Remote sensing image water body extraction method, device, electronic equipment and storage medium

Abstract

The present invention provides a method, device, electronic device and storage medium for extracting water from remote sensing images. The method comprises: constructing an expression of a water index based on the reflectance spectral characteristics of objects in a region to be studied; acquiring a reflectance remote sensing image of the region to be studied, and determining a remote sensing water index map based on the reflectance remote sensing image and the expression of the water index; extracting a water region in the remote sensing water index map based on the remote sensing water index map and the reflectance remote sensing image. The method, device, electronic device and storage medium for extracting water from remote sensing images provided by the present invention construct an expression of a water index based on the reflectance spectral characteristics of objects in a region to be studied, which can not only improve the accuracy of water extraction from remote sensing images, but also realize simple and quick water extraction from remote sensing images.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image processing, and in particular to a remote sensing image water body extraction method, device, electronic equipment and storage medium. Background Art

[0002] Water extraction is the basis of remote sensing water environment and ecosystem research. Existing remote sensing image water extraction methods mainly include threshold method and classification method. The commonly used classification method is a classification method based on machine learning. Compared with the threshold method water extraction, the classification method model is complex, inefficient, and requires a large number of training samples.

[0003] The water body extraction by threshold method is to set a single or multiple fixed thresholds according to the spectral characteristics of water body and main landforms to achieve the purpose of distinguishing water body from other landforms, and extract the water body area accordingly. The threshold method includes single-band threshold method and multi-band threshold method. The multi-band threshold method is mainly the water body index threshold method. The most commonly used water body index is the Normalized Difference Water Index (NDWI). NDWI makes full use of the high reflectivity of water body in the green light band and the strong absorption characteristics of the near-infrared band, and can effectively reflect the water body information. However, due to the influence of other substances such as sediment and algae in the water body, as well as the effect of factors such as water body depth, the reflectivity of the water body will change in the visible light and near-infrared regions, resulting in low extraction accuracy of NDWI. The existing improved water body index for NDWI greatly increases the number of bands and adjustment coefficients, which significantly increases the complexity of the water body index and is not conducive to application.

[0004] Therefore, how to achieve simple and quick water extraction from remote sensing images while ensuring the accuracy of water extraction has become an urgent problem that needs to be solved in the industry. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a method, device, electronic equipment and storage medium for extracting water from remote sensing images.

[0006] In a first aspect, the present invention provides a method for extracting water from a remote sensing image, comprising:

[0007] Based on the reflectance spectrum characteristics of the objects in the area to be studied, the expression of the water body index is constructed;

[0008] Acquire a reflectivity remote sensing image of the area to be studied, and determine a remote sensing water index map based on the reflectivity remote sensing image and an expression of the water index;

[0009] Based on the remote sensing water body index map and the reflectivity remote sensing image, the water body area in the remote sensing water body index map is extracted.

[0010] Optionally, according to a remote sensing image water body extraction method provided by the present invention, the expression of the water body index is constructed based on the reflectance spectrum characteristics of the ground objects in the area to be studied, including:

[0011] Based on the reflectance spectrum characteristics of the objects in the area to be studied, determining the reflectance adjustment coefficient of the green light band, the reflectance adjustment coefficient of the red light band, and the reflectance adjustment coefficient of the near infrared band;

[0012] Based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band and the reflectivity adjustment coefficient of the near infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band and the reflectivity of the near infrared band, an expression of the water body index is constructed.

[0013] Optionally, according to a remote sensing image water body extraction method provided by the present invention, the expression of the water body index is constructed based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band and the reflectivity adjustment coefficient of the near infrared band, and the reflectivity of the green light band, the reflectivity of the red light band and the reflectivity of the near infrared band, including:

[0014] Based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band and the adjusted reflectivity coefficient of the near infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band and the reflectivity of the near infrared band, an expression of the water body index as shown below is constructed:

[0015]

[0016] Among them, RWI represents the water body index, G represents the reflectivity of the green light band, NIR represents the reflectivity of the near-infrared band, R represents the reflectivity of the red light band, a represents the reflectivity adjustment coefficient of the green light band, b represents the reflectivity adjustment coefficient of the near-infrared band, and c represents the reflectivity adjustment coefficient of the red light band.

