Remote sensing image water area automatic extraction method and system based on deep learning
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A remote sensing image and deep learning technology, applied in the field of geographic information, can solve the problem of time-consuming and labor-intensive methods of water extraction from remote sensing images
Pending Publication Date: 2020-10-13
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF5 Cites 24 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] The technical problem to be solved by the present invention is to provide a method and system for automatic extraction of remote sensing image water area
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0014] Specific implementation mode 1. Combination figure 1 Describe this embodiment, the deep learning-based remote sensing image waters automatic extraction method described in this embodiment, it comprises the following steps:
[0015] Step (1), download the Sentinel-2 data (S2A MSIL1C) of the European Space Agency, open the CMD console, perform atmospheric correction through the command L2A_Process in Sen2cor, and resample the corrected data through the SNAP software (raster->geometric operations->resampling) to obtain the data of each band of remote sensing images that can be processed by ENVI 5.3 software.
[0016] Step (2), the normalized difference water index NDWI (NDWI=(Green-NIR) / (Green+NIR)), the improved water index model NDWI3 (NDWI3= (NIR-SWIR-2) / (NIR+SWIR-2)), improved normalized difference water index MNDWI (MNDWI=(Green-SWIR-1) / (Green+SWIR-1)), enhanced water index EWI (EWI=(Green-NIR-SWIR-1) / (Green+NIR+SWIR-1)), Normalized Difference Vegetation Cover Index...
specific Embodiment approach 2
[0023] Specific embodiment two, combine figure 2 , image 3 , Figure 4 and Figure 5 Describe this embodiment, the remote sensing image water area segmentation model WE-Net described in this embodiment, it comprises the following steps:
[0024] Encoding step: In the encoding stage, the feature information of the water area is extracted through convolution and pooling. In the encoding stage, 12 grayscale images are used as input data, and the feature map is obtained by convolving and fusing the input data. Every time the feature map passes through a pooling layer, it is a scale. There are 5 scales including the scale of the original image, namely 256*256*32 , 128*128*64, 64*64*128, 32*32*256, and 16*16*512; after the pooling layer, the size of the feature map is halved and the number of channels is doubled, and then two convolutional neural networks The network extracts the water feature information of the image.
[0025] Decoding step: In the decoding stage, the image ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention provides a remote sensing image water area automatic extraction method and system based on deep learning. The method comprises the following steps: preprocessing remote sensing image data, obtaining different water area indexes through waveband operation, obtaining prior feature information extracted from a water area, fusing the remote sensing image data, Google map tile data and the like to realize multi-source feature information fusion, and then constructing a data set through visual interpretation and vectorization; training, verifying and testing a semantic segmentation model WE-Net built by the convolutional neural network; and calling a remote sensing image water area segmentation model WE-Net to realize automatic classification of the water area, and outputting a binary grayscale image which is a classification and extraction result. The method has the advantages that a water area in a research area can be extracted by calling a remote sensing image water area segmentation model, manual visual interpretation can be replaced, manpower and material resources are saved, and auxiliary technical support is provided for updating of a high-precision image map, including lake area change detection, water system change and the like.
Description
technical field [0001] The present invention relates to the field of geographic information, in particular to the field of surface waters, and in particular to a method and system for automatically extracting waters from remote sensing images based on deep learning. Background technique [0002] Rivers and lakes are the most common manifestations of surface waters, which often increase or decrease due to changes in factors such as climate change, land use, and crustal activity. , River supervision and pollution control and other ecological issues are of great significance. With the continuous development of remote sensing technology, remote sensing images have gradually become an effective means of extracting changes in surface waters. Traditional remote sensing image water body extraction methods often use manual visual interpretation, which requires manual drawing. Although the accuracy is high, it is time-consuming and laborious. In addition, both the single-band thresh...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more