) | 2021-10-22 |
Family
ID=68545969
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910624094.2A Expired - Fee Related CN110490061B (en) | 2019-07-11 | 2019-07-11 | Uncertainty modeling and measuring method for remote sensing image characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110490061B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111595791A (en) * | 2020-06-04 | 2020-08-28 | 首都师范大学 | Inland water body FUI water color index extraction method based on hyperspectral data correction |
CN113326759A (en) * | 2021-05-26 | 2021-08-31 | 中国地质大学(武汉) | Uncertainty estimation method for remote sensing image building identification model |
CN115170179A (en) * | 2022-06-30 | 2022-10-11 | 中国科学院地理科学与资源研究所 | Trade policy uncertainty index determination method, device, equipment and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739396A (en) * | 2008-11-14 | 2010-06-16 | 电子科技大学 | Uncertainty spatial data mining-based regional metallogenic prediction method |
CN105260738A (en) * | 2015-09-15 | 2016-01-20 | 武汉大学 | Method and system for detecting change of high-resolution remote sensing image based on active learning |
CN105956612A (en) * | 2016-04-25 | 2016-09-21 | 西安电子科技大学 | Hyperspectral image classification method based on active learning and semi-supervised learning |
WO2017142788A1 (en) * | 2016-02-15 | 2017-08-24 | Pictometry International Corp. | Automated system and methodology for feature extraction |
CN109299668A (en) * | 2018-08-30 | 2019-02-01 | 中国科学院遥感与数字地球研究所 | A kind of hyperspectral image classification method based on Active Learning and clustering |
-
2019
- 2019-07-11 CN CN201910624094.2A patent/CN110490061B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739396A (en) * | 2008-11-14 | 2010-06-16 | 电子科技大学 | Uncertainty spatial data mining-based regional metallogenic prediction method |
CN105260738A (en) * | 2015-09-15 | 2016-01-20 | 武汉大学 | Method and system for detecting change of high-resolution remote sensing image based on active learning |
WO2017142788A1 (en) * | 2016-02-15 | 2017-08-24 | Pictometry International Corp. | Automated system and methodology for feature extraction |
CN105956612A (en) * | 2016-04-25 | 2016-09-21 | 西安电子科技大学 | Hyperspectral image classification method based on active learning and semi-supervised learning |
CN109299668A (en) * | 2018-08-30 | 2019-02-01 | 中国科学院遥感与数字地球研究所 | A kind of hyperspectral image classification method based on Active Learning and clustering |
Non-Patent Citations (2)
Title |
---|
LIAN-ZHI HUO ET AL.: "A Batch-Mode Active Learning Algorithm Using Region-Partitioning Diversity for SVM Classifier", 《IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING》 * |
张荟平: "基于光谱特征不确定性的遥感影像分类研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111595791A (en) * | 2020-06-04 | 2020-08-28 | 首都师范大学 | Inland water body FUI water color index extraction method based on hyperspectral data correction |
CN113326759A (en) * | 2021-05-26 | 2021-08-31 | 中国地质大学(武汉) | Uncertainty estimation method for remote sensing image building identification model |
CN115170179A (en) * | 2022-06-30 | 2022-10-11 | 中国科学院地理科学与资源研究所 | Trade policy uncertainty index determination method, device, equipment and medium |
CN115170179B (en) * | 2022-06-30 | 2023-03-24 | 中国科学院地理科学与资源研究所 | Trade policy uncertainty index determination method, device, equipment and medium |
Also Published As
Publication number | Publication date |
---|---|
CN110490061B (en) | 2021-10-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109685152B (en) | Image target detection method based on DC-SPP-YOLO | |
CN112836610B (en) | Land use change and carbon reserve quantitative estimation method based on remote sensing data | |
CN111161199B (en) | Space spectrum fusion hyperspectral image mixed pixel low-rank sparse decomposition method | |
CN111291826B (en) | Pixel-by-pixel classification method of multisource remote sensing image based on correlation fusion network | |
CN114254561A (en) | Waterlogging prediction method, waterlogging prediction system and storage medium | |
CN110490061B (en) | Uncertainty modeling and measuring method for remote sensing image characteristics | |
CN108428220B (en) | Automatic geometric correction method for ocean island reef area of remote sensing image of geostationary orbit satellite sequence | |
CN115641327B (en) | Building engineering quality supervision and early warning system based on big data | |
CN112200362A (en) | Landslide prediction method, device, equipment and storage medium | |
CN117992757B (en) | Homeland ecological environment remote sensing data analysis method based on multidimensional data | |
CN115359366A (en) | Remote sensing image target detection method based on parameter optimization | |
CN115272870A (en) | Remote sensing sample labeling method based on geological information and active learning | |
CN108509702B (en) | Soil erosion optimal space scale selection model and calculation method thereof | |
CN115810149A (en) | High-resolution remote sensing image building extraction method based on superpixel and image convolution | |
CN115953371A (en) | Insulator defect detection method, device, equipment and storage medium | |
CN112288744A (en) | SAR image change detection method based on integer reasoning quantification CNN | |
CN111192302A (en) | Feature matching method based on motion smoothness and RANSAC algorithm | |
CN107832805B (en) | Technology for eliminating influence of spatial position error on remote sensing soft classification precision evaluation based on probability position model | |
CN117671278A (en) | Power image data processing method, apparatus, device, medium, and program product | |
CN114972124B (en) | Remote sensing image brightness self-adaptive equalization method and system | |
CN117367404A (en) | Visual positioning mapping method and system based on SLAM (sequential localization and mapping) in dynamic scene | |
CN112819813B (en) | Intelligent underground pipeline identification method and device and storage medium | |
CN116129345A (en) | Method and device for detecting oil level of conservator of transformer and computer equipment | |
CN113079468B (en) | Indoor positioning method and system based on Wifi signal RSSI (received Signal Strength indicator) characteristics | |
CN115937395A (en) | Electrical equipment model rendering method and device, computer equipment and storage medium |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20211022 |