CN110296690A - A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform - Google Patents
A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform Download PDFInfo
- Publication number
- CN110296690A CN110296690A CN201910494413.2A CN201910494413A CN110296690A CN 110296690 A CN110296690 A CN 110296690A CN 201910494413 A CN201910494413 A CN 201910494413A CN 110296690 A CN110296690 A CN 110296690A
- Authority
- CN
- China
- Prior art keywords
- image
- ndwi
- pixel
- google earth
- maximum
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Astronomy & Astrophysics (AREA)
- Image Processing (AREA)
Abstract
A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform, it is related to Tideland resources rapid extracting method, the present invention is to solve the problems, such as that existing remote sensing technology can not accurately detect the distribution of acquisition Tideland resources and propose.It screens Sentinel-2MSI image and forms an image set；The water body index NDWI for calculating each image in image set obtains NDWI image spatially；Form the image of maximum NDWI pixel composition；Remove the region of not water body using mask function；Form the image of the pixel composition of maximum 8A reflectivity；Remove the region of the non-water surface using mask function；Space is carried out to the non-water-surface areas for all water-surface areas times of low water that climax can cover and asks friendship, obtains the distribution map of Tideland resources.The present invention can quickly and accurately detect Tideland resources distribution.
Description
Technical field
The present invention relates to a kind of Tideland resources rapid extracting method using cloud platform and remotely-sensed data, it is related to using distant
Sense technology makes the technical fields such as beach map.
Background technique
Important component of the beach as the seashore wetland ecosystem, to child care seashore wetland ecosystem two packing spaces
Property plays a significant role, and beach mainly includes 3 supratidal zone, intertidal zone and subtidal zone parts.Wherein Tideland resources have pole
High economy and the ecological value is maintaining marine biodiversity, Ecological Environment and Developing Ecological Tourism, is carrying out scientific research, maintenance littoral zone
The ecological balance and mitigation etc. play especially important effect.In recent years, large-scale sea reclamation and enclose sea cultivation live
It is dynamic, Tideland resources are largely reduced, the destruction and bio-diversity decline of the seashore wetland ecosystem are caused.Fast and accurately
Tideland resources distribution map is drawn, is the basis for effectively reinforcing red mud wetland conservative management and ecological recovery meaning.
In recent years, remote sensing technology has become the effective ways of production beach thematic maps.But since beach is distributed in tide
Between band area, the submergence of periodic tidewater is to bring difficulty to beach drawing.Using the image of Mono temporal, cannot effectively identify
Water surface beach range below at high tides.In recent years, a wide range of of remotely-sensed data cloud platform Google Earth Engine made
With-No. 2 multispectral datas of sentry (Sentinel-2MSI) of 2-5 days revisiting periods bring new to Tideland resources identification
Opportunity.Specific means is not provided for the extraction of Tideland resources remote sensing in the prior art.
Summary of the invention
The technical problem to be solved by the present invention is
The present invention obtains Tideland resources distribution to solve the problems, such as that existing remote sensing technology can not be detected accurately, thus
A kind of Tideland resources rapidly extracting based on Google Earth Engine Cloud platform and Sentinel-2MSI image is provided
Method.
The technical solution adopted by the present invention to solve the above technical problem is:
A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform, it includes
Following steps:
Step 1: Google Earth Engine Cloud platform is utilized, cloud amount is less in screening study area 1 year
Sentinel-2MSI image forms an image set；
Step 2: calculating the water body index (NDWI) of each image in image set, obtain NDWI image spatially, and
NDWI image is regarded into a wave band, is merged into raw video.NDWI calculation formula is as follows；
NDWI=(PGreen-PNIR)/(PGreen+PNIR)
In formula, PGreenAnd PNIRRepresent the reflectivity of green wave band and near infrared band.
Step 3: NDWI value is chosen in image set most using qualityMosaic function in Google Earth Engine
Big pixel forms the image of maximum NDWI pixel composition；
Step 4: setting NDWI threshold value is selected the range that water body covers at least once in 1 year, is gone using mask function
Fall the region of not water body；
Step 5: being greater than the principle of water body reflectivity according to beach in the 8A wave band reflectivity of Sentinel-2MSI image,
The maximum pixel of 8A band value in image set is chosen using qualityMosaic function in Google Earth Engine, is formed
The image of the pixel composition of maximum 8A reflectivity；
Step 6: setting 8A threshold value selects the non-water surface in maximum 8A albedo image, removes the water surface using mask function
Region；
Step 7: what step 4 waited until is all water-surface areas that climax can cover, and step 7 obtains the non-of time of low water
The non-water-surface areas in water-surface areas, climax period water-surface areas and low tide period carries out space intersection, has just obtained intertidal zone beach
The distribution map of painting.