[0017] Optionally, according to a remote sensing image water body extraction method provided by the present invention, extracting the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectivity remote sensing image includes:

[0018] Determining a water index threshold based on the remote sensing water index map and the reflectivity remote sensing image;

[0019] Based on the water index threshold, the water area in the remote sensing water index map is extracted.

[0020] Optionally, according to a remote sensing image water body extraction method provided by the present invention, the step of obtaining a reflectance remote sensing image of the area to be studied includes:

[0021] Acquiring a remote sensing image of the area to be studied;

[0022] Based on the processing level corresponding to the remote sensing image, the remote sensing image is preprocessed to obtain the reflectivity remote sensing image.

[0023] Optionally, according to a remote sensing image water body extraction method provided by the present invention, the expression of the water body index is constructed based on the reflectance spectrum characteristics of the ground objects in the area to be studied, including:

[0024] Determine the reflectance spectral characteristics of the ground object type corresponding to the area to be studied;

[0025] Based on the reflectance spectrum characteristics of the land feature type, an expression for the water body index is constructed.

[0026] In a second aspect, the present invention further provides a remote sensing image water body extraction device, comprising:

[0027] A construction module is used to construct an expression of water index based on the reflectance spectrum characteristics of the objects in the area to be studied;

[0028] A determination module, used for acquiring a reflectivity remote sensing image of the area to be studied, and determining a remote sensing water index map based on the reflectivity remote sensing image and an expression of the water index;

[0029] The extraction module is used to extract the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectivity remote sensing image.

[0030] In a third aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for extracting water bodies from remote sensing images as described in the first aspect is implemented.

[0031] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for extracting water bodies from remote sensing images as described in the first aspect.

[0032] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for extracting water bodies from remote sensing images.

[0033] The remote sensing image water body extraction method, device, electronic device and storage medium provided by the present invention construct an expression of a water body index based on the reflectance spectral characteristics of the objects in the area to be studied, and determine a remote sensing water body index map based on the expression of the water body index and the reflectance remote sensing image of the area to be studied. Then, based on the remote sensing water body index map and the reflectance remote sensing image, the water body area in the remote sensing water body index map is extracted, which can not only improve the accuracy of water body extraction from remote sensing images, but also realize simple and fast water body extraction from remote sensing images. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 This is one of the flow charts of the method for extracting water from remote sensing images provided by the present invention;

[0036] Figure 2 This is the second flow chart of the method for extracting water from remote sensing images provided by the present invention;

[0037] Figure 3 It is a schematic diagram of the lake water area based on RWI extraction provided by the present invention;

[0038] Figure 4 It is a schematic diagram of the lake water area extracted based on NDWI provided by the present invention;

[0039] Figure 5 It is a schematic diagram of the river water area based on RWI extraction provided by the present invention;

[0040] Figure 6 It is a schematic diagram of the river water area extracted based on NDWI provided by the present invention;

[0041] Figure 7 It is a structural schematic diagram of a remote sensing image water body extraction device provided by the present invention;

[0042] Figure 8 It is a schematic diagram of the physical structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In order to facilitate a clearer understanding of the embodiments of the present invention, some relevant background knowledge is first introduced as follows.

[0045] Water area extraction is the basis of water body research. Remote sensing technology has the characteristics of wide coverage, less restrictions from ground factors, and sustainable monitoring, and has significant advantages in water body extraction.

[0046] At present, the methods of remote sensing water body extraction can be mainly divided into two categories, one is the threshold method and the other is the classification method. The threshold method is to set a single or multiple fixed thresholds based on the spectral characteristics of the water body and the main objects to achieve the purpose of distinguishing the water body from other objects, and extract the water body area accordingly. The threshold method includes the single-band threshold method and the multi-band threshold method. The multi-band threshold method is mainly the water body index threshold method.

[0047] The reflectivity of water in the visible near-infrared and short-wave infrared (VNIR-SWIR) is highest in the blue light band. As the wavelength increases, the reflectivity of the water body gradually decreases, and the reflectivity in the near-infrared band approaches zero. The most commonly used NDWI in the water body index makes full use of the high reflectivity of the water body in the green light band and the strong absorption characteristics of the near-infrared band to effectively reflect the water body information. Due to the influence of other substances such as sediment and algae in the water body, as well as the effect of factors such as the depth of the water body, the reflectivity of the water body changes in the visible light and near-infrared regions, resulting in a decrease in the extraction accuracy of NDWI. According to the influence of water environmental factors on the reflectance spectrum of water bodies, various improved water body indices have emerged one after another.

