CN111310614A - Method and device for extracting remote sensing image - Google Patents
Method and device for extracting remote sensing image Download PDFInfo
- Publication number
- CN111310614A CN111310614A CN202010076021.7A CN202010076021A CN111310614A CN 111310614 A CN111310614 A CN 111310614A CN 202010076021 A CN202010076021 A CN 202010076021A CN 111310614 A CN111310614 A CN 111310614A
- Authority
- CN
- China
- Prior art keywords
- image
- channel
- area
- remote sensing
- processing
- 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
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
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Abstract
The invention provides a method and a device for extracting a remote sensing image, which relate to the technical field of image processing and comprise the following steps: acquiring a remote sensing image of a forest land area to be extracted; carrying out image processing on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted; determining a target area in the multi-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the four-channel image, and the number of the target areas is multiple; the method and the device have the advantages that the multiple target areas are combined to obtain the forest land extraction map of the forest land area to be extracted, and the technical problem that the accuracy of extraction results is low when the remote sensing image of the forest land area is extracted in the prior art is solved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for extracting a remote sensing image.
Background
The forest land as an important component of the ecological environment is one of the best marks reflecting the regional ecological environment, and has irreplaceable functions in supporting the sustainable development of the economy and the society. The current situation and the change situation of the forest land resource state can be mastered by continuously tracking and surveying the forest land resource state in a certain space and time, which provides important scientific data for predicting the change trend, making a forestry policy and policy, checking a forestry result and the like, and has an extremely important role in improving the scientific decision level of forestry development and social development and further promoting the sustainable development of forestry, resource environment and society.
Since the 70 s of the 20 th century, the remote sensing technology is applied to the investigation of the homeland resources, and the investigation of the forestry resources based on the remote sensing image is more and more widely applied. Most of traditional remote sensing image forest land extraction methods are based on artificially selected forest land spectrum and texture features and combine supervision and classification technology to extract forest lands, but due to the phenomena of 'same-object different-spectrum' and 'same-spectrum foreign matter' and the fact that a large number of manually selected samples are needed to correct results during extraction, the accuracy, applicability and automation degree of the extraction methods are limited to a certain extent.
No effective solution has been proposed to the above problems.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for extracting a remote sensing image, so as to alleviate the technical problem in the prior art that when a remote sensing image of a forest land area is extracted, the accuracy of an extraction result is low.
In a first aspect, an embodiment of the present invention provides a method for extracting a remote sensing image, including: acquiring a remote sensing image of a forest land area to be extracted; carrying out image processing on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted; determining a target area in the multi-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the four-channel image, and the target area is multiple; and combining a plurality of target areas to obtain a forest land extraction map of the forest land area to be extracted.
Further, the image processing is carried out on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted, and the method comprises the following steps: preprocessing the remote sensing image to obtain an initial remote sensing image, wherein the preprocessing comprises at least one of the following steps: geometric correction processing, image fusion processing and even light and color processing; and processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain the multi-channel image.
Further, the multi-channel image is a four-channel image; processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain the multi-channel image, wherein the method comprises the following steps: carrying out three-channel normalization processing on the initial remote sensing image to obtain three-channel values of the initial remote sensing image; calculating a visual characteristic index of the initial remote sensing image by using a visual characteristic index algorithm and the three channel values; determining the visual characteristic index and the three-channel value as a four-channel value of the initial remote sensing image; and processing the initial remote sensing image by combining the four-channel value and the true color image processing algorithm to obtain the four-channel image.
Further, the clustering algorithm includes: a first clustering algorithm and a second clustering algorithm, the target region comprising: a first target area and a second target area;
determining a target area in the four-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the four-channel image, and the method comprises the following steps: clustering the four-channel image by using the first clustering algorithm to determine a first sub-image area and a second sub-image area in the four-channel image, wherein the first sub-image area is an image area containing woodland in the four-channel image, and the second sub-image area is an image area except the first sub-image area in the four-channel image; clustering the second sub-image area by using the second clustering algorithm to determine a target image area in the second sub-image area, wherein the target image area is an image area containing woodland in the second sub-image area; determining the first sub-image area as the first target area and the target image area as the second target area.
