CN117036222B - Water body detection method, device and medium for fusing multi-scale polarized SAR images - Google Patents
Water body detection method, device and medium for fusing multi-scale polarized SAR images Download PDFInfo
- Publication number
- CN117036222B CN117036222B CN202311051666.5A CN202311051666A CN117036222B CN 117036222 B CN117036222 B CN 117036222B CN 202311051666 A CN202311051666 A CN 202311051666A CN 117036222 B CN117036222 B CN 117036222B
- Authority
- CN
- China
- Prior art keywords
- water body
- image
- scale
- polarized
- polarized sar
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 285
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 28
- 230000009467 reduction Effects 0.000 claims abstract description 26
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 238000003709 image segmentation Methods 0.000 claims abstract description 22
- 238000002922 simulated annealing Methods 0.000 claims abstract description 19
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 239000003550 marker Substances 0.000 claims description 37
- 238000012937 correction Methods 0.000 claims description 35
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 241001270131 Agaricus moelleri Species 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 4
- 238000012549 training Methods 0.000 abstract description 3
- 238000003672 processing method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000035772 mutation Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 210000000746 body region Anatomy 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000000137 annealing Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application discloses a water body detection method, a device and a medium for fusing multiscale polarized SAR images, wherein the method comprises the steps of obtaining a plurality of polarized SAR images of the same SAR image data, obtaining a water body mark image corresponding to each polarized SAR image through multiscale image segmentation operation and image multiscale fusion operation, carrying out image noise reduction processing by adopting a Markov random field and a simulated annealing noise reduction strategy, obtaining a plurality of single polarized water body extraction results, and obtaining a multi-polarized water body detection result according to the plurality of single polarized water body extraction results. The method can quickly identify the water body information in the SAR image in a large area without a complex model training process, is suitable for extracting the water body information in a complex environment, overcomes the noise interference problem through hydrologic constraint and elevation constraint, and utilizes a Markov random field and a simulated annealing strategy to make the image noise reduction achieve global optimum. The SAR image processing method and device are widely applied to the technical field of SAR image processing.
Description
Technical Field
The application relates to the technical field of SAR image processing, in particular to a water body detection method, device and medium for fusing multiscale polarized SAR images.
Background
Flood is one of the most serious natural disasters worldwide, has the characteristics of high occurrence speed, wide influence range, extreme weather and the like, and the traditional optical sensor has weak penetrating capacity in the visible light wave band, is easily influenced by climatic conditions and is easy to generate detection blind areas.
At present, a SAR technology is generally adopted to detect flood information, but in complex environments such as vegetation, urban areas and the like, the flood detection by using the SAR technology still needs to be further improved, on one hand, because local radar signals can be quite complex and difficult to predict, mirror scattering can be generated on smooth ground surfaces, and rough water surfaces can be caused by extreme weather such as strong rainfall, strong wind and the like, so that the backscattering contrast of water bodies and non-water bodies is reduced, and the classification precision is influenced. On the other hand, due to the influence of a ground slope blind area and radar back scattering mutation, noise pattern spots similar to water body characteristics easily appear on an image, and a large number of false detection of water body detection results are caused.
Disclosure of Invention
In order to solve at least one technical problem in the related art, the embodiment of the application provides a water body detection method, a device and a medium for fusing multiscale polarized SAR images.
The first aspect of the embodiment of the application provides a water body detection method for fusing multiscale polarized SAR images, which comprises the following steps:
acquiring a plurality of polarized SAR images of the same SAR image data;
Performing multi-scale image segmentation operation on each polarized SAR image to obtain a plurality of first-scale image blocks and a plurality of second-scale image blocks, and determining a plurality of first-scale pixel gray histograms and a plurality of second-scale pixel gray histograms; the first-scale pixel gray level histogram is a pixel gray level histogram of the first-scale image block; the second-scale pixel gray level histogram is the pixel gray level histogram of the second-scale image block;
determining a first-scale water body part and a second-scale water body part according to the first-scale pixel gray level histogram and the second-scale pixel gray level histogram; the first scale water body part is a water body area contained in the first scale image block; the second-scale water body part is a water body area contained in the second-scale image block;
Constructing an image block father-son relationship between the first-scale image block and the second-scale image block according to the spatial relationship of the image blocks;
performing image multi-scale fusion operation according to the image block father-son relationship, the first-scale water body part and the second-scale water body part to obtain a water body mark image corresponding to each polarized SAR image;
Performing grid pattern run-length coding on the water body mark images, and obtaining water body pattern spot mark images corresponding to each polarized SAR image through hydrologic constraint and high Cheng Yaoshu;
carrying out image noise reduction processing on the water body image spot marked image by adopting a Markov random field and a simulated annealing noise reduction strategy to obtain a single polarized water body extraction result corresponding to each polarized SAR image;
and determining a multi-polarization water body detection result according to the single-polarization water body extraction results.
In some embodiments, the method further comprises:
And generating a water body detection image according to the multi-polarization water body detection result and the SAR image data.
In some embodiments, the step of acquiring a plurality of polarized SAR images of the same SAR image data specifically includes:
SAR image data are obtained;
Preprocessing and decibeling are carried out on the SAR image data to obtain a plurality of polarized SAR images; the preprocessing includes focusing processing, multiview processing, filtering processing, geocoding processing, and radiation correction processing.
