CN107358161A - A kind of tidal saltmarsh method and system based on classification of remote-sensing images - Google Patents
A kind of tidal saltmarsh method and system based on classification of remote-sensing images Download PDFInfo
- Publication number
- CN107358161A CN107358161A CN201710431726.4A CN201710431726A CN107358161A CN 107358161 A CN107358161 A CN 107358161A CN 201710431726 A CN201710431726 A CN 201710431726A CN 107358161 A CN107358161 A CN 107358161A
- Authority
- CN
- China
- Prior art keywords
- tidal
- remote sensing
- msub
- sensing image
- 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.)
- Granted
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of tidal saltmarsh method and system based on classification of remote-sensing images.Including:Multi-scale division is carried out to the remote sensing image of input, the first land and sea junction line number evidence and the second land and sea junction line number evidence in remote sensing image is extracted, obtains the external boundary data to land side;Sampled in the external boundary data, and the first waterline difference data of two land and sea junction line number evidences is calculated on each sampled point;The first tidal level and the second tidal level of two width remote sensing images, and the highest water level in region to be extracted are calculated, and calculates the first tidal range between the first tidal level and the second tidal level, and the second tidal range between the second tidal level and highest water level;The second waterline difference data of highest water level is calculated according to the first tidal range, the second tidal range and the first waterline difference data, spline interpolation is carried out after elapsing all sampled points to land side according to the second waterline difference data, obtains the coastline data in region to be extracted.The present invention can effectively improve tidal saltmarsh efficiency and precision.
Description
Technical field
The present invention relates to ECOLOGICAL ENVIRONMENTAL MONITORING technical field, more particularly to a kind of coastline based on classification of remote-sensing images carries
Take method and system.
Background technology
Coastline is the function line of demarcation of flood and field.Wherein, general flour sand Muddy Bottoms light beach seashore water front is for I again
The important component in state coastline.The beach face of general flour sand Muddy Bottoms light beach seashore is very gentle, and the gradient only has 1/1000~
1/3000.The intertidal zone broad of general flour sand Muddy Bottoms light beach seashore, it can be seen that obvious tidal creek on intertidal zone
Development.Extraction is identified to general flour sand Muddy Bottoms light beach seashore water front, is not only to carry out extra large land coupling, city expansion
, the precondition of the action such as coastal region exploitation, while be also the research work such as geographical information management, Coastal Zone Investigation
Important topic.
Traditional flour sand Muddy Bottoms light beach seashore Extracting costline method tends to rely on data mapping on the spot, i.e., by surveying and drawing people
Member is measured in real time in spring tide or climax period on the spot using photogrammetric technology and certain instrument and equipment, this method
Waste time and energy, it is extremely inefficient and influenceed seriously by artificial experience, be the problem of most critical full coastline can not be carried out it is real
When, dynamically measure, it is difficult to reflect the dynamic change in coastline.In order to improve the efficiency surveyed and drawn on the spot, based on remote sensing skill
The tidal saltmarsh method of art is shown one's talent.The existing flour sand Muddy Bottoms light beach seashore Extracting costline based on remote sensing technology is typically sharp
Coastline is extracted with Remote Image Classification, using the spectrum and design feature of Target scalar, the side interpreted by visual observation
Method obtains the spatial positional information in coastline directly from remote sensing image.But due to time when aeroplane photography or satellite pass by
It is difficult to it is mapped with the high tide point of locality, so the water that general remote sensing supervision, semi-supervised or unsupervised classification are extracted
Land border is not often coastline (the seashore by the land and water boundary line in image data as the seashore truly
Line).From the point of view of existing correlation technique, most coastline automatic Extraction Algorithm is all to study how to utilize Digital Image Processing
Technology extracts instantaneous land and water boundary line, and it is substantially the process of a Digital Image Segmentation cluster, and related technical method is very
More, its basic technical scheme is as follows:
A, single time series remote sensing image data is inputted;Mainly include Landsat (US Terrestrial explorer satellite system),
SPOT (place), SAR (synthetic aperture radar), QuickBird (QuickBird Satellite), IKONOS (Yi Ke Northeys satellite) etc.;
B, coastline characteristic of division is chosen;Mainly include tone, color, shape, size, texture, shade, related layouts
Deng;
C, waters and land area decomposition method are studied:Mainly include visual interpretation, supervised classification, semisupervised classification, non-
Supervised classification etc.;
D, seashore line automatic tracing algorithm:Mainly include Roberts algorithms, Prewitt algorithms, Sobel algorithms,
Laplace algorithm, Canny algorithms etc..