Further, in step 1, the less Sentinel-2MSI image of cloud amount refers to cloud in 1 year in described 1 year
Amount is less than 20% image.
Further, in step 3, qualityMosaic function is a kind of image mosaic method pixel-based, is used
The new image of a width is formed in selecting the maximum pixel of value in a series of pixel in time serieses.
Further, in step 4, the pixel of threshold value in a certain range directly can be carried out exposure mask by mask function, be made
This partial pixel region is wiped free of, and described a certain range refers to that NDWI is less than or equal to 0.1.
Further, in step 5, shadow is chosen using qualityMosaic function in Google Earth Engine
The benchmark figure layer for being qualityMosaic by 8A band setting during the maximum pixel of 8A band value in image set.
Further, in step 6, the range of 8A threshold value is more than or equal to 1500.
Further, in step 6,8A threshold value is set, the non-water surface in maximum 8A albedo image is selected, utilize
During mask function removes the region of the non-water surface, using mask function to each pixel in maximum 8A albedo image into
Line mask wipes all pixels that pixel value is less than threshold value.
Further, in step 7, after two regions carry out space overlappings, space intersection analysis is carried out, is obtained between tide
Distribution map with beach.
The beneficial effects of the present invention are:
Technical key point of the present invention: screening Sentinel-2MSI image forms an image set；It calculates each in image set
The water body index NDWI of a image obtains NDWI image spatially；Form the image of maximum NDWI pixel composition；Utilize mask
Function removes the region of not water body；Form the image of the pixel composition of maximum 8A reflectivity；Removed using mask function non-aqueous
The region in face；The non-water-surface areas for all water-surface areas times of low water that can be covered to climax carries out space and asks friendship, obtains between tide
Distribution map with beach.The present invention can quickly and accurately detect Tideland resources distribution.
The present invention realizes the problem of remote sensing technology quickly and accurately detects Tideland resources distribution.The invention firstly uses
Google Earth Engine Cloud platform screens high-quality Sentinel-2 image.Then Google Earth is utilized
The qualityMosaic function that Engine is provided, to all images in image set into the fusion of property pixel scale.It merges respectively
The pixel and the maximum pixel of 8A wave band reflectivity of NDWI maximum value carries out threshold classification to newly-generated fusion evaluation, empty
Between overlay analysis, obtain the distribution of Tideland resources.The present invention overcomes periodic tidewater flood it is distant to Tideland resources
Sense interpretation bring is difficult, solves the problems, such as that the beach being submerged is divided into water body by mistake.Intertidal zone beach according to the present invention
Painting extracting method is effective and rapid, improves the accuracy and confidence of Tideland resources interpretation, has repeatability and robustness, right
Tideland resources remote sensing mapping has and its important meaning.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example and is used together to explain the present invention, be not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is image the selection result screenshot；
Fig. 2 is the image of NDWI maximum value pixel composition；
Fig. 3 is the attainable maximum water-surface areas figure of climax；
Fig. 4 is the striograph of 8A maximum value pixel composition；
Fig. 5 is Tideland resources distribution map.
