Wetland restoration status identification method and system based on remote sensing technology

Abstract

The present application discloses a method and system for identifying wetland restoration status based on remote sensing technology, which relates to the field of image data processing. The method includes: acquiring a remote sensing image corresponding to a target area; preprocessing the remote sensing image to obtain a first image to be processed; performing edge detection on the first image to be processed, and recording each closed area formed by an edge as a detection area to obtain a second image to be processed; performing feature detection on the second image to be processed, identifying the field area in the remote sensing image, and excluding the field area from the remote sensing image to obtain a third image to be processed; performing classification based on the third image to be processed to obtain a wetland area; and determining the wetland restoration status of the target area based on the range change of the wetland area. The method and system provided by the present application can reduce the interference of fields in remote sensing images on wetland classification, thereby improving the accuracy of wetland restoration status identification.

Description

Technical Field

[0001] The present application relates to the field of image data processing, and more specifically, to a method and system for identifying wetland restoration status based on remote sensing technology. Background Art

[0002] Wetlands are important natural resources and land types, and they are also the concrete manifestation of the natural ecological environment. In the two decades from the late 20th century to the early 21st century, my country's wetland ecosystem suffered significant damage. Therefore, it is extremely necessary to strengthen wetland protection.

[0003] When protecting wetland ecosystems, remote sensing technology can be used to conduct real-time, dynamic monitoring of wetlands and their surroundings, thereby identifying the status of wetland restoration. Currently, iterative self-organizing clustering methods are commonly used to delineate wetland areas in remote sensing images for monitoring purposes. However, when fields are located near wetlands, their color is similar to that of the wetlands, and the two have similar topography and band reflectance characteristics in remote sensing images. This makes it difficult to distinguish between closely spaced fields and wetlands with similar colors using iterative self-organizing clustering methods, leading to the misclassification of fields as wetlands.

[0004] Based on this, it is necessary to study a more accurate and reliable wetland restoration status identification method and system based on remote sensing technology to reduce the interference of fields on wetland classification and improve the accuracy of wetland restoration status identification results. Summary of the Invention

[0005] To solve the above problems, one aspect of the embodiments of this specification provides a method for identifying wetland restoration status based on remote sensing technology, the method comprising:

[0006] Acquiring a remote sensing image corresponding to a target area, wherein the remote sensing image is acquired within a specified time period;

[0007] Preprocessing the remote sensing image to obtain a first image to be processed;

[0008] Performing edge detection on the first image to be processed, and recording each closed area formed by an edge as a detected area, to obtain a second image to be processed;

[0009] performing feature detection on the second image to be processed, identifying a field area in the remote sensing image, and excluding the field area from the remote sensing image to obtain a third image to be processed;

[0010] Performing classification based on the third image to be processed to obtain a wetland area;

[0011] The wetland restoration status of the target area is determined based on the changes in the scope of the wetland area.

[0012] In some embodiments, the performing feature detection on the second image to be processed to identify the field area in the remote sensing image includes:

[0013] detecting color features of the area to be detected to obtain a suspected field area;

[0014] Dividing the suspected field area into a field area, a questionable area, and a non-field area according to edge shape characteristics of the suspected field area;

[0015] The surrounding area of the question area is identified, and it is determined whether the question area belongs to a field area or a non-field area based on the situation of the adjacent areas around the question area.

[0016] In some embodiments, detecting the color characteristics of the area to be detected to obtain a suspected field area includes:

[0017] For each area to be measured, the total number of pixels in the area to be measured and the grayscale value of each pixel are obtained;

[0018] Calculating the similarity of each pixel in the area to be measured to the overall color of the area to be measured;

[0019] Based on the similarity, calculating the color consistency within the area to be measured;

[0020] The area to be tested with color consistency greater than a first preset threshold is marked as a suspected field area.

