CN116385842A - Machine learning water body extraction method integrating multiple features of visible light-infrared-radar images - Google Patents
Machine learning water body extraction method integrating multiple features of visible light-infrared-radar images Download PDFInfo
- Publication number
- CN116385842A CN116385842A CN202310276856.0A CN202310276856A CN116385842A CN 116385842 A CN116385842 A CN 116385842A CN 202310276856 A CN202310276856 A CN 202310276856A CN 116385842 A CN116385842 A CN 116385842A
- Authority
- CN
- China
- Prior art keywords
- water body
- water
- data
- information
- infrared
- 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.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 50
- 238000000605 extraction Methods 0.000 title claims abstract description 21
- 238000010801 machine learning Methods 0.000 title claims abstract description 16
- 238000007637 random forest analysis Methods 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 4
- 230000010287 polarization Effects 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000003809 water extraction Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 5
- 102000006463 Talin Human genes 0.000 claims description 3
- 108010083809 Talin Proteins 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a machine learning water body extraction method integrating multiple features of visible light, infrared and radar images, and relates to the field of remote sensing image information extraction, in particular to the water body extraction aspect. The method specifically comprises the following steps: s1, acquiring temperatures calculated by Landsat-8 and Sentien1-2 as raw data; s2, multi-feature extraction is carried out on the processed data, and the extracted features are fused to form multi-source remote sensing data; s3, extracting water body information by using a random forest algorithm, and evaluating the accuracy of the water body obtained by classification; the invention can accurately extract the water body by combining the multisource remote sensing data, wherein the Sentien-2 image wave bands are rich; the sentien-1 image is all-weather and all-day-long, and can extract important information in shallow water areas and shadow areas; the Landsat-8 image can provide surface temperature data through calculation, and the surface temperature is closely related to the water body. Therefore, the extraction of the water body information by combining the characteristics has important significance for water body identification in areas with complex terrains.
Description
Technical Field
The invention relates to the field of remote sensing image information extraction, in particular to a machine learning water body extraction method integrating multiple features of visible light-infrared-radar images.
Background
Water is an important resource, is an important material basis for the survival and development of human beings and all organisms, but the extraction of water by using a single remote sensing data source has limitations to a certain extent. The wave band information in the Sentinel-2 image is very rich, but is easily interfered by various factors such as cloud, shadow and the like when the water body is identified; the Sentinel-1 image has fewer wave bands and more noise, but has the characteristics of all weather and all weather, and can extract meaningful signals in shallow water areas and shadow areas; notably, the effect of water on ambient temperature is significant, areas with water are typically cooler than areas without water, a feature that is helpful for water extraction, but few studies have linked surface temperature to water extraction.
Therefore, the invention provides a machine learning water body extraction method integrating multiple features of visible light-infrared-radar images aiming at the requirements.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a machine learning water body extraction method integrating multiple features of visible light-infrared-radar images, which solves the problems.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a machine learning water body extraction method integrating multiple features of visible light-infrared-radar images comprises the following steps:
s1, acquiring preprocessed Sentinel-2 and Sentinel-1 images and temperature data obtained through Landsat-8 calculation on the basis of a Google Earth Engine (GEE) cloud platform;
s2, acquiring wave band information of the image, and extracting NDWI, MNDWI, NDVI, AWEIsh, AWEInsh, SDWI and surface temperature characteristics through the wave band information of the image;
s3, fusing the characteristic information obtained in the step S2 to form new data;
s4, extracting water body information from the data obtained in the S3 by using a random forest classifier provided by the ENVI;
and S5, performing accuracy verification on the classified water body information through the confusion matrix.
Based on the technical scheme, the invention also provides the following optional technical schemes:
the technical scheme is as follows: in the S1, multispectral image, thermal infrared image and radar image data are used as an original data set, wherein the original data set comprises Sentinel-2, landsat-8 and Sentinel-1, and the data are all acquired in a GEE cloud computing platform.