Specific embodiment
A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform, it includes
Following steps:
Step 1: Google Earth Engine Cloud platform is utilized, cloud amount is less in screening study area 1 year
Sentinel-2MSI image forms an image set；
Step 2: calculating the water body index NDWI of each image in image set, obtains NDWI image spatially, and will
NDWI image regards a wave band, is merged into raw video, NDWI calculation formula is as follows；
NDWI=(PGreen-PNIR)/(PGreen+PNIR)
In formula, PGreenAnd PNIRRepresent the reflectivity of green wave band and near infrared band；
Step 3: NDWI value is chosen in image set most using qualityMosaic function in Google Earth Engine
Big pixel forms the image of maximum NDWI pixel composition；
Step 4: setting NDWI threshold value is selected the range that water body covers at least once in 1 year, is gone using mask function
Fall the region of not water body；
Step 5: being greater than the principle of water body reflectivity according to beach in the 8A wave band reflectivity of Sentinel-2MSI image,
The maximum pixel of 8A band value in image set is chosen using qualityMosaic function in Google Earth Engine, is formed
The image of the pixel composition of maximum 8A reflectivity；
Step 6: setting 8A threshold value selects the non-water surface in maximum 8A albedo image, removes the water surface using mask function
Region；
Step 7: what step 4 waited until is all water-surface areas that climax can cover, and step 7 obtains the non-of time of low water
Water-surface areas carries out space overlapping to the two regions, has just obtained the distribution map of Tideland resources；
In step 1, the less Sentinel-2MSI image of cloud amount refers to that cloud amount is less than in 1 year in described 1 year
20% image；
In step 3, qualityMosaic function is a kind of image mosaic method pixel-based, and being used for will be a series of
The maximum pixel of the value in pixel in time series selects to form the new image of a width；NDWI is carried out
QualityMosaic forms the new image of a width, each pixel is the maximum picture of NDWI value in time series in image
Element, that is, the pixel of most likely water.The NDWI value of some pixel is bigger, and it is bigger to represent a possibility that pixel is water；
In step 4, the pixel of threshold value in a certain range directly can be carried out exposure mask by mask function, make this part picture
Plain region is wiped free of, and described a certain range refers to that NDWI is less than or equal to 0.1；
In step 5,8A wave in image set is chosen using qualityMosaic function in Google Earth Engine
The benchmark figure layer for being qualityMosaic by 8A band setting during the maximum pixel of segment value；
In step 6, it is a wave of Sentinel-2MSI image that the range of 8A threshold value, which is more than or equal to 1500,8A,
Section, 1500 do not have dimension, and it is non-water area that 8A value, which is more than or equal to 1500,；
In step 6,8A threshold value is set, selects the non-water surface in maximum 8A albedo image, is removed using mask function
During the region of the non-water surface, exposure mask is carried out to each pixel in maximum 8A albedo image using mask function, by picture
The all pixels that element value is less than threshold value are wiped；
In step 7, after two regions carry out space overlapping, space intersection analysis is carried out, obtains point of Tideland resources
Butut.
Embodiment:
Step 1: utilizing Google Earth Engine Cloud platform, screens cloud amount in Xiamen City periphery 2018 and is less than 10%
Sentinel-2MSI image, form an image set, share within 2018 the qualified shadow of 11 scapes by calculating the region
Picture, image the selection result are as shown in Figure 1；
Step 2: calculating the water body index (NDWI) of each image in image set, obtain NDWI image spatially, and
NDWI image is regarded into a wave band, is merged into raw video.NDWI calculation formula is as follows；
NDWI=(PGreen-PNIR)/(PGreen+PNIR)
In formula, PGreenAnd PNIRRepresent the reflectivity of green wave band and near infrared band.
Step 3: NDWI value is chosen in image set most using qualityMosaic function in Google Earth Engine
Big pixel forms the image of maximum NDWI pixel composition, as shown in Figure 2；
Step 4: setting NDWI is greater than 0, selects the range that water body covers at least once in 1 year, utilizes mask function
Remove the region of not water body；The attainable maximum water-surface areas of climax is as shown in Figure 3；
Step 5: being greater than the principle of water body reflectivity according to beach in the 8A wave band reflectivity of Sentinel-2MSI image,
The maximum pixel of 8A band value in image set is chosen using qualityMosaic function in Google Earth Engine, is formed
The image of the pixel composition of maximum 8A reflectivity, as shown in Figure 4；
Step 6: setting 8A threshold value is greater than 1500, selects the non-water surface in maximum 8A albedo image, utilizes mask function
Remove the region of the water surface；
Step 7: what step 4 obtained is all water-surface areas that climax can cover, and step 7 obtains the non-of time of low water
Water-surface areas carries out space intersection to the two regions, has just obtained the distribution map of Tideland resources, as shown in Figure 5.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (8)
1. a kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform, feature exist
In it includes the following steps:
Step 1: utilizing Google Earth Engine Cloud platform, the less Sentinel- of cloud amount in screening study area 1 year
2MSI image forms an image set；
Step 2: calculating the water body index NDWI of each image in image set, obtain NDWI image spatially, and by NDWI
Image regards a wave band, is merged into raw video, NDWI calculation formula is as follows；
NDWI=(PGreen-PNIR)/(PGreen+PNIR)
In formula, PGreenAnd PNIRRepresent the reflectivity of green wave band and near infrared band；
Step 3: it is maximum that NDWI value in image set is chosen using qualityMosaic function in Google Earth Engine
Pixel forms the image of maximum NDWI pixel composition；
Step 4: setting NDWI threshold value is selected the range that water body covers at least once in 1 year, is removed not using mask function
There is the region of water body；
Step 5: it is greater than the principle of water body reflectivity, benefit in the 8A wave band reflectivity of Sentinel-2 MSI image according to beach
The maximum pixel of 8A band value in image set is chosen with qualityMosaic function in Google Earth Engine, is formed most
The image of the pixel composition of big 8A reflectivity；
Step 6: setting 8A threshold value is selected the non-water surface in maximum 8A albedo image, is removed the area of the water surface using mask function
Domain；
Step 7: what step 4 waited until is all water-surface areas that climax can cover, and step 7 obtains the non-water surface of time of low water
Region carries out space overlapping to the two regions, has just obtained the distribution map of Tideland resources.