Further, clustering the four-channel image by using the first clustering algorithm to determine a first sub-image region and a second sub-image region in the four-channel image, including: dividing the four-channel image according to a preset size to obtain a plurality of image blocks; clustering the plurality of image blocks by using a first clustering algorithm to determine a first image block and a second image block, wherein the first image block is an image block which comprises a forest land in the plurality of image blocks, and the second image block is an image block except the first image block in the plurality of image blocks; and merging the first image block to obtain the first sub-image area, and merging the second image block to obtain the second sub-image area.
Further, clustering the plurality of image blocks by using a first clustering algorithm to determine a first image block and a second image block, comprising: clustering the plurality of image blocks by using a first clustering algorithm to obtain a first preset number of classifications; determining visual characteristic indexes of image blocks contained in each classification based on the visual characteristic indexes of the four-channel images; calculating the average value of the visual characteristic indexes of the image blocks contained in each classification; determining target classifications in the first preset number of classifications based on the visual characteristic index average value, wherein the target classifications are a second preset number of classifications with the largest numerical value in the visual characteristic index average value; determining the video blocks included in the target classification as the first video block, and determining the video blocks of the plurality of video blocks except the first video block as the second video block.
In a second aspect, an embodiment of the present invention further provides an apparatus for extracting a remote sensing image, including: the system comprises an acquisition unit, a processing unit, a clustering unit and a merging unit, wherein the acquisition unit is used for acquiring remote sensing images of forest land areas to be extracted; the processing unit is used for carrying out image processing on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted; the clustering unit is used for determining a target area in the multi-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the four-channel image, and the target areas are multiple; and the merging unit is used for merging the target areas to obtain the forest land extraction map of the forest land area to be extracted.
Further, the processing unit is configured to: preprocessing the remote sensing image to obtain an initial remote sensing image, wherein the preprocessing comprises at least one of the following steps: geometric correction processing, image fusion processing and even light and color processing; and processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain the multi-channel image.
Further, the multi-channel image is a four-channel image; the processing unit is used for carrying out three-channel normalization processing on the initial remote sensing image to obtain three-channel values of the initial remote sensing image; calculating a visual characteristic index of the initial remote sensing image by using a visual characteristic index algorithm and the three channel values; determining the visual characteristic index and the three-channel value as a four-channel value of the initial remote sensing image; and processing the initial remote sensing image by combining the four-channel value and the true color image processing algorithm to obtain the four-channel image.
In a third aspect, an embodiment of the present invention further provides a computer-readable medium having a non-volatile program code executable by a processor, where the program code causes the processor to execute the method for extracting a remote sensing image according to the first aspect.
In the embodiment of the invention, firstly, a remote sensing image of a forest land area to be extracted is obtained; then, carrying out image processing on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted; then, determining a target area in the multi-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the four-channel image, and the number of the target areas is multiple; and finally, combining the target areas to obtain a forest land extraction map of the forest land area to be extracted.
In the embodiment of the invention, after the remote sensing image of the forest land area to be extracted is obtained, the remote sensing image is subjected to image processing to obtain the corresponding multi-channel image, the areas containing the forest land in the multi-channel image are determined by utilizing a clustering algorithm, the areas containing the forest land are merged to obtain the forest land extraction map of the forest land area to be extracted, the purpose of extracting the remote sensing image of the forest land area to be extracted is achieved, the technical problem that the accuracy of the extraction result is low when the remote sensing image of the forest land area is extracted in the prior art is solved, and the technical effect of improving the extraction accuracy of the forest land area is realized.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of an extraction method of a remote sensing image according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for generating a multi-channel image according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for determining a target area in a four-channel image according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an apparatus for extracting a remote sensing image according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
according to an embodiment of the present invention, there is provided an embodiment of a method for extracting a remote sensing image, where the steps illustrated in the flowchart of the drawings may be executed in a computer system such as a set of computer executable instructions, and although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be executed in an order different from that shown.
Fig. 1 is a flowchart of a method for extracting a remote sensing image according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, obtaining a remote sensing image of a forest land area to be extracted;
specifically, the remote sensing image may be obtained from a large amount of remote sensing data. For example, a plurality of images including a forest land area to be extracted can be obtained from a territorial satellite remote sensing application center of the department of natural resources. For example, if the forest land in the post-pentapeak river natural reserve of the Hubei province is extracted, the post-pentapeak river natural reserve of the Hubei province must be included in the image. And removing a forest land area to be processed if the forest land area is not contained in a plurality of remote sensing images or the forest land area is not concerned in the images.