The technical scheme is as follows: the specific step of S2 comprises the following steps:
s201, calculating an index NDWI, MNDWI, NDVI, AWEInsh and AWEish by utilizing the wave band of the Sentinel-2 data:
NDWI＝(band3-band8)/(band3+band8)
MNDWI＝(band3-band11)/(band3+band11)
NDVI＝(band8-band4)/(band8+band4)
AWEInsh＝4×(band3-band11)-(0.25×band8+2.75×band12)
AWEIsh＝band2+2.5×band3-1.5×(band8+band11)-0.25×band12
wherein band1 to band12 are the 1 st to 12 th bands of Sentinel-2 data.
S202, calculating SDWI by utilizing VV polarization and VH polarization of two polarization modes of a Sentinel-1 radar image:
SDWI＝alog10(10×b1×b2)
where b1 is VV polarization and b2 is VH polarization.
S203, extracting texture features of a Sentinel-1 radar image by using a gray level co-occurrence matrix (GLCM), and calculating 8 texture statistics commonly used by VV and VH polarization, wherein the texture statistics are respectively as follows: entropy (Entropy), contrast (Contrast), correlation (Correlation), median (Mean), covariance (Variance), homogeneity (Homogeneity), dissimilarity (Dissimilarity), and angular Second Moment (Second Moment), texture extraction operations are performed in ENVI.
The technical scheme is as follows: in the step S3:
carrying out layer fusion by using ENVI software, wherein each layer contains one piece of characteristic information, and carrying out multi-characteristic fusion to form multi-source remote sensing data;
the technical scheme is as follows: in the step S4:
and extracting the water body information by using the ENVI random forest classification plugin. And (3) inputting the grid images generated in the step (S3) into a random forest classification flow, drawing training samples, carrying out random forest classification, and finally obtaining a classification result. It is worth noting that the random forest algorithm can utilize all the pixels of the ROI, and the more pixels covered by the drawn ROI are, the longer the time is, so that the dot-shaped ROI is suggested to be drawn, and the time can be saved while the drawing precision of a sample is ensured.
The technical scheme is as follows: in the step S5:
s5, evaluating classification accuracy. The overall accuracy of the classification result and Kappa coefficient can be displayed in a Confusion Matrix by using a fusion Matrix tool in ENVI software, and the method is used for comparing the classification result and the information of the ground truth.
Advantageous effects
The invention provides a machine learning water body extraction method integrating multiple features of visible light, infrared and radar images, which has the following beneficial effects compared with the prior art:
1. according to the invention, the water information is extracted by combining the wave band characteristics of the Sentinel-2 and Sentinel-1 images and the water index to highlight the water information characteristics and combining the surface temperature characteristics, so that the effect of accurately extracting the water information is achieved, and the method has important significance in extracting the water information in areas with complex terrains such as mining areas.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this patent, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention. Wherein, in the drawings:
FIG. 1 is a schematic flow chart of a machine learning water extraction method integrating multiple features of visible light-infrared-radar images;
FIG. 2 is a pseudo color composite image of a Sentinel-2 image of a Huainan mining area in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of extracting water information in a Huainan mining area according to an embodiment of the present invention;
fig. 4 is a diagram of evaluation results of extraction accuracy of water bodies in a Huainan mining area in an embodiment of the invention.
Detailed Description
In order to make the technical scheme and advantages of the present invention more clear, the present invention and its advantageous effects will be described in further detail below with reference to the detailed description and the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Specific implementations of the invention are described in detail below in connection with specific embodiments.
Referring to fig. 1 to 4, a machine learning water extraction method integrating multiple features of visible light-infrared-radar images according to an embodiment of the present invention includes the following steps:
s1, acquiring preprocessed Sentinel-2 and Sentinel-1 images and temperature data obtained through Landsat-8 calculation on the basis of a Google Earth Engine (GEE) cloud platform;
s2, acquiring wave band information of the image, and extracting NDWI, MNDWI, NDVI, AWEIsh, AWEInsh, SDWI and surface temperature characteristics through the wave band information of the image;
s3, fusing the characteristic information obtained in the step S2 to form new data;
s4, extracting water body information from the data obtained in the S3 by using a random forest classifier provided by the ENVI;
and S5, performing accuracy verification on the classified water body information through the confusion matrix.
