An optical remote sensing data lake shoreline detection method and device

Abstract

The application discloses an optical remote sensing data lake shoreline detection method and device, and solves the problem of low detection precision of lake shoreline in the technical field of remote sensing. The optical remote sensing data lake shoreline detection method comprises the following steps: obtaining a monthly median image of a selected region in a single month; calculating an odd number of water body indexes not less than 3 for each pixel of the selected region according to the monthly median image; determining a corresponding water body index threshold value by using a dynamic threshold method; each water body index has a corresponding water body index threshold value; calculating the number of water body indexes greater than the water body index threshold value; in response to the number of water body indexes greater than the water body index threshold value being greater than half of the total number, the pixel is regarded as a water body pixel; and dividing the lake shoreline of the month according to the water body pixel and the non-water body pixel. The application adopts a dynamic threshold value for a specific lake water body index to determine water body and non-water body, and overcomes the missing and misclassification of water body caused by the one-size-fits-all threshold value determination.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of remote sensing application, and in particular to an optical remote sensing data lake shoreline detection method and device. BACKGROUND

[0002] Lakes are important sensitive indicators of regional climate change, and the changes in their area and water level can objectively reflect the water balance process in the basin. Therefore, the change rate of lake shoreline can measure the regional lake water change. Existing lake change research mainly focuses on the change of lake area, which is usually achieved by using various water body indexes such as Normalized Difference Water Index (NDWI), Modified NDWI (MNDWI), and Automated Water Extraction Index (AWEI) to automatically extract water body pixels on remote sensing images, or by using supervised classification and unsupervised classification schemes. The change of lake shoreline is still in the blank.

[0003] Based on remote sensing data, the water body boundary is extracted by using the water body index method, and the threshold determination is the key. However, due to different atmospheric and lighting conditions when acquiring remote sensing images, there is no fixed threshold for water body index, and in actual operation, a suitable threshold needs to be determined for each regional image. In addition, previous research on lake area only extracts the water surface area of a lake at a certain moment, which cannot capture the seasonal differences of the lake, causing difficulties in determining the change rate of the lake shoreline.

[0004] The supervised classification method is used to extract water body, which requires the establishment of a classification system, the selection of training samples and the selection of a classifier. Widely used classifiers include Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM), RandomForest, Classification and Regression Trees, K-Nearest Neighboralgorithm, Minimum Distance Classifier, etc. Although the above classifiers have high computational efficiency, the accuracy of classification still depends to a great extent on the representativeness, accuracy and completeness of the samples. This scheme requires that the training samples of various land cover types be relatively complete, and the requirements for sample selection personnel are relatively high, which is time-consuming and labor-intensive. The unsupervised classification method first classifies the remote sensing image unsupervisedly, and then removes noise by using prior knowledge and auxiliary data to extract water body, which is a relatively complex process and requires a lot of post-processing work. SUMMARY

[0005] This application provides a method and apparatus for detecting lake shorelines using optical remote sensing data, which solves the problem of low accuracy in lake shoreline detection in the field of remote sensing technology.

[0006] In a first aspect, embodiments of this application also provide a method for detecting lake shorelines using optical remote sensing data, comprising the following steps:

[0007] Find the monthly median value image for a selected region in a single month;

[0008] For each pixel in the selected area based on the mid-month value image, calculate an odd number of water body indices of at least 3 from NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015, and HRWI.

[0009] The dynamic threshold method is used to determine the threshold of the corresponding water body index; each water body index has a corresponding water body index threshold.

[0010] Compare each water index with its corresponding water index threshold, and calculate the number of water indices that are greater than the water index threshold.

[0011] If the number of such pixels is greater than half of the total number of water body indices, the pixel is considered a water body pixel.

[0012] The shoreline for the current month is defined based on water body pixels and non-water body pixels.

[0013] Furthermore, following the aforementioned steps, the following steps are also included:

[0014] Select months when the lake shoreline cannot be accurately determined due to cloud cover;

[0015] Using the spatiotemporal context reasoning method, the shoreline of the current month can be inferred by comparing the shorelines of the preceding and following months.

[0016] Alternatively, following the steps described above, the following steps are also included:

[0017] Find the maximum boundary of the lake in a given year by analyzing the shoreline data for each month of the year.

[0018] The maximum boundary of the lake is used as the shoreline location of the lake on an annual scale;

[0019] By comparing the shoreline positions of lakes on an annual scale in adjacent years, the annual rate of change of the lake shoreline can be calculated.

[0020] Furthermore, the median image of a single month is obtained by selecting months without snowfall.

[0021] Furthermore, the seven water body indices NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015, and HRWI are calculated. A pixel is considered a water body pixel if the water body index votes are greater than 5 / 7.

[0022] Furthermore, following the step of inferring the shoreline of the current month from the shorelines of previous and subsequent months using the spatiotemporal context reasoning method, the following steps are also included:

[0023] Each shoreline is labeled with temporal attributes and the percentage of effective observed pixels to create lake shoreline datasets at monthly and annual scales.

[0024] Furthermore, calculating the annual rate of change of the lake shoreline involves the following steps:

[0025] A linear best trend fit based on the least squares principle is performed on the change distance of all historical shoreline data relative to the baseline, and the slope of the fit is defined as the rate of change of the shoreline.

[0026] Secondly, embodiments of this application also provide an optical remote sensing data shoreline detection device for implementing the optical remote sensing data shoreline detection method described in any embodiment of the first aspect, comprising an input module, a determination module, and an output module. The input module is used to receive a dataset of the area to be detected. The determination module is used for at least one of the following functions: determining monthly images based on the dataset; determining the shoreline for the current month based on the monthly images; determining the annual rate of change of the shoreline by comparing its position on an annual scale; and determining the shoreline obscured by clouds based on the shoreline positions of previous and subsequent months. The output module is used to output the results of the determination module.

[0027] Thirdly, embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the first aspect of this application.

[0028] Fourthly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any embodiment of the first aspect of this application.

[0029] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0030] A dynamic threshold method is used to determine water bodies and non-water bodies for specific lake water indices, overcoming the omissions and misclassifications of water bodies caused by a one-size-fits-all threshold method. Monthly lake shoreline extraction based on a voting method and spatiotemporal context not only reflects the seasonal characteristics of water bodies but also characterizes the uncertainty of water body extraction through the percentage of effective observations, providing a reliable data source for determining subsequent shoreline change rates. Determining shoreline change rates based on the maximum water body boundary extends the practical significance of water body extraction, serving as a data foundation for climate change prediction and providing data support for regional production and livelihood planning. Attached Figure Description

[0031] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0032] Figure 1 This is a flowchart of an optical remote sensing data lake shoreline detection method according to an embodiment of this application;

[0033] Figure 2 This is the process for determining water body pixels in an embodiment of this application;

[0034] Figure 3 This is a flowchart of another optical remote sensing data lake shoreline detection method according to an embodiment of this application;

[0035] Figure 4 This is a flowchart of the third optical remote sensing data lake shoreline detection method according to an embodiment of this application;

[0036] Figure 5 This is a structural diagram of an optical remote sensing data lake shoreline detection device according to an embodiment of this application;

[0037] Figure 6 This is a flowchart of the shoreline change detection method using high-resolution optical remote sensing data in the embodiments of this application;

[0038] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0041] Figure 1 This is a flowchart of an optical remote sensing data lake shoreline detection method according to an embodiment of this application.

[0042] This application also provides a method for detecting lake shoreline using optical remote sensing data, including the following steps:

[0043] Step 110: Calculate the monthly median value image for the selected region in a single month;

[0044] Furthermore, the median image of a single month is obtained by selecting months without snowfall.

[0045] For example, for a selected area, choose the Landsat or Sentinel-2 dataset to synthesize monthly images from April to October. For all pixels falling within the study area, remove contaminated pixels (clouds, shadows, bad pixels) using a mask, and then select the median of the valid observations to synthesize a monthly median image.

