CN107358161B - Coastline extraction method and coastline extraction system based on remote sensing image classification - Google Patents
Coastline extraction method and coastline extraction system based on remote sensing image classification Download PDFInfo
- Publication number
- CN107358161B CN107358161B CN201710431726.4A CN201710431726A CN107358161B CN 107358161 B CN107358161 B CN 107358161B CN 201710431726 A CN201710431726 A CN 201710431726A CN 107358161 B CN107358161 B CN 107358161B
- Authority
- CN
- China
- Prior art keywords
- data
- sensing image
- remote sensing
- sea
- land
- 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.)
- Active
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Abstract
The invention relates to a coastline extraction method and system based on remote sensing image classification. The method comprises the following steps: carrying out multi-scale segmentation on the input remote sensing image, and extracting first sea-land boundary line data and second sea-land boundary line data in the remote sensing image to obtain outer boundary data of one side facing to the land; sampling the outer boundary data, and calculating first waterline difference data of two sea-land boundary data at each sampling point; calculating a first tide level and a second tide level of the two remote sensing images and a highest tide level of an area to be extracted, and calculating a first tide difference between the first tide level and the second tide level and a second tide difference between the second tide level and the highest tide level; and calculating second waterline difference data of the highest tide level according to the first tide difference, the second tide difference and the first waterline difference data, and pushing all sampling points to one side of land according to the second waterline difference data and then performing spline interpolation to obtain coastline data of the area to be extracted. The invention can effectively improve the coastline extraction efficiency and precision.
Description
Technical Field
The invention relates to the technical field of ecological environment monitoring, in particular to a coastline extraction method and a coastline extraction system based on remote sensing image classification.
Background
The coastline is the functional boundary between the ocean and land. Wherein, the common silt muddy light beach shoreline is an important component of the shoreline in China. The beach surface of the common silt smooth beach coast is very flat, and the slope is only 1/1000-1/3000. The intertidal zone of the common silt smooth beach coast is wide, and obvious tidal ditch development can be seen on the intertidal zone. The identification and extraction of the shore line of the light beach with general silt and muddy texture are not only preconditions for developing the work contents such as sea-land coupling effect, city expansion, coastal area development and the like, but also are important subjects of research works such as geographic information management, coastal zone survey and the like.
The traditional silt and muddy light beach shoreline extraction method usually depends on-site data mapping, namely, a mapping staff carries out real-time measurement on the spot by utilizing a photogrammetry technology and certain instrument equipment in a heavy tide or a high tide period. In order to improve the efficiency problem of field mapping, a shoreline extraction method based on a remote sensing technology is made out of the question. The existing silt silty light beach shoreline extraction based on the remote sensing technology generally utilizes a remote sensing image classification method to extract a shoreline, and utilizes the spectrum and the structural characteristics of a target ground object to directly obtain the spatial position information of the shoreline from the remote sensing image by a visual interpretation method. However, since the time when the aerial photograph or the satellite passes is difficult to correspond to the local time point of high tide, the water and land boundary extracted by the general remote sensing supervision, semi-supervision or unsupervised classification is not a coastline in the true sense (the water and land boundary line in the image data is used as the coastline of the coast). In view of the prior art, most of the automatic coastline extraction algorithms are designed to extract instantaneous land and water boundaries by using a digital image processing technology, which is essentially a process of segmenting and clustering digital images, and there are many related technical methods, and the basic technical solutions thereof are as follows:
A. inputting single time series remote sensing image data; mainly including Landsat (united states land detection satellite system), SPOT (venue), SAR (synthetic aperture radar), QuickBird (QuickBird), IKONOS (ionos satellite), etc.;
B. selecting classification characteristics of a coastline; mainly comprising hue, color, shape, size, texture, shadow, related layout, etc.;
C. research on interpretation methods of water areas and land areas: mainly comprises visual interpretation, supervised classification, semi-supervised classification, unsupervised classification and the like;
D. the coastline automatic tracking algorithm: the method mainly comprises a Roberts algorithm, a Prewitt algorithm, a Sobel algorithm, a Laplace algorithm, a Canny algorithm and the like.
In summary, although the remote sensing technology has the advantages of real-time performance, dynamic performance, short period, large range, etc., the existing coastline extraction method based on the remote sensing technology only uses the water-land boundary line in the image data as the coastline of the coast, but the actual situation is that the imaging time of a general remote sensing image cannot accurately correspond to the local high tide or high tide waterline, so that the high tide waterline must be deduced by using the general tide waterline, and therefore, the technology for identifying or extracting the coastline in a strict sense is not mature.