2. a kind of Tideland resources based on Google Earth Engine Cloud platform according to claim 1 are quickly distant
Feel extracting method, which is characterized in that it is characterized in that, in step 1, the less Sentinel-2MSI of cloud amount in described 1 year
Image refers to image of the cloud amount less than 20% in 1 year.
3. a kind of Tideland resources based on Google Earth Engine Cloud platform according to claim 2 are quickly distant
Feel extracting method, which is characterized in that in step 3, qualityMosaic function is a kind of image mosaic side pixel-based
Method forms the new image of a width for selecting the maximum pixel of value in a series of pixel in time serieses.
4. a kind of Tideland resources based on Google Earth Engine Cloud platform according to claim 1,2 or 3 are fast
Fast Remotely sensed acquisition method, in step 4, the pixel of threshold value in a certain range directly can be carried out exposure mask by mask function, make this
Partial pixel region is wiped free of, and described a certain range refers to that NDWI is less than or equal to 0.1.
5. a kind of Tideland resources based on Google Earth Engine Cloud platform according to claim 4 are quickly distant
Feel extracting method, which is characterized in that in step 5, select using qualityMosaic function in Google Earth Engine
Take the benchmark figure layer for being qualityMosaic by 8A band setting during the maximum pixel of 8A band value in image set.
6. a kind of Tideland resources based on Google Earth Engine Cloud platform according to claim 5 are quickly distant
Feel extracting method, which is characterized in that in step 6, the range of 8A threshold value is more than or equal to 1500.
7. a kind of Tideland resources based on Google Earth Engine Cloud platform according to claim 6 are quickly distant
Feel extracting method, which is characterized in that in step 6,8A threshold value is set, the non-water surface in maximum 8A albedo image is selected, benefit
During the region for removing the non-water surface with mask function, using mask function to each pixel in maximum 8A albedo image
Exposure mask is carried out, all pixels that pixel value is less than threshold value are wiped.
8. a kind of Tideland resources based on Google Earth Engine Cloud platform according to claim 7 are quickly distant
Feel extracting method, which is characterized in that in step 7, after two regions carry out space overlapping, carry out space intersection analysis, obtain
The distribution map of Tideland resources.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910494413.2A CN110296690A (en) | 2019-06-06 | 2019-06-06 | A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910494413.2A CN110296690A (en) | 2019-06-06 | 2019-06-06 | A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110296690A true CN110296690A (en) | 2019-10-01 |
Family
ID=68027637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910494413.2A Pending CN110296690A (en) | 2019-06-06 | 2019-06-06 | A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110296690A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597930A (en) * | 2020-04-30 | 2020-08-28 | 河海大学 | Coastline extraction method based on remote sensing cloud platform |
| CN111666953A (en) * | 2020-06-04 | 2020-09-15 | 电子科技大学 | Tidal zone surveying and mapping method and device based on semantic segmentation |
| CN113255808A (en) * | 2021-06-03 | 2021-08-13 | 中国科学院地理科学与资源研究所 | Long-time-sequence territorial space regional functional structure change detection method based on big data |
| CN113408467A (en) * | 2021-07-01 | 2021-09-17 | 中国科学院东北地理与农业生态研究所 | Coastal culture pond intelligent extraction method based on Sentinel-2 satellite images and cloud platform |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013089021A (en) * | 2011-10-18 | 2013-05-13 | Hitachi Solutions Ltd | Image processing unit and image processing method |
| CN105447274A (en) * | 2015-12-22 | 2016-03-30 | 中国科学院东北地理与农业生态研究所 | Method of performing coastal wetland drawing for medium-resolution remote sensing image by utilizing object-oriented classification technology |
| CN106650689A (en) * | 2016-12-30 | 2017-05-10 | 厦门理工学院 | Coastal city time sequence land utilization information extracting method |
-
2019
- 2019-06-06 CN CN201910494413.2A patent/CN110296690A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013089021A (en) * | 2011-10-18 | 2013-05-13 | Hitachi Solutions Ltd | Image processing unit and image processing method |