[0048] Classification water extraction refers to extracting the category of water from the classification results through the classification method of remote sensing images. Common classification methods are mainly based on machine learning classification methods, which classify remote sensing images in a supervised classification, semi-supervised or clustering manner. Common machine learning classification methods include maximum likelihood classification (MLC), support vector machine (SVM) and random forest (RF). With the development of deep learning technology, classification methods based on deep learning have made significant progress in remote sensing image classification. At present, the more mature deep learning models are mainly convolutional neural network (CNN) models. Compared with threshold water extraction, the classification model is complex and less efficient, especially the classification model based on deep learning, which requires a large number of training samples.

[0049] The existing improved water index for NDWI mainly adds mid-infrared (MIR) bands and adjustment coefficients. For most land remote sensing satellites, the spectral coverage is mainly visible near infrared-shortwave infrared, while there are few aviation and satellite sensors that carry visible near infrared-shortwave infrared and mid-infrared. Some improved water indexes for NDWI also significantly increase the number of bands and adjustment coefficients, which significantly increases the complexity of the water index and is not conducive to application.

[0050] In order to overcome the above-mentioned defects, the present invention provides a method, device, electronic device and storage medium for extracting water from remote sensing images. Figure 1-Figure 8 The invention describes a method, device, electronic equipment and storage medium for extracting water from remote sensing images.

[0051] Figure 1 FIG. 1 is one of the flow charts of the method for extracting water from remote sensing images provided by the present invention. Figure 1 As shown, the method comprises the following steps:

[0052] Step 100, constructing an expression of a water body index based on the reflectance spectrum characteristics of the ground objects in the area to be studied;

[0053] Step 110, obtaining a reflectivity remote sensing image of the area to be studied, and determining a remote sensing water index map based on the reflectivity remote sensing image and the expression of the water index;

[0054] Step 120: extracting the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectivity remote sensing image.

[0055] Specifically, in order to overcome the defect that the existing water body index threshold method is difficult to ensure the accuracy of water body extraction while realizing simple and fast water body extraction from remote sensing images, the present invention constructs an expression of the water body index based on the reflectance spectral characteristics of the objects in the area to be studied, and determines the remote sensing water body index map based on the expression of the water body index and the reflectivity remote sensing image of the area to be studied, and then extracts the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectivity remote sensing image, which can not only improve the accuracy of water body extraction from remote sensing images, but also realize simple and fast water body extraction from remote sensing images.

[0056] Optionally, the area to be studied may be determined first, which may include determining the spatial range and time range of the area to be studied.

[0057] For example, the area to be studied may be determined to be a target lake in Province A, and the target lake in October of a certain year may be determined to be the area to be studied.

[0058] Optionally, after the area to be studied is determined, the reflectance spectrum characteristics of the objects in the area to be studied may be determined.

[0059] For example, the area to be studied is a shallow trophic lake. In October, the reflectance spectrum characteristics of the lake are as follows: the spectrum of vegetation along the lake shore and in the lake water has a significant impact on the spectrum of the water body. In order to extract the water area of ​​the lake, it is necessary to suppress the spectral information of the vegetation and enhance the spectral information of the water body.

[0060] Optionally, an expression for the water body index may be constructed based on the reflectance spectral characteristics of the objects in the area to be studied.

[0061] Optionally, a reflectivity remote sensing image of the area to be studied may be obtained, and a remote sensing water index map may be determined based on the reflectivity remote sensing image and the expression of the water index constructed above.

[0062] Optionally, the water body area in the remote sensing water body index map may be extracted based on the determined remote sensing water body index map and the acquired reflectivity remote sensing image.

[0063] The remote sensing image water body extraction method provided by the present invention constructs an expression of a water body index based on the reflectance spectral characteristics of the objects in the area to be studied, and determines a remote sensing water body index map based on the expression of the water body index and the reflectance remote sensing image of the area to be studied, and then extracts the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectance remote sensing image, which can not only improve the accuracy of water body extraction from remote sensing images, but also realize simple and fast water body extraction from remote sensing images.