Disclosure of Invention
The invention provides a coastline extraction method and a coastline extraction system based on remote sensing image classification, and aims to solve at least one of the technical problems in the prior art to a certain extent.
In order to solve the above problems, the present invention provides the following technical solutions:
a coastline extraction method based on remote sensing image classification comprises the following steps:
step a: carrying out multi-scale segmentation on an input remote sensing image, wherein the input remote sensing image comprises a first remote sensing image and a second remote sensing image which are positioned in the same region;
step b: extracting first sea-land boundary data and second sea-land boundary data in the first remote sensing image and the second remote sensing image, combining the first sea-land boundary data and the second sea-land boundary data, and obtaining outer boundary data of one side facing the land according to the combined data;
step c: sampling the data of the outer boundary of the land facing side, and calculating first waterline difference data of the first sea-land boundary data and the second sea-land boundary data at each sampling point;
step d: respectively obtaining a first tide level and a second tide level of a first remote sensing image and a second remote sensing image and a highest tide level of an area to be extracted through tide checking data or tide model data, and calculating a first tide difference between the first tide level and the second tide level and a second tide difference between the second tide level and the highest tide level;
step e: and calculating second waterline difference data of the highest tide level according to the first tide difference, the second tide difference and the first waterline difference data, and pushing all sampling points to one side of land according to the second waterline difference data and then performing spline interpolation to obtain the coastline data of the area to be extracted.
The technical scheme adopted by the embodiment of the invention also comprises the following steps: in the step a, the multi-scale segmentation of the input remote sensing image specifically includes: carrying out multi-scale segmentation on the input remote sensing image by using an object-oriented image classification method, wherein the multi-scale segmented multispectral wave band comprises a blue-green spectrum band B1Green spectrum segment B2Red spectral band B3And near infrared spectrum band B4Weight factor Q of each multispectral bandiComprises the following steps:
the technical scheme adopted by the embodiment of the invention also comprises the following steps: in the step a, the performing multi-scale segmentation on the input remote sensing image specifically includes:
step a 1: respectively setting numerical values of a segmentation scale, a shape factor and a compactness factor;
step a 2: respectively aligning the multispectral wave band B according to the weight factor, the segmentation scale, the shape factor and the compactness factor1、B2、B3And B4And performing multi-scale segmentation.
The technical scheme adopted by the embodiment of the invention also comprises the following steps: in the step b, the extracting of the first sea-land boundary data and the second sea-land boundary data in the first remote sensing image and the second remote sensing image specifically includes: establishing an operational characteristic NDWI according to the multi-scale segmented object, extracting seawater areas in the first remote sensing image and the second remote sensing image by using a threshold classification method, converting surface vector data of the seawater areas in the first remote sensing image and the second remote sensing image into line vector data through spatial data processing, and obtaining first sea-land boundary line data and second sea-land boundary line data in the first remote sensing image and the second remote sensing image according to the line vector data; wherein, the formula of the NDWI is as follows:
the technical scheme adopted by the embodiment of the invention also comprises the following steps: in the step e, the second waterline difference data Δ SBCThe calculation formula of (2) is as follows:
in the above formula,. DELTA.TABDenotes the first tidal range, Δ TBCIndicates the second tidal range, Δ SABIndicating the first waterline difference data and i indicating the sample point number.
The embodiment of the invention adopts another technical scheme that: a coastline extraction system based on remote sensing image classification comprises:
an image segmentation module: the remote sensing image segmentation method comprises the steps of performing multi-scale segmentation on an input remote sensing image, wherein the input remote sensing image comprises a first remote sensing image and a second remote sensing image which are located in the same region;
sea-land boundary extraction module: the system comprises a first remote sensing image, a second remote sensing image, a third remote sensing image and a fourth remote sensing image, wherein the first remote sensing image and the second remote sensing image are used for acquiring first sea-land boundary data and second sea-land boundary data in the first remote sensing image and the second remote sensing image;
sea-land boundary line merging module: the data processing device is used for merging the first sea-land boundary data and the second sea-land boundary data and obtaining the outer boundary data of one side facing the land according to the merged data;
the first waterline difference calculating module: a first waterline difference data for sampling the outer boundary data on the land side and calculating the first and second sea-land boundary data at each sampling point;
a tidal range calculation module: the tidal range data acquisition unit is used for respectively obtaining a first tidal level and a second tidal level of the first remote sensing image and the second remote sensing image and a highest tidal level of an area to be extracted through tidal range data or tidal model data, and calculating a first tidal range between the first tidal level and the second tidal range and a second tidal range between the second tidal level and the highest tidal range;
the second waterline difference calculating module: second waterline difference data for calculating the highest tide level from the first tide difference, second tide difference and first waterline difference data;
a shoreline calculation module: and the system is used for pushing all sampling points to the land side according to the second waterline difference data and then carrying out spline interpolation to obtain the coastline data of the area to be extracted.