Step S104, carrying out image processing on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted;
step S106, determining a target area in the multi-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the four-channel image, and the target area is multiple;
and S108, combining the target areas to obtain a forest land extraction map of the forest land area to be extracted.
In the embodiment of the invention, after the remote sensing image of the forest land area to be extracted is obtained, the remote sensing image is subjected to image processing to obtain the corresponding multi-channel image, the areas containing the forest land in the multi-channel image are determined by utilizing a clustering algorithm, the areas containing the forest land are merged to obtain the forest land extraction map of the forest land area to be extracted, the purpose of extracting the remote sensing image of the forest land area to be extracted is achieved, the technical problem that the accuracy of the extraction result is low when the remote sensing image of the forest land area is extracted in the prior art is solved, and the technical effect of improving the extraction accuracy of the forest land area is realized.
In the embodiment of the present invention, as shown in fig. 2, step S104 further includes the following steps:
step S11, the remote sensing image is preprocessed to obtain an initial remote sensing image, wherein the preprocessing comprises at least one of the following steps: geometric correction processing, image fusion processing and even light and color processing;
and step S12, processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain the multichannel image.
In the embodiment of the invention, the initial remote sensing image is obtained by carrying out image processing such as geometric correction processing, image fusion processing, dodging and color homogenizing processing and the like on the remote sensing image.
And then, processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain a multi-channel image.
In an embodiment of the invention, the multi-channel image is a four-channel image.
Specifically, step S12 further includes the following steps:
step S121, carrying out three-channel normalization processing on the initial remote sensing image to obtain three-channel values of the initial remote sensing image;
step S122, calculating a visual characteristic index of the initial remote sensing image by using a visual characteristic index algorithm and the three-channel value;
step S123, determining the visual characteristic index and the three-channel value as a four-channel value of the initial remote sensing image;
and step S124, combining the four-channel value and the true color image processing algorithm to process the initial remote sensing image to obtain the four-channel image.
In the embodiment of the invention, three-channel normalization processing is firstly carried out on the initial remote sensing image to obtain three-channel values of the initial remote sensing image.
The three channels include an R channel, a G channel, and a B channel.
R＝R/255；G＝G/255；B＝B/255。
Then, finding out the maximum value in three channels, and dividing each channel by the maximum value to obtain three channel values, wherein the specific formula is as follows:
MAX＝max(R，G，B)
R1＝R/MAX；G1＝G/MAX；B1＝B/MAX。
and after the three-channel value is determined, calculating the visual characteristic index of the initial remote sensing image according to the three-channel value and by combining a visual characteristic index algorithm.
The visual characteristic index is an ExG-ExP visual characteristic index.
Wherein ExG and ExP are respectively
ExG＝2*G1-R1-B1
ExR＝1.4R1-G1
And finally, processing the initial remote sensing image according to the ExG-ExP visual characteristic index, the three-channel value and a true color image processing algorithm to obtain a four-channel image.
In the embodiment of the present invention, in step S106, the clustering algorithm includes: the target region comprises a first clustering algorithm and a second clustering algorithm: a first target area and a second target area.
It should be noted that, both the first clustering algorithm and the second clustering algorithm described above may adopt a Kmeans clustering algorithm.
As shown in fig. 3, step S106 further includes the following steps:
step S21, performing clustering processing on the four-channel image by using the first clustering algorithm, and determining a first sub-image region and a second sub-image region in the four-channel image, where the first sub-image region is an image region in the four-channel image that includes a woodland, and the second sub-image region is an image region in the four-channel image except for the first sub-image region;
step S22, performing clustering processing on the second sub-image region by using the second clustering algorithm, and determining a target image region in the second sub-image region, where the target image region is an image region including a woodland in the second sub-image region;
step S23, determining the first sub-image area as the first target area and the target image area as the second target area.
In the embodiment of the invention, firstly, a first clustering algorithm is utilized to perform clustering processing on the four-channel images to determine an image area (a first sub-image area) containing a woodland in the four-channel images and an image area (a second sub-image area) except the first sub-image area in the four-channel images.
