Coastline extraction method based on multi-temporal high-resolution remote sensing image
A high-resolution, remote-sensing image technology, which is applied to instruments, scene recognition, calculations, etc., can solve problems such as large changes, insufficient use of high-resolution remote-sensing image information, and extraction accuracy that cannot meet the needs of small-area coastline monitoring.
Active Publication Date: 2021-05-28
WUHAN UNIV
View PDF9 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The existing remote sensing image coastline extraction methods are mainly designed for medium-resolution remote sensing images represented by Landsat satellite images to monitor large-area coastlines. In high-resolution remote sensing images, coastlines have different characteristics, and the location of the sea-land separation line Affected by tides, the changes in the image are greater. The existing remote sensing image coastline extraction methods do not make full use of high-resolution remote sensing image information, and the extraction accuracy is difficult to meet the needs of small area coastline monitoring.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0033] The present invention will be described in further detail below through the embodiments and in conjunction with the accompanying drawings.
[0034] The present invention relates to a coastline extraction method based on multi-temporal high-resolution remote sensing images, such as figure 1 shown, including the following steps:
[0035] Step 1, data preparation. The input data required by this method include: 1) multi-temporal high-resolution orthophoto remote sensing image; 2) tide table data of the National Oceanographic Information Center; 3) mask of the invalid area of the image;
[0036] Step 2, extracting instantaneous water edge information from multi-temporal high-resolution remote sensing images, the specific method is as follows:
[0037] Step 2.1, image multi-scale segmentation. Using the Fractal Network Evolutionary Algorithm (FNEA) to perform multi-scale segmentation on the orthophoto, and obtain the image object with the smallest internal heterogeneity...
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 multi-type coastline extraction method based on a multi-temporal high-resolution remote sensing image. The method comprises that: firstly, sea area water body information of the high-resolution remote sensing image is extracted by using an object-oriented support vector machine method; a buffer area is constructed in a specified range on one side of the land of the instantaneous waterline as a reference coastline zone, and the ground feature category of the reference coastline zone is extracted as reference data for coastline category confirmation; and finally, different types of coastline features are analyzed, different coastline tide level correction models are constructed to correct the instantaneous waterline position vector, and the real position vector of the coastline is recorded as output. Compared with the prior art, the method can make full use of the coastline detail features in the high-resolution remote sensing image, overcomes the instantaneous disadvantage of the remote sensing monitoring means to the greatest extent, and has important use value and wide application prospect in the field of small-area coastline dynamic monitoring.
Description
technical field [0001] The invention belongs to the field of remote sensing science and technology, and relates to a coastline extraction method based on multi-temporal high-resolution remote sensing images, which is mainly used in the fields of coastline extraction of high-resolution remote sensing images, small area coastline dynamic monitoring and the like. Background technique [0002] The coastline refers to the sea-land separation line at the average high tide level of the spring tide. Under the influence of the tide, the sea-land separation line is dynamic, and its position will continue to change with the change of the tide water level. The remote sensing observation method can only record the surface information at the moment of imaging, so the sea-land separation line obtained on the image is usually not the sea-land separation line at the average high tide level of the spring tide. Therefore, how to accurately obtain the sea-land separation line in remote sensing ...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/62
CPCG06V20/13G06V10/267G06F18/2411G06F18/24323
Inventor 贾永红赵大卫
Owner WUHAN UNIV