The technical scheme adopted by the embodiment of the invention also comprises the following steps: the image segmentation module performs multi-scale segmentation on the input remote sensing image specifically as follows: carrying out multi-scale segmentation on the input remote sensing image by using an object-oriented image classification method, wherein the multi-scale segmented multispectral wave band comprises a blue-green spectrum band B1Green spectrum segment B2Red spectral band B3And near infrared spectrum band B4Weight factor Q of each multispectral bandiComprises the following steps:
the technical scheme adopted by the embodiment of the invention also comprises the following steps: the image segmentation module performs multi-scale segmentation on the input remote sensing image specifically as follows: respectively setting numerical values of a segmentation scale, a shape factor and a compactness factor; respectively aligning the multispectral wave band B according to the weight factor, the segmentation scale, the shape factor and the compactness factor1、B2、B3And B4And performing multi-scale segmentation.
The technical scheme adopted by the embodiment of the invention further comprises a seawater area extraction module, wherein the seawater area extraction module is used for establishing an operational characteristic 'NDWI' according to the multi-scale segmented object, extracting the seawater areas in the first remote sensing image and the second remote sensing image by using a threshold classification method, converting the surface vector data of the seawater areas in the first remote sensing image and the second remote sensing image into line vector data through space data processing, and obtaining the first sea-land boundary data and the second sea-land boundary data in the first remote sensing image and the second remote sensing image according to the line vector data; wherein, the formula of the NDWI is as follows:
the technical scheme adopted by the embodiment of the invention also comprises the following steps: the second waterline difference data Δ SBCThe calculation formula of (2) is as follows:
in the above formula,. DELTA.TABDenotes the first tidal range, Δ TBCIndicates the second tidal range, Δ SABIndicating the first waterline difference data and i indicating the sample point number.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: according to the coastline extraction method and system based on remote sensing image classification, provided by the embodiment of the invention, the waterline identification technology and the coastline deduction technology are effectively combined together according to the natural attributes and the pattern characteristics of the ordinary silt and muddy smooth beach coasts, so that the problem of coastline deviation caused by default of the instantaneous land-water interface line into the coastline of the coastline by the existing coastline automatic extraction technology is solved. The method has the advantages of simple scheme, low requirement on data quality, few operation parameters, high calculation efficiency, strong robustness, reliable coastline extraction result and capability of effectively improving the coastline extraction efficiency and precision.
Drawings
FIG. 1 is a flow chart of a coastline extraction method based on remote sensing image classification according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a coastline extraction system based on remote sensing image classification according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Fig. 1 is a flowchart of a coastline extraction method based on remote sensing image classification according to an embodiment of the present invention. The coastline extraction method based on remote sensing image classification comprises the following steps of:
step 100: inputting a first remote sensing image;
in step 100, the input first remote sensing image is a GF-2 (high score two) remote sensing image, and in other embodiments of the present invention, the input remote sensing image may also be other types of remote sensing images.
Step 200: 4 multispectral wave bands of the input first remote sensing image are named as B in sequence1(blue-green spectral band), B2(Green spectrum segment), B3(Red spectral band) and B4(near infrared spectrum);
step 300: performing multi-scale Segmentation (Multiresolution Segmentation) on the first remote sensing image by using an object-oriented image classification method;
in step 300, the multi-scale segmentation steps are as follows:
step 301: the multispectral bands participating in the multiscale segmentation include B1、B2、B3、B4Weight factor Q of each multispectral bandiThe following were used:
step 302: setting a segmentation Scale (Scale Parameter);
in the embodiment of the invention, the numerical value of the segmentation Scale is set to be equal to or less than 40, and can be specifically set according to actual requirements.
Step 303: setting a Shape factor (Shape);
in the embodiment of the invention, the numerical value of the Shape factor is set to be equal to or less than 0.1, and can be specifically set according to actual requirements.
Step 304: setting a Compactness factor (Compactness);
in the embodiment of the invention, the value of the Compactness factor is set to be smaller than or equal to 0.3, and can be specifically set according to actual requirements.