It should be noted that the second sub-image area may or may not include a woodland area.
Then, a second clustering algorithm is used for clustering the second sub-image area, and an image area (target image area) containing the forest land in the second sub-image area is determined.
Finally, the first sub-image area is determined as a first target area and the target image area is determined as a second target area.
Step S21 will be described in detail below:
in order to determine the first sub-image area and the second sub-image area, first, the four-channel image needs to be divided according to a preset size, so as to obtain a plurality of image blocks.
It should be noted that the preset size may be set by a worker according to the size of the four-channel image, and is not specifically limited in the embodiment of the present invention.
Then, clustering processing is carried out on the plurality of image blocks through a first clustering algorithm, and image blocks (first image blocks) including forest lands in the plurality of image blocks and image blocks (second image blocks) except the first image blocks in the plurality of image blocks are determined.
Specifically, a first clustering algorithm is utilized to cluster a plurality of image blocks to obtain a first preset number of classifications.
It should be noted that the first preset number may be set by an operator according to actual situations, and is not specifically limited in the embodiment of the present invention, and generally, the first preset number is 5.
And then, according to the visual characteristic indexes of the four-channel images, determining the visual characteristic index of the image block contained in each classification.
Then, the total number of the visual characteristic indexes of the image blocks included in each classification is calculated, and the average value of the visual characteristic indexes is calculated according to the total number and the number of the image blocks.
And finally, sorting the preset number of classifications from large to small according to the average value of the visual characteristic indexes of the classifications, determining the second preset number of classifications with the largest value in the average value of the visual characteristic indexes as a target classification, and determining the image blocks contained in the target classification as first image blocks.
For example, when the first preset number is 5, the second preset number is 3, that is, the image blocks included in the 3 categories with the largest average value of the visual feature indexes are the first image blocks.
And finally, merging the first image block to obtain a first sub-image area, and merging the second image block to obtain a second sub-image area.
It should be noted that, when the second clustering algorithm is used to perform clustering processing on the second sub-image region to determine the target image region in the second sub-image region, the processing may also be performed by using the steps in the above detailed description of step S21, and details are not described here again.
Example two:
the embodiment of the present invention further provides an extraction device of a remote sensing image, where the extraction device of a remote sensing image is used to execute the extraction method of a remote sensing image provided in the foregoing content of the embodiment of the present invention, and the following is a detailed description of the extraction device of a remote sensing image provided in the embodiment of the present invention.
As shown in fig. 4, fig. 4 is a schematic view of the remote sensing image extraction device, which includes: an acquisition unit 10, a processing unit 20, a clustering unit 30 and a merging unit 40.
The acquiring unit 10 is used for acquiring a remote sensing image of a forest land area to be extracted;
the processing unit 20 is configured to perform image processing on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted;
the clustering unit 30 is configured to determine a target area in the multi-channel image by using a clustering algorithm, where the target area is an area including a forest land in the four-channel image, and the number of the target areas is multiple;
the merging unit 40 is configured to merge the plurality of target areas to obtain a forest land extraction map of the forest land area to be extracted.
In the embodiment of the invention, after the remote sensing image of the forest land area to be extracted is obtained, the remote sensing image is subjected to image processing to obtain the corresponding multi-channel image, the areas containing the forest land in the multi-channel image are determined by utilizing a clustering algorithm, the areas containing the forest land are merged to obtain the forest land extraction map of the forest land area to be extracted, the purpose of extracting the remote sensing image of the forest land area to be extracted is achieved, the technical problem that the accuracy of the extraction result is low when the remote sensing image of the forest land area is extracted in the prior art is solved, and the technical effect of improving the extraction accuracy of the forest land area is realized.
Preferably, the processing unit is configured to: preprocessing the remote sensing image to obtain an initial remote sensing image, wherein the preprocessing comprises at least one of the following steps: geometric correction processing, image fusion processing and even light and color processing; and processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain the multi-channel image.
Preferably, the multi-channel image is a four-channel image;
the processing unit is used for carrying out three-channel normalization processing on the initial remote sensing image to obtain three-channel values of the initial remote sensing image; calculating a visual characteristic index of the initial remote sensing image by using a visual characteristic index algorithm and the three channel values; determining the visual characteristic index and the three-channel value as a four-channel value of the initial remote sensing image; and processing the initial remote sensing image by combining the four-channel value and the true color image processing algorithm to obtain the four-channel image.