[0064] Optionally, constructing an expression of a water body index based on the reflectance spectrum characteristics of the ground objects in the area to be studied includes:

[0065] Based on the reflectance spectrum characteristics of the objects in the area to be studied, determining the reflectance adjustment coefficient of the green light band, the reflectance adjustment coefficient of the red light band, and the reflectance adjustment coefficient of the near infrared band;

[0066] Based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band and the reflectivity adjustment coefficient of the near infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band and the reflectivity of the near infrared band, an expression of the water body index is constructed.

[0067] Specifically, we can first determine the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band, and the reflectivity adjustment coefficient of the near-infrared band based on the reflectivity spectral characteristics of the objects in the area to be studied; further, we can construct an expression for the water body index based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band, and the reflectivity of the near-infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band, and the reflectivity of the near-infrared band.

[0068] Since the existing improved water body indices for NDWI mainly add the mid-infrared band, and there are few aerial and satellite sensors that carry visible near-infrared-shortwave infrared and mid-infrared at the same time, and some improved water body indices for NDWI significantly increase the number of bands, the complexity of the water body index has increased significantly.

[0069] Therefore, the present invention constructs an expression of the water body index for the visible near-infrared spectrum based on the reflectivity and reflectivity adjustment coefficient of the green light band, the red light band and the near-infrared band. The calculation of the water body index is simple, and it can effectively realize fast and accurate water body extraction of multi-scale remote sensing images.

[0070] Optionally, constructing an expression for the water body index based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band, and the reflectivity adjustment coefficient of the near infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band, and the reflectivity of the near infrared band includes:

[0071] Based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band, and the reflectivity adjustment coefficient of the near infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band, and the reflectivity of the near infrared band, an expression of the water body index shown below is constructed:

[0072]

[0073] Among them, RWI (Revised Water Index) represents the water body index, G represents the reflectance of the green light band, NIR represents the reflectance of the near-infrared band, R represents the reflectance of the red light band, a represents the reflectance adjustment coefficient of the green light band, b represents the reflectance adjustment coefficient of the near-infrared band, and c represents the reflectance adjustment coefficient of the red light band.

[0074] Specifically, based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band, and the reflectivity adjustment coefficient of the near infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band, and the reflectivity of the near infrared band, the expression of the water body index shown below can be constructed:

[0075]

[0076] Among them, RWI represents the water body index, G represents the reflectance of the green light band, NIR represents the reflectance of the near-infrared band, R represents the reflectance of the red light band, a represents the reflectance adjustment coefficient of the green light band, b represents the reflectance adjustment coefficient of the near-infrared band, c represents the reflectance adjustment coefficient of the red light band, and a, b and c are all not zero.

[0077] It can be understood that the reflectivity adjustment coefficient a of the green light band, the reflectivity adjustment coefficient b of the near-infrared band and the reflectivity adjustment coefficient c of the red light band are all determined based on the reflectance spectral characteristics of the objects in the study area. It is possible to adjust the reflectance spectrum of the objects in the study area based on the reflectivity adjustment coefficients a, b and c based on the actual reflectance spectral characteristics of the objects in the study area, thereby improving the accuracy of water extraction in remote sensing images.

[0078] The present invention targets the visible near-infrared spectrum and constructs an expression of the water body index by based on the reflectivity and reflectivity adjustment coefficient of the green light band, the red light band and the near-infrared band. The calculation of the water body index is simple and can effectively realize fast and accurate water body extraction for multi-scale remote sensing images.

[0079] Optionally, extracting the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectivity remote sensing image includes:

[0080] Determining a water index threshold based on the remote sensing water index map and the reflectivity remote sensing image;

[0081] Based on the water index threshold, the water area in the remote sensing water index map is extracted.

[0082] Specifically, based on the remote sensing water index map and the reflectivity remote sensing image, a comparative analysis can be conducted on the distribution of objects on the remote sensing water index map and the reflectivity remote sensing image to determine the water index threshold; and then based on the determined water index threshold, the water area in the remote sensing water index map can be extracted.

[0083] For example, by comparing and analyzing the remote sensing water index map and the reflectance remote sensing image, it is determined that the water index threshold is greater than 0, and then the area with a value greater than 0 in the remote sensing water index map can be extracted as the water area.

[0084] The present invention determines the water index threshold by comparing and analyzing the distribution of objects on the remote sensing water index map and the reflectivity remote sensing image of the study area, which can overcome the defect of the existing threshold method for water extraction that sets a fixed threshold to extract the water area, resulting in low accuracy of water extraction.