Step 305: respectively aligning the multispectral wave band B according to the weight factor, the segmentation scale, the shape factor and the compactness factor1、B2、B3And B4Performing multi-scale segmentation, and assigning the object generated after multi-scale segmentation as 'unclassified'.
Step 400: establishing an operational characteristic 'NDWI (Normalized Difference Water Index, Normalized water Index, Normalized difference processing by using a specific wave band of the remote sensing image to highlight water body information' according to the multi-scale segmented object, and extracting a seawater area in the first remote sensing image by using a threshold classification method;
in step 400, the formula for "NDWI" is as follows:
in the formula (2), B2Is the brightness value of the green band of the first remote sensing image, B4The brightness value of the near-infrared band of the first remote sensing image is obtained.
In the foregoing, the threshold classification method is a process of assigning an object satisfying a certain threshold condition from "unclassified" to seawater, "and a calculation formula thereof is as follows:
in the formula (3), α is an extraction threshold, and can be set according to actual requirements.
Step 500: processing the first distance by spatial dataConverting the surface vector data of the seawater area in the sensed image into line vector data, and obtaining first sea-land boundary line data S of a common silt muddy beach coast in the first remote sensing image according to the line vector dataA；
Step 600: inputting a second remote sensing image in the same region as the first remote sensing image, and re-executing the steps 200 to 500 to obtain second sea-land boundary line data S of the ordinary silt muddy beach coast in the second remote sensing imageB；
Step 700: merging first sea-land boundary data S by spatial data processingAAnd second sea-land boundary line data SBAnd obtaining the outer boundary data S of the land side according to the merged dataA+BAnd seaside boundary data
Step 800: at the outer boundary data SA+BSampling every a certain distance d, and calculating the first sea-land boundary data S of the position at each sampling pointAAnd second sea-land boundary line data SBSpatially first waterline difference data Delta SABThe calculation formula is as follows:
in formula (4), i represents a sampling point number. The embodiment of the invention adopts a sampling method for converting continuous line vector data into discrete point vector data, thereby solving the problem that the continuous line vector data is inconvenient for space calculation; the numerical value of the sampling interval distance d is set by a user according to requirements.
Step 900: obtaining a first remote sensing image through tide checking data or tide model data and a first tide level T of the first remote sensing image during imagingAAnd a second tidal level TBAnd calculating a first tide level TAAnd a second tidal level TBFirst tidal difference Δ T therebetweenABThe calculation formula is as follows:
ΔTAB＝|TA-TB| (5)
step 1000: obtaining the highest tide level T of the area to be extracted through tide checking data or tide model dataCAnd calculating a second tide level TBAnd the highest tide level TCSecond tidal difference Δ T therebetweenBC；
ΔTBC＝|TB-TC| (6)
Step 1100: based on the linear relation between the tidal difference Delta T and the waterline difference Delta S, according to the first tidal difference Delta TABSecond tidal range DeltaTBCAnd first waterline difference data Delta SABCalculating the maximum tide level TCCorresponding second waterline difference data Delta SBC；
Step 1200: all sampling points are pushed to one side of the land by delta SBCiThen, a plurality of times of spline interpolation is carried out, the vector data of the discrete points are converted into smooth and continuous line vector data, and finally, the shore line data S of the general silt and muddy beach coast of the area to be extracted is obtainedC。
In step 1200, the spline interpolation frequency is three times, which may be set according to the time requirement.
Fig. 2 is a schematic structural diagram of a coastline extraction system based on remote sensing image classification according to an embodiment of the present invention. The coastline extraction system based on remote sensing image classification comprises an image input module, an image naming module, an image segmentation module, a seawater region extraction module, a sea-land boundary merging module, a first waterline difference calculation module, a tidal difference calculation module, a second waterline difference calculation module and a coastline calculation module.
An image input module: the remote sensing image input device is used for inputting a remote sensing image; in the embodiment of the invention, the input remote sensing images comprise a first remote sensing image and a second remote sensing image which are positioned in the same area, and the first remote sensing image and the second remote sensing image are GF-2 (high-score second) remote sensing images respectively.
The image naming module: the method is used for sequentially naming the 4 multispectral wave bands of the first remote sensing image and the second remote sensing image as B1(blue-green spectral band), B2(Green spectrum segment), B3(Red spectral band) and B4(near infrared spectrum);
an image segmentation module: the image classification method is used for respectively carrying out multi-scale segmentation on the first remote sensing image and the second remote sensing image by utilizing an object-oriented image classification method; wherein the multi-scale segmentation specifically comprises:
1: the multispectral bands participating in the multiscale segmentation include B1、B2、B3、B4Weight factor Q of each multispectral bandiThe following were used:
2: setting a segmentation Scale (Scale Parameter); in the embodiment of the invention, the numerical value of the segmentation Scale is set to be equal to or less than 40, and can be specifically set according to actual requirements.