In summary, it is existing based on distant although advantages such as remote sensing technology have real-time, dynamic, the cycle is short, scope is big
The tidal saltmarsh method of the sense technology but only coastline by the land and water boundary line in image data as the seashore, but real
Border situation is the spring tide or high water line that the imaging time of general remote sensing image often all can not accurately correspond to locality, so must
Climax waterline must be deduced using general tidal level waterline, therefore, identify or extract the technology in proper coastline also very not
It is ripe.
The content of the invention
The invention provides a kind of tidal saltmarsh method and system based on classification of remote-sensing images, it is intended at least certain
Solves one of above-mentioned technical problem of the prior art in degree.
In order to solve the above problems, the invention provides following technical scheme:
A kind of tidal saltmarsh method based on classification of remote-sensing images, comprises the following steps:
Step a:Multi-scale division is carried out to the remote sensing image of input, wherein, the remote sensing image of the input includes being located at
First remote sensing image and the second remote sensing image of the same area;
Step b:Extract the first land and sea junction line number evidence and second in first remote sensing image and the second remote sensing image
Land and sea junction line number evidence, and merge the first land and sea junction line number evidence and the second land and sea junction line number evidence, according to merging data
Obtain the external boundary data to land side;
Step c:Sampled in the external boundary data to land side, and described is calculated on each sampled point
First waterline difference data of one land and sea junction line number evidence and the second land and sea junction line number evidence;
Step d:The first remote sensing image and the second remote sensing image are respectively obtained by tidal observation data or tidal model data
The first tidal level and the second tidal level, and the highest water level in region to be extracted, and calculate first tidal level and the second tidal level it
Between the first tidal range, and the second tidal range between second tidal level and highest water level;
Step e:The of the highest water level is calculated according to first tidal range, the second tidal range and the first waterline difference data
Two waterline difference datas, and spline interpolation is carried out after elapsing all sampled points to land side according to the second waterline difference data,
Obtain the coastline data in the region to be extracted.
The technical scheme that the embodiment of the present invention is taken also includes:In the step a, the remote sensing image of described pair of input enters
Row multi-scale division is specially:Multi-scale division is carried out to the remote sensing image of input using the image classification method of object-oriented,
The multi light spectrum hands of the multi-scale division includes bluish-green spectral coverage B1, green spectral coverage B2, red spectral coverage B3With near-infrared spectral coverage B4, each
The weight factor Q of multi light spectrum handsiFor:
The technical scheme that the embodiment of the present invention is taken also includes:In the step a, the remote sensing image of described pair of input enters
Row multi-scale division specifically includes:
Step a1:The numerical value of segmentation yardstick, form factor and degree of the compacting factor is set respectively;
Step a2:According to weight factor, segmentation yardstick, form factor and degree of the compacting factor respectively to multi light spectrum hands B1、
B2、B3And B4Carry out multi-scale division.
The technical scheme that the embodiment of the present invention is taken also includes:In the step b, it is described extraction the first remote sensing image and
The first land and sea junction line number evidence and the second land and sea junction line number evidence in second remote sensing image are specially:After multi-scale division
Object establish operating characteristic " NDWI ", extracted using threshold classification method in first remote sensing image and the second remote sensing image
Seawater region, by spatial data handling by the face vector in the seawater region in first remote sensing image and the second remote sensing image
Data switch to line vector data, and obtain first in first remote sensing image and the second remote sensing image according to line vector data
Land and sea junction line number evidence and the second land and sea junction line number evidence;Wherein, the calculation formula of described " NDWI " is:
The technical scheme that the embodiment of the present invention is taken also includes:In the step e, the second waterline difference data Δ SBC
Calculation formula be:
In above-mentioned formula, Δ TABRepresent the first tidal range, Δ TBCRepresent the second tidal range, Δ SABThe first waterline difference data is represented,
I represents sampled point sequence number.
Another technical scheme that the embodiment of the present invention is taken is:A kind of tidal saltmarsh system based on classification of remote-sensing images
System, including:
Image Segmentation module:For carrying out multi-scale division to the remote sensing image of input, wherein, the remote sensing shadow of the input
As including the first remote sensing image and the second remote sensing image positioned at the same area;
Land and sea junction line drawing module:For extracting the first Hai Lu in first remote sensing image and the second remote sensing image
Boundary line data and the second land and sea junction line number evidence;
Land and sea junction line merging module:For merging the first land and sea junction line number evidence and the second land and sea junction line number
According to obtaining the external boundary data to land side according to merging data;
First waterline difference computing module:For being sampled in the external boundary data to land side, and each
The first waterline difference data of the first land and sea junction line number evidence and the second land and sea junction line number evidence is calculated on sampled point;
Tidal range computing module:For respectively obtaining the first remote sensing image and by tidal observation data or tidal model data
The first tidal level and the second tidal level of two remote sensing images, and the highest water level in region to be extracted, and calculate first tidal level with
The second tidal range between the first tidal range between second tidal level, and second tidal level and highest water level;
Second waterline difference computing module:Based on according to first tidal range, the second tidal range and the first waterline difference data
Calculate the second waterline difference data of the highest water level;
Water front computing module:For being carried out after elapsing all sampled points to land side according to the second waterline difference data
Spline interpolation, obtain the coastline data in the region to be extracted.
