CN112507763A - Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium - Google Patents
Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium Download PDFInfo
- Publication number
- CN112507763A CN112507763A CN201910872302.0A CN201910872302A CN112507763A CN 112507763 A CN112507763 A CN 112507763A CN 201910872302 A CN201910872302 A CN 201910872302A CN 112507763 A CN112507763 A CN 112507763A
- Authority
- CN
- China
- Prior art keywords
- water body
- remote sensing
- image
- sensing image
- ndwi
- 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.)
- Pending
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a water body extraction method, a system and a readable storage medium based on a multi-source multi-spectral remote sensing image, wherein the method comprises the steps of obtaining the multi-source remote sensing image and respectively carrying out size preprocessing on remote sensing objects; carrying out image atmospheric correction on the preprocessed remote sensing image; carrying out normalized water body index NDWI calculation on the remote sensing image after atmospheric correction; eliminating abnormal values of the normalized water body index NDWI, drawing an NDWI image gray level histogram, and determining a water body segmentation threshold value according to the peak value distribution of the NDWI image gray level histogram; judging whether the ground object in the remote sensing image is the water body or not according to the preset relation between the normalized water body index NDWI and the water body segmentation threshold; and if the ground object in the remote sensing image is the water body, performing binarization processing on the corresponding remote sensing image, extracting a water body contour from the image after binarization processing, cutting the water body image, and storing. The method overcomes the defect of low efficiency of the traditional extraction method and has higher universality.
Description
Technical Field
The invention relates to the technical field of remote sensing image processing, in particular to a program method, a system and a readable storage medium based on a multi-source multi-spectral remote sensing image water body extraction method.
Background
The development of the remote sensing technology provides a new idea for water resource management and utilization, the water body space-time distribution characteristics have important significance for water resource monitoring and application, and the water body information extraction by means of the remote sensing image has become the key point of the current water conservancy remote sensing research in order to quickly, accurately and efficiently acquire the surface water body information.
The process of obtaining the target ground object information from the remote sensing image is called remote sensing image interpretation and mainly comprises two modes of visual interpretation and computer interpretation. Wherein, visual interpretation refers to the process that professionals obtain information of specific target ground objects on remote sensing images through direct observation or by means of instruments; the remote sensing computer interpretation is based on remote sensing data, and technologies such as geoscience analysis, remote sensing image processing, mode recognition, artificial intelligence and the like are comprehensively applied under the support of a computer system to realize intelligent acquisition of thematic information of the remote sensing image. The information extraction of the traditional remote sensing image mainly depends on visual interpretation, but for the single water body research in the remote sensing image, the direct extraction of the water body of the remote sensing image by adopting a computer interpretation method can save a large amount of labor cost for visual interpretation, and simultaneously greatly improve the working efficiency.
Theoretically, the important basis for realizing water body extraction by remote sensing computer interpretation is that the spectral characteristic curve of the water body is mainly concentrated at the wavelength of 0.5um, the reflectivity of the near-infrared band exceeding 0.75um is obviously attenuated, the multispectral remote sensing image has a plurality of spectral channels, the distribution of the multispectral remote sensing image comprises visible light and the near-infrared band, and the multispectral remote sensing image can be combined by the advantages of different bands by adopting a multiband combination method, so that the effects of inhibiting vegetation and soil information and enhancing water body information are achieved. For the water body image obtained by the wave band combination, an image processing method needs to be further adopted, for example: various methods such as a threshold value method, a chromaticity discrimination method, a difference value method and the like can basically and effectively extract the water body information in the image.
The current remote sensing water body extraction mode mainly comprises visual interpretation and one-step flow processing by means of mature software, and is time-consuming and labor-consuming, so that an automatic method capable of quickly extracting the water body based on multi-source multi-spectral remote sensing image data needs to be developed.
Disclosure of Invention
In order to overcome the defects of low efficiency and high cost of water body extraction of remote sensing images in the prior art, the invention provides a program method, a system and a readable storage medium based on a multi-source multi-spectral remote sensing image water body extraction method.
In order to solve the technical problem, the invention discloses a program method of a water body extraction method based on a multi-source multi-spectral remote sensing image in a first aspect, which comprises the following steps:
acquiring a multi-source remote sensing image, and respectively carrying out size preprocessing on remote sensing objects;
carrying out image atmospheric correction on the preprocessed remote sensing image;
carrying out normalized water body index NDWI calculation on the remote sensing image after atmospheric correction;
eliminating abnormal values of the normalized water body index NDWI, drawing an NDWI image gray level histogram, and determining a water body segmentation threshold value according to the peak value distribution of the NDWI image gray level histogram;
judging whether the ground object in the remote sensing image is the water body or not according to the preset relation between the normalized water body index NDWI and the water body segmentation threshold;
and if the ground object in the remote sensing image is the water body, performing binarization processing on the corresponding remote sensing image, extracting a water body contour from the image after binarization processing, cutting the water body image, and storing.