3: setting a Shape factor (Shape); in the embodiment of the invention, the numerical value of the Shape factor is set to be equal to or less than 0.1, and can be specifically set according to actual requirements.
4: setting a Compactness factor (Compactness); in the embodiment of the invention, the value of the Compactness factor is set to be smaller than or equal to 0.3, and can be specifically set according to actual requirements.
5: respectively aligning the multispectral wave band B according to the weight factor, the segmentation scale, the shape factor and the compactness factor1、B2、B3And B4Performing multi-scale segmentation, and assigning the object generated after multi-scale segmentation as 'unclassified'.
Seawater area extraction module: the method comprises the steps of establishing an operational characteristic ' NDWI ' (Normalized Difference Water Index ') according to an object subjected to multi-scale segmentation, and extracting seawater areas in a first remote sensing image and a second remote sensing image respectively by using a threshold classification method; wherein, the calculation formula of "NDWI" is as follows:
in the formula (2), B2Is the brightness value of the green band of the first remote sensing image and the second remote sensing image, B4The brightness values of the near-infrared wave bands of the first remote sensing image and the second remote sensing image are obtained.
In the foregoing, the threshold classification method is a process of assigning an object satisfying a certain threshold condition from "unclassified" to seawater, "and a calculation formula thereof is as follows:
in the formula (3), α is an extraction threshold, and can be set according to actual requirements.
Sea-land boundary extraction module: the system is used for converting surface vector data of seawater areas in the first remote sensing image and the second remote sensing image into line vector data through spatial data processing, and obtaining first sea-land boundary line data S of a common silt muddy beach coast in the first remote sensing image and the second remote sensing image according to the line vector dataAAnd second sea-land boundary line data SB；
Sea-land boundary line merging module: for merging first sea-land boundary data S by spatial data processingAAnd second sea-land boundary line data SBAnd obtaining the outer boundary data S of the land side according to the merged dataA+BAnd seaside boundary data
The first waterline difference calculating module: for data S at the outer boundaryA+BSampling every a certain distance d, and calculating the first sea-land boundary data S of the position at each sampling pointAAnd second sea-land boundary line data SBSpatially first waterline difference data Delta SABThe calculation formula is as follows:
in formula (4), i represents a sampling point number. The embodiment of the invention adopts a sampling method for converting continuous line vector data into discrete point vector data, thereby solving the problem that the continuous line vector data is inconvenient for space calculation; the numerical value of the sampling interval distance d is set by a user according to requirements.
The tidal range calculation module comprises:
a first tidal range calculation unit: the tidal level imaging method is used for obtaining a first remote sensing image through tidal observation data or tidal model data and a first tidal level T of the first remote sensing image during imagingAAnd a second tidal level TBAnd calculating a first tide level TAAnd a second tidal level TBFirst tidal difference Δ T therebetweenABThe calculation formula is as follows:
ΔTAB＝|TA-TB| (5)
a second tidal range calculation unit: obtaining the highest tide level T of the area to be extracted through tide checking data or tide model dataCAnd calculating a second tide level TBAnd the highest tide level TCSecond tidal difference Δ T therebetweenBC；
ΔTBC＝|TB-TC| (6)
The second waterline difference calculating module: for determining a first tidal range DeltaT based on a linear relationship between the tidal range DeltaT and the waterline difference DeltaSABSecond tidal range DeltaTBCAnd first waterline difference data Delta SABCalculating the maximum tide level TCCorresponding second waterline difference data Delta SBC；
A shoreline calculation module: for shifting all sampling points by Δ S toward one side of landBCiThen, a plurality of times of spline interpolation is carried out, the vector data of the discrete points are converted into smooth and continuous line vector data, and finally the general silt and silt quality of the area to be extracted is obtainedShoreline data S of photosa coastC(ii) a The spline interpolation frequency is three times, and can be specifically set according to the time requirement.