The technical scheme that the embodiment of the present invention is taken also includes:The Image Segmentation module is carried out to the remote sensing image of input
Multi-scale division is specially:Multi-scale division, institute are carried out to the remote sensing image of input using the image classification method of object-oriented
Stating the multi light spectrum hands of multi-scale division includes bluish-green spectral coverage B1, green spectral coverage B2, red spectral coverage B3With near-infrared spectral coverage B4, Mei Geduo
The weight factor Q of spectral bandiFor:
The technical scheme that the embodiment of the present invention is taken also includes:The Image Segmentation module is carried out to the remote sensing image of input
Multi-scale division is specially:The numerical value of segmentation yardstick, form factor and degree of the compacting factor is set respectively;According to weight factor, divide
Yardstick, form factor and degree of the compacting factor are cut respectively to multi light spectrum hands B1、B2、B3And B4Carry out multi-scale division.
The technical scheme that the embodiment of the present invention is taken also includes seawater region extraction module, the seawater region extraction module
For establishing operating characteristic " NDWI " according to the object after multi-scale division, the first remote sensing shadow is extracted using threshold classification method
Seawater region in picture and the second remote sensing image, the land and sea junction line drawing module is by spatial data handling by described first
The face vector data in the seawater region in remote sensing image and the second remote sensing image switchs to line vector data, and according to line vector data
Obtain the first land and sea junction line number evidence and the second land and sea junction line number evidence in first remote sensing image and the second remote sensing image;
Wherein, the calculation formula of described " NDWI " is:
The technical scheme that the embodiment of the present invention is taken also includes:The second waterline difference data Δ SBCCalculation formula be:
In above-mentioned formula, Δ TABRepresent the first tidal range, Δ TBCRepresent the second tidal range, Δ SABThe first waterline difference data is represented,
I represents sampled point sequence number.
Relative to prior art, beneficial effect caused by the embodiment of the present invention is:The embodiment of the present invention based on remote sensing
The tidal saltmarsh method and system of image classification are become silted up by the way that waterline identification technology and water front are deduced into technology according to general flour sand
The natural quality and general layout feature of shale light beach seashore have been effectively incorporated into together, are solved existing coastline and are automatically extracted skill
Instantaneous land and water boundary line is often defaulted as water front offset issue caused by the coastline of the seashore by art.The present invention program letter
Single, relatively low to the quality requirement of data, operational parameter is seldom, and computational efficiency is higher, strong robustness, obtained tidal saltmarsh knot
Fruit is more reliable, can effectively improve tidal saltmarsh efficiency and precision.
Brief description of the drawings
Fig. 1 is the flow chart of the tidal saltmarsh method based on classification of remote-sensing images of the embodiment of the present invention;
Fig. 2 is the structural representation of the tidal saltmarsh system based on classification of remote-sensing images of the embodiment of the present invention.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.
Referring to Fig. 1, it is the flow chart of the tidal saltmarsh method based on classification of remote-sensing images of the embodiment of the present invention.This
The tidal saltmarsh method based on classification of remote-sensing images of inventive embodiments comprises the following steps:
Step 100:Input the first remote sensing image;
In step 100, the first remote sensing image of input is GF-2 (high score two) remote sensing image, the present invention other
In embodiment, the remote sensing image of input can also be other kinds of remote sensing image.
Step 200:4 multi light spectrum hands of the first remote sensing image of input are named as B successively1(bluish-green spectral coverage), B2
(green spectral coverage), B3(red spectral coverage) and B4(near-infrared spectral coverage);
Step 300:Multi-scale division is carried out to the first remote sensing image using the image classification method of object-oriented
(Multiresolution Segmentation);
In step 300, the step of multi-scale division is as follows:
Step 301:Participating in the multi light spectrum hands of multi-scale division includes B1、B2、B3、B4, the weight of each multi light spectrum hands
Factor QiIt is as follows:
Step 302:Segmentation yardstick (Scale Parameter) is set;
In embodiments of the present invention, the numerical value for splitting yardstick is arranged to Scale Parameter≤40, specifically can be according to reality
Border demand is set.
Step 303:Form factor (Shape) is set;
In embodiments of the present invention, the numerical value of form factor is arranged to Shape≤0.1, can specifically enter according to the actual requirements
Row setting.