Specifically, in the step S1, the specific steps are as follows:
acquiring a 'COPERNICUS/S2_SR' data set based on a GEE cloud computing platform, wherein the data set is L2A-level data, and the data in 12 months of 2022 are subjected to mean value processing by cloud removal, mean value synthesis, flooding and cutting; the data set of COPERNICUS/S1_GRD is filtered, IW mode, VV polarization, VH polarization and track lifting (ASCENDING) radar data are selected, screening is carried out according to the time set as 2022 month 12, average value processing is carried out, and filtering processing is carried out; the ground surface temperature data LST obtained by the calculation of the LANDSAT/LC08/C02/T1_L2 data set is filtered out and the data of 12 months in 2022 are subjected to average value processing. Resampling the data downloaded in the GEE platform to 10 meters by using a nearest neighbor method in the Arcmap software respectively, and converting the data into a unified projection coordinate system WGS_1984UTM_zone_50N; the method comprises the steps of carrying out a first treatment on the surface of the
In the step S2, the specific steps are as follows:
s201, calculating the following indexes of the data processed in the S1 in ENVI software by using a band math tool: band calculation index NDWI, MNDWI, NDVI, AWEInsh and AWEIsh using Sentinel-2 data:
NDWI＝(band3-band8)/(band3+band8)
MNDWI＝(band3-band11)/(band3+band11)
NDVI＝(band8-band4)/(band8+band4)
AWEInsh＝4×(band3-band11)-(0.25×band8+2.75×band12)
AWEIsh＝band2+2.5×band3-1.5×(band8+band11)-0.25×band12
wherein band1 to band12 are the 1 st to 12 th bands of Sentinel-2 data.
S202, calculating SDWI by utilizing VV polarization and VH polarization of two polarization modes of a Sentinel-1 radar image:
SDWI＝alog10(10×b1×b2)
where b1 is VV polarization and b2 is VH polarization.
S203, extracting texture features of a Sentinel-1 radar image by using a gray level co-occurrence matrix (GLCM), and calculating 8 texture statistics commonly used by VV and VH polarization, wherein the texture statistics are respectively as follows: entropy (Entropy), contrast (Contrast), correlation (Correlation), median (Mean), covariance (Variance), homogeneity (Homogeneity), dissimilarity (Dissimilarity), angular Second Moment (Second Moment), texture extraction operations are performed in ENVI, selecting a texture calculation window size of 3*3.
In the step S3, the specific steps are as follows:
on the basis of S2, carrying out layer fusion by using ENVI software, wherein each layer contains characteristic information, and the experiment has 37 characteristics, namely: 12 wave band information of the Sentinel-2 image, 5 indexes calculated by utilizing the wave band information are NDWI, MNDWI, NDVI, AWEInsh and AWEish respectively; 2 polarization modes of Sentinel-1, a dual polarization index SDWI calculated according to the two polarization modes, and 8 texture features and surface temperature features of each polarization mode. The 37 features are fused to form multi-source remote sensing data;
in the step S4, the specific steps are as follows:
and (3) extracting the water body information from the data obtained in the step (S3) by using an ENVI random forest classification plug-in. And (3) inputting the grid images generated in the step (S3) into a random forest classification flow, drawing training samples, carrying out random forest classification, and finally obtaining a water body information classification result. It is worth noting that the random forest algorithm can utilize all the pixels of the ROI, and the more pixels covered by the drawn ROI are, the longer the time is, so that the dot-shaped ROI is suggested to be drawn, and the time can be saved while the drawing precision of a sample is ensured.
In the step S5, the specific steps are as follows:
the overall accuracy of the classification result and Kappa coefficient can be displayed in a Confusion Matrix by using a fusion Matrix tool in ENVI software, and the method is used for comparing the classification result and the information of the ground truth. The extraction accuracy of this experiment was higher, with an overall accuracy of 99.9004% and a Kappa coefficient of 0.9968.
While the foregoing has been with reference to the preferred embodiments of the present invention, it will be appreciated that numerous changes, modifications, substitutions and alterations may be made herein without departing from the principles and spirit of the invention as defined by the appended claims and their equivalents.