[0046] Step 120: Calculate an odd number of water body indices of at least 3 from NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015 and HRWI for each pixel in the selected area based on the mid-month value image.

[0047] For example, a water body index image is calculated for each pixel of a selected area based on a mid-month image. Since water has lower reflectivity in the infrared band than in the visible light band, water body information can be extracted using water body indices. Therefore, an odd number of water body indices of at least three are calculated from seven different water body indices: NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015, and HRWI. Among them, NDWI1 and NDWI2 are the earlier proposed and used (1996) general water body indices, TCW is the humidity component after TC transformation, and AWEI1, AWEI2, WI2015, and HRWI are new water body indices developed and widely used after 2010.

[0048] Figure 2 This is the process for determining water body pixels in the embodiments of this application.

[0049] Furthermore, the seven water body indices NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015, and HRWI are calculated. A pixel is considered a water body pixel if the water body index votes are greater than 5 / 7.

[0050] The water index is calculated based on the atmospheric top reflectance in the multispectral-near-infrared bands of the Landsat series satellites, and the following seven water indices are calculated respectively:

[0051]

[0052]

[0053]

[0054]

[0055]

[0056]

[0057]

[0058] Step 130: Determine the corresponding water body index threshold using the dynamic threshold method; each water body index has a corresponding water body index threshold.

[0059] For example, for each lake and its surrounding land, assuming there exists a threshold that divides all pixels in the image into two classes, the optimal threshold is found by maximizing the inter-class variance.

[0060] The sensitivity of lake water transparency, suspended solids concentration, and depth varies to different water body indices. Therefore, the criteria for determining whether a pixel is a body of water differ, especially for pixels near the lake shore.

[0061] Step 140: Compare each water index with its corresponding water index threshold, and calculate the number of water indices that are greater than the water index threshold.

[0062] The water body index is compared with the corresponding water body index threshold, which is a preset value.

[0063] For example, for the water index calculated from the median image of each month, a dynamic thresholding method is used to determine the corresponding water index threshold to distinguish between water bodies and non-water bodies.

[0064] Step 150: In response to the above number being greater than half of the total number of water body indices, the pixel is considered a water body pixel;

[0065] The total number of water indices refers to the number of water indices actually used among the seven water indices: NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015, and HRWI.

[0066] For example, if three of the seven water body indices are used, a voting method is adopted to determine the water body pixel; that is, if the number of votes for a water body is greater than or equal to 2 / 3, the pixel is determined to be a water body pixel. If all seven water body indices are used in the calculation, a voting method is adopted to determine the water body pixel; that is, if the number of votes for a water body is greater than or equal to 4 / 7, the pixel is determined to be a water body pixel.

[0067] Preferably, a voting method is adopted to determine the water body pixel, that is, when the number of votes for the water body is greater than 5 / 7, the pixel is determined to be a water body pixel.

[0068] Step 160: Divide the shoreline for the current month based on water body pixels and non-water body pixels.

[0069] Figure 3 This is a flowchart of another optical remote sensing data lake shoreline detection method according to an embodiment of this application.

[0070] Furthermore, following steps 110-160, the following steps are also included:

[0071] Step 170: Select the month when the shoreline cannot be accurately determined due to cloud cover;

[0072] Step 180: Using the spatiotemporal context reasoning method, infer the shoreline of the current month from the shorelines of the preceding and following months.

[0073] Due to the influence of weather on optical imagery, some areas experience higher cloud cover frequencies in spring imagery, while summer and autumn imagery show more effective observations. To address this, a spatiotemporal contextual reasoning method is employed, combining intra-annual and inter-annual variations in lake water volume to infer the shoreline boundaries of severely polluted areas. Ultimately, monthly and annual lake shoreline datasets are generated, with each shoreline labeled with temporal attributes and the proportion of effective observation pixels.

[0074] Figure 4 This is a flowchart of the third optical remote sensing data lake shoreline detection method in this application.

[0075] Furthermore, following steps 110-160, the following steps are also included:

[0076] Step 190: Find the maximum boundary of the lake for the year from the shoreline data for each month of the year;

[0077] Step 200: Use the maximum boundary of the lake as the shoreline location of the lake on an annual scale;

[0078] Step 210: Compare the lake shoreline positions on an annual scale between adjacent years to calculate the annual rate of shoreline change. This further includes the following steps:

[0079] Step 220: Label each shoreline with time attributes and the percentage of effective observed pixels to obtain lake shoreline datasets at monthly and annual scales.

[0080] Furthermore, calculating the annual rate of change of the lake shoreline involves the following steps:

[0081] A linear best trend fit based on the least squares principle is performed on the change distance of all historical shoreline data relative to the baseline, and the slope of the fit is defined as the rate of change of the shoreline.

[0082] For example, lake shoreline expansion due to climate change poses safety hazards, potentially submerging surrounding agricultural and engineering facilities and increasing regional ecological security risks. Therefore, annual-scale lake shorelines are extracted based on the lake's maximum boundary, and the annual rate of shoreline change is calculated to give it practical application significance. Using the shoreline position of the earliest year as a benchmark, the change distance of all historical shoreline data relative to the benchmark is fitted with a linear best trend based on the least squares principle; the slope of the fit is defined as the shoreline change rate.

[0083] Figure 5This is a structural diagram of an optical remote sensing data lake shoreline detection device according to an embodiment of this application.

[0084] This application also provides an optical remote sensing data lake shoreline detection device for implementing the optical remote sensing data lake shoreline detection method described in any of the above embodiments, comprising an input module 501, a determination module 502, and an output module 503.

[0085] The input module is used to receive the dataset of the region to be detected.

[0086] The determining module is used for at least one of the following functions:

[0087] Monthly imagery is determined based on the dataset.

[0088] The shoreline for the current month is determined based on monthly imagery.

[0089] Compare the location of the lake shoreline on an annual scale.

[0090] Determine the annual rate of change of the lake shoreline.

[0091] Determine the shoreline obscured by clouds based on the location of the shoreline in the preceding and following months.

[0092] The output module is used to output the result of the determination module.

[0093] The specific methods for implementing the functions of the controller sending module, controller determining module, and controller receiving module are as described in the various method embodiments of this application, and will not be repeated here.

[0094] Figure 6 This is a flowchart of a method for detecting shoreline changes using high-resolution optical remote sensing data in an embodiment of this application.

[0095] like Figure 6 As shown, this application addresses the problems of low accuracy and low automation in the detection of lake shorelines and their changes in the field of remote sensing technology by using a process of monthly image synthesis, water index calculation, water pixel determination, lake shoreline extraction based on spatiotemporal context, and determination of lake shoreline change rate. The invention aims to extract lake water pixels based on dynamic thresholding and voting methods, and then delineate the lake shoreline on a monthly / annual scale to detect changes in lake shorelines caused by climate change. This method has high accuracy and good effect in detecting shoreline changes.

[0096] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] Therefore, this application also proposes a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the methods described in any embodiment of this application.

[0098] Furthermore, this application also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any embodiment of this application.

[0099] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0103] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0104] The electronic device 600 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application. It includes: one or more processors 620; and a storage device 610 for storing one or more programs, which, when executed by the one or more processors 620, enable the one or more processors 620 to implement the optical remote sensing data shoreline detection method provided in the embodiments of this application. This method includes:

[0105] Find the monthly median value image for a selected region in a single month;

[0106] Seven water body indices, namely NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015 and HRWI, are calculated for each pixel in the selected area based on the mid-month value image.

[0107] The dynamic threshold method is used to determine the threshold of the corresponding water body index; each water body index has a corresponding water body index threshold.

[0108] The water body index is compared with the corresponding water body index threshold. A water body index greater than the water body index threshold is considered a water body pixel.