Step 304:Setting degree of the compacting factor (Compactness);
In embodiments of the present invention, the numerical value of degree of the compacting factor is arranged to Compactness≤0.3, specifically can be according to reality
Border demand is set.
Step 305:According to weight factor, segmentation yardstick, form factor and degree of the compacting factor respectively to multi light spectrum hands B1、
B2、B3And B4Multi-scale division is carried out, and it is " unclassified " that caused object after multi-scale division is assigned into class.
Step 400:Operating characteristic " NDWI (Normalized Difference are established according to the object after multi-scale division
Water Index, aqua index is normalized, difference, which is normalized, with the specific band of remote sensing image is handled, to highlight in image
Water-Body Information) ", and extract the seawater region in the first remote sensing image using threshold classification method;
In step 400, the calculation formula of " NDWI " is as follows:
In formula (2), B2For the brightness value of the green wave band of the first remote sensing image, B4For the first remote sensing image near infrared band
Brightness value.
In above-mentioned, threshold classification method is that the object for meeting certain threshold condition is entered as into seawater by " unclassified "
The process of " seawater ", its calculation formula are as follows:
In formula (3), α is extraction threshold value, can be set according to the actual requirements.
Step 500:The face vector data in the seawater region in the first remote sensing image is switched to by line by spatial data handling
Vector data, and obtain according to line vector data the first Hai Lu of the general flour sand Muddy Bottoms light beach seashore in the first remote sensing image
Boundary line data SA;
Step 600:Input is located at second remote sensing image of the same area with the first remote sensing image, and re-executes step
200, to step 500, obtain the second land and sea junction line number evidence of the general flour sand Muddy Bottoms light beach seashore in the second remote sensing image
SB;
Step 700:First land and sea junction line number is merged according to S by spatial data handlingAWith the second land and sea junction line number evidence
SB, and the external boundary data S to land side is obtained according to merging dataA+BWith the external boundary data to extra large side
Step 800:In outer data boundary SA+BOn sampled at interval of certain distance d, and counted on each sampled point
The first land and sea junction line number of the position is calculated according to SAWith the second land and sea junction line number according to SBThe first waterline difference data Δ spatially
SAB, calculation formula is as follows:
In formula (4), i represents sampled point sequence number.The embodiment of the present invention converts by using by continuous lines vector data
Into the method for sampling of discrete point vector data, solve the problems, such as that continuous lines vector data is not easy to space calculating;Wherein, sample
Spacing distance d numerical value is set according to demand by user.
Step 900:The first remote sensing image is obtained by tidal observation data or tidal model data and the first remote sensing image exists
The first tidal level T during imagingAWith the second tidal level TB, and calculate the first tidal level TAWith the second tidal level TBBetween the first tidal range Δ TAB,
Calculation formula is as follows:
ΔTAB=| TA-TB| (5)
Step 1000:The highest water level T in region to be extracted is obtained by tidal observation data or tidal model dataC, and count
Calculate the second tidal level TBWith highest water level TCBetween the second tidal range Δ TBC;
ΔTBC=| TB-TC| (6)
Step 1100:Based on the linear relationship between tidal range Δ T and waterline difference Δ S, according to the first tidal range Δ TAB, second tide
Poor Δ TBCAnd the first waterline difference data Δ SABExtrapolate highest water level TCThe second corresponding waterline difference data Δ SBC;
Step 1200:All sampled points are elapsed into Δ S to land sideBCiAfter carry out multiple spline interpolation, discrete point is sweared
Amount data change into smooth, continuous line vector data, finally give the general flour sand Muddy Bottoms light beach seashore in region to be extracted
Water front data SC。
In step 1200, spline interpolation number is that three times, can specifically be set according to time demand.
Referring to Fig. 2, it is the structural representation of the tidal saltmarsh system based on classification of remote-sensing images of the embodiment of the present invention
Figure.The tidal saltmarsh system based on classification of remote-sensing images of the embodiment of the present invention includes image input module, image name mould
Block, Image Segmentation module, seawater region extraction module, land and sea junction line drawing module, land and sea junction line merging module, the first water
Line difference computing module, tidal range computing module, the second waterline difference computing module and water front computing module.
Image input module:For inputting remote sensing image;In embodiments of the present invention, the remote sensing image of input includes being located at
First remote sensing image and the second remote sensing image of the same area, the first remote sensing image and the second remote sensing image are respectively GF-2 (high
Divide No. two) remote sensing image.