According to the coastline extraction method and system based on remote sensing image classification, provided by the embodiment of the invention, the waterline identification technology and the coastline deduction technology are effectively combined together according to the natural attributes and the pattern characteristics of the ordinary silt and muddy smooth beach coasts, so that the problem of coastline deviation caused by default of the instantaneous land-water interface line into the coastline of the coastline by the existing coastline automatic extraction technology is solved. The method has the advantages of simple scheme, low requirement on data quality, few operation parameters, high calculation efficiency, strong robustness, reliable coastline extraction result and capability of effectively improving the coastline extraction efficiency and precision.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A coastline extraction method based on remote sensing image classification is characterized by comprising the following steps:
step a: carrying out multi-scale segmentation on an input remote sensing image, wherein the input remote sensing image comprises a first remote sensing image and a second remote sensing image which are positioned in the same region;
step b: extracting first sea-land boundary data and second sea-land boundary data in the first remote sensing image and the second remote sensing image, combining the first sea-land boundary data and the second sea-land boundary data, and obtaining outer boundary data of one side facing the land according to the combined data;
step c: sampling the data of the outer boundary of the land facing side, and calculating first waterline difference data of the first sea-land boundary data and the second sea-land boundary data at each sampling point;
step d: respectively obtaining a first tide level and a second tide level of a first remote sensing image and a second remote sensing image and a highest tide level of an area to be extracted through tide checking data or tide model data, and calculating a first tide difference between the first tide level and the second tide level and a second tide difference between the second tide level and the highest tide level;
step e: calculating second waterline difference data of the highest tide level according to the first tide difference, the second tide difference and the first waterline difference data, pushing all sampling points to one side of land according to the second waterline difference data, and then performing spline interpolation to obtain coastline data of the area to be extracted;
in the step e, the second waterline difference data Δ SBCThe calculation formula of (2) is as follows:
in the above formula,. DELTA.TABDenotes the first tidal range, Δ TBCIndicates the second tidal range, Δ SABIndicating the first waterline difference data and i indicating the sample point number.
2. The coastline extraction method based on remote sensing image classification as claimed in claim 1, wherein in the step a, the multi-scale segmentation of the input remote sensing image is specifically: carrying out multi-scale segmentation on the input remote sensing image by using an object-oriented image classification method, wherein the multi-scale segmented multispectral wave band comprises a blue-green spectrum band B1Green spectrum segment B2Red spectral band B3And near infrared spectrum band B4Weight factor Q of each multispectral bandiComprises the following steps:
3. the coastline extraction method based on remote sensing image classification as claimed in claim 2, wherein in the step a, the multi-scale segmentation of the input remote sensing image specifically comprises:
step a 1: respectively setting numerical values of a segmentation scale, a shape factor and a compactness factor;
step a 2: respectively aligning the multispectral wave band B according to the weight factor, the segmentation scale, the shape factor and the compactness factor1、B2、B3And B4And performing multi-scale segmentation.
4. The coastline extraction method based on remote-sensing image classification as claimed in claim 3, wherein in the step b, the extracting of the first and second sea-land boundary data in the first and second remote-sensing images is specifically: establishing an operational characteristic NDWI according to the multi-scale segmented object, extracting seawater areas in the first remote sensing image and the second remote sensing image by using a threshold classification method, converting surface vector data of the seawater areas in the first remote sensing image and the second remote sensing image into line vector data through spatial data processing, and obtaining first sea-land boundary line data and second sea-land boundary line data in the first remote sensing image and the second remote sensing image according to the line vector data; wherein, the formula of the NDWI is as follows:
5. a coastline extraction system based on remote sensing image classification is characterized by comprising:
an image segmentation module: the remote sensing image segmentation method comprises the steps of performing multi-scale segmentation on an input remote sensing image, wherein the input remote sensing image comprises a first remote sensing image and a second remote sensing image which are located in the same region;
sea-land boundary extraction module: the system comprises a first remote sensing image, a second remote sensing image, a third remote sensing image and a fourth remote sensing image, wherein the first remote sensing image and the second remote sensing image are used for acquiring first sea-land boundary data and second sea-land boundary data in the first remote sensing image and the second remote sensing image;
sea-land boundary line merging module: the data processing device is used for merging the first sea-land boundary data and the second sea-land boundary data and obtaining the outer boundary data of one side facing the land according to the merged data;
the first waterline difference calculating module: a first waterline difference data for sampling the outer boundary data on the land side and calculating the first and second sea-land boundary data at each sampling point;
a tidal range calculation module: the tidal range data acquisition unit is used for respectively obtaining a first tidal level and a second tidal level of the first remote sensing image and the second remote sensing image and a highest tidal level of an area to be extracted through tidal range data or tidal model data, and calculating a first tidal range between the first tidal level and the second tidal range and a second tidal range between the second tidal level and the highest tidal range;
the second waterline difference calculating module: second waterline difference data for calculating the highest tide level from the first tide difference, second tide difference and first waterline difference data;
a shoreline calculation module: the second waterline difference data is used for pushing all sampling points to one side of land according to the second waterline difference data and then carrying out spline interpolation to obtain the coastline data of the area to be extracted;
the second waterline difference data Δ SBCThe calculation formula of (2) is as follows:
in the above formula,. DELTA.TABDenotes the first tidal range, Δ TBCIndicates the second tidal range, Δ SABIndicating the first waterline difference data and i indicating the sample point number.
6. The coastline extraction system based on remote-sensing image classification as claimed in claim 5, wherein the image segmentation module performs multi-scale segmentation on the input remote-sensing image specifically as follows: remote sensing image input by object-oriented image classification methodPerforming multi-scale segmentation on the image, wherein the multi-spectral bands of the multi-scale segmentation comprise blue-green spectral bands B1Green spectrum segment B2Red spectral band B3And near infrared spectrum band B4Weight factor Q of each multispectral bandiComprises the following steps:
7. the coastline extraction system based on remote-sensing image classification as claimed in claim 6, wherein the image segmentation module performs multi-scale segmentation on the input remote-sensing image specifically as follows: respectively setting numerical values of a segmentation scale, a shape factor and a compactness factor; respectively aligning the multispectral wave band B according to the weight factor, the segmentation scale, the shape factor and the compactness factor1、B2、B3And B4And performing multi-scale segmentation.
8. The coastline extraction system based on remote-sensing image classification as claimed in claim 7, further comprising a seawater region extraction module, wherein the seawater region extraction module is configured to establish an operational feature "NDWI" according to the multi-scale segmented object, extract the seawater regions in the first and second remote-sensing images by using a threshold classification method, convert the surface vector data of the seawater regions in the first and second remote-sensing images into line vector data by spatial data processing, and obtain the first and second sea-land boundary data in the first and second remote-sensing images according to the line vector data; wherein, the formula of the NDWI is as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710431726.4A CN107358161B (en) | 2017-06-08 | 2017-06-08 | Coastline extraction method and coastline extraction system based on remote sensing image classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710431726.4A CN107358161B (en) | 2017-06-08 | 2017-06-08 | Coastline extraction method and coastline extraction system based on remote sensing image classification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107358161A CN107358161A (en) | 2017-11-17 |
| CN107358161B true CN107358161B (en) | 2020-01-10 |
Family
ID=60272705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710431726.4A Active CN107358161B (en) | 2017-06-08 | 2017-06-08 | Coastline extraction method and coastline extraction system based on remote sensing image classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107358161B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256419B (en) * | 2017-12-05 | 2018-11-23 | 交通运输部规划研究院 | A method of port and pier image is extracted using multispectral interpretation |
| CN108985274B (en) * | 2018-08-20 | 2023-07-14 | 上海磐导智能科技有限公司 | Water surface foreign matter identification method |
| CN109190538B (en) * | 2018-08-24 | 2021-06-08 | 华北水利水电大学 | Sediment-laden river delta coastal zone evolution analysis method based on remote sensing technology |
| CN111651707B (en) * | 2020-05-28 | 2023-04-25 | 广西大学 | Tidal level inversion method based on optical shallow water region satellite remote sensing image |
| CN113191989B (en) * | 2021-05-25 | 2021-11-19 | 宁波大学 | Water line remote sensing extraction method for muddy coast under near-shore complex environment |
| CN116580321B (en) * | 2023-07-12 | 2023-09-08 | 江苏省地质调查研究院 | Automatic recognition method for remote sensing image shoreline |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102013015A (en) * | 2010-12-02 | 2011-04-13 | 南京大学 | Object-oriented remote sensing image coastline extraction method |
| US8224768B1 (en) * | 2008-04-18 | 2012-07-17 | Wsi, Corporation | Tropical cyclone prediction system and method |
| CN103530635A (en) * | 2013-09-23 | 2014-01-22 | 上海海洋大学 | Coastline extracting method based on satellite microwave remote sensing image |
| CN103793907A (en) * | 2013-12-12 | 2014-05-14 | 中国科学院深圳先进技术研究院 | Water body information extracting method and device |
| CN105374041A (en) * | 2015-11-18 | 2016-03-02 | 国家海洋局第一海洋研究所 | Method of extracting sandy coastline by using multiple periods of remote sensing images |
| CN105740794A (en) * | 2016-01-27 | 2016-07-06 | 中国人民解放军92859部队 | Satellite image based coastline automatic extraction and classification method |
| CN106156758A (en) * | 2016-07-29 | 2016-11-23 | 辽宁工程技术大学 | A kind of tidal saltmarsh method in SAR coast chart picture |
-
2017
- 2017-06-08 CN CN201710431726.4A patent/CN107358161B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8224768B1 (en) * | 2008-04-18 | 2012-07-17 | Wsi, Corporation | Tropical cyclone prediction system and method |
| CN102013015A (en) * | 2010-12-02 | 2011-04-13 | 南京大学 | Object-oriented remote sensing image coastline extraction method |
| CN103530635A (en) * | 2013-09-23 | 2014-01-22 | 上海海洋大学 | Coastline extracting method based on satellite microwave remote sensing image |
| CN103793907A (en) * | 2013-12-12 | 2014-05-14 | 中国科学院深圳先进技术研究院 | Water body information extracting method and device |
| CN105374041A (en) * | 2015-11-18 | 2016-03-02 | 国家海洋局第一海洋研究所 | Method of extracting sandy coastline by using multiple periods of remote sensing images |
| CN105740794A (en) * | 2016-01-27 | 2016-07-06 | 中国人民解放军92859部队 | Satellite image based coastline automatic extraction and classification method |
| CN106156758A (en) * | 2016-07-29 | 2016-11-23 | 辽宁工程技术大学 | A kind of tidal saltmarsh method in SAR coast chart picture |
Non-Patent Citations (3)
| Title |
|---|
| Researching the Method of Coastline Extracted by Remote Sensing Image;Jianzhong Yin等;《IEEE》;20111231;全文 * |
| 海滨城市海岸带区域生态环境时空变化特征研究;易琳等;《海洋环境科学》;20170430;第36卷(第2期);全文 * |
| 近42年黄河口海岸线遥感监测与变迁分析;王集宁等;《国土资源遥感》;20160930;第28卷(第3期);第188-193页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107358161A (en) | 2017-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358161B (en) | Coastline extraction method and coastline extraction system based on remote sensing image classification | |
| Cheng et al. | FusionNet: Edge aware deep convolutional networks for semantic segmentation of remote sensing harbor images | |
| Liu et al. | A novel region-merging approach for coastline extraction from sentinel-1A IW mode SAR imagery | |
| Kavzoglu et al. | A comparative study of segmentation quality for multi-resolution segmentation and watershed transform | |
| CN107330875B (en) | Water body surrounding environment change detection method based on forward and reverse heterogeneity of remote sensing image | |
| Wang | A multi-scale approach for delineating individual tree crowns with very high resolution imagery | |
| CN111027446B (en) | Coastline automatic extraction method of high-resolution image | |
| Bramhe et al. | Extraction of built-up area by combining textural features and spectral indices from landsat-8 multispectral image | |
| CN105894513B (en) | Take the remote sensing image variation detection method and system of imaged object change in time and space into account | |
| Hou et al. | SAR image ship detection based on visual attention model | |
| CN103218811A (en) | Statistical distribution-based satellite multi-spectral image waveband registration method | |
| CN108710862A (en) | A kind of high-resolution remote sensing image Clean water withdraw method | |
| CN111080696A (en) | Underwater sea cucumber identification and positioning method based on computer vision | |
| CN103679740B (en) | ROI (Region of Interest) extraction method of ground target of unmanned aerial vehicle | |
| CN109886170A (en) | A kind of identification of oncomelania intelligent measurement and statistical system | |
| CN111597930A (en) | Coastline extraction method based on remote sensing cloud platform | |
| Li et al. | Integrating multiple textural features for remote sensing image change detection | |
| CN104866852B (en) | Extract the method and device of windy and sandy soil information in remote sensing image | |
| Li et al. | Dynamic waterline mapping of inland great lakes using time-series SAR data from GF-3 and S-1A satellites: A case study of DJK reservoir, China | |
| Elkhateeb et al. | A novel coarse-to-Fine Sea-land segmentation technique based on superpixel fuzzy C-means clustering and modified Chan-Vese model | |
| Aung et al. | Ayeyarwady river regions detection and extraction system from Google Earth imagery | |
| Duan et al. | An index-based shadow extraction approach on high-resolution images | |
| Singh et al. | A hybrid approach for information extraction from high resolution satellite imagery | |
| Wu et al. | Research on crack detection algorithm of asphalt pavement | |
| Ding et al. | Study on building extraction from high-resolution images using Mbi |
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 |