Preferably, the clustering algorithm comprises: a first clustering algorithm and a second clustering algorithm, the target region comprising: a first target region and a second target region, the clustering unit being applied to: clustering the four-channel image by using the first clustering algorithm to determine a first sub-image area and a second sub-image area in the four-channel image, wherein the first sub-image area is an image area containing woodland in the four-channel image, and the second sub-image area is an image area except the first sub-image area in the four-channel image; clustering the second sub-image area by using the second clustering algorithm to determine a target image area in the second sub-image area, wherein the target image area is an image area containing woodland in the second sub-image area; determining the first sub-image area as the first target area and the target image area as the second target area.
Preferably, the clustering unit is configured to: dividing the four-channel image according to a preset size to obtain a plurality of image blocks; clustering the plurality of image blocks by using a first clustering algorithm to determine a first image block and a second image block, wherein the first image block is an image block which comprises a forest land in the plurality of image blocks, and the second image block is an image block except the first image block in the plurality of image blocks; and merging the first image block to obtain the first sub-image area, and merging the second image block to obtain the second sub-image area.
Preferably, the clustering unit is configured to: clustering the plurality of image blocks by using a first clustering algorithm to obtain a first preset number of classifications;
determining visual characteristic indexes of image blocks contained in each classification based on the visual characteristic indexes of the four-channel images; calculating the average value of the visual characteristic indexes of the image blocks contained in each classification; determining target classifications in the first preset number of classifications based on the visual characteristic index average value, wherein the target classifications are a second preset number of classifications with the largest numerical value in the visual characteristic index average value; determining the video blocks included in the target classification as the first video block, and determining the video blocks of the plurality of video blocks except the first video block as the second video block.
In a third aspect, an embodiment of the present invention further provides a computer-readable medium having a non-volatile program code executable by a processor, where the program code causes the processor to execute the method for extracting a remote sensing image according to the first embodiment.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
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, may be located in one place, or may be 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, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for extracting a remote sensing image is characterized by comprising the following steps:
acquiring a remote sensing image of a forest land area to be extracted;
carrying out image processing on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted;
determining a target area in the multi-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the multi-channel image, and the number of the target areas is multiple;
and combining a plurality of target areas to obtain a forest land extraction map of the forest land area to be extracted.
2. The method according to claim 1, wherein the image processing of the remote sensing image to obtain the multichannel image of the forest land area to be extracted comprises:
preprocessing the remote sensing image to obtain an initial remote sensing image, wherein the preprocessing comprises at least one of the following steps: geometric correction processing, image fusion processing and even light and color processing;
and processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain the multi-channel image.
3. The method of claim 2, wherein the multi-channel image is a four-channel image;
processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain the multi-channel image, wherein the method comprises the following steps:
carrying out three-channel normalization processing on the initial remote sensing image to obtain three-channel values of the initial remote sensing image;
calculating a visual characteristic index of the initial remote sensing image by using a visual characteristic index algorithm and the three channel values;
determining the visual characteristic index and the three-channel value as a four-channel value of the initial remote sensing image;
and processing the initial remote sensing image by combining the four-channel value and the true color image processing algorithm to obtain the four-channel image.
4. The method of claim 1, wherein the clustering algorithm comprises: a first clustering algorithm and a second clustering algorithm, the target region comprising: a first target area and a second target area;
determining a target area in the four-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the four-channel image, and the method comprises the following steps:
clustering the four-channel image by using the first clustering algorithm to determine a first sub-image area and a second sub-image area in the four-channel image, wherein the first sub-image area is an image area containing woodland in the four-channel image, and the second sub-image area is an image area except the first sub-image area in the four-channel image;
clustering the second sub-image area by using the second clustering algorithm to determine a target image area in the second sub-image area, wherein the target image area is an image area containing woodland in the second sub-image area;
determining the first sub-image area as the first target area and the target image area as the second target area.