Image names module:For 4 multi light spectrum hands of the first remote sensing image and the second remote sensing image to be named successively
For B1(bluish-green spectral coverage), B2(green spectral coverage), B3(red spectral coverage) and B4(near-infrared spectral coverage);
Image Segmentation module:For distant to the first remote sensing image and second respectively using the image classification method of object-oriented
Feel image and carry out multi-scale division;Wherein, multi-scale division specifically includes:
1:Participating in the multi light spectrum hands of multi-scale division includes B1、B2、B3、B4, the weight factor Q of each multi light spectrum handsi
It is as follows:
2:Segmentation yardstick (Scale Parameter) is set;In embodiments of the present invention, the numerical value for splitting yardstick is arranged to
Scale Parameter≤40, it can specifically be set according to the actual requirements.
3:Form factor (Shape) is set;In embodiments of the present invention, the numerical value of form factor be arranged to Shape≤
0.1, it can specifically be set according to the actual requirements.
4:Setting degree of the compacting factor (Compactness);In embodiments of the present invention, the numerical value of degree of the compacting factor is arranged to
Compactness≤0.3, it can specifically be set according to the actual requirements.
5:According to weight factor, segmentation yardstick, form factor and degree of the compacting factor respectively to multi light spectrum hands B1、B2、B3With
B4Multi-scale division is carried out, and it is " unclassified " that caused object after multi-scale division is assigned into class.
Seawater region extraction module:For establishing operating characteristic " NDWI according to the object after multi-scale division
((Normalized Difference Water Index, normalizing aqua index)) ", and extracted respectively using threshold classification method
Seawater region in first remote sensing image and the second remote sensing image;Wherein, the calculation formula of " NDWI " is as follows:
In formula (2), B2For the first remote sensing image and the brightness value of the green wave band of the second remote sensing image, B4For the first remote sensing
The brightness value of image and the second remote sensing image near infrared band.
In above-mentioned, threshold classification method is that the object for meeting certain threshold condition is entered as into seawater by " unclassified "
The process of " seawater ", its calculation formula are as follows:
In formula (3), α is extraction threshold value, can be set according to the actual requirements.
Land and sea junction line drawing module:For by spatial data handling respectively by the first remote sensing image and the second remote sensing shadow
The face vector data in the seawater region as in switchs to line vector data, and obtains the first remote sensing image and the according to line vector data
First land and sea junction line number of the general flour sand Muddy Bottoms light beach seashore in two remote sensing images is according to SAWith the second land and sea junction line number
According to SB;
Land and sea junction line merging module:For merging the first land and sea junction line number according to S by spatial data handlingAWith second
Land and sea junction line number is according to SB, and the external boundary data S to land side is obtained according to merging dataA+BWith the external boundary to extra large side
Data
First waterline difference computing module:For in outer data boundary SA+BOn sampled at interval of certain distance d, and
The first land and sea junction line number of the position is calculated on each sampled point according to SAWith the second land and sea junction line number according to SBSpatially
First waterline difference data Δ SAB, calculation formula is as follows:
In formula (4), i represents sampled point sequence number.The embodiment of the present invention converts by using by continuous lines vector data
Into the method for sampling of discrete point vector data, solve the problems, such as that continuous lines vector data is not easy to space calculating;Wherein, sample
Spacing distance d numerical value is set according to demand by user.
Tidal range computing module includes:
First tidal range computing unit:For obtaining the first remote sensing image and by tidal observation data or tidal model data
First tidal level T of one remote sensing image in imagingAWith the second tidal level TB, and calculate the first tidal level TAWith the second tidal level TBBetween
First tidal range Δ TAB, calculation formula is as follows:
ΔTAB=| TA-TB| (5)
Second tidal range computing unit:For obtaining the highest in region to be extracted by tidal observation data or tidal model data
Tidal level TC, and calculate the second tidal level TBWith highest water level TCBetween the second tidal range Δ TBC;
ΔTBC=| TB-TC| (6)
Second waterline difference computing module:For based on the linear relationship between tidal range Δ T and waterline difference Δ S, according to first
Tidal range Δ TAB, the second tidal range Δ TBCAnd the first waterline difference data Δ SABExtrapolate highest water level TCThe second corresponding waterline
Difference data Δ SBC;
Water front computing module:For all sampled points to be elapsed into Δ S to land sideBCiAfter carry out multiple spline interpolation, will
Discrete point vector data changes into smooth, continuous line vector data, finally gives the general flour sand Muddy Bottoms in region to be extracted
The water front data S of light beach seashoreC;Wherein, spline interpolation number is that three times, can specifically be set according to time demand.
