CN105427305A - Green tide information extraction method - Google Patents

Abstract

The invention belongs to the technical field of remote sensing image processing, and relates to a green tide information extraction method. The method comprises: obtaining a sea area satellite remote sensing image with a conventional method, screening images of green tide regions, and performing preprocessing operations of geometric correction and image mosaicking; calculating and determining a green tide range by adopting a normalized difference vegetation index; cutting a region of interest in any shape to generate an irregular image file containing the green tide regions; extracting green tide information by adopting a split Bregman fast projection algorithm of a variational level set two-phase image segmentation based Chen-Wees model; and finally, quantitatively calculating the green tide regions by adopting a quantitative formula. The image segmentation based variational model accurately extracts and quantifies the green tide information on the satellite remote sensing image, so that a conventional manual threshold method can be completely replaced and operational application can be realized; and method is scientific and reasonable in principle, low in human factor quantity, high in calculation speed, accurate and stable in result, high in operability, friendly in application environment, high in practicality and easy to popularize.

Description

A kind of green damp information extracting method

Technical field:

The invention belongs to technical field of remote sensing image processing, relate to a kind of green damp information extracting method, adopt the Variation Model of Iamge Segmentation on satellite remote sensing images, extract green tidewater breath and extraction result is quantized.

Background technology:

Enteromorpha is a genus of Chlorophyta Chlorophyceae Ulvaceae, also cries tongue bar and green moss, and grow in the sea, frond is emerald green, and plant is very very thin, and the same as with terrestrial plant chlorophyll a and b, naked eyes look in green filament shape, have many branches.Enteromorpha itself is nontoxic, even edible, and the resident that Chinese Jiangsu and Zhejiang Provinces one is with can cultivate Enteromorpha and edible Enteromorpha goods on a small scale at offshore; Enteromorpha assembles outburst under the marine environmental conditions of preference temperature, causes the phenomenon of ecologic environment exception to be called as the green tide of Enteromorpha, is called for short green tide.The harm of green tide mainly contain following some: one is that Enteromorpha is floating consumes a large amount of oxygen across the sea, causes being covered undersea biology by Enteromorpha because anoxic impact is grown even dead, two is that the electrodeposition substance that Enteromorpha is secreted affects benthic growing to seabed, three is cover fishery cultivating base after Enteromorpha offshore, causes the underproduction of the marine animal of cultivation and plant even dead, brings huge property and emotional distress to raiser, four are Enteromorphas to seashore tourism, spend a holiday and marine regatta sailing causes and has a strong impact on, destroy the Tourist Destination Image of coastal city, reduce the fiscal revenue of government, at present, the main monitoring mode of the green tide of Enteromorpha has satellite remote sensing, aircraft, boats and ships and land bank are maked an inspection tour, it is wide that satellite remote sensing has monitoring range, the advantage that spatial and temporal resolution is high and monitoring means is various, become the major way of the green tide monitoring of Enteromorpha, the green damp monitoring result utilizing satellite remote sensing to obtain, carry out express-analysis, identify and decipher, interpretation result is reported to relevant departments in time, for decision maker provides the monitoring analysis result of forefront, to formulate counter-measure in time, the impact of green for Enteromorpha damp disaster on society is reduced to minimum, there is important social effect, green damp information extraction in decipher process directly affects generation and the prediction and warning work of subsequent statistical analysis and interpreting report.Green damp information extraction of the prior art mainly adopts the method for visual interpretation and artificial setting threshold value, although this method is simple to operate, but Existence dependency is in expertise, human factor causes result poor accuracy and unstable problem, and when satellite remote sensing images difference in brightness is larger, needs to set multiple threshold value and extract respectively, each picture dot participates in wave band and calculates, counting yield is low, when green damp large-scale outbreak, cannot meet the demands.Therefore, a kind of green damp information extracting method of research and development, adopts the Variation Model of Iamge Segmentation on satellite remote sensing images, extract green tidewater breath and quantizes extraction result, having good society and economic worth, have a extensive future.