In some embodiments, the step of performing a multi-scale image segmentation operation to obtain a plurality of first-scale image blocks and a plurality of second-scale image blocks and determining a plurality of first-scale pixel gray histograms and a plurality of second-scale pixel gray histograms for each of the polarized SAR images specifically includes:
acquiring a first scale image segmentation size and a second scale image segmentation size;
Dividing the polarized SAR image according to the first scale image dividing size to obtain a plurality of first scale image blocks;
dividing the polarized SAR image according to the dividing size of the second scale image to obtain a plurality of second scale image blocks;
Counting pixel gray scales rectangularities for each first-scale image block to obtain a first-scale pixel gray scale histogram;
and counting the pixel gray level rectangularities for each second-scale image block to obtain the second-scale pixel gray level histogram.
In some embodiments, the step of performing raster pattern run-length encoding on the water body marker image to obtain a water body map spot marker image corresponding to each polarized SAR image through hydrologic constraint and high Cheng Yaoshu specifically includes:
Performing grid pattern run-length coding on the water body marker image to determine a plurality of predetermined water body map spots and a plurality of land map spots;
Correcting the predetermined water body map spots and the land map spots through a digital elevation model to obtain a plurality of water body correction map spots;
Calculating the average gradient of each water body correction map spot by adopting a finite difference method;
Judging whether the water body correction pattern spots are water body pattern spots or not according to a preset gradient threshold value and the average gradient of the water body correction pattern spots;
and marking the water body image spots of each polarized SAR image to obtain the water body image spot marking image.
In some embodiments, the step of calculating the average gradient of each of the water body correction patches by using a finite difference method is specifically represented by the following formula:
formula 1:
formula 2:
Formula 3:
wherein G represents the average gradient of the water body correction pattern spot, dx represents the x-axis gradient of the water body correction pattern spot, dy represents the y-axis gradient of the water body correction pattern spot, and f (i, j) represents the elevation value of the pixel coordinate (i, j) on the digital elevation model.
In some embodiments, the step of performing image denoising processing on the water body map spot marker image by using a markov random field and a simulated annealing denoising strategy to obtain a single polarized water body extraction result corresponding to each polarized SAR image specifically includes:
constructing a second-order field energy field of the water body image spot marking image through a Markov random field, and calculating initial energy of the water body image spot marking image;
and performing minimization treatment on the initial energy through a simulated annealing noise reduction strategy and an iteration condition mode strategy to obtain the single-polarized water body extraction result.
In some embodiments, the step of constructing the second-order field energy field of the water body map spot marker image through a markov random field and calculating the initial energy of the water body map spot marker image is specifically represented by the following formula:
Where E is the initial energy of the water body pattern spot marker image, and represents the local energy of the energy group { x i,yi,xj }, h, β, η represents the non-negative weight, x i is the pixel in the water body pattern spot marker image, x j is the second-order neighborhood pixel of x i, and y i is the pixel in the noise map corresponding to x i.
A second aspect of an embodiment of the present application provides a water body detection device fusing multiscale polarized SAR images, including:
A first module for acquiring a plurality of polarized SAR images of the same SAR image data;
The second module is used for executing multi-scale image segmentation operation for each polarized SAR image to obtain a plurality of first-scale image blocks and a plurality of second-scale image blocks, and determining a plurality of first-scale pixel gray histograms and a plurality of second-scale pixel gray histograms; the first-scale pixel gray level histogram is a pixel gray level histogram of the first-scale image block; the second-scale pixel gray level histogram is the pixel gray level histogram of the second-scale image block;
A third module for determining a first scale water body portion and a second scale water body portion according to the first scale pixel gray level histogram and the second scale pixel gray level histogram; the first scale water body part is a water body area contained in the first scale image block; the second scale water body part is a water body area contained in the second image block;
A fourth module, configured to construct an image block parent-child relationship between the first-scale image block and the second-scale image block according to a spatial relationship of the image blocks;
A fifth module, configured to perform an image multi-scale fusion operation according to the image block father-son relationship, the first-scale water body portion, and the second-scale water body portion, and obtain a water body marker image corresponding to each polarized SAR image;
A sixth module, configured to perform raster graphics run-length encoding on the water body marker images, and obtain a water body map spot marker image corresponding to each polarized SAR image through hydrologic constraint and altitude Cheng Yaoshu;
A seventh module, configured to perform image noise reduction processing on the water body map spot marker image by using a markov random field and a simulated annealing noise reduction strategy, to obtain a single polarized water body extraction result corresponding to each polarized SAR image;
And an eighth module, configured to determine a multi-polarized water body detection result according to the multiple single-polarized water body extraction results.
A third aspect of an embodiment of the present application proposes a computer readable storage medium comprising a computer program which, when executed by a processor, implements the method for water detection of fusion of multiscale polarized SAR images described in the first aspect above.
The application provides a water body detection method, a device and a medium for fusing multiscale polarized SAR images, which are characterized in that a plurality of polarized SAR images of the same SAR image data are obtained, a water body mark image corresponding to each polarized SAR image is obtained through multiscale image segmentation operation and image multiscale fusion operation, a Markov random field and a simulated annealing noise reduction strategy are adopted to carry out image noise reduction treatment, a plurality of single polarized water body extraction results are obtained, and a multi-polarized water body detection result is obtained according to the plurality of single polarized water body extraction results. The method is free from complex model training process and large amount of manual participation, is simple and efficient, can quickly identify water body information in SAR images in a large area, is suitable for extracting the water body information in complex environments, reduces noise interference caused by slope blind areas and backward scattering mutation through hydrologic constraint and elevation constraint, overcomes the problem of noise interference, and utilizes a Markov random field and a simulated annealing strategy to enable the image noise reduction to achieve global optimum.