The tidal saltmarsh method and system based on classification of remote-sensing images of the embodiment of the present invention by waterline by identifying skill
Art and water front are deduced technology and are effectively incorporated into according to the natural quality and general layout feature of general flour sand Muddy Bottoms light beach seashore
Together, solve existing coastline and automatically extract technology and often produced the coastline that instantaneous land and water boundary line is defaulted as the seashore
Raw water front offset issue.The present invention program is simple, relatively low to the quality requirement of data, and operational parameter is seldom, computational efficiency compared with
Height, strong robustness, obtained tidal saltmarsh result is more reliable, can effectively improve tidal saltmarsh efficiency and precision.
The foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
- A kind of 1. tidal saltmarsh method based on classification of remote-sensing images, it is characterised in that comprise the following steps:Step a:Multi-scale division is carried out to the remote sensing image of input, wherein, the remote sensing image of the input is included positioned at same First remote sensing image and the second remote sensing image in region;Step b:Extract the first land and sea junction line number evidence and the second Hai Lu in first remote sensing image and the second remote sensing image Boundary line data, and merge the first land and sea junction line number evidence and the second land and sea junction line number evidence, obtained according to merging data To the external boundary data of land side;Step c:Sampled in the external boundary data to land side, and first sea is calculated on each sampled point First waterline difference data of land boundary line data and the second land and sea junction line number evidence;Step d:The of the first remote sensing image and the second remote sensing image is respectively obtained by tidal observation data or tidal model data One tidal level and the second tidal level, and the highest water level in region to be extracted, and calculate between first tidal level and the second tidal level The second tidal range between first tidal range, and second tidal level and highest water level;Step e:The second water of the highest water level is calculated according to first tidal range, the second tidal range and the first waterline difference data Line difference data, and spline interpolation is carried out after elapsing all sampled points to land side according to the second waterline difference data, obtain The coastline data in the region to be extracted.
- 2. the tidal saltmarsh method according to claim 1 based on classification of remote-sensing images, it is characterised in that in the step In rapid a, the remote sensing image of described pair of input carries out multi-scale division and is specially:Using the image classification method of object-oriented to defeated The remote sensing image entered carries out multi-scale division, and the multi light spectrum hands of the multi-scale division includes bluish-green spectral coverage B1, green spectral coverage B2、 Red spectral coverage B3With near-infrared spectral coverage B4, the weight factor Q of each multi light spectrum handsiFor:<mrow> <msub> <mi>Q</mi> <mi>i</mi> </msub> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <msub> <mi>Q</mi> <mn>1</mn> </msub> <mo>=</mo> <mn>1</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>Q</mi> <mn>2</mn> </msub> <mo>=</mo> <mn>2</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>Q</mi> <mn>3</mn> </msub> <mo>=</mo> <mn>1</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>Q</mi> <mn>4</mn> </msub> <mo>=</mo> <mn>3</mn> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>,</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>3</mn> <mo>,</mo> <mn>4.</mn> </mrow>
- 3. the tidal saltmarsh method according to claim 2 based on classification of remote-sensing images, it is characterised in that in the step In rapid a, the remote sensing image of described pair of input carries out multi-scale division and specifically included:Step a1:The numerical value of segmentation yardstick, form factor and degree of the compacting factor is set respectively;Step a2:According to weight factor, segmentation yardstick, form factor and degree of the compacting factor respectively to multi light spectrum hands B1、B2、B3 And B4Carry out multi-scale division.
- 4. the tidal saltmarsh method according to claim 3 based on classification of remote-sensing images, it is characterised in that in the step In rapid b, the first remote sensing image of the extraction and the first land and sea junction line number evidence and the second land and sea junction in the second remote sensing image Line number is according to being specially:Operating characteristic " NDWI " is established according to the object after multi-scale division, using described in the extraction of threshold classification method Seawater region in first remote sensing image and the second remote sensing image, by spatial data handling by first remote sensing image and The face vector data in the seawater region in two remote sensing images switchs to line vector data, and obtains described first according to line vector data The first land and sea junction line number evidence and the second land and sea junction line number evidence in remote sensing image and the second remote sensing image;Wherein, it is described The calculation formula of " NDWI " is:<mrow> <mi>N</mi> <mi>D</mi> <mi>W</mi> <mi>I</mi> <mo>=</mo> <mfrac> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mn>2</mn> </msub> <mo>-</mo> <msub> <mi>B</mi> <mn>4</mn> </msub> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mn>2</mn> </msub> <mo>+</mo> <msub> <mi>B</mi> <mn>4</mn> </msub> <mo>)</mo> </mrow> </mfrac> <mo>.</mo> </mrow>
- 5. the tidal saltmarsh method according to claim 4 based on classification of remote-sensing images, it is characterised in that in the step In rapid e, the second waterline difference data Δ SBCCalculation formula be:In above-mentioned formula, Δ TABRepresent the first tidal range, Δ TBCRepresent the second tidal range, Δ SABRepresent the first waterline difference data, i tables Show sampled point sequence number.
- A kind of 6. tidal saltmarsh system based on classification of remote-sensing images, it is characterised in that including:Image Segmentation module:For carrying out multi-scale division to the remote sensing image of input, wherein, the remote sensing image bag of the input Include the first remote sensing image and the second remote sensing image positioned at the same area;Land and sea junction line drawing module:For extracting the first land and sea junction in first remote sensing image and the second remote sensing image Line number evidence and the second land and sea junction line number evidence;Land and sea junction line merging module:For merging the first land and sea junction line number evidence and the second land and sea junction line number evidence, root The external boundary data to land side are obtained according to merging data;First waterline difference computing module:For being sampled in the external boundary data to land side, and in each sampling The first waterline difference data of the first land and sea junction line number evidence and the second land and sea junction line number evidence is calculated on point;Tidal range computing module:For respectively obtaining the first remote sensing image and second distant by tidal observation data or tidal model data Feel the first tidal level and the second tidal level of image, and the highest water level in region to be extracted, and calculate first tidal level and second The second tidal range between the first tidal range between tidal level, and second tidal level and highest water level;Second waterline difference computing module:For calculating institute according to first tidal range, the second tidal range and the first waterline difference data State the second waterline difference data of highest water level;Water front computing module:For carrying out batten after elapsing all sampled points to land side according to the second waterline difference data Interpolation, obtain the coastline data in the region to be extracted.
- 7. the tidal saltmarsh system according to claim 6 based on classification of remote-sensing images, it is characterised in that the image Segmentation module carries out multi-scale division to the remote sensing image of input:Using the image classification method of object-oriented to input Remote sensing image carry out multi-scale division, the multi light spectrum hands of the multi-scale division includes bluish-green spectral coverage B1, green spectral coverage B2, it is red Spectral coverage B3With near-infrared spectral coverage B4, the weight factor Q of each multi light spectrum handsiFor:<mrow> <msub> <mi>Q</mi> <mi>i</mi> </msub> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <msub> <mi>Q</mi> <mn>1</mn> </msub> <mo>=</mo> <mn>1</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>Q</mi> <mn>2</mn> </msub> <mo>=</mo> <mn>2</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>Q</mi> <mn>3</mn> </msub> <mo>=</mo> <mn>1</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>Q</mi> <mn>4</mn> </msub> <mo>=</mo> <mn>3</mn> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>,</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>3</mn> <mo>,</mo> <mn>4.</mn> </mrow>
- 8. the tidal saltmarsh system according to claim 7 based on classification of remote-sensing images, it is characterised in that the image Segmentation module carries out multi-scale division to the remote sensing image of input:Segmentation yardstick, form factor is set respectively and compacted Spend the numerical value of the factor;According to weight factor, segmentation yardstick, form factor and degree of the compacting factor respectively to multi light spectrum hands B1、B2、 B3And B4Carry out multi-scale division.
- 9. the tidal saltmarsh system according to claim 8 based on classification of remote-sensing images, it is characterised in that also include sea Aqua region extraction module, the seawater region extraction module are used to establish operating characteristic according to the object after multi-scale division " NDWI ", the seawater region in first remote sensing image and the second remote sensing image, the Hai Lu are extracted using threshold classification method Boundary line extraction module is by spatial data handling by the seawater region in first remote sensing image and the second remote sensing image Face vector data switchs to line vector data, and is obtained according to line vector data in first remote sensing image and the second remote sensing image The first land and sea junction line number evidence and the second land and sea junction line number evidence;Wherein, the calculation formula of described " NDWI " is:<mrow> <mi>N</mi> <mi>D</mi> <mi>W</mi> <mi>I</mi> <mo>=</mo> <mfrac> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mn>2</mn> </msub> <mo>-</mo> <msub> <mi>B</mi> <mn>4</mn> </msub> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <msub> <mi>B</mi> <mn>2</mn> </msub> <mo>+</mo> <msub> <mi>B</mi> <mn>4</mn> </msub> <mo>)</mo> </mrow> </mfrac> <mo>.</mo> </mrow>
- 10. the tidal saltmarsh system according to claim 9 based on classification of remote-sensing images, it is characterised in that described Two waterline difference data Δ SBCCalculation formula be:In above-mentioned formula, Δ TABRepresent the first tidal range, Δ TBCRepresent the second tidal range, Δ SABRepresent the first waterline difference data, i tables Show sampled point sequence number.