[0021] In some embodiments, the similarity of each pixel in the area to be measured to the overall color of the area to be measured, and the color consistency in the area to be measured are obtained based on the following method:

[0022] Calculate the average grayscale value in the area to be measured;

[0023] Obtaining a first parameter based on a ratio of a grayscale value of each pixel in the area to be measured to the average grayscale value;

[0024] Normalizing the first parameter to obtain a similarity between each pixel and the overall color of the area to be measured;

[0025] The average value of the similarity of all pixels in the area to be measured relative to the overall color of the area to be measured is calculated to obtain the color consistency of the area to be measured.

[0026] In some embodiments, dividing the suspected field area into a field area, a questionable area, and a non-field area based on edge shape features of the suspected field area includes:

[0027] Obtaining the major diameter, minor diameter, number of pixels, and pixel length of the edge of the suspected field area;

[0028] Calculating the area similarity between the suspected field area and the rectangle based on the major diameter, minor diameter, and number of pixels corresponding to the suspected field area;

[0029] Calculating a pixel length difference of a relative edge based on the pixel length of the edge of the region corresponding to the suspected field region;

[0030] determining a shape representation of the suspected field area according to the area similarity and the pixel length difference of the relative edges;

[0031] The suspected field area whose shape performance is less than the second preset threshold is divided into a non-field area; the suspected field area whose shape performance is greater than the third preset threshold is divided into a field area; the suspected field area whose shape performance is greater than or equal to the second preset threshold and less than or equal to the third preset threshold is divided into a questionable area.

[0032] In some embodiments, determining the shape of the suspected field area based on the area similarity and the pixel length difference between the relative edges includes:

[0033] The pixel length differences of the relative edges are normalized, and the product of the normalization result and the area similarity is used as the shape representation of the suspected field area.

[0034] In some embodiments, identifying the surrounding area of the question area and determining whether the question area is a field area or a non-field area based on the situation of the adjacent areas around the question area includes:

[0035] Based on the distance from the center of each adjacent area to the center of the question area and the average of the distances from the center of each adjacent area to the center of the question area, the distance representation of each adjacent area relative to other adjacent areas is obtained;

[0036] Based on the shape performance of each adjacent region and the maximum and minimum values of the shape performances corresponding to all adjacent regions adjacent to the question region, a shape performance difference of each adjacent region relative to the surrounding adjacent regions of the question region is obtained;

[0037] Based on the distance representation of each adjacent region relative to other adjacent regions and the shape difference of each adjacent region relative to the surrounding adjacent regions of the question region, a normalized feature value corresponding to each adjacent region is obtained;

[0038] Calculating the mean of the normalized feature values corresponding to all adjacent regions adjacent to the question region to obtain the feature representation of the question region;

[0039] The question area whose characteristic performance is greater than or equal to a fourth preset threshold is marked as a field area, and the question area whose characteristic performance is less than the fourth preset threshold is marked as a non-field area.

[0040] In some embodiments, the distance representation of the adjacent region relative to other adjacent regions is obtained based on the following method:

[0041] For the adjacent region m adjacent to the question region O, calculate the distance l from the center of the adjacent region m to the center of the question region O m The average value of the distance from the center of each adjacent area to the center of the question area O Ratio

[0042] The ratio It is expressed as the distance between the adjacent area m and other adjacent areas.

[0043] In some embodiments, the shape difference between the adjacent region and the surrounding adjacent regions of the question region is obtained based on the following method:

[0044] For the adjacent region m adjacent to the question region O, calculate the shape representation X of the adjacent region m m The minimum value min(X O,t ), and the maximum value max(X O,t ) and minimum value min(X O,t ) second difference;

[0045] The ratio of the first difference to the second difference is used as the shape representation difference of the adjacent region m.

[0046] Another aspect of the embodiments of this specification further provides a wetland restoration status identification system based on remote sensing technology, the system comprising:

[0047] An acquisition module is used to acquire a remote sensing image corresponding to a target area, wherein the remote sensing image is acquired within a specified time period;

[0048] A preprocessing module, configured to preprocess the remote sensing image to obtain a first image to be processed;

[0049] an edge detection module, configured to perform edge detection on the first image to be processed, and record each closed area formed by an edge as a detected area, to obtain a second image to be processed;

[0050] a feature detection module, configured to perform feature detection on the second image to be processed, identify a field area in the remote sensing image, and exclude the field area from the remote sensing image to obtain a third image to be processed;

[0051] a classification module, configured to perform classification based on the third image to be processed to obtain a wetland area;

[0052] The wetland restoration status determination module is used to determine the wetland restoration status of the target area according to the range change of the wetland area.

[0053] The beneficial effects of the wetland restoration status identification method and system based on remote sensing technology provided in the embodiments of this specification may include at least:

[0054] (1) By excluding the field area in the remote sensing image and then performing wetland identification on the remaining image, the interference of the field in the remote sensing image on the wetland classification can be effectively reduced, thereby improving the accuracy of wetland restoration status identification;

[0055] (2) By identifying the field areas in the remote sensing image based on color features, shape features and the conditions of the surrounding adjacent areas, the field areas in the remote sensing image can be accurately and effectively identified.

[0056] Additional features are described in part in the following description. The present invention will become apparent to those skilled in the art by reviewing the following and accompanying drawings, or by following the examples or practices. The features of this specification may be realized and obtained by practicing or using the various aspects of the methods, tools, and combinations described in the following detailed examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same numbers represent the same structures, wherein:

[0058] Figure 1 is a schematic diagram of an exemplary application scenario of a wetland restoration status identification system based on remote sensing technology according to some embodiments of this specification;

[0059] Figure 2 is an exemplary module diagram of a wetland restoration status identification system based on remote sensing technology according to some embodiments of this specification;

[0060] Figure 3 is an exemplary flow chart of a wetland restoration status identification method based on remote sensing technology according to some embodiments of this specification;

[0061] Figure 4 is a schematic diagram of the pre-processed image effect according to some embodiments of this specification;

[0062] Figure 5 It is a schematic diagram of edge detection image effects according to some embodiments of this specification. DETAILED DESCRIPTION

[0063] To more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0064] It should be understood that the terms "system," "device," "unit," and / or "module" used in this specification are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0065] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0066] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0067] The wetland restoration status identification method and system based on remote sensing technology provided in the embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0068] Figure 1 This is a schematic diagram of an exemplary application scenario of a wetland restoration status identification system based on remote sensing technology according to some embodiments of this specification.

[0069] Reference Figure 1 In some embodiments, the application scenario 100 of the wetland restoration status identification system based on remote sensing technology may include a remote sensing image acquisition device 110, a storage device 120, a processing device 130, a terminal device 140, and a network 150. The various components in the application scenario 100 can be connected in a variety of ways. For example, the remote sensing image acquisition device 110 can be connected to the storage device 120 and / or the processing device 130 through the network 150, or directly connected to the storage device 120 and / or the processing device 130. For another example, the storage device 120 can be directly connected to the processing device 130 or connected through the network 150. For another example, the terminal device 140 can be connected to the storage device 120 and / or the processing device 130 through the network 150, or directly connected to the storage device 120 and / or the processing device 130.

[0070] The remote sensing image acquisition device 110 can be used to acquire a remote sensing image corresponding to the target area, wherein the remote sensing image is acquired within a specified time period, and the remote sensing image can reflect the wetland conditions of the target area. In some embodiments, the remote sensing image acquisition device 110 can acquire a remote sensing image of the target area through GF-2 (Gaofen-2). In some embodiments, the remote sensing image can be acquired through GF-2 within a specified time period (for example, a time period when field vegetation grows well), thereby ensuring that the wetland area and field area in the remote sensing image have relatively obvious features, so as to facilitate classification research. In some embodiments, the remote sensing image acquisition device 110 can have an independent power supply, which can send the acquired remote sensing image to other components in the application scenario 100 (for example, storage device 120, processing device 130, terminal device 140) via wired or wireless means (for example, Bluetooth, WiFi, etc.).