Drawings
FIG. 1 is a flow chart of a water body detection method for fusing multiscale polarized SAR images provided by an embodiment of the application;
Fig. 2 is a schematic diagram of an image processing effect of a water body detection method for fusing multi-scale polarized SAR images according to an embodiment of the present application;
Fig. 3 is a schematic structural diagram of a water body detection device fusing multiscale polarized SAR images according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
It should be noted that although functional block division is performed in a device diagram and a logic sequence is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the block division in the device, or in the flowchart. The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.
Referring to fig. 1, fig. 1 is an optional flowchart of a method for detecting a water body fusing multiscale polarized SAR images according to an embodiment of the present application, including, but not limited to, steps S101 to S108:
step S101, acquiring a plurality of polarized SAR images of the same SAR image data;
Step S102, for each polarized SAR image, performing multi-scale image segmentation operation to obtain a plurality of first-scale image blocks and a plurality of second-scale image blocks, and determining a plurality of first-scale pixel gray histograms and a plurality of second-scale pixel gray histograms;
Step S103, determining a first-scale water body part and a second-scale water body part according to the first-scale pixel gray level histogram and the second-scale pixel gray level histogram;
step S104, constructing an image block father-son relationship between the first-scale image block and the second-scale image block according to the spatial relationship of the image blocks;
Step S105, performing image multi-scale fusion operation according to the father-son relationship of the image blocks, the first-scale water body part and the second-scale water body part to obtain a water body mark image corresponding to each polarized SAR image;
Step S106, performing grid pattern run-length coding on the water body mark images, and obtaining water body pattern spot mark images corresponding to each polarized SAR image through hydrologic constraint and high Cheng Yaoshu;
Step S107, performing image noise reduction processing on the water body image spot marked image by adopting a Markov random field and a simulated annealing noise reduction strategy to obtain a single polarized water body extraction result corresponding to each polarized SAR image;
step S108, determining a multi-polarization water body detection result according to the plurality of single-polarization water body extraction results.
In some embodiments, the method further comprises step S109:
Step S109, generating a water body detection image according to the multi-polarization water body detection result and SAR image data.
In step S101 of some embodiments, SAR image data of a region to be detected is acquired, preprocessing is performed on the SAR image data by using software ENVI, the preprocessing includes focusing processing, multi-view processing, filtering processing, geocoding processing and radiation correction processing, in the preprocessing operation, the filtering adopts REFIND LEE filtering algorithm to process the image, the window size is set to be 5×5, and the rest of the preprocessing operations adopt default parameters of SARscape. And performing decibel treatment on the preprocessed SAR image data to obtain a plurality of polarized SAR images of the SAR image data under a plurality of polarized channels.
In step S102 of some embodiments, the first-scale pixel gray-scale histogram is the pixel gray-scale histogram of the first-scale image block; the second scale pixel gray level histogram is the pixel gray level histogram of the second scale image block.
In some embodiments, step S102 may include, but is not limited to including, step S201 to step S205:
step S201, obtaining a first scale image segmentation size and a second scale image segmentation size;
Step S202, dividing a polarized SAR image according to the dividing size of the first scale image to obtain a plurality of first scale image blocks;
Step S203, dividing the polarized SAR image according to the dividing size of the second scale image to obtain a plurality of second scale image blocks;
Step S204, counting pixel gray scales rectangularities for each first-scale image block to obtain a first-scale pixel gray scale histogram;
step S205, for each second scale image block, counting the pixel gray scales rectangularities, and obtaining a second scale pixel gray scale histogram.
In steps S201 to S203 of some embodiments, optionally, the first-scale image segmentation size is 500×500, the second-scale image segmentation size is 1000×1000, each polarized SAR image is subjected to image segmentation processing according to two sets of image segmentation sizes, a portion where an image pixel is insufficient is filled with a null value, each polarized SAR image is divided into two sets of image blocks with different scales, the first set of image blocks includes a plurality of the first-scale image blocks, and the second set of image blocks includes a plurality of the second-scale image blocks.
In step S103 of some embodiments, the first scale water body portion is a water body region contained in the first scale image block; the second scale water body part is a water body area contained in the second scale image block.
Because radar waves are subjected to mirror scattering on the surface of the water body and have a low backscattering coefficient, normal fitting is carried out on the pixel gray level histogram of each image block, the area (a first-scale water body part and a second-scale water body part) of the water body in the image block is determined, if only one wave crest exists, the radar waves only contain one ground object type of the water body or the non-water body, and the radar waves are classified into the water body or the non-water body according to the pixel value of the wave crest of the histogram; if two wave peaks exist, the condition that two ground object types including a water body and a non-water body are included is described, an image block is divided into two types of the water body and the non-water body by using a KI threshold method, and a KI threshold judgment criterion function under Gaussian distribution is specifically expressed by the following formula:
J(T)＝1+2[Pw(T)lnσw(T)+Pn(T)lnσn(T)]+2H(Ω,T)
H(Ω,T)＝-[Pw(T)lnPw(T)+Pn(T)lnPn(T)]
Wherein J (T) is a criterion function of KI threshold segmentation, which is used for describing the correct classification performance when the threshold is T, H (Ω, T) represents entropy of class set Ω epsilon { w, n }, w represents water body, n represents non-water body, P w (T) and P n (T) are prior probabilities of water body and non-water body when the threshold is T, sigma w (T) and sigma n (T) are standard deviations of water body and non-water body, the optimal segmentation effect is obtained when J (T) reaches the minimum value by changing the threshold T and counting the size of J (T), and all pixel values smaller than T in the pixel gray level histogram of the image block are classified in the water body.
In step S104 of some embodiments, a parent-child relationship of image blocks under two sets of image scales is constructed according to the spatial relationship of the image blocks, where each child image block (first scale image block) corresponds to only a unique parent image block (second scale image block).
In step S105 of some embodiments, two sets of image blocks (a first-scale image block and a second-scale image block) are spatially superimposed according to a parent-child relationship of the image blocks, and water body portions in the image blocks with different scales (image segmentation sizes) are fused in a union manner, so that the water body marker images are obtained after fusion, and the water body portions and non-water body portions are respectively marked in the water body marker images, so that the probability of missed detection due to too small area of the water body region under a large scale is greatly reduced.
In some embodiments, step S106 may include, but is not limited to including, step S301 to step S305:
step S301, performing grid pattern run-length coding on the water body marker image, and determining a plurality of predetermined water body map spots and a plurality of land map spots;
step S302, correcting a predetermined water body map spot and a land map spot through a digital elevation model to obtain a plurality of water body correction map spots;
step S303, calculating the average gradient of each water body correction map spot by adopting a finite difference method;
step S304, judging whether the water body correction pattern spots are water body pattern spots or not according to a preset gradient threshold value and the average gradient of the water body correction pattern spots;
and step S305, marking the water body image spots of each polarized SAR image to obtain a water body image spot marking image.
In step S301 of some embodiments, a map spot is determined on the water body marker image by using the grid pattern run-length encoding, and according to the connectivity of the space, each land surrounded by the water body on the water body marker image is marked as a land map spot, and each water body surrounded by the land is marked as a predetermined water body map spot, so as to obtain a plurality of predetermined water body map spots.
In step S302 of some embodiments, DEM (digital elevation model) data is introduced, and the images of the predetermined water map spots and the land map spots determined in step S301 are superimposed on the digital elevation model, and according to the fluidity of water, the elevation of the water should be lower than the elevation of the surrounding land, so that the land map spots of Gao Chengxiao on the surrounding water are corrected to be water map spots, the predetermined water map spots of Gao Chengda on the surrounding land are corrected to be land map spots, and false detection caused by radar back scattering mutation can be effectively reduced, thereby realizing hydrologic restriction.
In step S303 and step S304 of some embodiments, the average gradient of each water body correction map spot is calculated by using a finite difference method to perform secondary determination, a gradient threshold is set, the theoretical water surface elevation gradient should approach 0, a certain tolerance is preset according to the DEM resolution in consideration of the existence of resolution errors, if the average gradient of the water body correction map spot is greater than the gradient threshold, the false detection caused by the slope blind area is illustrated, the water body correction map spot is modified into a land map spot, and if the average gradient of the water body correction map spot is less than the gradient threshold, the water body correction map spot is determined to be the water body map spot, thereby realizing the height Cheng Yaoshu.
The formula for calculating the water body correction pattern spots by adopting a finite difference method is specifically represented by the following formula:
formula 1:
formula 2:
Formula 3:
wherein G represents the average gradient of the water body correction pattern spot, dx represents the x-axis gradient of the water body correction pattern spot, dy represents the y-axis gradient of the water body correction pattern spot, and f (i, j) represents the elevation value of the pixel coordinate (i, j) on the digital elevation model.
In step S305 of some embodiments, after determining a corresponding water pattern spot in the polarized SAR image, the water pattern spot is marked, and a water pattern spot marking image is obtained.
In some embodiments, step S107 may include, but is not limited to including, step S401 to step S402:
step S401, constructing a second-order neighborhood energy field of the water body image spot marking image through a Markov random field, and calculating initial energy of the water body image spot marking image;
Step S402, performing minimization treatment on initial energy by simulating an annealing noise reduction strategy and an iteration condition mode strategy to obtain a water body extraction result.
In steps S401 to S402 of some embodiments, a second-order neighborhood energy field of an image is constructed by using a markov random field, initial energy of a whole image is calculated, and energy minimization is realized by using an ICM (iterative condition mode) strategy and a simulated annealing noise reduction strategy, so that a noise reduction effect is globally optimal, and a polarized SAR image corresponding to each polarized channel is obtained.
In step S401 of some embodiments, a second-order domain energy field of the water body map spot marker image is constructed through a markov random field, and initial energy of the water body map spot marker image is calculated, specifically expressed by the following formula:
Where E is the initial energy of the water body pattern spot marker image, and represents the local energy of the energy group { x i,yi,xj }, h, β, η represents the non-negative weight, x i is the pixel in the water body pattern spot marker image, x j is the second-order neighborhood pixel of x i, and y i is the pixel in the noise map corresponding to x i.