5. The method of claim 4, wherein clustering the four-channel image using the first clustering algorithm to determine a first sub-image region and a second sub-image region in the four-channel image comprises:
dividing the four-channel image according to a preset size to obtain a plurality of image blocks;
clustering the plurality of image blocks by using a first clustering algorithm to determine a first image block and a second image block, wherein the first image block is an image block which comprises a forest land in the plurality of image blocks, and the second image block is an image block except the first image block in the plurality of image blocks;
and merging the first image block to obtain the first sub-image area, and merging the second image block to obtain the second sub-image area.
6. The method of claim 5, wherein clustering the plurality of image blocks using a first clustering algorithm to determine a first image block and a second image block comprises:
clustering the plurality of image blocks by using a first clustering algorithm to obtain a first preset number of classifications;
determining visual characteristic indexes of image blocks contained in each classification based on the visual characteristic indexes of the four-channel images;
calculating the average value of the visual characteristic indexes of the image blocks contained in each classification;
determining target classifications in the first preset number of classifications based on the visual characteristic index average value, wherein the target classifications are a second preset number of classifications with the largest numerical value in the visual characteristic index average value;
determining the video blocks included in the target classification as the first video block, and determining the video blocks of the plurality of video blocks except the first video block as the second video block.
7. An extraction device for remote sensing images, comprising: an obtaining unit, a processing unit, a clustering unit and a merging unit, wherein,
the acquisition unit is used for acquiring a remote sensing image of a forest land area to be extracted;
the processing unit is used for carrying out image processing on the remote sensing image to obtain a multi-channel image of the forest land area to be extracted;
the clustering unit is used for determining a target area in the multi-channel image by using a clustering algorithm, wherein the target area is an area containing a forest land in the multi-channel image, and the target areas are multiple;
and the merging unit is used for merging the target areas to obtain the forest land extraction map of the forest land area to be extracted.
8. The apparatus of claim 7, wherein the processing unit is configured to:
preprocessing the remote sensing image to obtain an initial remote sensing image, wherein the preprocessing comprises at least one of the following steps: geometric correction processing, image fusion processing and even light and color processing;
and processing the initial remote sensing image by using a visual characteristic index algorithm and a true color image processing algorithm to obtain the multi-channel image.
9. The apparatus of claim 8, wherein the multi-channel image is a four-channel image;
the processing unit is used for carrying out three-channel normalization processing on the initial remote sensing image to obtain three-channel values of the initial remote sensing image;
calculating a visual characteristic index of the initial remote sensing image by using a visual characteristic index algorithm and the three channel values;
determining the visual characteristic index and the three-channel value as a four-channel value of the initial remote sensing image;
and processing the initial remote sensing image by combining the four-channel value and the true color image processing algorithm to obtain the four-channel image.
10. A computer-readable medium having non-volatile program code executable by a processor, wherein the program code causes the processor to execute the method for extracting a remote sensing image according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010076021.7A CN111310614B (en) | 2020-01-22 | 2020-01-22 | Remote sensing image extraction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010076021.7A CN111310614B (en) | 2020-01-22 | 2020-01-22 | Remote sensing image extraction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111310614A true CN111310614A (en) | 2020-06-19 |
| CN111310614B CN111310614B (en) | 2023-07-25 |
Family
ID=71145431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010076021.7A Active CN111310614B (en) | 2020-01-22 | 2020-01-22 | Remote sensing image extraction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111310614B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101922914A (en) * | 2010-08-27 | 2010-12-22 | 中国林业科学研究院资源信息研究所 | Crown information extraction method and system based on high spatial resolution remote sense image |
| CN105139015A (en) * | 2015-07-24 | 2015-12-09 | 河海大学 | Method for extracting water body from remote sensing image |