The multi-source remote sensing image is a multi-source multi-spectral remote sensing image, the multi-spectral remote sensing image is provided with a plurality of spectral channels, the distribution of the multi-spectral remote sensing image comprises visible light and near infrared wave bands, and a multi-band combination method is adopted to combine the advantages of different wave bands, so that the effects of inhibiting vegetation and soil information and enhancing water body information are achieved.
In the scheme, the remote sensing image after pretreatment is subjected to atmospheric correction of the image by adopting an internal average relative reflectivity method, wherein the internal average relative reflectivity method is to divide each pixel of each wave band of the remote sensing image by the average value of the gray value of the whole image of the wave band to obtain an apparent reflectivity image.
In this scheme, the normalized water body index NDWI calculation formula is:
wherein, R (Green) and R (NIR) respectively represent remote sensing reflectivity values of multispectral remote sensing images after atmospheric correction of green wave bands and near infrared wave bands, and the NDWI value is dimensionless.
In the scheme, before eliminating the abnormal value of the normalized water body index, the abnormal value is judged, the abnormal value is a value that the normalized water body index NDWI is less than-1 or a value that the normalized water body index NDWI is greater than 1, and the abnormal value eliminating formula of the normalized water body index is as follows:
(NDWI≤-1)*0+(NDWI≥1)*0+(NDWI≥-1and NDWI≤1)*NDW]。
in the scheme, the process of dividing the water body by the threshold value is as follows:
when the maximum peak value is positioned at the right side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of the first mutation point on the left side of the peak value,
when the maximum peak value is positioned at the left side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of a first mutation point at the right side of the peak value,
and when the maximum peak value is positioned in the middle of the NDWI image gray level histogram, if the peak exists on the right side, setting the position of the first mutation point on the left side of the peak value as a water body segmentation threshold, and if the peak does not exist on the right side, setting the position of the first mutation point on the right side of the peak value as a water body segmentation threshold.
In the scheme, the water body segmentation threshold is recorded as threshold, and the preset relation between the normalized water body index NDWI and the water body segmentation threshold is used for judging whether the ground object in the remote sensing image is a water body, specifically:
if the threshold is more than NDWI and less than or equal to 1, the ground object is a water body;
if NDWI is more than 0 and less than or equal to threshold, the ground object is a non-water body.
In this scheme, the multi-source remote sensing image is a multi-source multispectral remote sensing image, and the multi-source multispectral remote sensing image comprises: landsat TM remote sensing images, sentinel second satellite remote sensing images and domestic high-resolution second satellite remote sensing images.
The invention provides a water body extraction system based on multi-source multi-spectral remote sensing images in a second aspect, which comprises: the system comprises a memory and a processor, wherein the memory comprises a program of a water body extraction method based on a multi-source multi-spectral remote sensing image, and the program of the water body extraction method based on the multi-source multi-spectral remote sensing image realizes the following steps when being executed by the processor:
acquiring a multi-source remote sensing image, and respectively carrying out size preprocessing on remote sensing objects;
carrying out image atmospheric correction on the preprocessed remote sensing image;
carrying out normalized water body index NDWI calculation on the remote sensing image after atmospheric correction;
eliminating abnormal values of normalized water body indexes, drawing an NDWI image gray level histogram, and determining a water body segmentation threshold value according to the peak value distribution of the NDWI image gray level histogram;
judging whether the ground object in the remote sensing image is the water body or not according to the preset relation between the normalized water body index NDWI and the water body segmentation threshold;
and if the ground object in the remote sensing image is the water body, performing binarization processing on the corresponding remote sensing image, extracting the water body outline, cutting the water body image and storing.
In the scheme, the remote sensing image after pretreatment is subjected to atmospheric correction of the image by adopting an internal average relative reflectivity method, wherein the internal average relative reflectivity method is to divide each pixel of each wave band of the remote sensing image by the average value of the gray value of the whole image of the wave band to obtain an apparent reflectivity image.
The invention provides a computer-readable storage medium, wherein the computer-readable storage medium comprises a program of a water body extraction method based on a multi-source multi-spectral remote sensing image, and when the program of the water body extraction method based on the multi-source multi-spectral remote sensing image is executed by a processor, the steps of the water body extraction method based on the multi-source multi-spectral remote sensing image are realized.