[0071] In some embodiments, the remote sensing image acquisition device 110 can transmit the acquired remote sensing images to the storage device 120, the processing device 130, the terminal device 140, etc. via the network 150. In some embodiments, the remote sensing images acquired by the remote sensing image acquisition device 110 can be processed by the processing device 130. For example, the processing device 130 can identify a field region within the target area based on the remote sensing image, exclude the field region from the remote sensing image, and then classify the image after excluding the field region to identify a wetland region. In some embodiments, the data processed by the processing device 130 can be transmitted to the storage device 120 for recording or to the terminal device 140 for feedback to the user.

[0072] The network 150 can facilitate the exchange of information and / or data. The network 150 may include any suitable network capable of facilitating the exchange of information and / or data for the application scenario 100. In some embodiments, at least one component of the application scenario 100 (e.g., the remote sensing image acquisition device 110, the storage device 120, the processing device 130, the terminal device 140) can exchange information and / or data with at least one other component in the application scenario 100 via the network 150. For example, the processing device 130 can obtain remote sensing images captured for a target area from the remote sensing image acquisition device 110 and / or the storage device 120 via the network 150. For another example, the processing device 130 can obtain user operation instructions from the terminal device 140 via the network 150. Exemplary operation instructions may include, but are not limited to, accessing remote sensing images, reading field areas and / or wetland areas determined based on the remote sensing images, and the like.

[0073] In some embodiments, network 150 may be any form of wired or wireless network, or any combination thereof. By way of example only, network 150 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a Bluetooth network, a ZigBee network, a near field communication (NFC) network, or the like, or any combination thereof. In some embodiments, network 150 may include at least one network access point, and at least one component of application scenario 100 may connect to network 150 via the access point to exchange data and / or information.

[0074] The storage device 120 can store data, instructions, and / or any other information. In some embodiments, the storage device 120 can store data obtained from the remote sensing image acquisition device 110, the processing device 130, and / or the terminal device 140. For example, the storage device 120 can store remote sensing images acquired by the remote sensing image acquisition device 110; for another example, the storage device 120 can store data processed by the processing device 130 (such as the first image to be processed, the second image to be processed, the third image to be processed, etc., referred to below). In some embodiments, the storage device 120 can store data and / or instructions used by the processing device 130 to execute or complete the exemplary methods described herein. In some embodiments, the storage device 120 can include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), or any combination thereof. Exemplary mass storage can include magnetic disks, optical disks, solid-state disks, and the like. In some embodiments, the storage device 120 can be implemented on a cloud platform. By way of example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or any combination thereof.

[0075] In some embodiments, the storage device 120 can be connected to the network 150 to communicate with at least one other component in the application scenario 100 (e.g., the remote sensing image acquisition device 110, the processing device 130, and the terminal device 140). At least one component in the application scenario 100 can access data, instructions, or other information stored in the storage device 120 via the network 150. In some embodiments, the storage device 120 can be directly connected to or communicate with one or more components in the application scenario 100 (e.g., the remote sensing image acquisition device 110 and the terminal device 140). In some embodiments, the storage device 120 can be part of the remote sensing image acquisition device 110 and / or the processing device 130.

[0076] The processing device 130 can process data and / or information obtained from the remote sensing image acquisition device 110, the storage device 120, the terminal device 140, and / or other components of the application scenario 100. In some embodiments, the processing device 130 can obtain remote sensing images from any one or more of the remote sensing image acquisition device 110, the storage device 120, or the terminal device 140, process the remote sensing images to identify field areas within the target area, exclude the field areas from the remote sensing images, and then classify the images after excluding the field areas to obtain wetland areas. In some embodiments, the processing device 130 can retrieve pre-stored computer instructions from the storage device 120 and execute the computer instructions to implement the remote sensing technology-based wetland restoration status identification method described herein.

[0077] In some embodiments, the processing device 130 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processing device 130 may be local or remote. For example, the processing device 130 may access information and / or data from the remote sensing image acquisition device 110, the storage device 120, and / or the terminal device 140 via the network 150. For another example, the processing device 130 may be directly connected to the remote sensing image acquisition device 110, the storage device 120, and / or the terminal device 140 to access information and / or data. In some embodiments, the processing device 130 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud cloud, a multi-cloud, or any combination thereof.

[0078] The terminal device 140 can receive, transmit, and / or display data. The received data may include data collected by the remote sensing image acquisition device 110, data stored in the storage device 120, data processed by the processing device 130, and the like. For example, the data received and / or displayed by the terminal device 140 may include remote sensing images acquired by the remote sensing image acquisition device 110, and field areas, wetland areas, and the like determined by the processing device 130 based on the remote sensing images. The transmitted data may include user input data and instructions. For example, the terminal device 140 may transmit user-input operation instructions to the remote sensing image acquisition device 110 via the network 150 to control the remote sensing image acquisition device 110 to perform corresponding remote sensing image acquisition. For another example, the terminal device 140 may transmit user-input processing instructions to the processing device 130 via the network 150 to control the processing device 130 to perform corresponding data processing.

[0079] In some embodiments, the terminal device 140 may include a mobile device 141, a tablet computer 142, a laptop computer 143, or the like, or any combination thereof. For example, the mobile device 141 may include a mobile phone, a personal digital assistant (PDA), a dedicated mobile terminal, or the like, or any combination thereof. In some embodiments, the terminal device 140 may include an input device (e.g., a keyboard, a touch screen), an output device (e.g., a display, a speaker), or the like. In some embodiments, the processing device 130 may be part of the terminal device 140.

[0080] It should be noted that the above description of application scenario 100 is for illustrative purposes only and does not limit the scope of application of this specification. Those skilled in the art will be able to make various modifications and alterations to application scenario 100 under the guidance of this specification. However, such modifications and alterations remain within the scope of this specification. For example, remote sensing image acquisition device 110 may include more or fewer functional components.

[0081] Figure 2 This is a module diagram of a wetland restoration status identification system based on remote sensing technology according to some embodiments of this specification. In some embodiments, Figure 2 The wetland restoration status identification system 200 based on remote sensing technology can be applied to Figure 1 The application scenario 100 shown, for example, can be configured in the form of software and / or hardware to the processing device 130 and / or the terminal device 140, so as to process the remote sensing image acquired by the remote sensing image acquisition device 110, and determine the field area in the target area based on the remote sensing image, and then exclude the field area from the remote sensing image, and finally classify the image after excluding the field area to obtain the wetland area.

[0082] Reference Figure 2In some embodiments, the wetland restoration status identification system 200 based on remote sensing technology may include an acquisition module 210, a preprocessing module 220, an edge detection module 230, a feature detection module 240, a classification module 250 and a wetland restoration status determination module 260.

[0083] The acquisition module 210 may be configured to acquire a remote sensing image corresponding to a target area, wherein the remote sensing image is acquired within a specified time period.

[0084] The preprocessing module 220 may be configured to preprocess the remote sensing image to obtain a first image to be processed.

[0085] The edge detection module 230 may be configured to perform edge detection on the first image to be processed, and record each closed area formed by an edge as a detected area to obtain a second image to be processed.

[0086] The feature detection module 240 can be used to perform feature detection on the second image to be processed, identify the field area in the remote sensing image, and exclude the field area from the remote sensing image to obtain a third image to be processed.

[0087] The classification module 250 may be configured to perform classification based on the third image to be processed to obtain a wetland area.

[0088] The wetland restoration status determination module 260 may be configured to determine the wetland restoration status of the target area according to changes in the range of the wetland area.

[0089] For more details about the above modules, please refer to other places in this manual (for example Figures 3 to 5 part and its related description), which will not be repeated here.

[0090] It should be understood that Figure 2The illustrated remote sensing-based wetland restoration status identification system 200 and its modules can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented using hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will appreciate that the above-described methods and systems can be implemented using computer-executable instructions and / or contained in processor control code, such as provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can be implemented not only with hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays and programmable logic devices, but can also be implemented using software executed by various types of processors, or by a combination of the above-described hardware circuits and software (e.g., firmware).

[0091] It should be noted that the above description of the wetland restoration status identification system 200 based on remote sensing technology is provided for illustrative purposes only and is not intended to limit the scope of this specification. It is understood that those skilled in the art can, based on the description of this specification, arbitrarily combine the modules or form subsystems connected with other modules without departing from the principles of this specification. For example, Figure 2 The acquisition module 210, pre-processing module 220, edge detection module 230, feature detection module 240, classification module 250, and wetland restoration status determination module 260 described above can be different modules in one system, or one module can implement the functions of two or more of the above modules. For another example, the wetland restoration status identification system 200 based on remote sensing technology can also include other modules. Such variations are all within the scope of protection of this specification. In some embodiments, the aforementioned modules can be part of the processing device 130 and / or the terminal device 140.

[0092] Figure 3 This is an exemplary flow chart of a method for identifying the status of a wetland restoration based on remote sensing technology according to some embodiments of this specification. In some embodiments, the method 300 for identifying the status of a wetland restoration based on remote sensing technology can be executed by processing logic, which can include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, etc.), software (instructions running on a processing device to perform hardware simulation), etc., or any combination thereof. In some embodiments, Figure 3One or more operations in the flowchart of the remote sensing technology-based wetland restoration status identification method 300 can be performed by Figure 1 The processing device 130 and / or terminal device 140 shown are implemented. For example, the remote sensing-based wetland restoration status identification method 300 can be stored in the storage device 120 in the form of instructions and called and / or executed by the processing device 130 and / or terminal device 140. The following describes the execution process of the remote sensing-based wetland restoration status identification method 300 using the processing device 130 as an example.

[0093] Reference Figure 3 In some embodiments, the remote sensing-based wetland restoration status identification method 300 may include:

[0094] Step 310 , obtaining a remote sensing image corresponding to the target area, wherein the remote sensing image is acquired within a specified time period. In some embodiments, step 310 may be performed by the acquisition module 210 .

[0095] In some embodiments, the remote sensing image acquired by the remote sensing image acquisition device 110 for the target area may be stored in the storage device 120, and the acquisition module 210 may acquire the remote sensing image corresponding to the target area from the storage device 120, wherein the remote sensing image was acquired within a specified time period. In some embodiments, the acquisition module 210 may be in communication with the remote sensing image acquisition device 110, and the acquisition module 210 may directly acquire the remote sensing image corresponding to the target area from the remote sensing image acquisition device 110.

[0096] In this specification, a target area refers to an area whose wetland restoration status needs to be identified. In some embodiments, the aforementioned designated time period may refer to a period when field vegetation is growing well, such as May to July. It will be appreciated that during this designated time period, both field vegetation and wetland vegetation exhibit distinct characteristics, and accordingly, remote sensing images acquired during this designated time period also exhibit distinct image features. Remote sensing images acquired during this designated time period enable more accurate image analysis and classification.

[0097] Step 320 , pre-processing the remote sensing image to obtain a first image to be processed. In some embodiments, step 320 may be performed by the pre-processing module 220 .

[0098] After the remote sensing image corresponding to the aforementioned target area is obtained by the acquisition module 210, it can be pre-processed by grayscale conversion, filtering, etc. by the pre-processing module 220. Specifically, in some embodiments, the pixel values of each channel (red, green, and blue) of the remote sensing image can be weighted averaged to obtain the grayscale value corresponding to each pixel, thereby preserving the details and texture information of the remote sensing image as much as possible.

[0099] In some embodiments, the pre-processing module 220 may perform low-pass filtering on the image obtained after grayscale conversion to obtain a first image to be processed. It should be noted that in the embodiments of this specification, grayscale conversion and low-pass filtering of the remote sensing image can reduce the computational complexity of subsequent processes to a certain extent, and can also smooth the image while preserving edge information in the image, thereby improving image quality.

[0100] In step 330 , edge detection is performed on the first image to be processed, and each closed area formed by an edge is recorded as a detected area to obtain a second image to be processed. In some embodiments, step 330 may be performed by the edge detection module 230 .

[0101] Reference Figure 4 , Figure 4 This is a schematic diagram of the pre-processed image effect according to some embodiments of this specification, that is, a schematic diagram of the first image to be processed. After obtaining the first image to be processed, the edge detection module 230 can use the Canny algorithm to perform edge detection on it, and obtain the following Figure 5 Schematic diagram of edge detection image effect shown.

[0102] Furthermore, the edge detection module 230 may record each closed area formed by an edge as a region to be detected, to obtain a second image to be processed.

[0103] Step 340 : Perform feature detection on the second image to be processed, identify the field area in the remote sensing image, and exclude the field area from the remote sensing image to obtain a third image to be processed. In some embodiments, step 340 may be performed by the feature detection module 240 .

[0104] After obtaining the second image to be processed through the aforementioned processing, the feature detection module 240 may perform feature detection on the second image to be processed, thereby identifying the field area in the remote sensing image.

[0105] In remote sensing images, crops within fields are often human-dominated and largely identical, resulting in a uniform color appearance. In contrast, wetlands contain a wide variety of plant species, resulting in varying colors. Furthermore, fields are generally human-planned and rectangular in shape, while wetlands are often naturally formed or have irregular shapes influenced by the natural environment. Therefore, in some embodiments, when fields and wetlands are mixed together, the fields can be excluded from remote sensing images based on these characteristics.

[0106] Based on the above rules, in some embodiments, the feature detection module 240 can first detect the color features of the aforementioned area to be tested to obtain a suspected field area; then, based on the edge shape features of the suspected field area, the suspected field area is divided into a field area, a question area, and a non-field area; finally, the surrounding areas of the question area are identified, and each question area is determined to belong to a field area or a non-field area through the situation of the adjacent areas around the question area.

[0107] Specifically, in some embodiments, for each area to be tested, the feature detection module 240 can obtain the total number of pixels in the area to be tested and the grayscale value of each pixel; then calculate the similarity of each pixel in the area to be tested relative to the overall color of the area to be tested; and based on the similarity, calculate the color consistency in the area to be tested; finally, mark the area to be tested whose color consistency is greater than a first preset threshold as a suspected field area.

[0108] It is understandable that fields, due to human planning, usually have the same crop planted in a single field; while wetlands, due to the need for natural environmental diversity, require a variety of plants. Therefore, the color of fields in remote sensing images is usually relatively simple, while the color of wetlands in remote sensing images is diverse and changes frequently. Therefore, field areas usually have the same grayscale level on the grayscale image (that is, the grayscale level of each pixel in the field area is relatively small compared to the average grayscale level in the area); wetland areas have multiple grayscale levels on the grayscale image and are randomly distributed (that is, the grayscale levels of many pixels in the wetland area are significantly different from the average grayscale level in the area).

[0109] Based on the above characteristics, the following formula can be constructed to preliminarily screen out the field areas in the remote sensing image:

[0110]

[0111] Among them, S w represents the color consistency of the area to be measured w (also called color performance, which represents the relative relationship between the grayscale of the pixels in the area to be measured and the average grayscale in the area); n is the total number of pixels in the area to be measured w; h i represents the gray value of pixel i in the area to be measured w; exp represents the exponential function with the natural constant e as the base, which can be obtained by exp(-f(x)) to calculate the f(x) part (i.e. ) to perform negative correlation normalization.

[0112] In the above formula, Represents the average gray value in the area to be measured w; Indicates the similarity between the color (grayscale) of pixel i and the overall color (average grayscale) of the test area w, ranging from 0 to 1. The closer the value is to 1, the closer the overall color of pixel i is to the test area w, and the closer the value is to 0, the greater the difference in overall color between pixel i and the test area w. That is S w It indicates the color consistency within the tested area w, and its value range is from 0 to 1. The smaller the value, the greater the color difference within the tested area w, the worse the color consistency, and the smaller the possibility of belonging to the field area; the closer the value is to 1, the smaller the color difference within the tested area w, the higher the color consistency, and the greater the possibility of belonging to the field area.