| CN105761266A (en) * | 2016-02-26 | 2016-07-13 | 民政部国家减灾中心 | Method of extracting rectangular building from remote sensing image |
| CN106709517A (en) * | 2016-12-19 | 2017-05-24 | 航天恒星科技有限公司 | Mangrove recognition method and system |
| CN107657207A (en) * | 2016-12-30 | 2018-02-02 | 航天星图科技（北京）有限公司 | A kind of forest land sorting technique based on remote sensing image |
| CN108195771A (en) * | 2017-12-18 | 2018-06-22 | 河海大学 | A kind of ocean target in hyperspectral remotely sensed image target identification method |
| CN109543630A (en) * | 2018-11-28 | 2019-03-29 | 苏州中科天启遥感科技有限公司 | Remote sensing image forest land extracting method and system, storage medium, electronic equipment based on deep learning |
| CN109977991A (en) * | 2019-01-23 | 2019-07-05 | 彭广惠 | Forest resourceies acquisition method based on high definition satellite remote sensing |
-
2020
- 2020-01-22 CN CN202010076021.7A patent/CN111310614B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101922914A (en) * | 2010-08-27 | 2010-12-22 | 中国林业科学研究院资源信息研究所 | Crown information extraction method and system based on high spatial resolution remote sense image |
| CN105139015A (en) * | 2015-07-24 | 2015-12-09 | 河海大学 | Method for extracting water body from remote sensing image |
| CN105761266A (en) * | 2016-02-26 | 2016-07-13 | 民政部国家减灾中心 | Method of extracting rectangular building from remote sensing image |
| CN106709517A (en) * | 2016-12-19 | 2017-05-24 | 航天恒星科技有限公司 | Mangrove recognition method and system |
| CN107657207A (en) * | 2016-12-30 | 2018-02-02 | 航天星图科技（北京）有限公司 | A kind of forest land sorting technique based on remote sensing image |
| CN108195771A (en) * | 2017-12-18 | 2018-06-22 | 河海大学 | A kind of ocean target in hyperspectral remotely sensed image target identification method |
| CN109543630A (en) * | 2018-11-28 | 2019-03-29 | 苏州中科天启遥感科技有限公司 | Remote sensing image forest land extracting method and system, storage medium, electronic equipment based on deep learning |
| CN109977991A (en) * | 2019-01-23 | 2019-07-05 | 彭广惠 | Forest resourceies acquisition method based on high definition satellite remote sensing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111310614B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hermosilla et al. | Regional detection, characterization, and attribution of annual forest change from 1984 to 2012 using Landsat-derived time-series metrics | |
| CN110705405B (en) | Target labeling method and device | |
| CN103164692B (en) | A kind of special vehicle instrument automatic identification system based on computer vision and method | |
| CN103994786B (en) | Image detecting method for arc ruler lines of pointer instrument scale | |
| US9679354B2 (en) | Duplicate check image resolution | |
| CN112348765A (en) | Data enhancement method and device, computer readable storage medium and terminal equipment | |
| CN110909640A (en) | Method and device for determining water level line, storage medium and electronic device | |
| CN109858441A (en) | A kind of monitoring abnormal state method and apparatus for construction site | |
| JP2021531571A (en) | Certificate image extraction method and terminal equipment | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| CN110674360A (en) | Method and system for constructing data association graph and tracing data | |
| CN111191601A (en) | Method, device, server and storage medium for identifying peer users | |
| CN114998310A (en) | Saliency detection method and system based on image processing | |
| CN111310614A (en) | Method and device for extracting remote sensing image | |
| CN111753642A (en) | Method and device for determining key frame | |
| CN114998732A (en) | Plant disease severity assessment method and device | |
| CN113781469A (en) | Method and system for detecting wearing of safety helmet based on YOLO improved model | |
| CN112633142A (en) | Power transmission line violation building identification method and related device | |
| CN110866911A (en) | Dial defect detection method and device, image processing equipment and storage medium | |
| CN111897907B (en) | Method, device and storage medium for filtering pseudo-change information of earth surface coverage data | |
| CN114068030B (en) | Sand table splitting topic identification system, method and equipment based on visual analysis | |
| LU500861B1 (en) | Identification method, device, equipment and storage medium for soil type with remote sensing | |
| CN114299037B (en) | Quality evaluation method and device for object detection result, electronic equipment and computer readable storage medium | |
| CN117392009B (en) | Automatic fog penetrating processing method, system, terminal and storage medium for image | |
| CN117807173A (en) | Geospatial data quality assessment method, device, electronic equipment and medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100094 building 4, yard 2, Cuihu North Ring Road, Haidian District, Beijing Applicant after: Aerospace Hongtu Information Technology Co.,Ltd. Address before: 100144 Room 301, 3 / F, building 5, zone 4, Xishan Creative Park, Haidian District, Beijing Applicant before: BEIJING PIESAT INFORMATION TECHNOLOGY CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |