CN113343945B - Water body identification method and device, electronic equipment and storage medium - Google Patents
Water body identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113343945B CN113343945B CN202110878395.5A CN202110878395A CN113343945B CN 113343945 B CN113343945 B CN 113343945B CN 202110878395 A CN202110878395 A CN 202110878395A CN 113343945 B CN113343945 B CN 113343945B
- Authority
- CN
- China
- Prior art keywords
- water body
- vector data
- target
- image
- remote sensing
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
The application provides a water body identification method, a water body identification device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a target image data set of a target geographic area and first vector data containing a water body mask; determining a normalized difference water body index NDWI image data set and a near infrared band NIR image data set according to the target image data set; performing spatial superposition on the remote sensing image and the first vector data aiming at each scene of the remote sensing image in the target image data set, and determining second vector data and third vector data in the first vector data; and identifying the water body data of the NDWI image data set and the NIR image data set according to the second vector data and the third vector data to obtain the water body data of the target geographic area. According to the embodiment, the water body mask is utilized to reduce background environment interference and problem complexity, the water body is identified by utilizing the reverse expression of the water body on NDWI and NIR, and the water body identification precision and efficiency are improved.
Description
Technical Field
The application relates to the technical field of computers, in particular to a water body identification method and device, electronic equipment and a storage medium.
Background
At present, water body monitoring based on remote sensing images is an important means for identifying the range of a water body area, and for high-resolution images, a threshold segmentation method or a machine learning classification method is adopted to realize water body monitoring on characteristic space, comprehensive application spectrum or space characteristics. However, on the one hand, the threshold segmentation method or the machine learning classification method is developed for specific data and applications, and has low universality in time and space and low engineering application degree. On the other hand, the high-resolution satellite image has high spatial resolution, but the spectral information is relatively insufficient, only 4 bands of blue, green, red and near infrared exist, and the high-resolution satellite image has the limitations of missing and false lifting phenomena caused by cloud, snow, ice, object shadows, roads, houses and dry water bodies in a dry period, and has low accuracy in the aspect of water body identification.
Disclosure of Invention
An object of the embodiments of the present application is to provide a water body identification method, device, electronic device, and storage medium, which aim to solve the problem of low accuracy of current water body identification.
In a first aspect, an embodiment of the present application provides a water body identification method, including:
acquiring a target image data set of a target geographic area and first vector data containing a water body mask, wherein each scene of a remote sensing image of the target image data set has a spatial intersection with the first vector data;
determining a normalized difference water body index NDWI image data set and a near infrared band NIR image data set according to the target image data set;
performing spatial superposition on the remote sensing image and the first vector data aiming at each remote sensing image in the target image data set, and determining second vector data and third vector data in the first vector data, wherein the second vector data are vector data of a water body mask corresponding to the whole area of the remote sensing image and containing a water body, and the third vector data are vector data of a water body mask corresponding to a part of area of the remote sensing image and containing a water body;
and identifying the water body data of the NDWI image data set and the NIR image data set according to the second vector data and the third vector data to obtain the water body data of the target geographic area.
In the embodiment, by acquiring the target image data set of the target geographic area and the first vector data containing the water body mask, the water body mask is utilized to reduce the background environment interference and the problem complexity and improve the accuracy of water body identification; according to the target image data set, determining a normalized difference water body index NDWI image data set and a near infrared band NIR image data set, so that the water body can be identified by utilizing the reverse expression of the water body on NDWI and NIR in the follow-up process, and the water body identification precision is improved; performing spatial superposition on the remote sensing image and the first vector data aiming at each scene of the remote sensing image in the target image data set, and determining second vector data and third vector data in the first vector data, so as to automatically distinguish regions containing all water, partial water and no water on the remote sensing image; and according to the water content conditions of different areas, the water body data of the NDWI image data set and the NIR image data set are identified by utilizing the second vector data and the third vector data, so that the water body data of the target geographical area are obtained, and the automatic distinguishing and automatic extraction of the water body area are realized.
In one embodiment, acquiring a target image dataset of a target geographic area and a first vector data comprising a water mask comprises:
acquiring an original image data set of a target geographic area and first vector data containing a water body mask;
performing orthorectification and image fusion on the original image data set to obtain a multispectral image data set;
and performing spatial superposition on the multispectral image data and the first vector data, and determining a target image data set which has a spatial intersection with the first vector data in the multispectral image data.
In the embodiment, the water body mask is utilized to effectively reduce the complex background information and the machine operand in the water body identification process, and improve the water body identification precision and the identification efficiency.
In an embodiment, for each remote sensing image in the target image data set, spatially superimposing the remote sensing image and the first vector data, and determining the second vector data and the third vector data in the first vector data includes:
carrying out spatial superposition on each remote sensing image and the first vector data to obtain a water mask area of a target water mask of the first vector data, which corresponds to the remote sensing image;
determining whether the ground object type of the remote sensing image is a single ground object or not according to the near-infrared band standard deviation of all pixels in the water mask area;
if the ground object type of the remote sensing image is a single ground object, determining first vector data containing a target water body mask meeting a first preset condition as second vector data;
and if the ground object type of the remote sensing image is not a single ground object, determining the first vector data containing the target water body mask meeting the second preset condition as third vector data.
In the embodiment, whether the water body mask area of the remote sensing image contains all water or part of water is determined through whether the water body mask area is a single ground object, so that the area identification of all water and part of water is realized.
Further, if the feature type of the remote sensing image is a single feature, determining first vector data including a target water mask meeting a first preset condition as second vector data, including:
if the ground object type of the remote sensing image is a single ground object, calculating the near-infrared band mean value, the target ratio and the first brightness mean value of all pixels in the water body mask area, wherein the target ratio is the ratio between the near-infrared band total value and all band total values;
if the near-infrared band mean value is larger than the first threshold value, the target ratio is larger than the second threshold value, and the first lightness mean value is larger than the third threshold value, the target water body mask meets the first preset condition, and the first vector data containing the target water body mask is the second vector data.
In the present embodiment, for an area containing water in its entirety, it is further identified whether or not the area is a water-free area such as a cloud, snow, ice, bare soil, or the like, which is not really water-containing in its entirety, thereby further improving the water body identification accuracy.
Further, if the feature type of the remote sensing image is not a single feature, determining the first vector data containing the target water mask meeting the second preset condition as third vector data, including:
if the ground object type of the remote sensing image is not a single ground object, calculating the target proportion and a second lightness average value of all pixels in the water body mask area, wherein the target proportion is the proportion that the near infrared band values of all pixels in the water body mask area are lower than a preset water body threshold value;
if the target proportion is greater than the fourth threshold and the second lightness average value is greater than the fifth threshold, the target water body mask meets a second preset condition, and the first vector data containing the target water body mask is third vector data.
In the embodiment, for the area partially containing water, whether the area actually contains water is further identified, and the area is not a water-free area such as cloud, snow, ice, bare soil and the like, so that the water body identification precision is further improved.
In an embodiment, identifying the water body data in the NDWI image data set and the NIR image data set according to the second vector data and the third vector data to obtain the water body data in the target geographic area includes:
performing spatial superposition on the second vector data and the NDWI image data set, and determining first water body data of a first water body mask area corresponding to a water body mask of the second vector data on the remote sensing image;
and determining second water body data of a second water body mask area corresponding to the water body mask of the third vector data on the remote sensing image according to the third vector data and the NIR image data set of the NDWI image data, wherein the water body data of the target geographic area comprise the first water body data and the second water body data.
In the embodiment, based on the fact that the gray value of the water body on the NDWI gray scale map is higher, and the gray value of the water body on the NIR gray scale map is lower, the water body identification is realized by combining the two through utilizing the reverse representation of the water body on the NDWI gray scale map and the NIR gray scale map, and the water body identification precision is improved.
Further, spatially superimposing the second vector data with the NDWI image data set, and determining first water body data of a first water body mask region corresponding to the water body mask of the second vector data on the remote sensing image, including:
for each NDWI image in the NDWI image data set, carrying out spatial superposition on the NDWI image and the second vector data to obtain a first water mask area corresponding to a water mask of the second vector data on the NDWI image;
determining a centroid pixel of the first water mask region;
determining NDWI values corresponding to four-neighborhood pixels of the centroid pixel;
and if the NDWI value is larger than the preset value, the first water body mask area is a water body, and first water body data are obtained.
In the embodiment, the water body region identification is realized by using the growth of the water body region and circularly calculating the regions containing water.
Further, determining second water body data of a second water body mask area corresponding to the water body mask of the third vector data on the remote sensing image according to the third vector data and the NDWI image data set NIR image data set, including:
the third vector data are respectively overlapped with the NDWI image in the NDWI image data set and the NIR image in the NIR image data set in a space mode to obtain a third water body mask area corresponding to the water body mask of the third vector data on the NDWI image and a fourth water body mask area corresponding to the water body mask of the third vector data on the NIR image, and the second water body mask area comprises the third water body mask area and the fourth water body mask area;
carrying out Dajin segmentation on the third water body mask area and the fourth water body mask area to obtain a first target value corresponding to the third water body mask area and a second target value corresponding to the fourth water body mask area;
and if the NDWI value of the target area on the remote sensing image is larger than the first target value and the near infrared value of the remote sensing image is smaller than the second target value, the target area is the water body, and second water body data of the remote sensing image are obtained.
In this embodiment, the Otsu segmentation technology is based on the combined application of the normalized difference water body index and the near-infrared band, and makes full use of the reverse performance of the water body on the normalized difference water body index and the near-infrared band, so as to improve the water body identification precision.
In a second aspect, an embodiment of the present application provides a water body identification device, including:
the acquisition module is used for acquiring a target image data set of a target geographic area and first vector data containing a water body mask, and each remote sensing image of the target image data set has a spatial intersection with the first vector data;
the first determination module is used for determining a normalized difference water body index NDWI image data set and a near infrared band NIR image data set according to the target image data set;
the second determination module is used for performing spatial superposition on the remote sensing image and the first vector data aiming at each remote sensing image in the target image data set to determine second vector data and third vector data in the first vector data, wherein the second vector data are vector data of a water body mask corresponding to the whole area of the remote sensing image and containing a water body, and the third vector data are vector data of a water body mask corresponding to a part of area of the remote sensing image and containing a water body;
and the identification module is used for identifying the water body data of the NDWI image data set and the NIR image data set according to the second vector data and the third vector data to obtain the water body data of the target geographic area.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory and a processor, where the memory is used to store a computer program, and the processor runs the computer program to make the electronic device execute the water body identification method in any one of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the water body identification method of any one of the first aspect.
It should be noted that, for the beneficial effects of the second aspect to the fourth aspect, reference is made to the description of the first aspect, and details are not repeated here.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a water body identification method provided in an embodiment of the present application;
fig. 2 is a schematic diagram of a first remote sensing image provided in an embodiment of the present application;
fig. 3 is a schematic diagram of a second remote sensing image provided in the present application;
fig. 4 is a schematic diagram of a third remote sensing image provided in the embodiment of the present application;
fig. 5 is a schematic diagram of a fourth remote sensing image provided in the embodiment of the present application;
fig. 6 is a schematic diagram of a fifth remote sensing image provided in the present application;
fig. 7 is a schematic structural diagram of a water body identification device provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
As described in the related art, for high-resolution images, a threshold segmentation method or a machine learning classification method is adopted to realize water body monitoring on characteristic space, comprehensive application spectrum or spatial characteristics. The common threshold segmentation method is to separate a water body from a non-water body on an entire scene image through a global threshold, but the spectral features of the water body in a large range have great difference, the monitoring effects of different water bodies are different, and the stability is poor. The machine learning classification method usually requires a large amount of sample data for support, and a large amount of manpower and time are required for sample labeling and model training. It can be seen that the current methods are developed for specific data and applications, and the universality in time and space and the degree of engineering application are low.
The current water body identification process has the phenomena of missing extraction and wrong extraction caused by cloud, snow and ice, shadows of cloud, mountain and buildings, dark roads and houses and dryness of water bodies in a dry water period. The high-resolution satellite image has high spatial resolution, but spectral information is relatively insufficient, and only 4 bands of blue, green, red and near infrared exist, so that the high-resolution satellite image has great limitation in the aspect of water body identification.
In order to solve the problems in the prior art, the application provides a water body identification method, which is characterized in that a target image data set of a target geographic region and first vector data containing a water body mask are obtained, so that background environment interference and problem complexity are reduced by using the water body mask, and the accuracy of water body identification is improved; according to the target image data set, determining a normalized difference water body index NDWI image data set and a near infrared band NIR image data set, so that the water body can be identified by utilizing the reverse expression of the water body in NDWI and NIR, and the water body identification precision is improved; performing spatial superposition on the remote sensing image and the first vector data aiming at each scene of the remote sensing image in the target image data set, and determining second vector data and third vector data in the first vector data, so as to automatically distinguish regions containing all water, partial water and no water on the remote sensing image; and according to the water content conditions of different areas, the water body data of the NDWI image data set and the NIR image data set are identified by utilizing the second vector data and the third vector data, so that the water body data of the target geographical area are obtained, and the automatic distinguishing and automatic extraction of the water body area are realized.
Referring to fig. 1, fig. 1 shows a flowchart of an implementation of a water body identification method provided by an embodiment of the present application. The water body identification method described in the embodiments of the present application can be applied to electronic devices, including but not limited to computer devices such as smart phones, tablet computers, desktop computers, supercomputers, personal digital assistants, physical servers, and cloud servers. The water body identification method of the embodiment of the application comprises the following steps of S101 to S104:
step S101, a target image data set of a target geographic area and first vector data containing a water body mask are obtained, and a spatial intersection exists between each remote sensing image of the target image data set and the first vector data.
In this embodiment, the target image dataset is an image set obtained by screening all remote sensing images in the target geographic area through a water mask. The water body mask is used for shielding the remote sensing image so as to realize the image template for controlling the image processing area. The first vector data is vector data including a plurality of water body mask vector planes, and exemplarily, the first vector data of the embodiment is vector data in which the water surface area is greater than 0.5km2Vector data formed by water masks of lakes, reservoirs and rivers of more than three levels of the country.
Optionally, the water mask vector surface includes no water, partial water, and total water. When no water exists, no water exists on the water mask vector plane; when part of water exists, part of water exists on the water mask vector surface; when the water is full, all the water body mask vector surfaces are water bodies.
Optionally, the vector surface has an area greater than the water surface during the flat or flooded periods.
And S102, determining a normalized difference water body index NDWI image data set and a near infrared band NIR image data set according to the target image data set.
In this embodiment, the NDWI image data set includes a plurality of NDWI images, which are obtained by performing normalized difference processing on a specific band of a remote sensing image in the target image data set, and optionally, the NDWI may be a normalized ratio index of a green band and a near-infrared band, or a normalized ratio index of a middle-infrared band and a near-infrared band, which is not limited herein. The NIR image data includes a plurality of NIR images, which are images obtained by performing near-infrared band extraction on the remote sensing images in the target image data set.
Step S103, carrying out spatial superposition on the remote sensing image and the first vector data aiming at each scene of the remote sensing image in the target image data set, and determining second vector data and third vector data in the first vector data, wherein the second vector data is vector data of a water body mask corresponding to the whole area of the remote sensing image and containing a water body, and the third vector data is vector data of a water body mask corresponding to a part of area of the remote sensing image and containing a water body.
In an embodiment, the second vector data is vector data of all water bodies in the water body mask vector plane, and the third vector data is vector data of a part of water bodies in the water body mask vector plane. In this embodiment, each remote sensing image and the first vector data are spatially superposed to calculate an intersection in a spatial range between the two remote sensing images, and according to the intersection degree of the two remote sensing images, the water content condition of the corresponding region of each remote sensing image in the target geographic region can be determined, so that the second vector data and the third vector data in the first vector data are screened out.
And step S104, identifying the water body data of the NDWI image data set and the NIR image data set according to the second vector data and the third vector data to obtain the water body data of the target geographic area.
In this embodiment, the water body data of the target geographic area includes a water body area range. Optionally, the second vector data is vector data in which the vector plane of the water body mask completely contains water, and only the actual water containing range needs to be determined, so that the actual water body range in the remote sensing image can be identified by using the NDWI image data set based on the characteristic that the gray value of the water body on the NDWI gray scale map is high.
Optionally, the third vector data is vector data of water contained in the vector surface portion of the water body mask, that is, the vector data contains other object information besides the water body, so that a boundary between the water body and the non-water body needs to be distinguished, and therefore, the water body range boundary in the remote sensing image is identified by using the NDWI image data set and the NIR image data set by using the characteristics that the gray value of the water body on the NDWI gray scale image is higher and the gray value of the water body on the NIR gray scale image is lower, so that the identification of the water body data in the remote sensing image is realized.
In an embodiment, on the basis of the embodiment in fig. 1, the step S101 includes: acquiring an original image data set of a target geographic area and first vector data containing a water body mask; performing orthorectification and image fusion on the original image data set to obtain a multispectral image data set; and performing spatial superposition on the multispectral image data and the first vector data, and determining a target image data set which has a spatial intersection with the first vector data in the multispectral image data.
In this embodiment, the input data includes multi-scene original image data and first vector data including a water mask, the original image data is subjected to orthorectification and image fusion to obtain a multi-spectral image data set, the multi-spectral image data set and the first vector data are subjected to spatial superposition, and an intersection of the multi-spectral image data set and the first vector data in a spatial range is calculated to exclude image data in the multi-spectral image data set which does not have a spatial intersection with the first vector data, so as to obtain a target image data set.
In an embodiment, on the basis of the embodiment in fig. 1, the step S103 includes:
carrying out spatial superposition on each remote sensing image and the first vector data to obtain a water mask area of a target water mask of the first vector data, which corresponds to the remote sensing image;
determining whether the ground object type of the remote sensing image is a single ground object or not according to the near-infrared band standard deviation of all pixels in the water mask area;
if the ground object type of the remote sensing image is a single ground object, determining first vector data containing a target water body mask meeting a first preset condition as second vector data;
and if the ground object type of the remote sensing image is not a single ground object, determining the first vector data containing the target water body mask meeting the second preset condition as third vector data.
In this embodiment, each remote sensing image in the target image data set is superimposed with the first vector data in a spatial range, and each water body mask vector plane (represented by WAOI) in the first vector data is screened according to multiple thresholds, so as to obtain the WAOIAll water、WAOIPart of waterAnd WAOIWithout water. The second vector data is composed of all WAOIsAll waterThe third vector data isContaining all WAOIPart of waterThe vector data of (2).
Optionally, for each WAOI, calculating the standard deviation of the WAOI corresponding to the near-infrared wave bands of all the image elements covered by the water body mask area on the remote sensing image; if the standard deviation is not larger than a preset near-infrared band standard deviation threshold value, the ground object type of the remote sensing image is a single ground object; and if the standard deviation is larger than a preset near-infrared band standard deviation threshold value, the ground object type of the remote sensing image is not a single ground object.
Optionally, if the ground object type of the remote sensing image is a single ground object, calculating a near-infrared band mean value, a target ratio and a first brightness mean value of all pixels in a water mask area, wherein the target ratio is a ratio between a near-infrared band total value and all band total values; if the near-infrared band mean value is larger than the first threshold value, the target ratio is larger than the second threshold value, and the first lightness mean value is larger than the third threshold value, the target water body mask meets the first preset condition, and the first vector data containing the target water body mask is the second vector data.
In this embodiment, the first threshold is a threshold of the near-infrared band average value for excluding non-full water, the second threshold is a threshold of the near-infrared occupancy for excluding non-full water, and the third threshold is a brightness threshold when expressed as a water body.
Illustratively, for each WAOI, calculating a mean value of the WAOI corresponding to the near-infrared bands of all the pixels covered by the water body mask area on the remote-sensing image, if the mean value is not greater than a first threshold, it is indicated that the moisture condition of the water body mask vector plane is likely to be full water, if the mean value is greater than the first threshold, it is indicated that the moisture condition of the water body mask vector plane can be excluded as non-full water, that is, it is determined that the water body mask vector plane is the WAOIWithout water。
Further, calculating a target ratio between the total value of the near-infrared bands of all pixels covered by the WAOI corresponding to the water mask area on the remote sensing image and the total value of all bands, optionally, calculating by the following calculation formula:
wherein, the
The total value of the blue band is the blue band total value,
is the total value of the green band and is,
is the total value of the red wave band,
is the total value of the near-infrared wave band,
in order to achieve the target ratio,iindicating the number of bands, e.g.BiIs shown asiThe value of the blue band is determined,i=[1，n]。
if the target ratio is not greater than the second threshold, it is determined that the water-containing condition of the water body mask vector plane has the possibility of full water, and if the target ratio is greater than the second threshold, it is determined that the water-containing condition of the water body mask vector plane can be excluded as non-full water, that is, it is determined that the water body mask vector plane isWAOIWithout water。
Further, calculating the brightness mean value of all pixels covered by the WAOI corresponding to the water body mask area on the remote sensing image, if the brightness mean value is not larger than a third threshold value, it is indicated that the water containing condition of the water body mask vector plane has the possibility of full water, and if the brightness mean value is larger than the third threshold value, it is indicated that the water containing condition of the water body mask vector plane can be excluded as non-full water, that is, it can be determined that the water body mask vector plane is the WAOIWithout water。
If the near-infrared band mean value is larger than the first threshold value, the target ratio is larger than the second threshold value and the first brightness mean value is larger than the third threshold value, the water body mask vector plane is WAOIAll water。
Optionally, if the ground object type of the remote sensing image is not a single ground object, calculating a target ratio and a second lightness average value of all pixels in the water mask area, wherein the target ratio is a ratio that the near-infrared band values of all pixels in the water mask area are lower than a preset water threshold value; if the target proportion is greater than the fourth threshold and the second lightness average value is greater than the fifth threshold, the target water body mask meets a second preset condition, and the first vector data containing the target water body mask is third vector data.
In this embodiment, the fourth threshold is a proportion threshold for removing water, the fifth threshold is a lightness threshold when the water is not water, and the preset water threshold is a proportion of pixels occupied by the water. Optionally, the preset water body threshold may be adjusted according to the image pixel resolution.
Illustratively, for each WAOI, calculating a target proportion of the WAOI corresponding to all the pixels covered by the water body mask area on the remote sensing image, if the target proportion is greater than a fourth threshold, excluding that the water body mask vector plane is anhydrous, and if the target proportion is not greater than the fourth threshold, determining that the water body mask vector plane is the WAOIWithout water. Further, calculating a second lightness average value of all pixels covered by the WAOI corresponding to the water mask area on the remote sensing image, and if the second lightness average value is greater than a fifth threshold value, determining that the water mask vector plane is the WAOIWithout waterIf the second brightness mean is not greater than the fifth threshold, it is saidThe water content of the mask vector surface of the bright water body is the possibility of partial water.
If the target proportion is greater than the fourth threshold value and the second brightness mean value is greater than the fifth threshold value, the water body mask vector plane is WAOIPart of water。
In an embodiment, on the basis of the embodiment in fig. 1, the step S104 includes:
performing spatial superposition on the second vector data and the NDWI image data set, and determining first water body data of a first water body mask area corresponding to a water body mask of the second vector data on the remote sensing image;
and determining second water body data of a second water body mask area corresponding to the water body mask of the third vector data on the remote sensing image according to the third vector data and the NIR image data set of the NDWI image data, wherein the water body data of the target geographic area comprise the first water body data and the second water body data.
In this embodiment, the first water body data is a WAOIAll waterCorresponding to the water body data on the remote sensing image, the second water body data is WAOIPart of waterAnd corresponding to the water body data on the remote sensing image. Further, will be for WAOIAll waterWater body area growth and for WAOIPart of waterAnd performing smoothing treatment on all water body data obtained by image segmentation and extraction, performing vectorization on the data after treatment to obtain vector data, and merging all the vector data to obtain final water body extraction vector data.
Optionally, spatially superimposing the second vector data with the NDWI image data set, and determining first water body data of a first water body mask region corresponding to the water body mask of the second vector data on the remote sensing image, including:
for each NDWI image in the NDWI image data set, carrying out spatial superposition on the NDWI image and the second vector data to obtain a first water mask area corresponding to a water mask of the second vector data on the NDWI image;
determining a centroid pixel of the first water mask region;
determining NDWI values corresponding to four-neighborhood pixels of the centroid pixel;
and if the NDWI value is larger than the preset value, the first water body mask area is a water body, and first water body data are obtained.
In an embodiment, the WAOIAll waterAnd the actual water body range of the first water body mask area is larger than or equal to the range of the WAOI, for the situation, each WAOI of the second vector data is taken as a space range in the NDWI image data set, a starting pixel and a threshold range are given, and a given threshold is taken as a judgment index for area growth so as to extract the whole water body range.
Illustratively, a WAOI is superimposed on the NDWI image, with the WAOI on top and the image on the bottom, for example. In the WAOI range, a pixel position corresponding to the WAOI centroid is found on the NDWI image, the pixel is taken as an initial pixel position, pixels in four neighborhoods of the pixel are judged, if the NDWI is larger than the given threshold value, the pixel is regarded as a water body, and the water body is increased according to the rule until the whole water body range is extracted. Optionally, the given threshold is the average of the NDWI values of all the image elements covered in the WAOI minus an empirical value.
Optionally, determining second water body data of a second water body mask region corresponding to the water body mask of the third vector data on the remote sensing image according to the third vector data and the NIR image data set of the NDWI image data set, including:
the third vector data are respectively overlapped with the NDWI image in the NDWI image data set and the NIR image in the NIR image data set in a space mode to obtain a third water body mask area corresponding to the water body mask of the third vector data on the NDWI image and a fourth water body mask area corresponding to the water body mask of the third vector data on the NIR image, and the second water body mask area comprises the third water body mask area and the fourth water body mask area;
carrying out Dajin segmentation on the third water body mask area and the fourth water body mask area to obtain a first target value corresponding to the third water body mask area and a second target value corresponding to the fourth water body mask area;
and if the NDWI value of the target area on the remote sensing image is larger than the first target value and the near infrared value of the remote sensing image is smaller than the second target value, the target area is the water body, and second water body data of the remote sensing image are obtained.
In this embodiment, the WAOIPart of waterRepresenting that the actual water body range of the second water body mask area is smaller than the range of the WAOI, for which case image segmentation is performed in the NDWI image data set and the NIR image data set in order to reject other terrain in the WAOI range and only extract the water body part.
Illustratively, the NDWI image data set and the NIR image data set are respectively superposed with the third vector data, the superposed result is divided by using a great deal of fluid, a corresponding dividing target value is determined, the dividing target value of the NDWI is set as a first target value, and the dividing target value of the near-infrared band is set as a second target value. In each WAOI, the part satisfying both NDWI greater than the threshold A and near-infrared band less than the threshold B is the water body part of the WAOI.
By way of example, and not limitation, to facilitate an understanding of the present method, the following provides an application scenario. The specific implementation is to take GF2 (high score No. 2 satellite) data as an example, and obtain the WAOI after data processing and multiple threshold value screeningAll water、WAOIPart of waterAnd WAOIWithout water. For WAOIAll waterPerforming water body region growth treatment to WAOIPart of waterPerforming image segmentation and extraction processing, merging all types of water bodies and performing vectorization, wherein the result is exemplified as follows:
as shown in FIG. 2, the frame with number A of the image is WAOIWithout water，WAOIWithout waterAll the materials are ice and other places, and water extraction is not carried out. As shown in FIG. 3, the frame with number B of the image is WAOIWithout water，WAOIWithout waterAll the plants are other types, and water body extraction is not carried out. As shown in FIG. 4, the frame C of the image is WAOIPart of waterIn the WAOIPart of waterAnd (4) performing image segmentation, wherein the numbered frame D is the water body range of automatic extraction. As shown in FIG. 5, the image has the frame number E as WAOIPart of water，WAOIPart of waterAnd (4) performing image segmentation, wherein the frame with the number F is the water body range of automatic extraction. As shown in FIG. 6, the frame with the number G of the image is WAOIAll waterIn the WAOIAll waterAnd finding a mass center as an initial pixel to increase the water body area, wherein the numbered H frame is the water body range of automatic extraction.
In order to implement the method corresponding to the above method embodiment to achieve the corresponding function and technical effect, a water body identification device is provided below. Referring to fig. 7, fig. 7 is a block diagram of a water body identification device according to an embodiment of the present application. For convenience of explanation, only the parts related to the present embodiment are shown, and the water body identification device provided in the embodiments of the present application includes:
an obtaining module 701, configured to obtain a target image data set of a target geographic area and first vector data including a water mask, where a spatial intersection exists between each remote sensing image of the target image data set and the first vector data;
a first determining module 702, configured to determine a normalized difference water body index NDWI image data set and a near-infrared band NIR image data set according to the target image data set;
a second determining module 703, configured to perform spatial superposition on the remote-sensing image and the first vector data for each remote-sensing image in the target image data set, and determine second vector data and third vector data in the first vector data, where the second vector data is vector data in which all regions of the water body mask corresponding to the remote-sensing image contain a water body, and the third vector data is vector data in which a part of regions of the water body mask corresponding to the remote-sensing image contain a water body;
an identifying module 704, configured to identify water body data of the NDWI image data set and the NIR image data set according to the second vector data and the third vector data, so as to obtain water body data of the target geographic area.
In an embodiment, the obtaining module 701 includes:
the system comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring an original image data set of a target geographic area and first vector data containing a water body mask;
the preprocessing unit is used for performing orthorectification and image fusion on the original image data set to obtain a multispectral image data set;
the first determining unit is used for performing spatial superposition on the multispectral image data and the first vector data and determining a target image data set which has a spatial intersection with the first vector data in the multispectral image data.
In an embodiment, the second determining module 703 includes:
the superposition unit is used for carrying out spatial superposition on each scene remote sensing image and the first vector data to obtain a water body mask area of a target water body mask of the first vector data, which corresponds to the remote sensing image;
the second determining unit is used for determining whether the ground object type of the remote sensing image is a single ground object or not according to the near-infrared band standard deviation of all pixels in the water mask area;
the third determining unit is used for determining the first vector data containing the target water body mask meeting the first preset condition as second vector data if the ground object type of the remote sensing image is a single ground object;
and the fourth determining unit is used for determining the first vector data containing the target water body mask meeting the second preset condition as third vector data if the ground object type of the remote sensing image is not a single ground object.