The invention discloses a water body extraction method, a system and a readable storage medium based on multi-source multi-spectral remote sensing images, which finish the extraction of water body information by preprocessing the multi-spectral remote sensing images, calculating normalized water body indexes and extracting water body outlines, overcome the defect of low efficiency of the traditional extraction method, simultaneously process based on multi-source data, overcome the defect of single data source and have higher universality.
Drawings
FIG. 1 shows a flow chart of a water body extraction method based on multi-source multi-spectral remote sensing images;
FIG. 2 shows a block diagram of a water body extraction system based on multi-source multi-spectral remote sensing images;
FIG. 3 shows an effect diagram of water body extraction based on a domestic high-resolution second satellite (GF-2) remote sensing image;
FIG. 4 shows an effect diagram of water body extraction based on remote sensing images of Sentinel second satellite (Sentinel-2);
fig. 5 shows an effect diagram of water body extraction based on the Landsat (TM) remote sensing image.
Detailed description of the invention
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Noun interpretation
Atmospheric correction
Atmospheric correction means that the total radiance of the ground target finally measured by the sensor is not a reflection of the true reflectivity of the ground, including the radiant quantity error caused by atmospheric absorption, especially scattering. Atmospheric correction is the process of inverting the real surface reflectivity of the ground object by eliminating the radiation errors caused by atmospheric influence.
Atmospheric correction method
There are two main types: statistical type and physical type. The statistical type is based on the correlation between the land surface variables and the remote sensing data, and has the advantages that the statistical type is easy to establish and can effectively summarize the data acquired from the local area, such as an empirical linear scaling method, an internal flat field method and the like, and on the other hand, the physical model follows the physical rules of the remote sensing system and can establish the causal relationship. If the initial model is not good, it can be known where the model should be improved by adding new knowledge and information. The process of building and learning these physical models is lengthy and tortuous. The model is an abstraction of reality; a realistic model can be very complex, containing a large number of variables. Such as the 6s model, Mortran, etc. And radiometric correction refers to the correction of all radiometric-related errors (including radiometric calibration and atmospheric corrections) that occur during the optical telemetry data acquisition process.
NDWI (normalized water index)
And carrying out normalized difference processing by using a specific waveband of the remote sensing image so as to highlight the water body information in the image.
FIG. 1 shows a flow chart of a water body extraction method based on a multi-source multi-spectral remote sensing image.
As shown in fig. 1, a first aspect of the embodiments of the present invention provides a method for extracting a water body based on a multi-source multispectral remote sensing image, which can quickly identify a water body in an image region range, monitor a water body distribution condition, save time and labor, has high monitoring efficiency, is suitable for multispectral data at home and abroad, is easy to popularize and use, and specifically includes:
s102, acquiring a multi-source remote sensing image, and respectively carrying out size preprocessing on remote sensing objects;
it should be noted that the multi-source remote sensing image is a multi-source multi-spectral remote sensing image, the multi-spectral remote sensing image has a plurality of spectral channels, the distribution of the multi-spectral remote sensing image comprises visible light and near infrared wave bands, and a multi-band combination method is adopted to combine advantages of different wave bands, so that the effects of inhibiting vegetation and soil information and enhancing water body information are achieved.
In addition, size preprocessing is performed on the obtained multi-source remote sensing image, and the obtained multi-source remote sensing image is cut in any size. For example, the high-resolution second remote sensing image can be cut to be one fourth of the size of the original image data, the sentinel second satellite remote sensing image and the Landsat TM remote sensing image are cut according to the row number and the column number, and the cutting sizes are respectively 0 to 3454,3650 to 7299 (0: 3454,3650: 7299), 0 to 1790 and 0 to 2411 (0: 1790,0: 2411) of the whole image. The specific situation of the remote sensing image is determined by the operator.
S104, carrying out image atmospheric correction on the preprocessed remote sensing image;
in the scheme, the remote sensing image after pretreatment is subjected to atmospheric correction of the image by adopting an internal average relative reflectivity method, wherein the internal average relative reflectivity method is to divide each pixel of each wave band of the remote sensing image by the average value of the gray value of the whole image of the wave band to obtain an apparent reflectivity image.
It should be noted that the atmospheric correction of the image includes, but is not limited to, an internal average relative reflectance method, and the atmospheric correction is to eliminate the influence of factors such as atmosphere and illumination on the reflection of the ground object.
S106, calculating a normalized water body index (NDWI) of the remote sensing image after atmospheric correction;
the normalized water body index NDWI calculation formula provided by the invention is as follows:
wherein, R (Green) and R (NIR) respectively represent remote sensing reflectivity values of multispectral remote sensing images after atmospheric correction of green wave bands and near infrared wave bands, and the NDWI value is dimensionless.
S108, eliminating abnormal values of the normalized water body index NDWI, drawing an NDWI image gray histogram, and determining a water body segmentation threshold value according to the peak value distribution of the NDWI image gray histogram;
the invention firstly judges whether the normalized water body index is abnormal, and the specific judgment method comprises the following steps: and if the normalized water body index NDWI is less than-1 or the normalized water body index NDWI is more than 1, the corresponding normalized water body index is an abnormal numerical value.
Judging the abnormal normalized water body index, and then adopting an elimination formula to eliminate the abnormal normalized water body index, wherein the specific elimination formula is as follows:
(NDWI≤-1)*0+(NDWI≥1)*0+(NDWI≥-1and NDWI≤1)*NDW]。
s110, judging whether the ground object in the remote sensing image is the water body or not according to the preset relation between the normalized water body index NDWI and the water body segmentation threshold;
in this scheme, the process of dividing the water body by the threshold specifically comprises:
when the maximum peak value is positioned at the right side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of the first mutation point on the left side of the peak value,
when the maximum peak value is positioned at the left side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of a first mutation point at the right side of the peak value,
and when the maximum peak value is positioned in the middle of the NDWI image gray level histogram, if the peak exists on the right side, setting the position of the first mutation point on the left side of the peak value as a water body segmentation threshold, and if the peak does not exist on the right side, setting the position of the first mutation point on the right side of the peak value as a water body segmentation threshold.
The water body segmentation threshold is obtained, the water body segmentation threshold is recorded as threshold, and the preset relation between the normalized water body index NDWI and the water body segmentation threshold is used for judging whether the ground objects in the remote sensing image are water bodies, specifically:
if the threshold is more than NDWI and less than or equal to 1, the ground object is a water body;
if NDWI is more than 0 and less than or equal to threshold, the ground object is a non-water body.
And S112, if the ground object in the remote sensing image is a water body, performing binarization processing on the corresponding remote sensing image, extracting a water body contour from the binarized image, cutting the water body image, and storing.
It should be noted that the multi-source remote sensing image is a multi-source multispectral remote sensing image, and the multi-source multispectral remote sensing image includes: landsat TM remote sensing images, sentinel second satellite remote sensing images and domestic high-resolution second satellite remote sensing images. The method disclosed by the invention has the advantages that various multispectral data are tested, the defect of single data source is overcome, and meanwhile, the method disclosed by the invention has certain universality.
Fig. 2 shows a block diagram of a water body extraction system based on multi-source multi-spectral remote sensing images.
The invention provides a water body extraction system based on multi-source multi-spectral remote sensing images in a second aspect, which comprises: the system comprises a memory 21 and a processor 22, wherein the memory comprises a multi-source multi-spectral remote sensing image-based water body extraction method program, and the multi-source multi-spectral remote sensing image-based water body extraction method program realizes the following steps when executed by the processor:
s102, acquiring a multi-source remote sensing image, and respectively carrying out size preprocessing on remote sensing objects;
it should be noted that the multi-source remote sensing image is a multi-source multi-spectral remote sensing image, the multi-spectral remote sensing image has a plurality of spectral channels, the distribution of the multi-spectral remote sensing image comprises visible light and near infrared wave bands, and a multi-band combination method is adopted to combine advantages of different wave bands, so that the effects of inhibiting vegetation and soil information and enhancing water body information are achieved.
In addition, size preprocessing is performed on the obtained multi-source remote sensing image, and the obtained multi-source remote sensing image is cut in any size. The high-resolution second satellite remote sensing image can be cut to be one fourth of the size of original image data, the sentinel second satellite remote sensing image and the Landsat TM image are cut according to the row number and the column number, and the cutting sizes are respectively 0 to 3454 lines, 3650 to 7299 columns (0: 3454,3650: 7299), 0 to 1790 lines and 0 to 2411 columns (0: 1790,0: 2411) of the whole image. The specific situation of the remote sensing image is determined by the operator.
S104, carrying out image atmospheric correction on the preprocessed remote sensing image;
in the scheme, the remote sensing image after pretreatment is subjected to atmospheric correction of the image by adopting an internal average relative reflectivity method, wherein the internal average relative reflectivity method is to divide each pixel of each wave band of the remote sensing image by the average value of the gray value of the whole image of the wave band to obtain an apparent reflectivity image. It should be noted that the atmospheric correction of the image includes, but is not limited to, an internal average relative reflectance method, and the atmospheric correction is to eliminate the influence of factors such as atmosphere and illumination on the reflection of the ground object.
S106, calculating a normalized water body index (NDWI) of the remote sensing image after atmospheric correction;
the normalized water body index NDWI calculation formula provided by the invention is as follows:
wherein, R (Green) and R (NIR) respectively represent remote sensing reflectivity values of multispectral remote sensing images after atmospheric correction of green wave bands and near infrared wave bands, and the NDWI value is dimensionless.
S108, eliminating abnormal values of the normalized water body index NDWI, drawing an NDWI image gray histogram, and determining a water body segmentation threshold value according to the peak value distribution of the NDWI image gray histogram;
the invention firstly judges whether the normalized water body index is abnormal, and the specific judgment method comprises the following steps: and if the normalized water body index NDWI is less than-1 or the normalized water body index NDWI is more than 1, the corresponding normalized water body index is an abnormal numerical value.
Judging the abnormal normalized water body index, and then adopting an elimination formula to eliminate the abnormal normalized water body index, wherein the specific elimination formula is as follows:
(NDWI≤-1)*0+(NDWI≥1)*0+(NDWI≥-1and NDW1≤1)*NDW]。
s110, judging whether the ground object in the remote sensing image is the water body or not according to the preset relation between the normalized water body index NDWI and the water body segmentation threshold;
in this scheme, the process of dividing the water body by the threshold specifically comprises:
when the maximum peak value is positioned at the right side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of the first mutation point on the left side of the peak value,
when the maximum peak value is positioned at the left side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of a first mutation point at the right side of the peak value,
and when the maximum peak value is positioned in the middle of the NDWI image gray level histogram, if the peak exists on the right side, setting the position of the first mutation point on the left side of the peak value as a water body segmentation threshold, and if the peak does not exist on the right side, setting the position of the first mutation point on the right side of the peak value as a water body segmentation threshold.
The water body segmentation threshold is obtained, the water body segmentation threshold is recorded as threshold, and the preset relation between the normalized water body index NDWI and the water body segmentation threshold is used for judging whether the ground objects in the remote sensing image are water bodies, specifically:
if the threshold is more than NDWI and less than or equal to 1, the ground object is a water body;
if NDWI is more than 0 and less than or equal to threshold, the ground object is a non-water body.
And S112, if the ground object in the remote sensing image is a water body, performing binarization processing on the corresponding remote sensing image, extracting a water body contour from the binarized image, cutting the water body image, and storing.
It should be noted that the multi-source remote sensing image is a multi-source multispectral remote sensing image, and the multi-source multispectral remote sensing image includes: landsat TM remote sensing images, sentinel second satellite remote sensing images and domestic high-resolution second satellite remote sensing images. The method disclosed by the invention has the advantages that various multispectral data are tested, the defect of single data source is overcome, and meanwhile, the method disclosed by the invention has certain universality.
The invention provides a computer-readable storage medium, wherein the computer-readable storage medium comprises a program of a water body extraction method based on a multi-source multi-spectral remote sensing image, and when the program of the water body extraction method based on the multi-source multi-spectral remote sensing image is executed by a processor, the steps of the water body extraction method based on the multi-source multi-spectral remote sensing image are realized.
The principle of the specific implementation of this embodiment is as follows: the spectral characteristic curve of the water body is mainly concentrated at the wavelength of 0.5um, the reflectivity of a near-infrared band exceeding 0.75um is obviously attenuated, the multispectral remote sensing image has a plurality of spectral channels, the distribution of the multispectral remote sensing image comprises visible light and the near-infrared band, and the multispectral remote sensing image can be combined by the advantages of different bands by adopting a multiband combination method, so that the effects of inhibiting vegetation and soil information and enhancing water body information are achieved. For the water body image obtained by the wave band combination, an image processing method threshold value method is further adopted, and the water body information in the image can be effectively extracted.
Example one
A multi-source multispectral remote sensing image-based water body extraction method comprises the following steps:
(1) obtaining a multi-source multispectral remote sensing image, wherein the multi-source multispectral remote sensing image comprises: landsat TM remote sensing images, sentinel second satellite remote sensing images and domestic high-grade second satellite remote sensing images;
(2) compiling a data reading and cutting script based on a Python language, and respectively reading and cutting a Landsat remote sensing image, a sentinel second satellite remote sensing image and a domestic high-grade second satellite remote sensing image; keeping the same size of the cut remote sensing image;
(3) respectively carrying out atmospheric correction on the Landsat TM remote sensing image, the sentinel second satellite remote sensing image and the domestic high-grade second satellite remote sensing image by adopting an internal average relative reflectivity method;
(4) aiming at the Landsat TM remote sensing image, the sentinel second satellite remote sensing image and the domestic high-grade second satellite remote sensing image after atmospheric correction, the normalized water body index NDWI is calculated, and the calculation formula is as follows:
wherein R (Green) and R (NIR) respectively represent remote sensing reflectivity values of multispectral remote sensing images after atmospheric correction of green wave bands and near infrared wave bands, and the NDWI value is dimensionless;
(5) judging whether the normalized water body index NDWI value contains an abnormal value, if the normalized water body index NDWI value is smaller than-1 or larger than 1, judging that the normalized water body index NDWI value is the abnormal value, wherein an elimination formula of the abnormal value is as follows:
(NDWI≤-1)*0+(NDWI≥1)*0+(NDWI≥-1and NDWI≤1)*NDWI。
(6) drawing an NDWI image gray level histogram, and determining a water body segmentation threshold according to the histogram peak value distribution condition;
the method specifically comprises the following steps: when the maximum peak value is positioned at the right side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of the first mutation point on the left side of the peak value,
when the maximum peak value is positioned at the left side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of a first mutation point at the right side of the peak value,
and when the maximum peak value is positioned in the middle of the NDWI image gray level histogram, if the peak exists on the right side, setting the position of the first mutation point on the left side of the peak value as a water body segmentation threshold, and if the peak does not exist on the right side, setting the position of the first mutation point on the right side of the peak value as a water body segmentation threshold.
(7) Judging whether the image ground object type is the water body or not according to the size relation between the normalized water body index NDWI value and the water body segmentation threshold, wherein the specific judgment indexes are as follows:
when the threshold is more than NDWI and less than or equal to 1, the ground object is a water body;
when NDWI is more than 0 and less than or equal to threshold, the ground object is a non-water body;
(8) and performing binarization processing on the remote sensing image by using the water body discrimination result, and extracting a water body contour from the binarized image to respectively cut and store the water body image in the Landsat TM remote sensing image, the sentinel second satellite remote sensing image and the domestic high-grade second satellite remote sensing image.
Fig. 3 shows an effect diagram of water body extraction based on a domestic high-resolution second satellite (GF-2) remote sensing image, fig. 4 shows an effect diagram of water body extraction based on a Sentinel second satellite (Sentinel-2) remote sensing image, and fig. 5 shows that extraction times corresponding to the effect diagram of water body extraction based on a Landsat TM remote sensing image are 145.37s, 68.47s and 30.877s, respectively, so that rapid water body extraction based on a multi-source multi-spectral remote sensing image can be well realized.
The invention discloses a water body extraction method, a system and a readable storage medium based on multi-source multi-spectral remote sensing images, which finish the extraction of water body information by preprocessing the multi-spectral remote sensing images, calculating normalized water body indexes and extracting water body outlines, overcome the defect of low efficiency of the traditional extraction method, simultaneously process based on multi-source data, overcome the defect of single data source and have higher universality.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A multi-source multispectral remote sensing image-based water body extraction method is characterized by comprising the following steps:
acquiring a multi-source remote sensing image, and respectively carrying out size preprocessing on remote sensing objects;
carrying out image atmospheric correction on the preprocessed remote sensing image;
carrying out normalized water body index NDWI calculation on the remote sensing image after atmospheric correction;
eliminating abnormal values of the normalized water body index NDWI, drawing an NDWI image gray level histogram, and determining a water body segmentation threshold value according to the peak value distribution of the NDWI image gray level histogram;
judging whether the ground object in the remote sensing image is the water body or not according to the preset relation between the normalized water body index NDWI and the water body segmentation threshold;
and if the ground object in the remote sensing image is the water body, performing binarization processing on the corresponding remote sensing image, extracting a water body contour from the image after binarization processing, cutting the water body image, and storing.
2. The method for extracting the water body based on the multi-source multi-spectral remote sensing image according to claim 1, wherein an internal average relative reflectivity method is adopted for carrying out atmospheric correction on the preprocessed remote sensing image, and the internal average relative reflectivity method is to divide each pixel of each wave band of the remote sensing image by an average value of gray values of the whole image of the wave band to obtain an apparent reflectivity image.
3. The method for extracting the water body based on the multi-source multi-spectral remote sensing image according to claim 1, wherein the normalized water body index (NDWI) is calculated by the following formula:
wherein, R (Green) and R (NIR) respectively represent remote sensing reflectivity values of multispectral remote sensing images after atmospheric correction of green wave bands and near infrared wave bands, and the NDWI value is dimensionless.
4. The method for extracting the water body based on the multi-source multi-spectral remote sensing image according to claim 1, wherein before eliminating the abnormal value of the normalized water body index, the method further comprises judging the abnormal value, wherein the abnormal value is a value that the normalized water body index NDWI is less than-1 or a value that the normalized water body index NDWI is greater than 1, and the normalized water body index abnormal value elimination formula is as follows:
(NDWI≤-1)*0+(NDWI≥1)*0+(NDWI≥-1 and NDWI≤1)*NDW]。
5. the method for extracting the water body based on the multi-source multi-spectral remote sensing image according to claim 1, wherein the process of dividing the water body segmentation threshold is as follows:
when the maximum peak value is positioned at the right side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of the first mutation point on the left side of the peak value,
when the maximum peak value is positioned at the left side of the NDWI image gray level histogram, the water body segmentation threshold value is set to be the position of a first mutation point at the right side of the peak value,
and when the maximum peak value is positioned in the middle of the NDWI image gray level histogram, if the peak exists on the right side, setting the position of the first mutation point on the left side of the peak value as a water body segmentation threshold, and if the peak does not exist on the right side, setting the position of the first mutation point on the right side of the peak value as a water body segmentation threshold.
6. The method for extracting the water body based on the multi-source multi-spectral remote sensing image according to claim 1, wherein the water body segmentation threshold is recorded as threshold, and the preset relationship between the normalized water body index NDWI and the water body segmentation threshold is used for judging whether the ground object in the remote sensing image is a water body, specifically:
if the threshold is more than NDWI and less than or equal to 1, the ground object is a water body;
if NDWI is more than 0 and less than or equal to threshold, the ground object is a non-water body.
7. The method for extracting the water body based on the multi-source multi-spectral remote sensing image according to claim 1, wherein the multi-source multi-spectral remote sensing image is a multi-source multi-spectral remote sensing image, and the multi-source multi-spectral remote sensing image comprises: landsat TM remote sensing images, sentinel second satellite remote sensing images and domestic high-resolution second satellite remote sensing images.
8. A water body extraction system based on multi-source multispectral remote sensing images is characterized by comprising: the system comprises a memory and a processor, wherein the memory comprises a program of a water body extraction method based on a multi-source multi-spectral remote sensing image, and the program of the water body extraction method based on the multi-source multi-spectral remote sensing image realizes the following steps when being executed by the processor:
acquiring a multi-source remote sensing image, and respectively carrying out size preprocessing on remote sensing objects;
carrying out image atmospheric correction on the preprocessed remote sensing image;
carrying out normalized water body index NDWI calculation on the remote sensing image after atmospheric correction;
eliminating abnormal values of normalized water body indexes, drawing an NDWI image gray level histogram, and determining a water body segmentation threshold value according to the peak value distribution of the NDWI image gray level histogram;
judging whether the ground object in the remote sensing image is the water body or not according to the preset relation between the normalized water body index NDWI and the water body segmentation threshold;
and if the ground object in the remote sensing image is the water body, performing binarization processing on the corresponding remote sensing image, extracting the water body outline, cutting the water body image and storing.
9. The multi-source multispectral remote sensing image-based water body extraction system according to claim 1, wherein the preprocessed remote sensing image is subjected to atmospheric correction by adopting an internal average relative reflectivity method, and the internal average relative reflectivity method is to divide each pixel of each wave band of the remote sensing image by the average value of the gray value of the whole image of the wave band to obtain an apparent reflectivity image.
10. A computer-readable storage medium, wherein the computer-readable storage medium includes a program of a multi-source multi-spectral remote sensing image-based water body extraction method, and when the program of the multi-source multi-spectral remote sensing image-based water body extraction method is executed by a processor, the steps of the multi-source multi-spectral remote sensing image-based water body extraction method according to any one of claims 1 to 7 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872302.0A CN112507763A (en) | 2019-09-16 | 2019-09-16 | Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872302.0A CN112507763A (en) | 2019-09-16 | 2019-09-16 | Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112507763A true CN112507763A (en) | 2021-03-16 |
Family
ID=74923894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910872302.0A Pending CN112507763A (en) | 2019-09-16 | 2019-09-16 | Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112507763A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177964A (en) * | 2021-05-25 | 2021-07-27 | 北京大学 | Method and device for extracting optical remote sensing image large-range surface water |
| CN113484245A (en) * | 2021-07-05 | 2021-10-08 | 重庆市规划和自然资源调查监测院 | Remote sensing rapid monitoring method and system for paddy field planting pattern in hilly and mountainous areas and computer readable storage medium |
| CN113591732A (en) * | 2021-08-03 | 2021-11-02 | 台州市污染防治工程技术中心 | Urban water body identification method and system based on multispectral remote sensing |
| CN115984711A (en) * | 2022-12-30 | 2023-04-18 | 中国科学院空天信息创新研究院 | Non-cyanobacterial bloom monitoring method and system based on satellite remote sensing |
-
2019
- 2019-09-16 CN CN201910872302.0A patent/CN112507763A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177964A (en) * | 2021-05-25 | 2021-07-27 | 北京大学 | Method and device for extracting optical remote sensing image large-range surface water |
| CN113177964B (en) * | 2021-05-25 | 2023-08-18 | 北京大学 | Method and device for extracting optical remote sensing image from surface water in large scale |
| CN113484245A (en) * | 2021-07-05 | 2021-10-08 | 重庆市规划和自然资源调查监测院 | Remote sensing rapid monitoring method and system for paddy field planting pattern in hilly and mountainous areas and computer readable storage medium |
| CN113484245B (en) * | 2021-07-05 | 2022-11-22 | 重庆市规划和自然资源调查监测院 | Remote sensing rapid monitoring method and system for paddy field planting pattern in hilly and mountainous areas and computer readable storage medium |
| CN113591732A (en) * | 2021-08-03 | 2021-11-02 | 台州市污染防治工程技术中心 | Urban water body identification method and system based on multispectral remote sensing |
| CN115984711A (en) * | 2022-12-30 | 2023-04-18 | 中国科学院空天信息创新研究院 | Non-cyanobacterial bloom monitoring method and system based on satellite remote sensing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112507763A (en) | Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium | |
| CN110796001B (en) | Satellite image film-covering farmland identification and extraction method and system | |
| CN112183209B (en) | Regional crop classification method and system based on multidimensional feature fusion | |
| CN105809140B (en) | A kind of extracting method and its device of the surface water body information based on Remote Sensing Model | |
| CN112541921B (en) | Urban green land vegetation information data accurate determination method | |
| CN108596103A (en) | High resolution ratio satellite remote-sensing image building extracting method based on optimal spectrum Index selection | |
| CN115439759B (en) | Method and device for extracting vegetation in remote sensing image, electronic equipment and medium | |
| CN110648347A (en) | Coastline extraction method and device based on remote sensing image | |
| CN112364681B (en) | Vegetation coverage estimation method and device based on two-dimensional table | |
| CN111553922A (en) | Automatic cloud detection method for satellite remote sensing image | |
| CN114926748A (en) | Soybean remote sensing identification method combining Sentinel-1/2 microwave and optical multispectral images | |
| CN110781831A (en) | Hyperspectral optimal waveband selection method and device based on self-adaption | |
| CN111007013A (en) | Crop rotation fallow remote sensing monitoring method and device for northeast cold region | |
| CN112765556A (en) | Method for evaluating tree age of new-born mangrove forest based on intensive time remote sensing data | |
| CN110796113B (en) | City blue terrain detection method based on WorldView-2 image | |
| CN113421273B (en) | Remote sensing extraction method and device for forest and grass collocation information | |
| CN113298086A (en) | Red tide multispectral detection method based on U-Net network | |
| CN113343808A (en) | Tropical forest resource measuring method based on satellite remote sensing technology | |
| Chung et al. | Wildfire damage assessment using multi-temporal Sentinel-2 data | |
| CN111751295A (en) | Modeling method and application of wheat powdery mildew severity detection model based on imaging hyperspectral data | |
| CN111882573A (en) | Cultivated land plot extraction method and system based on high-resolution image data | |
| CN116994126A (en) | Crop leaf area index obtaining method and device based on canopy reflectivity spectrum | |
| CN116205678A (en) | Agricultural land physical quantity investigation and value quantity estimation method based on remote sensing automatic interpretation | |
| CN115965863A (en) | Forest fire plaque and occurrence time extraction method based on GEE platform and VCT algorithm | |
| CN115311566A (en) | Cloud mask image generation method and pre-training network training method |
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 |