Summary of the invention:

The object of the invention is to the shortcoming overcoming prior art existence, seek a kind of green damp information extracting method of design, adopt the Variation Model of Iamge Segmentation on satellite remote sensing images, extract green tidewater breath, the green moisture knot fruit extracted is quantized, obtain accurate green tide and extract area.

To achieve these goals, the green damp information extracting method technique that the present invention relates to comprises screening and preprocessed data source, calculating determine green damp scope, the irregular green damp range image of cutting, extract green tidewater and cease and territory, quantum chemical method green tidal zone five steps:

(1), screening and preprocessed data source: fine, partly cloudy, without rain and the weather without typhoon, conventionally obtain sea area satellite remote sensing images, screening noise is few, sharpness is high, brightness uniformity and image resolution ratio are less than or equal to 30 meters and can cover the image in territory, green tidal zone, the image data filtered out is carried out to the pretreatment operation of geometry correction and image mosaic, complete screening and the pre-service of data source;

(2), calculate and determine green damp scope: for biological nature and the spectral characteristic of Enteromorpha, adopt vegetation index calculate and determine green damp scope, formula is as follows:

$NDVI=\frac{IR-R}{IR+R}---(1-1)$

In formula, IR represents the near-infrared band in satellite remote sensing images, selects 4 wave band datas, and R is red wave band, selects 3 wave band datas, and the vegetation index completing satellite remote sensing images calculates;

(3), the irregular green damp range image of cutting: determine green damp scope according to vegetation index computing method, cutting arbitrary shape region of interest also records the total number of pixel and the total area of region of interest, generate region of interest document data set, generate the irregular image file containing territory, green tidal zone import the region of interest document data set generated at remote sensing processing platform after, complete the cutting of irregular green damp range image;

(4) green tidewater breath, is extracted:

Adopt the division Donald Bragg graceful fast projection algorithm based on the old-Wei Si model of variation level set two-phase Iamge Segmentation to extract green tidewater breath, old-Wei Si model energy functional is as follows:

$\underset{\mathrm{\φ}}{Min}\left\{E\left(\mathrm{\φ}\right)={\∫}_{\mathrm{\Ω}}R\left(u_1,u_2\right)H\left(\mathrm{\φ}\right)dx+\mathrm{\γ}{\∫}_{\mathrm{\Ω}}\left|\▿H\left(\mathrm{\φ}\right)\right|dx\right\}---\left(1-2\right)$

$s.t.\left|\▿\mathrm{\φ}\right|=1---(1-3)$

In formula (1-2),

R(u ₁，u ₂)＝α ₁(u ₁-f) ²-α ₂(u ₂-f) ²(1-4)

Wherein u ₁and u ₂represent prospect and the background of image respectively, f represents the original image of Noise, introduces auxiliary separating fission amount order $\stackrel{\→}{w}=\▿\mathrm{\φ},$ Because with equivalence, is rewritten as formula (1-5) and formula (1-6) respectively by formula (1-2) and formula (1-3):

$\underset{\mathrm{\φ},\stackrel{\→}{w}}{Min}\left\{E\left(\mathrm{\φ},\stackrel{\→}{w}\right)={\∫}_{\mathrm{\Ω}}RH\left(\mathrm{\φ}\right)dx+\mathrm{\γ}{\∫}_{\mathrm{\Ω}}\left|\stackrel{\←}{w}\right|\mathrm{\δ}\left(\mathrm{\φ}\right)dx+\frac{\mathrm{\θ}}{2}\∫{\left(\stackrel{\→}{w}-\▿\mathrm{\φ}-{\stackrel{\→}{b}}^k\right)}^{2}dx\right\}---\left(1-5\right)$

$s.t.\stackrel{\→}{w}=1---\left(1-6\right)$

In formula (1-5),

${\stackrel{\→}{b}}^{k+1}={\stackrel{\→}{b}}^k+\▿{\mathrm{\φ}}^k-{\stackrel{\→}{w}}^k---(1-7)$

For the graceful iteration parameter of Donald Bragg, θ is positive punishment parameter, with initial value is 0,