Further, a third determination unit includes:
the first calculating subunit is used for calculating the near-infrared band mean value, the target ratio and the first lightness mean value of all pixels in the water mask area if the ground object type of the remote sensing image is a single ground object, wherein the target ratio is the ratio between the near-infrared band total value and all band total values;
the first judging subunit is configured to, if the near-infrared band mean value is greater than a first threshold, the target ratio is greater than a second threshold, and the first brightness mean value is greater than a third threshold, determine that the target water body mask meets a first preset condition, and determine that first vector data including the target water body mask is second vector data.
Further, a fourth determination unit includes:
the second calculating subunit is used for calculating a target proportion and a second lightness average value of all pixels in the water body mask area if the ground object type of the remote sensing image is not a single ground object, wherein the target proportion is a proportion that the near infrared band value of all the pixels in the water body mask area is lower than a preset water body threshold value;
and the second judgment subunit is used for judging that the target water body mask accords with a second preset condition if the target proportion is greater than a fourth threshold and the second lightness average value is greater than a fifth threshold, and the first vector data containing the target water body mask is third vector data.
In one embodiment, the identifying module 704 includes:
a fifth determining unit, configured to spatially superimpose the second vector data and the NDWI image data set, and determine first water body data of a first water body mask region corresponding to a water body mask of the second vector data on the remote sensing image;
and a sixth determining unit, configured to determine, according to the third vector data and the NIR image data set of the NDWI image data set, second water data of a second water mask region corresponding to the water mask of the third vector data on the remote sensing image, where the water data of the target geographic region includes the first water data and the second water data.
Further, a fifth determining unit includes:
the first superposition subunit is used for carrying out spatial superposition on the NDWI image and the second vector data aiming at each NDWI image in the NDWI image data set to obtain a first water body mask area corresponding to the water body mask of the second vector data on the NDWI image;
a first determining subunit, configured to determine a centroid pixel of the first water-body mask region;
the second determining subunit is used for determining NDWI values corresponding to the four-neighborhood pixels of the centroid pixel;
and the third judging subunit is used for judging that the first water body mask area is the water body if the NDWI value is larger than the preset value, so as to obtain the first water body data.
Further, a sixth determining unit includes:
the second superposition subunit is used for spatially superposing the third vector data with the NDWI image in the NDWI image data set and the NIR image in the NIR image data set respectively to obtain a third water body mask area corresponding to the water body mask of the third vector data on the NDWI image and a fourth water body mask area corresponding to the water body mask of the third vector data on the NIR image, wherein the second water body mask area comprises the third water body mask area and the fourth water body mask area;
the dividing unit is used for carrying out large body fluid division on the third water body mask area and the fourth water body mask area to obtain a first target value corresponding to the third water body mask area and a second target value corresponding to the fourth water body mask area;
and the fourth judging subunit is used for determining that the target area is the water body if the NDWI value of the target area on the remote sensing image is larger than the first target value and the near-infrared value of the remote sensing image is smaller than the second target value, so as to obtain second water body data of the remote sensing image.
The water body identification device can implement the water body identification method of the method embodiment. The alternatives in the above-described method embodiments are also applicable to this embodiment and will not be described in detail here. The rest of the embodiments of the present application may refer to the contents of the above method embodiments, and in this embodiment, details are not described again.
Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 8, the electronic apparatus 8 of this embodiment includes: at least one processor 80 (only one shown in fig. 8), a memory 81, and a computer program 82 stored in the memory 81 and executable on the at least one processor 80, the processor 80 implementing the steps of any of the method embodiments described above when executing the computer program 82.
The electronic device 8 may be a computing device such as a smartphone, a tablet computer, a desktop computer, a supercomputer, a personal digital assistant, a physical server, and a cloud server. The electronic device may include, but is not limited to, a processor 80, a memory 81. Those skilled in the art will appreciate that fig. 8 is merely an example of the electronic device 8, and does not constitute a limitation of the electronic device 8, and may include more or less components than those shown, or combine some of the components, or different components, such as an input-output device, a network access device, etc.
The Processor 80 may be a Central Processing Unit (CPU), and the Processor 80 may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 81 may in some embodiments be an internal storage unit of the electronic device 8, such as a hard disk or a memory of the electronic device 8. The memory 81 may also be an external storage device of the electronic device 8 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 8. Further, the memory 81 may also include both an internal storage unit and an external storage device of the electronic device 8. The memory 81 is used for storing an operating system, an application program, a BootLoader (BootLoader), data, and other programs, such as program codes of the computer program. The memory 81 may also be used to temporarily store data that has been output or is to be output.
In addition, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps in any of the method embodiments described above.
The embodiments of the present application provide a computer program product, which when running on an electronic device, enables the electronic device to implement the steps in the above method embodiments when executed.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (8)
1. A water body identification method is characterized by comprising the following steps:
acquiring a target image data set of a target geographic area and first vector data containing a water body mask, wherein each scene of a remote sensing image of the target image data set has a spatial intersection with the first vector data;
determining a normalized difference water body index NDWI image data set and a near infrared band NIR image data set according to the target image data set;
performing spatial superposition on the remote sensing image and the first vector data aiming at each scene of the target image data set, and determining second vector data and third vector data in the first vector data, wherein the second vector data are vector data of a water body mask corresponding to the whole area of the remote sensing image containing a water body, and the third vector data are vector data of a water body mask corresponding to a part of area of the remote sensing image containing a water body;
according to the second vector data and the third vector data, identifying water body data of the NDWI image data set and the NIR image data set to obtain water body data of the target geographic area;
and performing spatial superposition on the remote sensing image and the first vector data aiming at each scene of the remote sensing image in the target image data set, and determining second vector data and third vector data in the first vector data, wherein the steps comprise:
performing spatial superposition on each remote sensing image and the first vector data to obtain a water mask area of a target water mask of the first vector data, which corresponds to the remote sensing image;
determining whether the ground object type of the remote sensing image is a single ground object or not according to the near-infrared band standard deviation of all pixels in the water mask area;
if the ground object type of the remote sensing image is a single ground object, determining first vector data containing a target water body mask meeting a first preset condition as second vector data;
if the ground object type of the remote sensing image is not a single ground object, determining first vector data containing a target water body mask meeting a second preset condition as third vector data;
and if the ground feature type of the remote sensing image is a single ground feature, determining first vector data containing a target water body mask meeting a first preset condition as second vector data, wherein the method comprises the following steps:
if the ground object type of the remote sensing image is a single ground object, calculating a near-infrared band mean value, a target ratio and a first lightness mean value of all pixels in the water mask area, wherein the target ratio is a ratio between a near-infrared band total value and all band total values;
if the near-infrared band mean value is greater than a first threshold value, the target ratio is greater than a second threshold value, and the first lightness mean value is greater than a third threshold value, the target water body mask meets the first preset condition, and the first vector data containing the target water body mask is second vector data;
and if the ground object type of the remote sensing image is not a single ground object, determining first vector data containing a target water body mask meeting a second preset condition as third vector data, wherein the third vector data comprises the following steps:
if the ground object type of the remote sensing image is not a single ground object, calculating a target proportion and a second lightness mean value of all pixels in the water body mask area, wherein the target proportion is a proportion that near infrared band values of all pixels in the water body mask area are lower than a preset water body threshold value;
if the target proportion is greater than a fourth threshold and the second lightness average value is greater than a fifth threshold, the target water body mask meets the second preset condition, and the first vector data containing the target water body mask is third vector data.
2. The water body identification method according to claim 1, wherein the acquiring a target image data set of a target geographical area and a first vector data containing a water body mask comprises:
acquiring an original image data set of the target geographic area and first vector data containing a water body mask;
performing orthorectification and image fusion on the original image data set to obtain a multispectral image data set;
and performing spatial superposition on the multispectral image data and the first vector data, and determining the target image data set with a spatial intersection with the first vector data in the multispectral image data.
3. The method of claim 1, wherein identifying water data of the NDWI image data set and the NIR image data set from the second vector data and the third vector data to obtain water data of the target geographic region comprises:
spatially superposing the second vector data and the NDWI image data set, and determining first water body data of a first water body mask area corresponding to a water body mask of the second vector data on a remote sensing image;
and according to the third vector data and the NIR image data set collected by the NDWI image data, determining second water body data of a second water body mask area corresponding to a water body mask of the third vector data on a remote sensing image, wherein the water body data of the target geographic area comprise the first water body data and the second water body data.
4. The method for identifying water body according to claim 3, wherein the spatially superimposing the second vector data with the NDWI image data set to determine the first water body data of the first water body mask region corresponding to the water body mask of the second vector data on the remote sensing image comprises:
for each NDWI image in the NDWI image data set, spatially superposing the NDWI image and the second vector data to obtain a first water mask area corresponding to a water mask of the second vector data on the NDWI image;
determining centroid pixels of the first water mask region;
determining NDWI values corresponding to four-neighborhood pixels of the centroid pixel;
and if the NDWI value is larger than a preset value, the first water body mask area is a water body, and the first water body data are obtained.
5. The method of claim 4, wherein determining second water body data of a second water body mask region corresponding to the water body mask of the third vector data on the remote sensing image according to the third vector data, the NDWI image data and the NIR image data set comprises:
spatially superposing third vector data with an NDWI image in the NDWI image data set and an NIR image in the NIR image data set respectively to obtain a third water body mask area corresponding to a water body mask of the third vector data on the NDWI image and a fourth water body mask area corresponding to the water body mask of the third vector data on the NIR image, wherein the second water body mask area comprises the third water body mask area and the fourth water body mask area;
carrying out Otsu segmentation on the third water body mask area and the fourth water body mask area to obtain a first target value corresponding to the third water body mask area and a second target value corresponding to the fourth water body mask area;
and if the NDWI value of the target area on the remote sensing image is larger than the first target value and the near-infrared value of the remote sensing image is smaller than the second target value, the target area is a water body, and second water body data of the remote sensing image are obtained.
6. A water body identification device, comprising:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a target image data set of a target geographic area and first vector data containing a water body mask, and each remote sensing image of the target image data set and the first vector data have a spatial intersection;
the first determination module is used for determining a normalized difference water body index (NDWI) image data set and a near infrared band (NIR) image data set according to the target image data set;
a second determining module, configured to perform spatial superposition on the remote-sensing image and the first vector data for each remote-sensing image in the target image data set, and determine second vector data and third vector data in the first vector data, where the second vector data is vector data in which all regions of the water body mask corresponding to the remote-sensing image contain a water body, and the third vector data is vector data in which a part of regions of the water body mask corresponding to the remote-sensing image contain a water body;
the identification module is used for identifying the water body data of the NDWI image data set and the NIR image data set according to the second vector data and the third vector data to obtain the water body data of the target geographic area;
and the second determining module comprises:
the superposition unit is used for carrying out spatial superposition on each scene of the remote sensing image and the first vector data to obtain a water body mask area, corresponding to a target water body mask of the first vector data, on the remote sensing image;
the second determination unit is used for determining whether the ground object type of the remote sensing image is a single ground object or not according to the near-infrared band standard deviation of all pixels in the water body mask area;
a third determining unit, configured to determine, as second vector data, first vector data including a target water mask meeting a first preset condition if the feature type of the remote sensing image is a single feature;
a fourth determining unit, configured to determine, if the feature type of the remote sensing image is not a single feature, first vector data including a target water mask meeting a second preset condition as third vector data;
and, the third determination unit includes:
the first calculating subunit is used for calculating a near-infrared band mean value, a target ratio and a first brightness mean value of all pixels in the water mask area if the ground object type of the remote sensing image is a single ground object, wherein the target ratio is a ratio between a near-infrared band total value and all band total values;
a first determining subunit, configured to determine that the target water body mask meets the first preset condition if the near-infrared band mean value is greater than a first threshold, the target ratio is greater than a second threshold, and the first brightness mean value is greater than a third threshold, where the first vector data including the target water body mask is second vector data;
and the fourth determination unit includes:
the second calculating subunit is used for calculating a target proportion and a second lightness average value of all pixels in the water body mask area if the ground object type of the remote sensing image is not a single ground object, wherein the target proportion is a proportion that near infrared band values of all pixels in the water body mask area are lower than a preset water body threshold value;
and the second judging subunit is configured to, if the target proportion is greater than a fourth threshold and the second lightness average value is greater than a fifth threshold, determine that the target water body mask meets the second preset condition, and determine that the first vector data including the target water body mask is third vector data.