[0109] If the water index is greater than half of the elements that are identified as water body pixels, then that element is a water body pixel, and the shoreline for that month is defined accordingly.

[0110] The electronic device 600 also includes an input device 630 and an output device 640; the processor 620, storage device 610, input device 630 and output device 640 in the electronic device can be connected by a bus or other means, as shown in the figure, which is connected by a bus 650.

[0111] Storage device 610, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and module units, such as the program instructions corresponding to the cloud bottom height determination method in the embodiments of this application. Storage device 610 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on terminal usage. Furthermore, storage device 610 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, storage device 610 may further include memory remotely located relative to processor 620, and these remote memories can be connected via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0112] Input device 630 can be used to receive input digital, character, or voice information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 640 may include electronic devices such as a display screen and a speaker.

[0113] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0114] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for detecting lake shorelines using optical remote sensing data, characterized in that, Includes the following steps: Find the monthly median value image for a selected region in a single month; For each pixel in the selected area based on the mid-month value image, calculate an odd number of water body indices of at least 3 from NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015, and HRWI. ； ； ； ； The water index is calculated based on the atmospheric top reflectance in the multispectral-near-infrared band of Landsat series satellites. The dynamic threshold method is used to determine the threshold of the corresponding water body index; each water body index has a corresponding water body index threshold. Compare each water index with its corresponding water index threshold, and calculate the number of water indices that are greater than the water index threshold. If the number of such pixels is greater than half of the total number of water body indices, the pixel is considered a water body pixel. The shoreline for the current month is defined based on water body pixels and non-water body pixels.

2. The method for detecting lake shorelines using optical remote sensing data according to claim 1, characterized in that, Following the steps described above, the following steps are also included: Select months when the lake shoreline cannot be accurately determined due to cloud cover; Using the spatiotemporal context reasoning method, the shoreline of the current month can be inferred by comparing the shorelines of the preceding and following months.

3. The method for detecting lake shorelines using optical remote sensing data according to claim 1, characterized in that, Following the steps described above, the following steps are also included: Find the maximum boundary of the lake in a given year by analyzing the shoreline data for each month of the year. The maximum boundary of the lake is used as the shoreline location of the lake on an annual scale; By comparing the shoreline positions of lakes on an annual scale in adjacent years, the annual rate of change of the lake shoreline can be calculated.

4. The method for detecting lake shorelines using optical remote sensing data according to claim 1, characterized in that, Calculate the median image of a single month for which there is no snowfall.

5. The method for detecting lake shorelines using optical remote sensing data according to claim 1, characterized in that, Calculate the seven water body indices: NDWI1, NDWI2, TCW, AWEI1, AWEI2, WI2015, and HRWI. A pixel is considered a water body pixel if the water body index votes are greater than 5 / 7.

6. The method for detecting lake shorelines using optical remote sensing data according to claim 2, characterized in that, Following the steps described above, the following steps are also included: Each shoreline is labeled with temporal attributes and the percentage of effective observed pixels to create lake shoreline datasets at monthly and annual scales.

7. The method for detecting lake shorelines using optical remote sensing data according to claim 3, characterized in that, The calculation of the annual rate of change of the lake shoreline specifically includes the following steps: A linear best trend fit based on the least squares principle is performed on the change distance of all historical shoreline data relative to the baseline, and the slope of the fit is defined as the rate of change of the shoreline.

8. An optical remote sensing data shoreline detection device, used to implement the optical remote sensing data shoreline detection method according to any one of claims 1-7, characterized in that, It includes an input module, a determination module, and an output module; The input module is used to receive the dataset of the region to be detected; The determining module is used for at least one of the following functions: Determine monthly imagery based on the dataset; The shoreline for the current month is determined based on monthly imagery; By comparing the location of the shoreline on an annual scale, the annual rate of change of the shoreline can be determined. Determine the shoreline obscured by clouds based on the location of the shoreline in the preceding and following months; The output module is used to output the result of the determination module.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

10. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-7.

Images