In step S402 of some embodiments, the ICM strategy calculates local energy variations of the waterbody patch marker image by changing the current pixel and fixing other pixels. In simulated annealing, a local acceptable probability q is calculated according to the current temperature t and local energy change, and the calculation formula is as follows:
Wherein exp (x) represents an exponential function with a natural constant E as a base, and is equivalent to E *,E(xnew) and E (x k) respectively represent local energy before and after the current pixel of the water body map spot marked image changes, the temperature t controls the whole algorithm flow, and along with the progress of iterative calculation, the temperature t finally approaches 0, and the calculation formula is as follows:
where s is a constant, the temperature drop rate is controlled, and k and kmax are the current iteration number and the maximum iteration number. According to the Metropolis criterion, it is probabilistic to determine whether to keep a new state, as follows:
Where q represents the above-mentioned locally acceptable probability, x k represents the current pixel value of the image in the kth iteration, x new represents the new value after the current pixel of the image is changed, x k+1 represents the current pixel value entering k+1 iterations after the kth iteration is completed, and ζ is a random number uniformly distributed over the [0, 1] interval. When q is greater than ζ or q is greater than or equal to 1, then the current pixel change is accepted, and vice versa.
In step S108 of some embodiments, the multiple unipolar water body extraction results are combined in an intersection manner, that is, if and only if a pixel is a water body under different polarization channels (all the unipolar water body extraction results show that the pixel is a water body portion), the pixel is finally marked as a water body, so as to determine a multi-polarization water body detection result, and the water body detection result can be greatly improved by the multi-polarization fusion manner.
Referring to fig. 2, fig. 2 is a schematic diagram showing an optional image processing effect of a water body detection method for fusing multi-scale polarized SAR images according to an embodiment of the present application, wherein, in a first step, different polarized SAR images of the same SAR image data are obtained (step S101); second, preprocessing the image (step S202); third, multi-scale fusion threshold segmentation (step S102 to step S105); fourth, elevation constraints and hydrologic constraints (step S106); fifth, the Markov random field and simulated annealing reduce noise (step S107); sixth, multi-polarization channel fusion (step S108).
Referring to fig. 3, fig. 3 is an optional structural schematic diagram of a water body detection device for fusing multiscale polarized SAR images according to an embodiment of the present application, where the device includes:
A first module for acquiring a plurality of polarized SAR images of the same SAR image data;
the second module is used for executing multi-scale image segmentation operation for each polarized SAR image to obtain a plurality of first-scale image blocks and a plurality of second-scale image blocks, and determining a plurality of first-scale pixel gray histograms and a plurality of second-scale pixel gray histograms; the first-scale pixel gray level histogram is a pixel gray level histogram of the first-scale image block; the second scale pixel gray level histogram is the pixel gray level histogram of the second scale image block;
A third module for determining a first scale water body portion and a second scale water body portion according to the first scale pixel gray histogram and the second scale pixel gray histogram; the first scale water body part is a water body area contained in the first scale image block; the second scale water body part is a water body area contained in the second scale image block;
A fourth module, configured to construct an image block parent-child relationship between the first-scale image block and the second-scale image block according to the spatial relationship of the image blocks;
A fifth module, configured to perform image multi-scale fusion operation according to the image block father-son relationship, the first-scale water body portion, and the second-scale water body portion, and obtain a water body marker image corresponding to each polarized SAR image;
a sixth module, configured to perform raster pattern run-length encoding on the water body marker image, and obtain a water body map spot marker image corresponding to each polarized SAR image through hydrologic constraint and high Cheng Yaoshu;
A seventh module, configured to perform image noise reduction processing on the water body map spot marker image by using a markov random field and a simulated annealing noise reduction strategy, so as to obtain a unipolar water body extraction result corresponding to each polarized SAR image;
and the eighth module is used for determining a multi-polarization water body detection result according to the plurality of single-polarization water body extraction results.
The specific implementation manner of the water body detection device for fusing the multi-scale polarized SAR image is basically the same as the specific embodiment of the water body detection method for fusing the multi-scale polarized SAR image, and is not repeated here.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the water body detection method for fusing the multi-scale polarized SAR images when being executed by a processor.
The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The embodiment of the application provides a water body detection method, a device and a medium for fusing multiscale polarized SAR images, which are characterized in that a plurality of polarized SAR images of the same SAR image data are obtained, a water body mark image corresponding to each polarized SAR image is obtained through multiscale image segmentation operation and image multiscale fusion operation, a Markov random field and a simulated annealing noise reduction strategy are adopted for image noise reduction treatment, a plurality of single polarized water body extraction results are obtained, and a multi-polarized water body detection result is obtained according to the plurality of single polarized water body extraction results. The method is free from complex model training process and large amount of manual participation, is simple and efficient, can quickly identify water body information in SAR images in a large area, is suitable for extracting the water body information in complex environments, reduces noise interference caused by slope blind areas and backward scattering mutation through hydrologic constraint and elevation constraint, overcomes the problem of noise interference, and utilizes a Markov random field and a simulated annealing strategy to enable the image noise reduction to achieve global optimum.
The embodiments described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.
It will be appreciated by persons skilled in the art that the embodiments of the application are not limited by the illustrations, and that more or fewer steps than those shown may be included, or certain steps may be combined, or different steps may be included.
The preferred embodiments of the present application have been described above with reference to the accompanying drawings, and are not thereby limiting the scope of the claims of the embodiments of the present application. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the embodiments of the present application shall fall within the scope of the claims of the embodiments of the present application.