7. An electronic device, comprising a memory for storing a computer program and a processor for executing the computer program to cause the electronic device to perform the water body identification method according to any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the water body identification method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110878395.5A CN113343945B (en) | 2021-08-02 | 2021-08-02 | Water body identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110878395.5A CN113343945B (en) | 2021-08-02 | 2021-08-02 | Water body identification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113343945A CN113343945A (en) | 2021-09-03 |
| CN113343945B true CN113343945B (en) | 2021-12-31 |
Family
ID=77480512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110878395.5A Active CN113343945B (en) | 2021-08-02 | 2021-08-02 | Water body identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113343945B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822255B (en) * | 2021-11-24 | 2022-03-01 | 腾讯科技（深圳）有限公司 | Water body identification method and related device |
| CN114724048B (en) * | 2022-04-11 | 2023-07-07 | 中国农业大学 | Identification method and device for high-temperature abnormal region and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108288059A (en) * | 2017-12-29 | 2018-07-17 | 中国电子科技集团公司第二十七研究所 | A kind of building waste monitoring method based on high-definition remote sensing technology |
| CN109784251A (en) * | 2019-01-04 | 2019-05-21 | 中国铁路总公司 | Small water remote sensing recognition method along high-speed rail |
| CN110703244A (en) * | 2019-09-05 | 2020-01-17 | 中国科学院遥感与数字地球研究所 | Method and device for identifying urban water body based on remote sensing data |
| CN111931696A (en) * | 2020-09-04 | 2020-11-13 | 中国水利水电科学研究院 | Lake and reservoir water area remote sensing automatic extraction method based on space constraint |
| CN112164083A (en) * | 2020-10-13 | 2021-01-01 | 上海商汤智能科技有限公司 | Water body segmentation method and device, electronic equipment and storage medium |
| CN113177964A (en) * | 2021-05-25 | 2021-07-27 | 北京大学 | Method and device for extracting optical remote sensing image large-range surface water |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140119639A1 (en) * | 2012-10-31 | 2014-05-01 | Microsoft Corporation | Water-body classification |
-
2021
- 2021-08-02 CN CN202110878395.5A patent/CN113343945B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108288059A (en) * | 2017-12-29 | 2018-07-17 | 中国电子科技集团公司第二十七研究所 | A kind of building waste monitoring method based on high-definition remote sensing technology |
| CN109784251A (en) * | 2019-01-04 | 2019-05-21 | 中国铁路总公司 | Small water remote sensing recognition method along high-speed rail |
| CN110703244A (en) * | 2019-09-05 | 2020-01-17 | 中国科学院遥感与数字地球研究所 | Method and device for identifying urban water body based on remote sensing data |
| CN111931696A (en) * | 2020-09-04 | 2020-11-13 | 中国水利水电科学研究院 | Lake and reservoir water area remote sensing automatic extraction method based on space constraint |
| CN112164083A (en) * | 2020-10-13 | 2021-01-01 | 上海商汤智能科技有限公司 | Water body segmentation method and device, electronic equipment and storage medium |
| CN113177964A (en) * | 2021-05-25 | 2021-07-27 | 北京大学 | Method and device for extracting optical remote sensing image large-range surface water |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113343945A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khandelwal et al. | An approach for global monitoring of surface water extent variations in reservoirs using MODIS data | |
| Lin et al. | Effects of atmospheric correction and pansharpening on LULC classification accuracy using WorldView-2 imagery | |
| Estoque et al. | Classification and change detection of built-up lands from Landsat-7 ETM+ and Landsat-8 OLI/TIRS imageries: A comparative assessment of various spectral indices | |
| Movia et al. | Shadow detection and removal in RGB VHR images for land use unsupervised classification | |
| CN106447721B (en) | Image shadow detection method and device | |
| CN110781756A (en) | Urban road extraction method and device based on remote sensing image | |
| CN111931709B (en) | Water body extraction method and device for remote sensing image, electronic equipment and storage medium | |
| CN113343945B (en) | Water body identification method and device, electronic equipment and storage medium | |
| Aytekın et al. | Unsupervised building detection in complex urban environments from multispectral satellite imagery | |
| Im et al. | An automated binary change detection model using a calibration approach | |
| Lal et al. | Semi-supervised change detection approach combining sparse fusion and constrained k means for multi-temporal remote sensing images | |
| CN110781911A (en) | Image matching method, device, equipment and storage medium | |
| CN114563378B (en) | Method, device, medium and equipment for quantitatively describing space distribution of cyanobacterial bloom in lakes and reservoirs | |
| Kotkar et al. | Analysis of various change detection techniques using satellite images | |
| JP6958743B2 (en) | Image processing device, image processing method and image processing program | |
| Rokni et al. | A new approach for detection of surface water changes based on principal component analysis of multitemporal normalized difference water index | |
| CN113284066B (en) | Automatic cloud detection method and device for remote sensing image | |
| JP6509887B2 (en) | Image change detection | |
| CN109523570B (en) | Motion parameter calculation method and device | |
| Dong et al. | A cloud detection method for GaoFen-6 wide field of view imagery based on the spectrum and variance of superpixels | |
| Koc-San et al. | A model-based approach for automatic building database updating from high-resolution space imagery | |
| CN116543325A (en) | Unmanned aerial vehicle image-based crop artificial intelligent automatic identification method and system | |
| Kok et al. | Principles of full autonomy in image interpretation. The basic architectural design for a sequential process with image objects | |
| Butenko et al. | Geospatial data processing characteristics for environmental monitoring tasks | |
| CN110689549B (en) | Object extraction method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Liu Xiang Inventor after: Wang Yuxiang Inventor after: Fan Lei Inventor after: Shen Xin Inventor after: Qu Yangxu Inventor after: Guan Yuanxiu Inventor after: Sun Na Inventor after: Huang Beibei Inventor before: Qu Yangxu Inventor before: Wang Yuxiang Inventor before: Guan Yuanxiu Inventor before: Tian Jingguo Inventor before: Rong Jun Inventor before: Fan Lei Inventor before: Huang Fei Inventor before: Du Ye |