Claims (6)
1. The machine learning water body extraction method integrating the visible light, infrared and radar images is characterized by comprising the following steps of:
s1, acquiring preprocessed Sentine1-2 and Sentinel-1 images and temperature data obtained through Landsat-8 calculation on the basis of a Google Earth Engine (GEE) cloud platform;
s2, acquiring wave band information of the image, and extracting a Normalized Difference Water Index (NDWI), an improved normalized difference water index (MNDWI), a normalized vegetation index (NDVI), a shadowed automatic water extraction index (AWEish), a shadowless automatic water extraction index (AWEnsh), a dual-polarized water index (SDWI) and surface temperature characteristics through the wave band information of the image;
s3, fusing the characteristic information obtained in the step S2 to form new data;
s4, extracting water body information from the data obtained in the S3 by using a random forest classifier provided by the ENVI;
and S5, performing accuracy verification on the classified water body information through the confusion matrix.
2. The method for extracting machine learning water body fused with multiple features of visible light-infrared-radar images according to claim 1, wherein in the step S1, senfienl-2, sentien-1 and temperature data are used as original data, wherein the original data comprise Sentien-2, landsat-8 and Sentien-1, the data are all acquired in a GEE cloud computing platform, and the surface temperature data are obtained by calculation of Landsat-8 images. The effect of water on ambient temperature is significant, areas with water are typically cooler than areas without water, a feature that is helpful for extraction of water, but few studies have linked surface temperature to water extraction.
3. The machine learning water extraction method integrating multiple features of visible light-infrared-radar images according to claim 1, wherein the specific operation steps of S2 are as follows:
s201, band calculation NDWI, MNDWI, NDVI, AWEIsh and AWEINsh by utilizing Sentinel-2 data:
NDWI＝(band3-band8)/(band3+band8)
MNDWI＝(band3-band11)/(band3+band11)
NDVI＝(band8-band4)/(band8+band4)
AWEInsh＝4×(band3-band11)-(0.25×band8+2.75×band12)
AWEIsh＝band2+2.5×band3-1.5×(band8+band11)-0.25×band12
wherein band1 to band12 are the 1 st to 12 th bands of Sentinel-2 data.
S202, calculating SDWI by utilizing VV polarization and VH polarization of two polarization modes of a Sentinel-1 radar image:
SDWI＝alog10(10×b1×b2)
where b1 is VV polarization and b2 is VH polarization.
S203, extracting texture features of a Sentinel-1 radar image by using a gray level co-occurrence matrix (GLCM), and calculating 8 texture statistics commonly used by VV and VH polarization, wherein the texture statistics are respectively as follows: entropy (Entropy), contrast (Contrast), correlation (Correlation), median (Mean), covariance (Variance), homogeneity (Homogeneity), dissimilarity (Dissimilarity), and angular Second Moment (Second Moment), texture extraction operations are performed in ENVI.
4. The method for extracting machine learning water body with multiple features fused with visible light-infrared-radar images according to claim 1, wherein in the step S3, image layer fusion is performed by using ENVI software, each image layer contains one feature information, and the multiple features are fused to form multi-source remote sensing data.
5. The machine learning water extraction method integrating multiple features of visible light-infrared-radar images according to claim 1, wherein in S4, the water information is extracted by using ENVI random forest classification plug-in. And (3) inputting the grid images generated in the step (S3) into a random forest classification flow, drawing training samples, carrying out random forest classification, and finally obtaining a classification result. It is worth noting that the random forest algorithm can utilize all the pixels of the ROI, and the more pixels covered by the drawn ROI are, the longer the time is, so that the dot-shaped ROI is suggested to be drawn, and the time can be saved while the drawing precision of a sample is ensured.
