CN116129145B - Method and system for extracting sandy coastline of high-resolution remote sensing image - Google Patents
Method and system for extracting sandy coastline of high-resolution remote sensing image Download PDFInfo
- Publication number
- CN116129145B CN116129145B CN202310395276.3A CN202310395276A CN116129145B CN 116129145 B CN116129145 B CN 116129145B CN 202310395276 A CN202310395276 A CN 202310395276A CN 116129145 B CN116129145 B CN 116129145B
- Authority
- CN
- China
- Prior art keywords
- image
- ndwi
- sequence
- coastline
- time
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The present disclosure provides a method and a system for extracting a sandy coastline of a high-resolution remote sensing image, which acquire a plurality of remote sensing images at different moments, convert the remote sensing images into NDWI images, form NDWI images into NDWI image sequences, and perform penetration processing on the NDWI image sequences to obtain coastline extraction points, and obtain a corrected coastline according to the coastline extraction points, thereby being beneficial to improving the accuracy of the coastline.
Description
Technical Field
The disclosure belongs to the field of data processing, and particularly relates to a method and a system for extracting a sandy coastline of a high-resolution remote sensing image.
Background
Along with the continuous development and application of the remote sensing technology, the high-resolution remote sensing image is widely applied to the aspect of coastline extraction. The traditional coastline extraction method is mainly carried out by adopting a threshold segmentation or edge detection method, but the traditional method is easy to have a large error due to the influence of factors such as complicated topography of the coastline, illumination and the like. Therefore, many new methods for coastline extraction have emerged in recent years. For example, some scholars have proposed using Convolutional Neural Networks (CNNs) to classify remote sensing images to improve accuracy; still other scholars have proposed deep learning-based methods that use a Full Convolution Network (FCN) to semantically segment remote sensing images and extract coastline therefrom. However, these methods also have some limitations and disadvantages. For example, in the coastline remote sensing extraction method described in the patent document with publication number CN113221813B, due to the complexity and variability of coastline topography, noise and ambiguity of the remote sensing image itself, some errors still exist in practical application of these methods. In addition, some algorithms require a large amount of manual annotation data, which makes it difficult to popularize and popularize in practical applications. At the same time, these algorithms require high performance computing devices for computation, increasing operating and time costs.
Disclosure of Invention
The invention aims to provide a method and a system for extracting a sandy coastline of a high-resolution remote sensing image, which are used for solving one or more technical problems in the prior art and at least providing a beneficial selection or creation condition.
The present disclosure provides a method and a system for extracting a sandy coastline of a high-resolution remote sensing image, which acquire a plurality of remote sensing images at different moments, convert the remote sensing images into NDWI images, form NDWI images into NDWI image sequences, and perform penetration processing on the NDWI image sequences to obtain coastline extraction points, and obtain a corrected coastline according to the coastline extraction points, thereby being beneficial to improving the accuracy of the coastline.
In order to achieve the above object, according to an aspect of the present disclosure, there is provided a method for extracting a sandy coastline of a high-resolution remote sensing image, the method comprising the steps of:
s100, acquiring a plurality of remote sensing images at different moments;
s200, converting the remote sensing image into an NDWI image, and forming the NDWI image into an NDWI image sequence;
s300, carrying out penetration processing on the NDWI image sequence to obtain coastline extraction points;
s400, obtaining the corrected coastline according to the coastline extraction points.
Further, in S100, the time intervals between each of the plurality of different moments are the same, the order of arrangement of each of the plurality of different moments is according to time sequence, each remote sensing image corresponds to each moment, each moment corresponds to only one remote sensing image, and the remote sensing image is a high resolution remote sensing image of the coastline.
Further, in S200, remote sensing images at each moment are respectively converted into NDWI images by calculating a normalized water index (Normalized Difference Water Index), and the obtained NDWI images are sequentially formed into an NDWI image sequence, and pixel values on the NDWI images can be mapped into values belonging to [0,1] through graying and normalization processes, preferably, the closer the pixel value is to black, the closer the pixel value is to white, the closer the pixel value is to 1, the closer the pixel value is to white, the closer the black is to indicate that the water content of the corresponding position on the NDWI image is less, and the closer the pixel value is to white, the more the water content of the corresponding position on the NDWI image is indicated.