[0085] Optionally, obtaining a reflectivity remote sensing image of the area to be studied includes:

[0086] Acquiring a remote sensing image of the area to be studied;

[0087] Based on the processing level corresponding to the remote sensing image, the remote sensing image is preprocessed to obtain the reflectivity remote sensing image.

[0088] Specifically, after determining the area to be studied, a remote sensing image of the area to be studied may be obtained, and then based on the processing level corresponding to the acquired remote sensing image, the remote sensing image may be preprocessed to obtain a reflectance remote sensing image.

[0089] Optionally, the acquired remote sensing image of the area to be studied may be either a satellite remote sensing image or an aerial remote sensing image, which is not specifically limited in the present invention.

[0090] Optionally, based on the processing level corresponding to the remote sensing image, preprocessing operations including but not limited to radiation correction and / or geometric correction may be performed on the remote sensing image.

[0091] Optionally, constructing an expression of a water body index based on the reflectance spectrum characteristics of the ground objects in the area to be studied includes:

[0092] Determine the reflectance spectral characteristics of the ground object type corresponding to the area to be studied;

[0093] Based on the reflectance spectrum characteristics of the land feature type, an expression for the water body index is constructed.

[0094] Specifically, after determining the area to be studied, the type of land feature corresponding to the area to be studied can be determined, for example, the type of land feature corresponding to the area to be studied is a shallow trophic lake or a river channel containing rigid non-submerged vegetation.

[0095] Specifically, after determining the land object type corresponding to the area to be studied, the reflection spectrum characteristics of the land object type corresponding to the area to be studied can be determined, and then the expression of the water body index can be constructed based on the reflection spectrum characteristics of the land object type.

[0096] For example, the type of landform in the area to be studied is a shallow trophic lake. In October, the corresponding reflectance spectrum characteristics of the lake are: the spectrum of vegetation along the lake shore and in the lake has a significant impact on the spectrum of the water body. In order to extract the water area of ​​the lake, it is necessary to suppress the spectral information of the vegetation and enhance the spectral information of the water body. The expression of the water body index can be further constructed based on the reflectance spectrum characteristics.

[0097] The present invention can improve the accuracy of water body extraction in remote sensing images by constructing an expression of a water body index based on the reflectance spectrum characteristics of the land object type corresponding to the area to be studied.

[0098] Figure 2 FIG. 2 is a flow chart of the method for extracting water from remote sensing images provided by the present invention. Figure 2 As shown, the method includes the following steps 200 to 240:

[0099] Step 200: Determine the study area.

[0100] For example, a target lake in Province A can be determined as the research area for water extraction, and a target lake in a certain period (such as October of a certain year) can be determined as the research area.

[0101] Step 210: Construct a water body index based on the reflectance spectral characteristics of the objects in the study area.

[0102] For example, suppose the target lake in Province A identified above is a shallow trophic lake, with most of the lake area less than 1 meter deep and rich in fish, shrimp, reeds and lotus, etc. In October of a certain year, the lake area is reduced, and at this time, the vegetation along the coast and in the lake has a significant impact on the water spectrum.

[0103] In order to suppress the spectral information of the vegetation in the lake and enhance the spectral information of the water body, for example, the following water body index calculation formula is constructed:

[0104]

[0105] Among them, RWI represents the water body index, G represents the reflectivity of the green light band, NIR represents the reflectivity of the near-infrared band, and R represents the reflectivity of the red light band.

[0106] Step 220: Acquire remote sensing images of the study area and perform preprocessing.

[0107] For example, according to the research area determined in step 200, a Sentinel-2 multispectral remote sensing image of the target lake area in Province A in October of a certain year is obtained. The obtained Sentinel-2 multispectral remote sensing image is a level 2 reflectance product with high geometric accuracy. Therefore, no preprocessing is required.

[0108] Step 230: Calculate the water index of the remote sensing image.

[0109] For example, the green light band, red light band and near infrared band are selected from the Sentinel-2 satellite multispectral remote sensing image obtained in step 220, that is, the 3rd band, the 4th band and the 8th band of the Sentinel-2 satellite multispectral data, and the reflectivity of the selected green light band, red light band and near infrared band is substituted into the water body index calculation formula constructed in step 210 to obtain the remote sensing water body index map.

[0110] Step 240: Based on the remote sensing water index map, a threshold is set to extract the water area of ​​the remote sensing image.

[0111] For example, the Sentinel-2 multispectral remote sensing image obtained in step 220 and the remote sensing water index map calculated in step 230 are compared and analyzed to determine that the threshold is greater than 0, the water area is the area where the remote sensing water index value is greater than 0, and the area where the value is greater than 0 in the remote sensing water index map is extracted as the water area, thereby obtaining the water body range and area.

[0112] Figure 3 This is a schematic diagram of the lake water area based on RWI extraction provided by the present invention. Figure 4 This is a schematic diagram of the lake water area extracted based on NDWI provided by the present invention, where Figure 3 and Figure 4 The white area in the figure represents water bodies, and the black area represents other land features except water bodies. Figure 3 and Figure 4 It can be seen that compared with the lake water area extracted based on NDWI, the extraction accuracy of the water area in the center of the lake affected by shallow water grasses is significantly improved based on RWI.

[0113] Figure 5 This is a schematic diagram of the river water area based on RWI extraction provided by the present invention. Figure 6 is a schematic diagram of the river water area extracted based on NDWI provided by the present invention, wherein Figure 5 and Figure 6 The white area in the figure represents water bodies, and the black area represents other land features except water bodies. Figure 5 and Figure 6 It can be seen that narrow river water bodies can be extracted based on RWI, and its accuracy in extracting river water bodies is better than that based on NDWI.

[0114] The remote sensing image water body extraction method provided by the present invention constructs an expression of a water body index based on the reflectance spectral characteristics of the objects in the area to be studied, and determines a remote sensing water body index map based on the expression of the water body index and the reflectance remote sensing image of the area to be studied, and then extracts the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectance remote sensing image, which can not only improve the accuracy of water body extraction from remote sensing images, but also realize simple and fast water body extraction from remote sensing images.

[0115] The remote sensing image water body extraction device provided by the present invention is described below. The remote sensing image water body extraction device described below and the remote sensing image water body extraction method described above can be referenced to each other.

[0116] Figure 7 Schematic diagram of the structure of the remote sensing image water body extraction device provided by the present invention. Figure 7 As shown, the device includes: a construction module 710, a determination module 720 and an extraction module 730; wherein:

[0117] The construction module 710 is used to construct an expression of a water body index based on the reflectance spectrum characteristics of the ground objects in the area to be studied;

[0118] The determination module 720 is used to obtain a reflectivity remote sensing image of the area to be studied, and determine a remote sensing water index map based on the reflectivity remote sensing image and the expression of the water index;

[0119] The extraction module 730 is used to extract the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectivity remote sensing image.

[0120] Specifically, the remote sensing image water body extraction device provided by the present invention can construct an expression of the water body index through a construction module 710 based on the reflectance spectral characteristics of the objects in the area to be studied; then obtain the reflectance remote sensing image of the area to be studied, and based on the reflectance remote sensing image and the expression of the water body index, determine the remote sensing water body index map through a determination module 720; finally, based on the remote sensing water body index map and the reflectance remote sensing image, extract the water body area in the remote sensing water body index map through an extraction module 730.

[0121] The remote sensing image water body extraction device provided by the present invention constructs an expression of a water body index based on the reflectance spectral characteristics of the objects in the area to be studied, and determines a remote sensing water body index map based on the expression of the water body index and the reflectance remote sensing image of the area to be studied, and then extracts the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectance remote sensing image, which can not only improve the accuracy of water body extraction from remote sensing images, but also realize simple and fast water body extraction from remote sensing images.

[0122] It should be noted here that the above-mentioned device provided by the embodiment of the present invention can implement all the method steps implemented in the above-mentioned remote sensing image water body extraction method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0123] Figure 8 is a schematic diagram of the physical structure of the electronic device provided by the present invention, such as Figure 8 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the remote sensing image water body extraction method provided by the above methods, and the method includes:

[0124] Based on the reflectance spectrum characteristics of the objects in the area to be studied, the expression of the water body index is constructed;

[0125] Acquire a reflectivity remote sensing image of the area to be studied, and determine a remote sensing water index map based on the reflectivity remote sensing image and an expression of the water index;

[0126] Based on the remote sensing water body index map and the reflectivity remote sensing image, the water body area in the remote sensing water body index map is extracted.

[0127] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0128] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer can execute the remote sensing image water body extraction method provided by the above methods, the method comprising:

[0129] Based on the reflectance spectrum characteristics of the objects in the area to be studied, the expression of the water body index is constructed;

[0130] Acquire a reflectivity remote sensing image of the area to be studied, and determine a remote sensing water index map based on the reflectivity remote sensing image and an expression of the water index;

[0131] Based on the remote sensing water body index map and the reflectivity remote sensing image, the water body area in the remote sensing water body index map is extracted.

[0132] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the above-mentioned remote sensing image water body extraction method, the method comprising:

[0133] Based on the reflectance spectrum characteristics of the objects in the area to be studied, the expression of the water body index is constructed;

[0134] Acquire a reflectivity remote sensing image of the area to be studied, and determine a remote sensing water index map based on the reflectivity remote sensing image and an expression of the water index;

[0135] Based on the remote sensing water body index map and the reflectivity remote sensing image, the water body area in the remote sensing water body index map is extracted.

[0136] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0137] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for extracting water from remote sensing images, characterized in that: include: Based on the reflectance spectrum characteristics of the ground objects in the area to be studied, the reflectance adjustment coefficient of the green light band, the reflectance adjustment coefficient of the red light band, and the reflectance adjustment coefficient of the near infrared band are determined; based on the reflectance adjustment coefficient of the green light band, the reflectance adjustment coefficient of the red light band, and the reflectance adjustment coefficient of the near infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band, and the reflectivity of the near infrared band, the expression of the water body index shown below is constructed: in, represents the water index, represents the reflectivity of the green light band, represents the reflectivity in the near-infrared band, represents the reflectivity of the red light band, represents the reflectivity adjustment coefficient of the green light band, represents the reflectivity adjustment coefficient in the near-infrared band, Indicates the reflectivity adjustment coefficient of the red light band; Acquire a reflectivity remote sensing image of the area to be studied, and determine a remote sensing water index map based on the reflectivity remote sensing image and an expression of the water index; Based on the remote sensing water body index map and the reflectivity remote sensing image, the water body area in the remote sensing water body index map is extracted.

2. The method for extracting water from remote sensing images according to claim 1, characterized in that: The extracting the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectivity remote sensing image comprises: Determining a water index threshold based on the remote sensing water index map and the reflectivity remote sensing image; Based on the water index threshold, the water area in the remote sensing water index map is extracted.

3. The method for extracting water from remote sensing images according to claim 1, characterized in that: The step of acquiring the reflectivity remote sensing image of the area to be studied comprises: Acquiring a remote sensing image of the area to be studied; Based on the processing level corresponding to the remote sensing image, the remote sensing image is preprocessed to obtain the reflectivity remote sensing image.

4. The method for extracting water from remote sensing images according to any one of claims 1 to 3, characterized in that: Based on the reflectance spectral characteristics of the objects in the area to be studied, the expression of the water index can be constructed in the following way: Determine the reflectance spectral characteristics of the ground object type corresponding to the area to be studied; Based on the reflectance spectrum characteristics of the land feature type, an expression for the water body index is constructed.

5. A remote sensing image water extraction device, characterized in that: include: A construction module is used to determine the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band, and the reflectivity adjustment coefficient of the near infrared band based on the reflectivity spectral characteristics of the ground objects in the area to be studied; based on the reflectivity adjustment coefficient of the green light band, the reflectivity adjustment coefficient of the red light band, and the reflectivity adjustment coefficient of the near infrared band, as well as the reflectivity of the green light band, the reflectivity of the red light band, and the reflectivity of the near infrared band, an expression of the water body index as shown below is constructed: in, represents the water index, represents the reflectivity of the green light band, represents the reflectivity in the near-infrared band, represents the reflectivity of the red light band, represents the reflectivity adjustment coefficient of the green light band, represents the reflectivity adjustment coefficient in the near-infrared band, Indicates the reflectivity adjustment coefficient of the red light band; A determination module, used for acquiring a reflectivity remote sensing image of the area to be studied, and determining a remote sensing water index map based on the reflectivity remote sensing image and an expression of the water index; The extraction module is used to extract the water body area in the remote sensing water body index map based on the remote sensing water body index map and the reflectivity remote sensing image.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the remote sensing image water body extraction method as described in any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for extracting water from remote sensing images as claimed in any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for extracting water from remote sensing images as claimed in any one of claims 1 to 4 is implemented.

Images