Claims (9)
1. The water body detection method for fusing the multi-scale polarized SAR image is characterized by comprising the following steps of:
acquiring a plurality of polarized SAR images of the same SAR image data;
Performing multi-scale image segmentation operation on each polarized SAR image to obtain a plurality of first-scale image blocks and a plurality of second-scale image blocks, and determining a plurality of first-scale pixel gray histograms and a plurality of second-scale pixel gray histograms; the first-scale pixel gray level histogram is a pixel gray level histogram of the first-scale image block; the second-scale pixel gray level histogram is the pixel gray level histogram of the second-scale image block;
determining a first-scale water body part and a second-scale water body part according to the first-scale pixel gray level histogram and the second-scale pixel gray level histogram; the first scale water body part is a water body area contained in the first scale image block; the second-scale water body part is a water body area contained in the second-scale image block;
Constructing an image block father-son relationship between the first-scale image block and the second-scale image block according to the spatial relationship of the image blocks;
performing image multi-scale fusion operation according to the image block father-son relationship, the first-scale water body part and the second-scale water body part to obtain a water body mark image corresponding to each polarized SAR image;
Performing grid pattern run-length coding on the water body mark images, and obtaining water body pattern spot mark images corresponding to each polarized SAR image through hydrologic constraint and high Cheng Yaoshu;
carrying out image noise reduction processing on the water body image spot marked image by adopting a Markov random field and a simulated annealing noise reduction strategy to obtain a single polarized water body extraction result corresponding to each polarized SAR image;
Determining a multi-polarization water body detection result according to the single-polarization water body extraction results;
The step of performing grid pattern run-length coding on the water body mark images and obtaining the water body pattern spot mark image corresponding to each polarized SAR image through hydrologic constraint and high Cheng Yaoshu specifically comprises the following steps:
Performing grid pattern run-length coding on the water body marker image to determine a plurality of predetermined water body map spots and a plurality of land map spots;
Correcting the predetermined water body map spots and the land map spots through a digital elevation model to obtain a plurality of water body correction map spots;
Calculating the average gradient of each water body correction map spot by adopting a finite difference method;
Judging whether the water body correction pattern spots are water body pattern spots or not according to a preset gradient threshold value and the average gradient of the water body correction pattern spots;
and marking the water body image spots of each polarized SAR image to obtain the water body image spot marking image.
2. The method for water detection fusing multiscale polarized SAR images according to claim 1, further comprising:
And generating a water body detection image according to the multi-polarization water body detection result and the SAR image data.
3. The method for detecting a water body by fusing multiscale polarized SAR images according to claim 1, wherein said step of acquiring a plurality of polarized SAR images of the same SAR image data comprises:
SAR image data are obtained;
Preprocessing and decibeling are carried out on the SAR image data to obtain a plurality of polarized SAR images; the preprocessing includes focusing processing, multiview processing, filtering processing, geocoding processing, and radiation correction processing.
4. The method for detecting a water body by fusing multi-scale polarized SAR images according to claim 1, wherein said step of performing multi-scale image segmentation operation to obtain a plurality of first-scale image blocks and a plurality of second-scale image blocks and determining a plurality of first-scale pixel gray level histograms and a plurality of second-scale pixel gray level histograms for each of said polarized SAR images specifically comprises:
acquiring a first scale image segmentation size and a second scale image segmentation size;
Dividing the polarized SAR image according to the first scale image dividing size to obtain a plurality of first scale image blocks;
dividing the polarized SAR image according to the dividing size of the second scale image to obtain a plurality of second scale image blocks;
Counting pixel gray scales rectangularities for each first-scale image block to obtain a first-scale pixel gray scale histogram;
and counting the pixel gray level rectangularities for each second-scale image block to obtain the second-scale pixel gray level histogram.
5. The method for detecting a water body by fusing multiscale polarized SAR images according to claim 1, wherein said step of calculating the average gradient of each of said water body corrected patches by finite difference method is specifically represented by the following formula:
formula 1:
formula 2:
Formula 3:
wherein G represents the average gradient of the water body correction pattern spot, dx represents the x-axis gradient of the water body correction pattern spot, dy represents the y-axis gradient of the water body correction pattern spot, and f (i, j) represents the elevation value of the pixel coordinate (i, j) on the digital elevation model.
6. The method for detecting water body by fusing multi-scale polarized SAR images according to claim 1, wherein the step of performing image denoising processing on the water body map spot marker images by using a markov random field and a simulated annealing denoising strategy to obtain a single polarized water body extraction result corresponding to each polarized SAR image specifically comprises the steps of:
constructing a second-order field energy field of the water body image spot marking image through a Markov random field, and calculating initial energy of the water body image spot marking image;
and performing minimization treatment on the initial energy through a simulated annealing noise reduction strategy and an iteration condition mode strategy to obtain the single-polarized water body extraction result.
7. The method for detecting water body by fusing multiscale polarized SAR images according to claim 6, wherein said step of constructing a second-order domain energy field of said water body speckle marker image by markov random field and calculating the initial energy of said water body speckle marker image is specifically represented by the following formula:
Where E is the initial energy of the water body pattern spot marker image, and represents the local energy of the energy group { x i,yi,xj }, h, β, η represents the non-negative weight, x i is the pixel in the water body pattern spot marker image, x j is the second-order neighborhood pixel of x i, and y i is the pixel in the noise map corresponding to x i.