Further, in S300, the method for obtaining the coastline extraction point by performing the penetration processing on the NDWI image sequence includes:
the NDWI image sequence is recorded as a sequence NDseq, the number of NDWI images serving as elements in the NDWI image sequence is recorded as t, the sequence number of the elements in the NDWI image sequence is made to be q, q belongs to a 1-t interval, the sequence number of each moment in the plurality of different moments is consistent with the sequence number q, and the element with the q-th sequence number in the NDWI image sequence is ND (q);
each NDWI image in the NDWI image sequence is an image matrix with the size of n rows and m columns, wherein i is a row sequence number and j is a column sequence number in each NDWI image, i is a 1-n interval, j is a 1-m interval, and the numerical value of the j-th column position of the ith row in ND (q) is represented as ND (q) [ i, j ];
the next of the last element in the NDWI image sequence is pointed to the first element, namely the next of the last element ND (t) is pointed to the first element ND (1), so that the operation is that the change of tides is periodically back and forth, the tidal advance and retreat is large for the fuzzy image interference factor of the coastline, the data sequence connected end to end can better reflect the periodic data distribution of the coastline, and the subsequent extraction of the coastline is convenient;
the function TimeGAP (,) represents the time interval that elapses between the time of calculation of the sequence number at the rear in brackets and the time of the sequence number at the front, specifically: the time gap (1, q) represents a time interval that the time of the sequence number q is past from the time of the sequence number 1, the time gap (1, t) represents a time interval that the time of the sequence number t is past from the time of the sequence number 1, the time gap (q-1, q) represents a time interval that the time of the sequence number q is past from the time of the last time of the sequence number q-1, wherein when the q of the time gap (q-1, q) represents the time of the sequence number 1, the time interval that the time of the last time of the sequence number q is the time of the sequence number t, namely, the time interval that the time of the sequence number q is subtracted by the time of the sequence number 1, the time interval takes only absolute value without positive or negative score, for example, the time of the sequence number q is 23:00 of one day, the time of the sequence number 1 is 3:00 of the same day, the time interval that the time of the sequence number q is subtracted by the time of the sequence number 1 is 20 hours, and when the time of the sequence number t is 24:00 of the same day, and when the time of the time gap (q-1, q) represents the time of the sequence number 1 is equal to the time of the sequence number 1, namely, the time gap (1, 21, and the time interval is equal to 21).
Calculating the time sequence penetration degree of each NDWI image, specifically:
recording the time sequence penetration degree of ND (q) as a period (q), and acquiring the last element ND (q-1) of ND (q) in the NDWI image sequence and each pixel value ND (q-1) [ i, j ], wherein after dimensionless processing, the calculation formula of period (q) can be as follows:
wherein exp is an exponential function based on a natural constant e, exp (|ND (q) [ i, j ] -ND (q-1) [ i, j ] |) is an exponential representation after taking absolute value of the difference between the numerical values of the same row and column positions in an NDWI image of a sequence number q and the previous sequence number, a denominator is an exponential representation after taking absolute value of the difference between the numerical values of the same row and column positions in an NDWI image of a sequence number q and the previous sequence number by traversing i and j in each row and column position, and accumulation and summation are carried out, so that the numerical value characteristic distribution rule of the normalized water index corresponding to each position changing along with time and place change can be better extracted, a denominator part has traversing accumulated symbols, and brackets are used in the denominator part to represent traversing circulation and summation of the sequence numbers j and i respectively, then dividing the numerical value of the numerator by the denominator, wherein the time gap (q-1, q)/time gap (1, t) represents the proportion of the time interval of the sequence number q and the time of the previous sequence number to the total time change interval (time gap (1, t)), the fluctuation degree of time change can be extracted, the time sequence penetration degree is calculated by combining the numerical value characteristic distribution rule changed by the change of the normalized water index along with the change of time and the fluctuation degree of time change, the data characteristic breakthrough of the contour characteristic of the coastline on the image sequence is penetrated at each time, the precise capturing of the fuzzy contour characteristic of the coastline caused by the tide advance and retreat due to the time change is facilitated, the attaching precision of the sandy coastline extraction is improved, the bigger the time sequence penetration degree value is, the higher the response degree of the NDWI image to the contour characteristic of the coastline is represented, the more advantageous is for improving the accuracy of extraction;
calculating an arithmetic average value, a median or a mode of time sequence penetration of each NDWI image in the NDWI image sequence as a time sequence penetration threshold value of the NDWI image sequence (which is favorable for obtaining the average level of normal distribution), screening out the NDWI images of which the corresponding time sequence penetration in the NDWI image sequence reaches (the numerical value is greater than or equal to) the time sequence penetration threshold value as super-threshold images, wherein the screened super-threshold images still keep the corresponding time sequence penetration in the NDWI image sequence;
multiplying each super-threshold image by the corresponding time sequence penetration degree of each pixel point of each super-threshold image, so that each super-threshold image is converted into a time sequence penetration degree image, then calculating the matrix obtained by carrying out Hadamard product multiplication on each time sequence penetration degree image as an accumulated image matrix, (multiplication between values and arrays is widely used all the time from the time sequence penetration degree calculation to the time sequence penetration degree image calculation, point-to-point value multiplication is carried out on each image matrix by utilizing Hadamard product, and the value linearity of multiplication by utilizing a plurality of variables is continuously conductive, so that the value linear correlation is helpful for coastline extraction);
on the cumulative image matrix, the numerical value of each row position is converted into a numerical value of either positive or negative through a binarization algorithm, and then a point of the row position in which the positive numerical value is converted is selected as a coastline extraction point, wherein the positive or negative numerical value can be a numerical value of either 0 or 1, a numerical value or a sign which can represent a logical inverse relation with a logical not, a boolean value (or a numerical value of True or False), and the like, and specifically can be: the values of each row and column position are mapped and converted into values of 0 or 1 through a Binarization algorithm (Binarization) or a decision tree classification algorithm (for example, a Keras-based binary classification network, a sklearn-based cart_tree decision tree, etc.), and then the point of the row and column position, in which the value of 1 is converted, is selected as a coastline extraction point. Compared with the method that the coastline is extracted by directly converting by using a binarization algorithm or a decision tree classification algorithm and then directly using an original NDWI image, the method measures the periodic data distribution of the coastline on the basis of using the numerical characteristic distribution rule changed by the change of the normalized water index along with the change of time and place and the fluctuation degree of time change, thereby being beneficial to avoiding the influence of time and further improving the accuracy of the coastline.
Further, in S400, the method for obtaining the corrected coastline according to the coastline extraction point is as follows: and taking a curve obtained by curve fitting or interpolation of the coastline extraction points as the corrected coastline.
The present disclosure also provides a sandy coastline extraction system of high-resolution remote sensing image, the sandy coastline extraction system of high-resolution remote sensing image includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements steps in a sandy coastline method of the high resolution remote sensing image when the processor executes the computer program, the sandy coastline extraction system of the high resolution remote sensing image can be executed in a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud data center, and the like, and the executable system can include, but is not limited to, a processor, a memory, and a server cluster, and the processor executes the computer program to be executed in units of the following systems:
the image acquisition unit is used for acquiring a plurality of remote sensing images at different moments;
the serialization unit is used for converting the remote sensing image into an NDWI image and forming the NDWI image into an NDWI image sequence;
the extraction unit is used for carrying out penetration processing on the NDWI image sequence to obtain coastline extraction points;
and the correction output unit is used for obtaining a corrected coastline according to the coastline extraction point.
The beneficial effects of the present disclosure are: according to the sandy coastline extraction method and system for the high-resolution remote sensing image, remote sensing images at different moments are converted into the NDWI image sequence, the NDWI image sequence is subjected to penetrating processing, coastline extraction points are obtained, and the corrected coastline is further obtained. Compared with the existing method, the method provided by the disclosure has the advantages of small calculated amount, less manual intervention, high accuracy and the like, and is expected to be widely popularized and applied in practical application.
Drawings
The above and other features of the present disclosure will become more apparent from the detailed description of the embodiments illustrated in the accompanying drawings, in which like reference numerals designate like or similar elements, and which, as will be apparent to those of ordinary skill in the art, are merely some examples of the present disclosure, from which other drawings may be made without inventive effort, wherein:
FIG. 1 is a flow chart of a method for extracting a sandy coastline of a high-resolution remote sensing image;
fig. 2 is a system configuration diagram of a sandy coastline extraction system for high resolution remote sensing images.
Detailed Description
The conception, specific structure, and technical effects produced by the present disclosure will be clearly and completely described below in connection with the embodiments and the drawings to fully understand the objects, aspects, and effects of the present disclosure. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
In the description of the present invention, a number means one or more, a number means two or more, and greater than, less than, exceeding, etc. are understood to not include the present number, and above, below, within, etc. are understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
Fig. 1 is a flowchart of a method for extracting a sandy coastline of a high-resolution remote sensing image according to the present invention, and a method and a system for extracting a sandy coastline of a high-resolution remote sensing image according to an embodiment of the present invention are described below with reference to fig. 1.
The invention discloses a method for extracting a sandy coastline of a high-resolution remote sensing image, which specifically comprises the following steps:
s100, acquiring a plurality of remote sensing images at different moments;
s200, converting the remote sensing image into an NDWI image, and forming the NDWI image into an NDWI image sequence;
s300, carrying out penetration processing on the NDWI image sequence to obtain coastline extraction points;
s400, obtaining the corrected coastline according to the coastline extraction points.
Further, in S100, the time intervals between each of the plurality of different moments are the same, the order of arrangement of each of the plurality of different moments is according to time sequence, each remote sensing image corresponds to each moment, each moment corresponds to only one remote sensing image, and the remote sensing image is a high resolution remote sensing image of the coastline.
Further, in S200, remote sensing images at each moment are respectively converted into NDWI images by calculating a normalized water index, and the obtained NDWI images are sequentially formed into an NDWI image sequence, wherein the pixel values on the NDWI images are already subjected to graying and normalization processing to be values belonging to 0,1, wherein the closer the pixel value is to 0, the closer to black, the closer the pixel value is to 1, the closer to white, the closer to black indicates that the water content at the corresponding position on the NDWI image is less, and the closer to white indicates that the water content at the corresponding position on the NDWI image is more. (preferably, the time interval between the moments may be 1 hour.)
Further, in S300, the method for obtaining the coastline extraction point by performing the penetration processing on the NDWI image sequence includes:
recording the NDWI image sequence as a sequence NDseq, recording the number of NDWI images serving as elements in the NDWI image sequence as t, enabling the sequence number of the elements in the NDWI image sequence to be q, wherein q belongs to a 1-t interval, preferably, the 1-t interval can be a 1-24 or 25-hour interval, preferably, a closed recyclable time period is formed, the sequence number of each moment in the plurality of different moments is consistent with the sequence number q, and the q-th element in the NDWI image sequence is ND (q);
each NDWI image in the NDWI image sequence is an image matrix with the size of n rows and m columns, wherein i is a row sequence number and j is a column sequence number in each NDWI image, i is a 1-n interval, j is a 1-m interval, and the numerical value of the j-th column position of the ith row in ND (q) is represented as ND (q) [ i, j ];
the next of the last element in the NDWI image sequence is pointed to the first element, namely the next of the last element ND (t) is pointed to the first element ND (1), so that the operation is that the change of tides is periodically back and forth, the tidal advance and retreat is large for the fuzzy image interference factor of the coastline, the data sequence connected end to end can better reflect the periodic data distribution of the coastline, and the subsequent extraction of the coastline is convenient;
the function TimeGAP (,) represents the time interval that elapses between the time of calculation of the sequence number at the rear in brackets and the time of the sequence number at the front, specifically: timeGAP (1, q) represents the time interval over which the time of sequence number q is distant from the time of sequence number 1, i.e., the time interval of sequence number q minus the time of sequence number 1; timeGAP (1, t) represents the time interval over which the time of sequence number t is distant from the time of sequence number 1; timeGAP (q-1, q) represents the time interval elapsed from the time of sequence number q to the time of the last time of sequence number q, q-1; when q of the TimeGAP (q-1, q) represents the time of the sequence number 1, the time of subtracting 1 from the time q of the last time of the sequence number q is the time of the sequence number t, which is equivalent to that, on the serialization arrangement of the sequence number q, as the sequence number t and the sequence number 1 are connected end to end, when q is equal to 1, q is subtracted by 1 to be equal to t; the time interval only takes absolute value and has no positive or negative score; for example, when the time of the sequence number q is 23:00 of one day, the time of the sequence number 1 is 3:00 of the same day, the time interval of subtracting the time of the sequence number 1 from the time of the sequence number q is 20 hours, when the time of the sequence number t is 24:00 of the same day, when q of the time gap (q-1, q) represents the time of the sequence number 1, the time gap (q-1, q) is equal to the time gap (t, 1), that is, 21 hours, and at this time the time gap (1, t) is also equal to 21 hours;
calculating the time sequence penetration degree of each NDWI image, specifically:
recording the time sequence penetration degree of ND (q) as a period (q), acquiring the last element ND (q-1) of ND (q) in an NDWI image sequence and each pixel value ND (q-1) [ i, j ], and after dimensionless processing, obtaining a calculation formula of period (q) as follows:
wherein exp () is an exponential function based on a natural constant e, exp (|ND (q) [ i, j ] -ND (q-1) [ i, j ] |) is an exponential representation after taking absolute value of the difference between the numerical values of the same line position in the NDWI image of the sequence number q and the previous sequence number, the denominator is an exponential representation after taking absolute value of the difference between the numerical values of the same line position in the NDWI image of the sequence number q and the previous sequence number by traversing i and j in each line position, and accumulation summation is carried out, so that the numerical value characteristic distribution rule that the normalized water index corresponding to each position changes along with the change of time and place can be better extracted, the time gap (q-1, q)/time gap (1, t) represents the proportion of the time interval of the time of the sequence number q and the previous sequence number to the total time change interval (time gap (1, t)), the fluctuation degree of time change can be extracted, the time sequence penetration degree is calculated by combining the numerical value characteristic distribution rule changed by the change of the normalized water index along with the change of time and place and the fluctuation degree of time change, the data characteristic breakthrough of the coastline profile characteristic on the image sequence is penetrated at each moment, the precise capturing of the fuzzy coastline profile characteristic caused by the advance and retreat of tides due to the time change is facilitated, the attaching precision of the sandy coastline extraction is improved, the higher the time sequence penetration degree value is, the higher the response degree of the NDWI image to the coastline profile characteristic is represented, and the extraction precision is facilitated;
calculating an arithmetic average value of time sequence penetration of each NDWI image in an NDWI image sequence as a time sequence penetration threshold of the NDWI image sequence, screening out the NDWI images with the corresponding time sequence penetration reaching (the numerical value being greater than or equal to) the time sequence penetration threshold as super-threshold images, and keeping the corresponding time sequence penetration of the super-threshold images in the NDWI image sequence after screening;
multiplying each super-threshold image by the corresponding time sequence penetration degree of each pixel point of each super-threshold image, so that each super-threshold image is converted into a time sequence penetration degree image, the time sequence penetration degree images are calculated and the matrix obtained by Hadamard product multiplication is used as an accumulated image matrix, (multiplication between numerical values and arrays is widely used all the time from the time sequence penetration degree calculation to the time sequence penetration degree image calculation and the Hadamard product multiplication is obtained, point-to-point numerical value multiplication is carried out between the image matrices by utilizing Hadamard product, and numerical value linearity of multiplication by utilizing a plurality of variables is continuously conductive, so that the method has the interpretability in mathematical analysis, and the interpretable numerical value linear correlation is more guaranteed for coastline extraction as compared with a non-linear non-continuously conductive non-interpretable mathematical model based on machine learning, a deep neural network and the like;
on the cumulative image matrix, the numerical value of each row position is converted into a numerical value of either positive or negative through a binarization algorithm, and then a point of the row position in which the positive numerical value is converted is selected as a coastline extraction point, wherein the positive or negative numerical value can be a numerical value of either 0 or 1, a logical value or a sign which can represent a logical inverse relation with a logical negation, a Boolean value and the like, and the method specifically can be as follows: the values of each line position are mapped to be converted into values of either 0 or 1 by a Binarization algorithm (Binarization) or a decision tree classification algorithm (e.g., a Keras-based bi-classification network, a sklearn-based cart_tree decision tree), and then the point of the line position in which the value of 1 is converted is selected as a coastline extraction point. Compared with the method that the coastline is extracted by directly converting by using a binarization algorithm or a decision tree classification algorithm and then directly using an original NDWI image, the method measures the periodic data distribution of the coastline on the basis of using the numerical characteristic distribution rule changed by the change of the normalized water index along with the change of time and place and the fluctuation degree of time change, thereby being beneficial to avoiding the influence of time and further improving the accuracy of the coastline.
Further, in S400, the method for obtaining the corrected coastline according to the coastline extraction point is as follows: a curve obtained by curve fitting (Least square) or interpolation (Spline Interpolation) to the coastline extraction points is used as the corrected coastline.
The invention also comprises a sandy coastline extraction system of the high-resolution remote sensing image, wherein the sandy coastline extraction system of the high-resolution remote sensing image runs in any computing equipment of a desktop computer, a notebook computer, a palm computer or a cloud data center, and the computing equipment comprises: the processor executes the computer program to implement the steps in the method for extracting the sandy coastline of the high-resolution remote sensing image, and the operable system can include, but is not limited to, a processor, a memory, a server cluster and the like.
As shown in fig. 2, a system for extracting a sandy coastline of a high-resolution remote sensing image according to an embodiment of the present disclosure includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned embodiments of a method for extracting a sandy coastline of a high-resolution remote sensing image when the computer program is executed, and the processor executes the computer program to execute the steps in the following units of a system:
the image acquisition unit is used for acquiring a plurality of remote sensing images at different moments;
the serialization unit is used for converting the remote sensing image into an NDWI image and forming the NDWI image into an NDWI image sequence;
the extraction unit is used for carrying out penetration processing on the NDWI image sequence to obtain coastline extraction points;
and the correction output unit is used for obtaining a corrected coastline according to the coastline extraction point.
Preferably, all undefined variables in the present invention may be threshold set manually if not explicitly defined.
The sandy coastline extraction system of the high-resolution remote sensing image can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud data center and the like. The system for extracting the sandy coastline of the high-resolution remote sensing image comprises, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that the examples are merely examples of a method and a system for extracting a sandy coastline of a high-resolution remote sensing image, and are not limited to the method and the system for extracting a sandy coastline of a high-resolution remote sensing image, and may include more or fewer components than examples, or may combine some components, or different components, for example, the system for extracting a sandy coastline of a high-resolution remote sensing image may further include an input/output device, a network access device, a bus, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete component gate or transistor logic devices, discrete hardware components, or the like. The general processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor is a control center of the sandy coastline extraction system of the high-resolution remote sensing image, and various interfaces and lines are used to connect the respective sub-areas of the sandy coastline extraction system of the whole high-resolution remote sensing image.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the method and system for extracting a sandy coastline of a high-resolution remote sensing image by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The present disclosure provides a method and a system for extracting a sandy coastline of a high-resolution remote sensing image, which acquire a plurality of remote sensing images at different moments, convert the remote sensing images into NDWI images, form NDWI images into NDWI image sequences, and perform penetration processing on the NDWI image sequences to obtain coastline extraction points, and obtain a corrected coastline according to the coastline extraction points, thereby being beneficial to improving the accuracy of the coastline.
Although the description of the present disclosure has been illustrated in considerable detail and with particularity, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the present disclosure. Furthermore, the foregoing description of the present disclosure has been presented in terms of embodiments foreseen by the inventor for the purpose of providing a enabling description for enabling the enabling description to be available, notwithstanding that insubstantial changes in the disclosure, not presently foreseen, may nonetheless represent equivalents thereto.
Claims (4)
1. The method for extracting the sandy coastline of the high-resolution remote sensing image is characterized by comprising the following steps of:
s100, acquiring a plurality of remote sensing images at different moments;
s200, converting the remote sensing image into an NDWI image, and forming the NDWI image into an NDWI image sequence;
s300, carrying out penetration processing on the NDWI image sequence to obtain coastline extraction points;
s400, obtaining a corrected coastline according to the coastline extraction points;
in S200, remote sensing images at each moment are respectively converted into corresponding NDWI images through calculating normalized water indexes, and the obtained NDWI images sequentially form an NDWI image sequence, wherein pixel values on the NDWI images are values belonging to [0,1] after being subjected to graying and normalization processing;
in S300, the method for obtaining the coastline extraction point by performing the penetration processing on the NDWI image sequence includes:
recording the NDWI image sequence as a sequence NDseq, recording the number of NDWI images serving as elements in the NDWI image sequence as t, enabling the sequence number of the elements in the NDWI image sequence to be q, keeping the sequence number of each moment in a plurality of different moments consistent with the sequence number q, and enabling the element with the q-th sequence number in the sequence NDseq to be ND (q);
each NDWI image in the NDWI image sequence is an image matrix with the size of n rows and m columns, i is the serial number of a row and j is the serial number of a column in each NDWI image, and the numerical value of the j-th column position of the i-th row in ND (q) is represented as ND (q) [ i, j ];
directing the next of the last element in the NDWI image sequence to the first element;
the function TimeGAP (,) represents the time interval that the time of the subsequent sequence number in the bracket is calculated to pass from the time of the preceding sequence number;
calculating the time sequence penetration degree of each NDWI image: recording the time sequence penetration degree of ND (q) as a period (q), and acquiring the last element ND (q-1) of ND (q) in the NDWI image sequence and the numerical value ND (q-1) [ i, j ] of the element ND (q), wherein the calculation formula of period (q) is as follows:
calculating an arithmetic average value of time sequence penetration of each NDWI image in an NDWI image sequence as a time sequence penetration threshold of the NDWI image sequence, and screening out the NDWI images of which the corresponding time sequence penetration in the NDWI image sequence reaches the time sequence penetration threshold as super-threshold images;
multiplying each super-threshold image by the corresponding time sequence penetration degree on the pixel value of each pixel point of each super-threshold image so as to convert each super-threshold image into time sequence penetration degree images, and multiplying each time sequence penetration degree image together by Hadamard product to obtain an accumulated image matrix;
on the cumulative image matrix, the numerical value of each row and column position is converted into a numerical value with the positive or the negative through a binarization algorithm, wherein the numerical value with the positive or the negative represents the numerical value or sign with the logical inverse relation, the numerical value including the numerical value of 0 or 1, the logical AND logic NOT and the Boolean value, and then the point of the row and column position converted into the positive numerical value is selected as a coastline extraction point.
2. The method for extracting a coastline from a sand of a high-resolution remote sensing image according to claim 1, wherein in S100, time intervals among the time points in the plurality of different time points are the same, the order of arrangement of the time points in the plurality of different time points is in time sequence, each remote sensing image corresponds to each time point, wherein each time point corresponds to only one remote sensing image, and the remote sensing image is the high-resolution remote sensing image of the coastline.
3. The method for extracting a coastline from a sand of a high-resolution remote sensing image according to claim 1, wherein in S400, the method for obtaining a corrected coastline according to the coastline extraction point comprises: and taking a curve obtained by curve fitting or interpolation on the coastline extraction points as the corrected coastline.
4. A sandy coastline extraction system of high resolution remote sensing image, characterized in that the sandy coastline extraction system of high resolution remote sensing image is operated in any computing device of a desktop computer, a notebook computer or a cloud data center, the computing device comprising: a processor, a memory and a computer program stored in the memory and running on the processor, the processor implementing the steps in a method for extracting a sandy coastline of a high resolution remote sensing image as claimed in any one of claims 1 to 2 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310395276.3A CN116129145B (en) | 2023-04-14 | 2023-04-14 | Method and system for extracting sandy coastline of high-resolution remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310395276.3A CN116129145B (en) | 2023-04-14 | 2023-04-14 | Method and system for extracting sandy coastline of high-resolution remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116129145A CN116129145A (en) | 2023-05-16 |
| CN116129145B true CN116129145B (en) | 2023-06-23 |
Family
ID=86306622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310395276.3A Active CN116129145B (en) | 2023-04-14 | 2023-04-14 | Method and system for extracting sandy coastline of high-resolution remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116129145B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034083A (en) * | 2018-08-03 | 2018-12-18 | 青岛大学 | A kind of natural Extracting costline method and apparatus based on more scape remote sensing images |
| CN109577272A (en) * | 2018-12-20 | 2019-04-05 | 国家海洋局第二海洋研究所 | Chiltern water front restorative procedure |
| CN110097101A (en) * | 2019-04-19 | 2019-08-06 | 大连海事大学 | A kind of remote sensing image fusion and seashore method of tape sorting based on improvement reliability factor |
| CN110991393A (en) * | 2019-12-17 | 2020-04-10 | 北京航天泰坦科技股份有限公司 | Method and device for remote sensing monitoring and analysis of coastline transition |
| CN113139550A (en) * | 2021-03-29 | 2021-07-20 | 山东科技大学 | Remote sensing image coastline extraction method based on deep semantic segmentation network |
| CN114627372A (en) * | 2022-02-24 | 2022-06-14 | 中国电子科技集团公司第五十四研究所 | Method for rapidly detecting wide remote sensing image ship target based on intra-domain transfer learning |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8238658B2 (en) * | 2009-01-21 | 2012-08-07 | The United States Of America, As Represented By The Secretary Of The Navy | Boundary extraction method |
| US20130039574A1 (en) * | 2011-08-09 | 2013-02-14 | James P. McKay | System and method for segmenting water, land and coastline from remote imagery |
| CN104732215A (en) * | 2015-03-25 | 2015-06-24 | 广西大学 | Remote-sensing image coastline extracting method based on information vector machine |
| EP3113470B1 (en) * | 2015-07-02 | 2020-12-16 | Nokia Technologies Oy | Geographical location visual information overlay |
| CN105374041A (en) * | 2015-11-18 | 2016-03-02 | 国家海洋局第一海洋研究所 | Method of extracting sandy coastline by using multiple periods of remote sensing images |
| CN105572694A (en) * | 2015-12-23 | 2016-05-11 | 国家海洋局第一海洋研究所 | Motorized high precision sandy shoreline and mud shoreline measuring device |
| CN108446489A (en) * | 2018-03-17 | 2018-08-24 | 北京师范大学 | Measurement method and its processing unit of the Coastline Changes to wetland influence on groundwater |