| CN105447274A (en) * | 2015-12-22 | 2016-03-30 | 中国科学院东北地理与农业生态研究所 | Method of performing coastal wetland drawing for medium-resolution remote sensing image by utilizing object-oriented classification technology |
| CN106650689A (en) * | 2016-12-30 | 2017-05-10 | 厦门理工学院 | Coastal city time sequence land utilization information extracting method |
Non-Patent Citations (2)
| Title |
|---|
| 刘向阳: "基于遥感水边线的环渤海地区潮滩研究", 《中国优秀硕士学位论文全文数据库基础科学辑》 * |
| 胥为: "基于Sentinel-1和Landsat8数据的潮间带盐沼湿地分类研究", 《中国优秀硕士学位论文全文数据库工程科技I辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597930A (en) * | 2020-04-30 | 2020-08-28 | 河海大学 | Coastline extraction method based on remote sensing cloud platform |
| CN111666953A (en) * | 2020-06-04 | 2020-09-15 | 电子科技大学 | Tidal zone surveying and mapping method and device based on semantic segmentation |
| CN111666953B (en) * | 2020-06-04 | 2022-07-01 | 电子科技大学 | Tidal zone surveying and mapping method and device based on semantic segmentation |
| CN113255808A (en) * | 2021-06-03 | 2021-08-13 | 中国科学院地理科学与资源研究所 | Long-time-sequence territorial space regional functional structure change detection method based on big data |
| CN113408467A (en) * | 2021-07-01 | 2021-09-17 | 中国科学院东北地理与农业生态研究所 | Coastal culture pond intelligent extraction method based on Sentinel-2 satellite images and cloud platform |
| CN113408467B (en) * | 2021-07-01 | 2022-04-29 | 中国科学院东北地理与农业生态研究所 | Coastal culture pond intelligent extraction method based on Sentinel-2 satellite images and cloud platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110296690A (en) | A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform | |
| Cheng et al. | Cloud removal for remotely sensed images by similar pixel replacement guided with a spatio-temporal MRF model | |
| CN107067012B (en) | Submarine geomorphy cell edges intelligent identification Method based on image procossing | |
| Ma et al. | Tracking three decades of land use and land cover transformation trajectories in C hina's large river deltas | |
| CN109741446B (en) | Method for dynamically generating fine coast terrain by three-dimensional digital earth | |
| Liu et al. | Seasonal pattern of tidal-flat topography along the Jiangsu middle coast, China, using HJ-1 optical images | |
| CN110147746B (en) | Method and system for rapidly extracting maximum and minimum possible surface water body ranges based on Sentinel-2 image | |
| Zhang et al. | MRSE-Net: multiscale residuals and SE-attention network for water body segmentation from satellite images | |
| CN106530313A (en) | Sea-sky line real-time detection method based on region segmentation | |
| Xu et al. | Characterizing wetland change at landscape scale in Jiangsu Province, China | |
| Skinner et al. | Underwater image dehazing with a light field camera | |
| Li et al. | Mapping water bodies under cloud cover using remotely sensed optical images and a spatiotemporal dependence model | |
| CN114266958A (en) | Cloud platform based mangrove remote sensing rapid and accurate extraction method | |
| Rokni et al. | A new approach for detection of surface water changes based on principal component analysis of multitemporal normalized difference water index | |
| Zhu et al. | An APMLP deep learning model for bathymetry retrieval using adjacent pixels | |
| CN110120050A (en) | Remote sensing image sea land dividing method based on sketch information and super-pixel segmentation | |
| Qin et al. | MUSTFN: A spatiotemporal fusion method for multi-scale and multi-sensor remote sensing images based on a convolutional neural network | |
| Deng et al. | Mapping bathymetry from multi-source remote sensing images: A case study in the Beilun Estuary, Guangxi, China | |
| Hamylton et al. | Spatial modelling of benthic cover using remote sensing data in the Aldabra lagoon, western Indian Ocean | |
| Singh et al. | Estimation of revised capacity in Gobind Sagar reservoir using Google earth engine and GIS | |
| Meng et al. | Monitoring human-induced surface water disturbance around Taihu Lake since 1984 by time series Landsat images | |
| Ma et al. | Feature enhanced deep learning network for digital elevation model super-resolution | |
| He et al. | Accurate estimation of surface water volume in tufa lake group using UAV-captured imagery and ANNs | |
| Arif et al. | Analysis of shoreline dynamics for coastal management practice in Pariaman, West Sumatera | |
| Liu et al. | A Deep Learning Method for Offshore Raft Aquaculture Extraction Based on Medium Resolution Remote Sensing Images |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191001 |