8. A water body detection device fusing multiscale polarized SAR images is characterized by comprising:
A first module for acquiring a plurality of polarized SAR images of the same SAR image data;
The second module is used for executing multi-scale image segmentation operation for each polarized SAR image to obtain a plurality of first-scale image blocks and a plurality of second-scale image blocks, and determining a plurality of first-scale pixel gray histograms and a plurality of second-scale pixel gray histograms; the first-scale pixel gray level histogram is a pixel gray level histogram of the first-scale image block; the second-scale pixel gray level histogram is the pixel gray level histogram of the second-scale image block;
A third module for determining a first scale water body portion and a second scale water body portion according to the first scale pixel gray level histogram and the second scale pixel gray level histogram; the first scale water body part is a water body area contained in the first scale image block; the second-scale water body part is a water body area contained in the second-scale image block;
A fourth module, configured to construct an image block parent-child relationship between the first-scale image block and the second-scale image block according to a spatial relationship of the image blocks;
A fifth module, configured to perform an image multi-scale fusion operation according to the image block father-son relationship, the first-scale water body portion, and the second-scale water body portion, and obtain a water body marker image corresponding to each polarized SAR image;
A sixth module, configured to perform raster graphics run-length encoding on the water body marker images, and obtain a water body map spot marker image corresponding to each polarized SAR image through hydrologic constraint and altitude Cheng Yaoshu; the step of performing grid pattern run-length coding on the water body mark images and obtaining the water body pattern spot mark image corresponding to each polarized SAR image through hydrologic constraint and high Cheng Yaoshu specifically comprises the following steps:
Performing grid pattern run-length coding on the water body marker image to determine a plurality of predetermined water body map spots and a plurality of land map spots;
Correcting the predetermined water body map spots and the land map spots through a digital elevation model to obtain a plurality of water body correction map spots;
Calculating the average gradient of each water body correction map spot by adopting a finite difference method;
Judging whether the water body correction pattern spots are water body pattern spots or not according to a preset gradient threshold value and the average gradient of the water body correction pattern spots;
marking the water body image spots of each polarized SAR image to obtain the water body image spot marking image;
A seventh module, configured to perform image noise reduction processing on the water body map spot marker image by using a markov random field and a simulated annealing noise reduction strategy, to obtain a single polarized water body extraction result corresponding to each polarized SAR image;
And an eighth module, configured to determine a multi-polarized water body detection result according to the multiple single-polarized water body extraction results.
9. A computer readable storage medium comprising a computer program, characterized in that the computer program, when executed by a processor, implements the method for water detection of fusion of multiscale polarized SAR images according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311051666.5A CN117036222B (en) | 2023-08-18 | 2023-08-18 | Water body detection method, device and medium for fusing multi-scale polarized SAR images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311051666.5A CN117036222B (en) | 2023-08-18 | 2023-08-18 | Water body detection method, device and medium for fusing multi-scale polarized SAR images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117036222A CN117036222A (en) | 2023-11-10 |
| CN117036222B true CN117036222B (en) | 2024-04-19 |
Family
ID=88635155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311051666.5A Active CN117036222B (en) | 2023-08-18 | 2023-08-18 | Water body detection method, device and medium for fusing multi-scale polarized SAR images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117036222B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103076612A (en) * | 2013-01-07 | 2013-05-01 | 河海大学 | Building surveying and mapping method combining laser radar with aerial photography |
| CN103208121A (en) * | 2013-04-12 | 2013-07-17 | 南京师范大学 | Remote sensing image segmentation method based on hard boundary constraint and two-stage combination |
| CN105046087A (en) * | 2015-08-04 | 2015-11-11 | 中国资源卫星应用中心 | Water body information automatic extraction method for multi-spectral image of remote sensing satellite |
| KR101814023B1 (en) * | 2017-01-09 | 2018-01-03 | 한양대학교 에리카산학협력단 | Apparatus and Method for Automatic Calibration of Finite Difference Grid Data |
| CN109816674A (en) * | 2018-12-27 | 2019-05-28 | 北京航天福道高技术股份有限公司 | Registration figure edge extracting method based on Canny operator |
| CN111931709A (en) * | 2020-09-17 | 2020-11-13 | 航天宏图信息技术股份有限公司 | Water body extraction method and device for remote sensing image, electronic equipment and storage medium |
| CN113484245A (en) * | 2021-07-05 | 2021-10-08 | 重庆市规划和自然资源调查监测院 | Remote sensing rapid monitoring method and system for paddy field planting pattern in hilly and mountainous areas and computer readable storage medium |
| CN113848551A (en) * | 2021-09-24 | 2021-12-28 | 成都理工大学 | Landslide depth inversion method using InSAR lifting rail deformation data |
| WO2022252242A1 (en) * | 2021-06-04 | 2022-12-08 | 江苏南大五维电子科技有限公司 | Multispectral image-based water pollution area identification method and system |