Formula (1-5) and formula (1-6) are solved and obtain:

In formula (1-9), g is edge indicator function, and formula is:

$g\left(x\right)=\frac{1}{1+\mathrm{\γ}{|\▿(f\left(x\right)*G_{\mathrm{\σ}}\left)\right|}^2}---(1-10)$

In formula (1-10), G _σfor standard deviation is the gaussian kernel function of σ, setting initial parameter is γ=1, σ=1, θ=3000, brings formula (1-8) and formula (1-9) into and carries out solving and obtain green damp information extraction result, complete the extraction of green tidewater breath;

(5), territory, quantum chemical method green tidal zone: adopt the green damp information quantization that quantitative formula extracts step (4), quantitative formula is:

Last_area＝(clip_pixel-last_sum)/clip_pixel×clip_area(1-11)

In formula (1-11), Last_area is the total area of the green tidewater breath extracted, clip_pixel is the total number of picture element of irregular image, last_sum is the total number of background pixels point in irregular image, and clip_area is the total area of irregular image, and unit is square kilometre, bring given data into, draw the green tidewater breath total area, unit is square kilometre, completes the quantum chemical method of green tidewater breath.

The vegetation index that the present invention relates to judges the mode that the coverage condition of green vegetation mainly adopts, and vegetation index higher expression green vegetation is more intensive, and it is better to grow; Enteromorpha frond is emerald green, containing chlorophyll a and b, the spectral characteristic of Enteromorpha and seawater there are differences, Enteromorpha has stronger absorbability at blue wave band and red band, reflectivity is low, has stronger reflection peak at green band, and reflectivity is slightly high, have very strong reflection peak at near-infrared band, reflectivity is very high; The reflectivity change of seawater does not have Enteromorpha obvious, whole reflectance curve is on a declining curve, at green band, seawater equally has stronger reflection peak with Enteromorpha, the reflection peak of seawater is relatively milder, and at near-infrared band, the reflectivity of seawater is very low, the curve of spectrum of seawater and Enteromorpha has obvious difference, can calculate and determine green damp scope based on vegetation index; The result that vegetation index calculates is black white image, black is ocean, white is land and Enteromorpha, can see seawater and Enteromorpha clearly on a large scale, need the irregular green damp range image of cutting, extract green tidewater breath and territory, quantum chemical method green tidal zone obtains the green damp total area; Satellite remote sensing images comprises the non-green tidal zone of land and cloud, utilize conventional threshold values method and Variation Model to extract green tidewater breath and automatically cannot identify green tidal zone and non-green tidal zone, after the vegetation index of land and Enteromorpha calculates, result is close, land picture dot participates in Iamge Segmentation, causes green damp information extraction result inaccurate; Regular image does not have operational use to be worth in reality, needs the cutting carrying out irregular image.

The principle that the green damp information extracting method that the present invention relates to carries out quantizing is: when service regeulations image, and the prospect in level set function segmentation result image is 1, and background is 0; When using irregular image, the prospect in level set function segmentation result image is 0, and background is 1, and the region outside image is all 0; Prospect represents green tide, background pp seawater.

Compared with prior art, the Variation Model based on Iamge Segmentation accurately extracts and quantizes green tidewater breath on satellite remote sensing images, can substitute traditional artificial threshold method completely, realize operational use in the present invention; Its scientific in principle is reasonable, and human factor is few, and computing velocity is fast, and result is precise and stable, strong operability, and applied environment is friendly, and practicality is good, is easy to promote.

Embodiment:

Below by embodiment, the invention will be further described.

Embodiment 1:

The green damp information extracting method that the present embodiment relates to completes by means of computing machine and satellite remote sensing images, and its technique comprises screening and preprocessed data source, calculating determine green damp scope, the irregular green damp range image of cutting, extract green tidewater and cease and territory, quantum chemical method green tidal zone five steps:

(1), screening and preprocessed data source: fine, partly cloudy, without rain and the weather without typhoon, conventionally obtain sea area satellite remote sensing images, screening noise is few, sharpness is high, brightness uniformity and image resolution ratio are less than or equal to 30 meters and can cover the image in territory, green tidal zone, and the image data filtered out is carried out to the pretreatment operation of geometry correction and image mosaic, complete screening and the pre-service of data source;

(2), calculate and determine green damp scope:

For biological nature and the spectral characteristic of Enteromorpha, adopt vegetation index (NDVI index) calculate and determine green damp scope, formula is as follows:

$NDVI=\frac{IR-R}{IR+R}---(1-1)$

In formula, IR represents the near-infrared band in satellite remote sensing images, selects 4 wave band datas, and R is red wave band, selects 3 wave band datas, and the NDVI index completing satellite remote sensing images calculates;

(3), the irregular green damp range image of cutting: determine green damp scope according to NDVI index calculation method, cutting arbitrary shape region of interest also records the total number of pixel and the total area of region of interest, generate region of interest document data set, generate the irregular image file containing territory, green tidal zone import the region of interest document data set generated at remote sensing processing platform after, complete the cutting of irregular green damp range image;

(4) green tidewater breath, is extracted:

Adopt division Donald Bragg graceful (Bregman) the fast projection algorithm based on old-Wei Si (Chan-Vese) model of variation level set two-phase Iamge Segmentation to extract green tidewater breath, Chan-Vese model energy functional is as follows:

$\underset{\mathrm{\φ}}{Min}\left\{E\left(\mathrm{\φ}\right)={\∫}_{\mathrm{\Ω}}R\left(u_1,u_2\right)H\left(\mathrm{\φ}\right)dx+\mathrm{\γ}{\∫}_{\mathrm{\Ω}}\left|\▿H\left(\mathrm{\φ}\right)\right|dx\right\}---\left(1-2\right)$

$s.t.\left|\▿\mathrm{\φ}\right|=1---(1-3)$

In formula (1-2),

R(u ₁，u ₂)＝α ₁(u ₁-f) ²-α ₂(u ₂-f) ²(1-4)

Wherein u ₁and u ₂represent prospect and the background of image respectively, f represents the original image of Noise, introduces auxiliary separating fission amount order $\stackrel{\→}{w}=\▿\mathrm{\φ},$ Because with equivalence, is rewritten as formula (1-5) and (1-6) respectively by formula (1-2) and formula (1-3):

$\underset{\mathrm{\φ},\stackrel{\→}{w}}{Min}\left\{E\left(\mathrm{\φ},\stackrel{\→}{w}\right)={\∫}_{\mathrm{\Ω}}RH\left(\mathrm{\φ}\right)dx+\mathrm{\γ}{\∫}_{\mathrm{\Ω}}\left|\stackrel{\→}{w}\right|\mathrm{\δ}\left(\mathrm{\φ}\right)dx+\frac{\mathrm{\θ}}{2}\∫{\left(\stackrel{\→}{w}-\▿\mathrm{\φ}-{\stackrel{\→}{b}}^k\right)}^{2}dx\right\}---\left(1-5\right)$

$s.t.\stackrel{\→}{w}=1---\left(1-6\right)$

In formula (1-5),

${\stackrel{\→}{b}}^{k+1}={\stackrel{\→}{b}}^k+\▿{\mathrm{\φ}}^k-{\stackrel{\→}{w}}^k---(1-7)$

For Bregman iteration parameter, θ is positive punishment parameter, with initial value is 0.

Formula (1-5) and formula (1-6) are solved and obtain:

In formula (1-9), g is edge indicator function, and formula is:

$g\left(x\right)=\frac{1}{1+\mathrm{\γ}{|\▿(f\left(x\right)*G_{\mathrm{\σ}}\left)\right|}^2}---(1-10)$

In formula (1-10), G _σfor standard deviation is the gaussian kernel function of σ, setting initial parameter is γ=1, σ=1, θ=3000, brings formula (1-8) and formula (1-9) into and carries out solving and obtain green damp information extraction result, complete the extraction of green tidewater breath;

(5), territory, quantum chemical method green tidal zone: adopt the green damp information quantization that quantitative formula extracts step (4), quantitative formula is:

Last_area＝(clip_pixel-last_sum)/clip_pixel×clip_area(1-11)

In formula (1-11), Last_area is the total area of the green tidewater breath extracted, and clip_pixel is the total number of picture element of irregular image, and last_sum is the total number of background pixels point in irregular image, clip_area is the total area of irregular image, and unit is square kilometre.Bring given data into, draw the green tidewater breath total area, unit is square kilometre, completes the quantum chemical method of green tidewater breath.

The NDVI index that the present embodiment relates to judges the mode that the coverage condition of green vegetation mainly adopts, and NDVI index higher expression green vegetation is more intensive, and it is better to grow; Biological nature due to Enteromorpha is Enteromorpha frond is emerald green, with liver moss with to tie up the terrestrial plants such as pipe the same, Enteromorpha contains chlorophyll a and b, there is notable difference in the spectral characteristic of Enteromorpha and seawater, the spectral characteristic of Enteromorpha is that Enteromorpha has stronger absorbability at blue wave band (436nm) and red band (670nm), low at these two wave band reflectivity, stronger reflection peak is had at green band (546nm), slightly high at this wave band reflectivity, very strong reflection peak is had at near-infrared band (750nm-850nm), very high at this wave band reflectivity; The spectral characteristic of seawater is that the change of its reflectivity does not have Enteromorpha obvious, whole reflectance curve is on a declining curve, at green band, seawater equally has stronger reflection peak with Enteromorpha, the reflection peak of seawater is milder, at near-infrared band, the reflectivity of seawater is very low, and the curve of spectrum of seawater and Enteromorpha has obvious difference.So, can calculate based on NDVI index and determine green damp scope; The result that NDVI index calculates is black white image, black is ocean, white is land and Enteromorpha, can see seawater and Enteromorpha clearly on a large scale, need the irregular green damp range image of cutting, extract green tidewater breath and territory, quantum chemical method green tidal zone obtains the green damp total area; Satellite remote sensing images comprises the non-green tidal zone such as land and cloud, utilize conventional threshold values method and Variation Model to extract green tidewater breath and automatically cannot identify green tidal zone and non-green tidal zone, because result is close after the NDVI index of land and Enteromorpha calculates, land picture dot participates in Iamge Segmentation, causes green damp information extraction result inaccurate; Regular image does not have operational use to be worth in reality, so, need the cutting carrying out irregular image.

The quantization principles that the present embodiment relates to is: when service regeulations image, and the prospect in level set function segmentation result image is 1, and background is 0; When using irregular image, the prospect in level set function segmentation result image is 0, and background is 1, and the region outside image is all 0; Prospect represents green tide, background pp seawater.

Embodiment 2:

The green damp information extracting method step that the present embodiment relates to is with embodiment 1, and the green tidewater breath obtained adopt the threshold method of traditional artificial cognition and setting to draw data parameters that green tidewater ceases is in table 1, show that data parameters that green tidewater ceases is in table 2 based on Variation Model and quantization method, time in table 1 and table 2 be from carry out green tidewater breath and extract the working time obtaining the green tidewater breath total area, difference slightly different according to initial parameter of the total area extracted based on Variation Model and quantization method, wherein, α value affects operational efficiency, it is crucial initial parameter, analytical table 1 show that the green tidewater breath total area (51.0678) of extracting when NDVI threshold value is-0.17 is the most accurate, except 1 in table 2, the green tidewater breath total area and 51.0678 of 5 and 6 has outside deviation, other the green tidewater breath total area and 51.0678 is substantially close, in extraction green tidewater breath total area data, result based on Variation Model and quantization method is more stable, precision is higher, analytical table 1 draw working time the shortest be 2 ' 10 ", the longest is 2 ' 40 ", what in table 2, working time was the shortest is 14.4301 ", the longest is 41.0595 ", and on operationally, the computing velocity based on Variation Model and quantization method is faster.

Table 1: conventional threshold values method extracts the data parameters of green tidewater breath

Sequence number	NDVI threshold value	The total area (km 2)	Time
				1	-0.07	30.3012	2′30″
2	-0.08	30.8826	2′20″
				3	-0.09	32.7393	2′25″
4	-0.1	34.8390	2′20″
				5	-0.11	35.6310	2′15″
6	-0.12	38.5047	2′30″
				7	-0.13	40.7160	2′30″
8	-0.14	42.1542	2′30″

9	-0.15	44.0622	2′10″
				10	-0.16	47.5317	2′40″

Table 2: the data parameters extracting green tidewater breath based on Variation Model and quantization method

Sequence number	Method	α	Iterations	The total area (km 2)	Time
						1	SBPM	1	6	54.5173	14.4301″
2	SBPM	1	7	50.4127	14.8513″
						3	SBPM	1	8	49.1825	15.4750″
4	SBPM	1	9	48.7244	17.0041″
						5	SBPM	0.1	33	59.7911	37.0970″
6	SBPM	0.1	34	55.3782	38.5166″
						7	SBPM	0.1	35	52.3157	38.3294″
8	SBPM	0.1	36	50.3048	41.0595″

Claims (3)

1. a green damp information extracting method, is characterized in that technique comprises screening and preprocessed data source, calculating determine green damp scope, the irregular green damp range image of cutting, extract green tidewater and cease and territory, quantum chemical method green tidal zone five steps:

(1), screening and preprocessed data source: fine, partly cloudy, without rain and the weather without typhoon, conventionally obtain sea area satellite remote sensing images, screening noise is few, sharpness is high, brightness uniformity and image resolution ratio are less than or equal to 30 meters and can cover the image in territory, green tidal zone, the image data filtered out is carried out to the pretreatment operation of geometry correction and image mosaic, complete screening and the pre-service of data source;

(2), calculate and determine green damp scope: for biological nature and the spectral characteristic of Enteromorpha, adopt vegetation index calculate and determine green damp scope, formula is as follows:

$NDVI=\frac{IR-R}{IR+R}---\left(1-1\right)$

In formula, IR represents the near-infrared band in satellite remote sensing images, selects 4 wave band datas, and R is red wave band, selects 3 wave band datas, and the vegetation index completing satellite remote sensing images calculates;

(3), the irregular green damp range image of cutting: determine green damp scope according to vegetation index computing method, cutting arbitrary shape region of interest also records the total number of pixel and the total area of region of interest, generate region of interest document data set, generate the irregular image file containing territory, green tidal zone import the region of interest document data set generated at remote sensing processing platform after, complete the cutting of irregular green damp range image;

(4) green tidewater breath, is extracted:

Adopt the division Donald Bragg graceful fast projection algorithm based on the old-Wei Si model of variation level set two-phase Iamge Segmentation to extract green tidewater breath, old-Wei Si model energy functional is as follows:

$\underset{\mathrm{\φ}}{Min}\left\{E\left(\mathrm{\φ}\right)={\∫}_{\mathrm{\Ω}}R\left(u_1,u_2\right)H\left(\mathrm{\φ}\right)dx+\mathrm{\γ}{\∫}_{\mathrm{\Ω}}|\▿H\left(\mathrm{\φ}\right)|dx\right\}---\left(1-2\right)$

$s.t.|\▿\mathrm{\φ}|=1---(1-3)$

In formula (1-2),

R(u ₁，u ₂)＝α ₁(u ₁-f) ²-α ₂(u ₂-f) ²(1-4)

Wherein u ₁and u ₂represent prospect and the background of image respectively, f represents the original image of Noise, introduces auxiliary separating fission amount order because with equivalence, is rewritten as formula (1-5) and formula (1-6) respectively by formula (1-2) and formula (1-3):