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 true CN107358161A (en) | 2017-11-17 |
CN107358161B 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) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108256419A (en) * | 2017-12-05 | 2018-07-06 | 交通运输部规划研究院 | A kind of method for extracting port and pier image using multispectral interpretation |
CN108985274A (en) * | 2018-08-20 | 2018-12-11 | 上海磐波智能科技有限公司 | Water surface method for recognizing impurities |
CN109190538A (en) * | 2018-08-24 | 2019-01-11 | 华北水利水电大学 | A kind of fully-loaded stream river deposition coast band evolution analysis method based on remote sensing technology |
CN111651707A (en) * | 2020-05-28 | 2020-09-11 | 广西大学 | Tidal level inversion method based on optical shallow water satellite remote sensing image |
CN113191989A (en) * | 2021-05-25 | 2021-07-30 | 宁波大学 | Water line remote sensing extraction method for muddy coast under near-shore complex environment |
CN116580321A (en) * | 2023-07-12 | 2023-08-11 | 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***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***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 |
---|
JIANZHONG YIN等: "Researching the Method of Coastline Extracted by Remote Sensing Image", 《IEEE》 * |
易琳等: "海滨城市海岸带区域生态环境时空变化特征研究", 《海洋环境科学》 * |
王集宁等: "近42年黄河口海岸线遥感监测与变迁分析", 《国土资源遥感》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108256419A (en) * | 2017-12-05 | 2018-07-06 | 交通运输部规划研究院 | A kind of method for extracting port and pier image using multispectral interpretation |
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 |
US10325151B1 (en) | 2017-12-05 | 2019-06-18 | Transport Planning and Research Institute Ministry of Transport | Method of extracting image of port wharf through multispectral interpretation |
CN108985274A (en) * | 2018-08-20 | 2018-12-11 | 上海磐波智能科技有限公司 | Water surface method for recognizing impurities |
CN109190538A (en) * | 2018-08-24 | 2019-01-11 | 华北水利水电大学 | A kind of fully-loaded stream river deposition coast band evolution analysis method based on remote sensing technology |
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 |
CN111651707A (en) * | 2020-05-28 | 2020-09-11 | 广西大学 | Tidal level inversion method based on optical shallow water satellite remote sensing image |
CN113191989A (en) * | 2021-05-25 | 2021-07-30 | 宁波大学 | Water line remote sensing extraction method for muddy coast under near-shore complex environment |
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 |
CN116580321A (en) * | 2023-07-12 | 2023-08-11 | 江苏省地质调查研究院 | Automatic recognition method for remote sensing image shoreline |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN107358161B (en) | 2020-01-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107358161A (en) | A kind of tidal saltmarsh method and system based on classification of remote-sensing images | |
CN103971115B (en) | Automatic extraction method for newly-increased construction land image spots based on NDVI and PanTex index | |
CN103679675B (en) | Remote sensing image fusion method oriented to water quality quantitative remote sensing application | |
Liao et al. | High-resolution remote sensing mapping of global land water | |
CN108596108B (en) | Aerial remote sensing image change detection method based on triple semantic relation learning | |
CN103839267B (en) | Building extracting method based on morphological building indexes | |
CN110147743A (en) | Real-time online pedestrian analysis and number system and method under a kind of complex scene | |
CN105608692B (en) | Polarization SAR image segmentation method based on deconvolution network and sparse classification | |
Yang et al. | Detecting and mapping tree crowns based on convolutional neural network and Google Earth images | |
CN105279769B (en) | A kind of level particle filter tracking method for combining multiple features | |
CN107423537A (en) | A kind of method of the surface temperature NO emissions reduction based on adaptive threshold | |
CN106650812A (en) | City water body extraction method for satellite remote sensing image | |
CN106294705A (en) | A kind of batch remote sensing image preprocess method | |
CN105894513B (en) | Take the remote sensing image variation detection method and system of imaged object change in time and space into account | |
Ban et al. | EO4Urban: Sentinel-1A SAR and Sentinel-2A MSI data for global urban services | |
CN106127144B (en) | Using when compose the point source risk source extraction method of empty integral feature model | |
CN107292328A (en) | The remote sensing image shadow Detection extracting method and system of multiple dimensioned multiple features fusion | |
CN105956544A (en) | Remote sensing image road intersection extraction method based on structural index characteristic | |
Wang et al. | Color-and texture-based image segmentation for improved forest delineation | |
CN103268587A (en) | Method for obtaining urban building land information by means of imitated building land index | |
CN108932474A (en) | A kind of remote sensing image cloud based on full convolutional neural networks compound characteristics sentences method | |
Singh et al. | A hybrid approach for information extraction from high resolution satellite imagery | |
An et al. | Object-oriented urban dynamic monitoring—A case study of Haidian District of Beijing | |
CN106846325B (en) | Automatic method for determining optimal segmentation result of remote sensing image | |
CN105513042A (en) | Significance detection method based on multilayer analysis and layered reasoning |
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 |