| US11373314B2 (en) * | 2018-04-05 | 2022-06-28 | Nec Corporation | Land mask image generation for ocean surface and land surface |
| CN111310681B (en) * | 2020-02-24 | 2021-03-16 | 中国科学院地理科学与资源研究所 | Mangrove forest distribution remote sensing extraction method integrated with geoscience knowledge |
| CN113205016B (en) * | 2021-04-21 | 2022-05-17 | 武汉大学 | River and lake shoreline change detection method of constant residual error type Unet and remote sensing water body index |
| CN216994848U (en) * | 2022-04-08 | 2022-07-19 | 广东海洋大学 | A unmanned aerial vehicle that takes photo by plane for coastline draws |
-
2023
- 2023-04-14 CN CN202310395276.3A patent/CN116129145B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034083A (en) * | 2018-08-03 | 2018-12-18 | 青岛大学 | A kind of natural Extracting costline method and apparatus based on more scape remote sensing images |
| CN109577272A (en) * | 2018-12-20 | 2019-04-05 | 国家海洋局第二海洋研究所 | Chiltern water front restorative procedure |
| CN110097101A (en) * | 2019-04-19 | 2019-08-06 | 大连海事大学 | A kind of remote sensing image fusion and seashore method of tape sorting based on improvement reliability factor |
| CN110991393A (en) * | 2019-12-17 | 2020-04-10 | 北京航天泰坦科技股份有限公司 | Method and device for remote sensing monitoring and analysis of coastline transition |
| CN113139550A (en) * | 2021-03-29 | 2021-07-20 | 山东科技大学 | Remote sensing image coastline extraction method based on deep semantic segmentation network |
| CN114627372A (en) * | 2022-02-24 | 2022-06-14 | 中国电子科技集团公司第五十四研究所 | Method for rapidly detecting wide remote sensing image ship target based on intra-domain transfer learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116129145A (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245659B (en) | Image salient object segmentation method and device based on foreground and background interrelation | |
| Li et al. | SAR image change detection using PCANet guided by saliency detection | |
| CN110598558B (en) | Crowd density estimation method, device, electronic equipment and medium | |
| CN109165538B (en) | Bar code detection method and device based on deep neural network | |
| CN110501278B (en) | Cell counting method based on YOLOv3 and density estimation | |
| Lagona et al. | A hidden Markov model for the analysis of cylindrical time series | |
| CN111951297B (en) | Target tracking method based on structured pixel-by-pixel target attention mechanism | |
| CN109726649B (en) | Remote sensing image cloud detection method and system and electronic equipment | |
| Han et al. | An improved corner detection algorithm based on harris | |
| Ngugi et al. | A new approach to learning and recognizing leaf diseases from individual lesions using convolutional neural networks | |
| CN115345905A (en) | Target object tracking method, device, terminal and storage medium | |
| CN115620118A (en) | Saliency target detection method based on multi-scale expansion convolutional neural network | |
| CN118115502B (en) | Sewage discharge monitoring method and system based on image features | |
| CN117113189A (en) | Comprehensive evaluation method for land classification, electronic equipment and storage medium | |
| CN117541983B (en) | Model data quality analysis method and system based on machine vision | |
| CN116129145B (en) | Method and system for extracting sandy coastline of high-resolution remote sensing image | |
| CN116580063B (en) | Target tracking method, target tracking device, electronic equipment and storage medium | |
| CN113239785A (en) | Method, system, storage medium and electronic device for automatically identifying house type based on convolutional neural network | |
| CN111815627A (en) | Remote sensing image change detection method, model training method and corresponding device | |
| CN115757386B (en) | Anomaly detection method, system, equipment and medium for ocean space observation data | |
| CN110598732A (en) | Plant health detection method and device based on image recognition | |
| CN102129687B (en) | Self-adapting target tracking method based on local background subtraction under dynamic scene | |
| CN112861874B (en) | Expert field denoising method and system based on multi-filter denoising result | |
| CN116343039A (en) | Environment monitoring method and device | |
| CN114550288B (en) | Action recognition method and device based on event data |
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 |