| CN115659733A (en) * | 2022-10-17 | 2023-01-31 | 武汉大学 | Regional scale large-scale water delivery channel leakage characteristic estimation method and device |
| CN116305902A (en) * | 2023-03-09 | 2023-06-23 | 中国水利水电科学研究院 | Flood maximum submerged depth space simulation method based on multi-mode remote sensing |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3844633A4 (en) * | 2018-08-31 | 2022-05-18 | The Climate Corporation | Subfield moisture model improvement using overland flow modeling with shallow water computations |
-
2023
- 2023-08-18 CN CN202311051666.5A patent/CN117036222B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103076612A (en) * | 2013-01-07 | 2013-05-01 | 河海大学 | Building surveying and mapping method combining laser radar with aerial photography |
| CN103208121A (en) * | 2013-04-12 | 2013-07-17 | 南京师范大学 | Remote sensing image segmentation method based on hard boundary constraint and two-stage combination |
| CN105046087A (en) * | 2015-08-04 | 2015-11-11 | 中国资源卫星应用中心 | Water body information automatic extraction method for multi-spectral image of remote sensing satellite |
| KR101814023B1 (en) * | 2017-01-09 | 2018-01-03 | 한양대학교 에리카산학협력단 | Apparatus and Method for Automatic Calibration of Finite Difference Grid Data |
| CN109816674A (en) * | 2018-12-27 | 2019-05-28 | 北京航天福道高技术股份有限公司 | Registration figure edge extracting method based on Canny operator |
| CN111931709A (en) * | 2020-09-17 | 2020-11-13 | 航天宏图信息技术股份有限公司 | Water body extraction method and device for remote sensing image, electronic equipment and storage medium |
| WO2022252242A1 (en) * | 2021-06-04 | 2022-12-08 | 江苏南大五维电子科技有限公司 | Multispectral image-based water pollution area identification method and system |
| CN113484245A (en) * | 2021-07-05 | 2021-10-08 | 重庆市规划和自然资源调查监测院 | Remote sensing rapid monitoring method and system for paddy field planting pattern in hilly and mountainous areas and computer readable storage medium |
| CN113848551A (en) * | 2021-09-24 | 2021-12-28 | 成都理工大学 | Landslide depth inversion method using InSAR lifting rail deformation data |
| CN115659733A (en) * | 2022-10-17 | 2023-01-31 | 武汉大学 | Regional scale large-scale water delivery channel leakage characteristic estimation method and device |
| CN116305902A (en) * | 2023-03-09 | 2023-06-23 | 中国水利水电科学研究院 | Flood maximum submerged depth space simulation method based on multi-mode remote sensing |
Non-Patent Citations (6)
| Title |
|---|
| Extraction and Classification of Flood-Affected Areas Based on MRF and Deep Learning;Jie Wang et al.;water;全文 * |
| Object-Scale Adaptive Convolutional Neural Networks for High-Spatial Resolution Remote Sensing Image Classification;Jie Wang et al.;IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING;全文 * |
| 土结构相互作用体系动力响应的敏感性分析;古泉等;地下空间与工程学报;第11卷(第S1期);全文 * |
| 基于图斑空间关系的遥感专家分类方法研究;蔡晓斌;陈晓玲;王涛;吴忠宜;;武汉大学学报(信息科学版)(04);全文 * |
| 基于数字高程模型的复杂地表红外辐射特性模拟;丁伟利;刘晓民;付双飞;王文锋;;系统仿真学报(12);全文 * |
| 融合梯度与平坦度的城区点云滤波算法;盛志娟;;遥感信息(06);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117036222A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106960436A (en) | A kind of remote sensing image process performance appraisal procedure | |
| CN115564926B (en) | Three-dimensional patch model construction method based on image building structure learning | |
| CN106920235B (en) | Automatic correction method for satellite-borne optical remote sensing image based on vector base map matching | |
| CN102542561B (en) | Active contour synthetic aperture radar (SAR) image segmentation method based on Fisher distribution | |
| CN113569760B (en) | Three-dimensional change detection method based on multi-mode deep learning | |
| CN104197933A (en) | Method for enhancing and extracting star sliding in telescope field of view | |
| CN108764132A (en) | A kind of lake and marshland remote sensing images error detection method | |
| CN113281749A (en) | Time sequence InSAR high-coherence point selection method considering homogeneity | |
| CN104700427B (en) | A kind of road damage information extracting method based on SAR image | |
| CN105205485B (en) | Large scale image partitioning algorithm based on maximum variance algorithm between multiclass class | |
| CN117036222B (en) | Water body detection method, device and medium for fusing multi-scale polarized SAR images | |
| CN117409320A (en) | River basin flood monitoring method, system and storage medium based on satellite remote sensing | |
| CN116879886A (en) | Early warning method for graded communication of micro-change monitoring radar on landslide surface | |
| CN115546658B (en) | Night cloud detection method combining quality improvement and CNN improvement of data set | |
| CN103886289A (en) | Direction self-adaptive method and system for identifying on-water bridge targets | |
| CN113450456B (en) | DEM manufacturing method with high recognition degree | |
| CN116164771A (en) | Mining area road real-time detection method based on semantic map | |
| CN115760701A (en) | Land change detection method and device | |
| CN115661382A (en) | Filtering method based on morphological template angle protection in three-dimensional landform reconstruction | |
| Zhang et al. | A road extraction method based on high resolution remote sensing image | |
| CN111310649A (en) | Method for extracting high-resolution image of unmanned aerial vehicle for melting mountain ice-water movement | |
| CN116503464B (en) | Farmland building height prediction method based on remote sensing image | |
| CN114708514B (en) | Method and device for detecting forest felling change based on deep learning | |
| CN117274584B (en) | Shadow processing method and device for remote sensing image, storage medium and terminal | |
| CN103679725B (en) | Based on the blade area automatic retrieval method of straight-line detection and template matches |
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 |