$\underset{\mathrm{\φ},\stackrel{\→}{w}}{Min}\left\{E\left(\mathrm{\φ},\stackrel{\→}{w}\right)={\∫}_{\mathrm{\Ω}}RH\left(\mathrm{\φ}\right)dx+\mathrm{\γ}{\∫}_{\mathrm{\Ω}}\left|\stackrel{\→}{w}\right|\mathrm{\δ}\left(\mathrm{\φ}\right)dx+\frac{\mathrm{\θ}}{2}\∫{\left(\stackrel{\→}{w}-\▿\mathrm{\φ}-{\stackrel{\→}{b}}^k\right)}^{2}dx\right\}---\left(1-5\right)$

$s.t.\stackrel{\→}{w}=1---\left(1-6\right)$

In formula (1-5),

${\stackrel{\→}{b}}^{k+1}={\stackrel{\→}{b}}^k+\▿{\mathrm{\φ}}^k-{\stackrel{\→}{w}}^k---(1-7)$

For the graceful iteration parameter of Donald Bragg, θ is positive punishment parameter, with initial value is 0,

Formula (1-5) and formula (1-6) are solved and obtain:

In formula (1-9), g is edge indicator function, and formula is:

$g\left(x\right)=\frac{1}{1+\mathrm{\γ}|\▿\left(f\right(x)*G_{\mathrm{\σ}}){|}^2}---(1-10)$

In formula (1-10), G _σfor standard deviation is the gaussian kernel function of σ, setting initial parameter is γ=1, σ=1, θ=3000, brings formula (1-8) and formula (1-9) into and carries out solving and obtain green damp information extraction result, complete the extraction of green tidewater breath;

(5), territory, quantum chemical method green tidal zone: adopt the green damp information quantization that quantitative formula extracts step (4), quantitative formula is:

Last_area＝(clip_pixel-last_sum)/clip_pixel×clip_area(1-11)

In formula (1-11), Last_area is the total area of the green tidewater breath extracted, clip_pixel is the total number of picture element of irregular image, last_sum is the total number of background pixels point in irregular image, and clip_area is the total area of irregular image, and unit is square kilometre, bring given data into, draw the green tidewater breath total area, unit is square kilometre, completes the quantum chemical method of green tidewater breath.

2. green damp information extracting method according to claim 1, it is characterized in that described vegetation index judges the mode that the coverage condition of green vegetation mainly adopts, vegetation index higher expression green vegetation is more intensive, and it is better to grow; Enteromorpha frond is emerald green, containing chlorophyll a and b, the spectral characteristic of Enteromorpha and seawater there are differences, Enteromorpha has stronger absorbability at blue wave band and red band, reflectivity is low, has stronger reflection peak at green band, and reflectivity is slightly high, have very strong reflection peak at near-infrared band, reflectivity is very high; The reflectivity change of seawater does not have Enteromorpha obvious, whole reflectance curve is on a declining curve, at green band, seawater equally has stronger reflection peak with Enteromorpha, the reflection peak of seawater is relatively milder, and at near-infrared band, the reflectivity of seawater is very low, the curve of spectrum of seawater and Enteromorpha has obvious difference, can calculate and determine green damp scope based on vegetation index; The result that vegetation index calculates is black white image, black is ocean, white is land and Enteromorpha, can see seawater and Enteromorpha clearly on a large scale, need the irregular green damp range image of cutting, extract green tidewater breath and territory, quantum chemical method green tidal zone obtains the green damp total area; Satellite remote sensing images comprises the non-green tidal zone of land and cloud, utilize conventional threshold values method and Variation Model to extract green tidewater breath and automatically cannot identify green tidal zone and non-green tidal zone, after the vegetation index of land and Enteromorpha calculates, result is close, land picture dot participates in Iamge Segmentation, causes green damp information extraction result inaccurate; Regular image does not have operational use to be worth in reality, needs the cutting carrying out irregular image.

3. green damp information extracting method according to claim 1, it is characterized in that the principle of carrying out quantizing is: when service regeulations image, the prospect in level set function segmentation result image is 1, and background is 0; When using irregular image, the prospect in level set function segmentation result image is 0, and background is 1, and the region outside image is all 0; Prospect represents green tide, background pp seawater.