6. The machine learning water extraction method integrating multiple features of visible light-infrared-radar images according to claim 1, wherein in S5, the overall accuracy and Kappa coefficient of the classification result can be displayed in an Confusion Matrix by using a fusion Matrix tool in ENVI software, so as to compare the classification result with information of ground truth.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310276856.0A CN116385842A (en) | 2023-03-17 | 2023-03-17 | Machine learning water body extraction method integrating multiple features of visible light-infrared-radar images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310276856.0A CN116385842A (en) | 2023-03-17 | 2023-03-17 | Machine learning water body extraction method integrating multiple features of visible light-infrared-radar images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116385842A true CN116385842A (en) | 2023-07-04 |
Family
ID=86979902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310276856.0A Pending CN116385842A (en) | 2023-03-17 | 2023-03-17 | Machine learning water body extraction method integrating multiple features of visible light-infrared-radar images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116385842A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117173584A (en) * | 2023-08-02 | 2023-12-05 | 宁波大学 | Land small micro water body extraction method and device for fusion of PolSAR and Pan images |
| CN117611888A (en) * | 2023-11-23 | 2024-02-27 | 云南师范大学 | Water body classification method and device based on shape and water body submerged frequency characteristics |
-
2023
- 2023-03-17 CN CN202310276856.0A patent/CN116385842A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117173584A (en) * | 2023-08-02 | 2023-12-05 | 宁波大学 | Land small micro water body extraction method and device for fusion of PolSAR and Pan images |
| CN117611888A (en) * | 2023-11-23 | 2024-02-27 | 云南师范大学 | Water body classification method and device based on shape and water body submerged frequency characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ebel et al. | SEN12MS-CR-TS: A remote-sensing data set for multimodal multitemporal cloud removal | |
| CN116385842A (en) | Machine learning water body extraction method integrating multiple features of visible light-infrared-radar images | |
| Lu | The potential and challenge of remote sensing‐based biomass estimation | |
| CN102622738B (en) | Method for recovering spectral information of hill shade area of Landsat thematic mapper/enhanced thematic mapper plus (TM/ETM+) image | |
| Shahtahmassebi et al. | Review of shadow detection and de-shadowing methods in remote sensing | |
| Degerickx et al. | Enhancing the performance of Multiple Endmember Spectral Mixture Analysis (MESMA) for urban land cover mapping using airborne lidar data and band selection | |
| Wicaksono | Improving the accuracy of Multispectral-based benthic habitats mapping using image rotations: the application of Principle Component Analysis and Independent Component Analysis | |
| CN111008664B (en) | Hyperspectral sea ice detection method based on space-spectrum combined characteristics | |
| CN103646246A (en) | Decision tree model based multispectral remote sensing image river information extraction method | |
| Lu et al. | Detection of urban expansion in an urban-rural landscape with multitemporal QuickBird images | |
| Szantoi et al. | Fast and robust topographic correction method for medium resolution satellite imagery using a stratified approach | |
| CN111062368A (en) | City update region monitoring method based on Landsat time sequence remote sensing image | |
| Palandro et al. | Detection of changes in coral reef communities using Landsat-5 TM and Landsat-7 ETM+ data | |
| CN112052757B (en) | Method, device, equipment and storage medium for extracting fire trace information | |
| CN109696406B (en) | Moon table hyperspectral image shadow region unmixing method based on composite end member | |
| CN105139369A (en) | Method for eliminating city building pixels in forest classification result based on PALSAR radar image | |
| Farasin et al. | Supervised Burned Areas Delineation by Means of Sentinel-2 Imagery and Convolutional Neural Networks. | |
| Gamba et al. | Limits and challenges of optical high-resolution satellite remote sensing for urban applications | |
| Xiao et al. | A Novel Image Fusion Method for Water Body Extraction Based on Optimal Band Combination. | |
| CN115661675A (en) | Multi-cloud area earthquake landslide remote sensing identification method, system, equipment and storage medium | |
| CN110706212A (en) | Mineralization alteration information extraction method, terminal equipment and storage medium | |
| CN113628098B (en) | Multi-temporal cloud-free satellite image reconstruction method | |
| CN112036264B (en) | Automatic extraction method of superglacial moraine covering type glacier | |
| El-Mezouar et al. | A high-resolution index for vegetation extraction in IKONOS images | |
| Li et al. | A novel image-fusion method based on the un-mixing of mixed MS sub-pixels regarding high-resolution DSM |
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 |