[0113] Specifically, in the embodiment of this specification, the feature detection module 240 can determine the similarity of each pixel point in the test area to the overall color of the test area, as well as the color consistency in the test area, by:

[0114] First, the feature detection module 240 can calculate the average grayscale value in the area to be detected by dividing the sum of the grayscale values of all pixels in the area to be detected by the number of pixels in the area to be detected. Then, the feature detection module 240 can obtain the first parameter based on the ratio of the gray value of each pixel point in the detection area to the average gray value. Furthermore, the feature detection module 240 can perform normalization processing on the first parameter to obtain the similarity of each pixel point to the overall color of the area to be detected. Finally, the feature detection module 240 can calculate the average value of the similarity of all pixels in the area to be detected relative to the overall color of the area to be detected. The color consistency in the area to be tested is obtained.

[0115] In some embodiments of the present specification, the area to be tested with a color consistency greater than a first preset threshold can be marked as a suspected field area, and further analyzed in subsequent steps to determine the field area in the remote sensing image corresponding to the target area. As an example only, in some embodiments, the first preset threshold can be set to 0.7. In other words, the color consistency S w The tested area with a value greater than 0.7 may belong to a field area and needs to be further screened and checked. Therefore, in some embodiments, the color consistency S of each tested area is calculated through the above steps. w After that, all color consistency S w The tested areas with a value greater than 0.7 are marked as suspected field areas.

[0116] Furthermore, after obtaining the aforementioned suspected field regions, the feature detection module 240 may further divide each suspected field region into a field region, a questionable region, and a non-field region according to edge shape features of the suspected field region.

[0117] Since farmland is primarily cultivated through human planning and is often maintained during labor, wetlands are mostly naturally formed. Although there are some artificially planned wetlands, the evolution of the natural environment has caused them to deviate from the original plan. Therefore, farmland areas appear approximately rectangular in remote sensing images, and their area can be replaced by the rectangular area calculation formula: the pixel area within the field area is roughly equal to the product of the long and short diameters of the area, and the field also has the corresponding rectangular feature of two sets of approximately equal opposite sides. However, wetland areas appear irregular in remote sensing images, and their pixel area and the product of the long and short diameters may or may not be equal, but it is impossible for all opposite sides to be approximately equal.

[0118] Based on this, in some embodiments, the following formula model can be constructed to further determine the field area according to the shape characteristics of each suspected field area:

[0119]

[0120] Among them, X v A represents the shape performance of the suspected field area v (i.e., the matching degree between the suspected field area and the rectangular shape feature); v represents the total number of pixels in the suspected field area v; c represents the major axis of the suspected field area v; d represents the minor axis of the suspected field area v; b1, b2, b3, and b4 represent the pixel lengths of the edge of the suspected field area v, respectively; exp represents the exponential function with the natural constant e as the base. Its specific function can be referred to above and will not be repeated here.

[0121] It should be noted that, in this specification, the major axis of a suspected field region v may refer to the length of a straight line segment passing through the geometric center of the suspected field region v and connecting its two farthest endpoints. Similarly, the minor axis of a suspected field region v may refer to the length of a straight line segment passing through the geometric center of the suspected field region v and connecting its two closest endpoints. b1, b2, b3, and b4 represent the pixel lengths of the edges of the suspected field region v, respectively. The edge corresponding to b1 is opposite to the edge corresponding to b3, and the edge corresponding to b2 is opposite to the edge corresponding to b4. In some embodiments, the four edges corresponding to b1, b2, b3, and b4 can be determined based on the directions of the major axis and minor axis. For example, in some embodiments, a maximum inscribed rectangle (or parallelogram) can be determined within the suspected field area v, and two sides of the rectangle (or parallelogram) are parallel to their corresponding major diameters, and the other two sides are parallel to their corresponding minor diameters, so that the four sides corresponding to b1, b2, b3, and b4 are determined based on the intersection of the maximum inscribed rectangle (or parallelogram) and the suspected field area v (the edge line between two adjacent intersection points is regarded as a side of the suspected field area v).

[0122] It should also be noted that in the embodiments of this specification, represents the area similarity between the suspected field region v and the rectangle. The closer this value is to 1, the closer the suspected field region v is to a rectangle in terms of area characteristics. |b1-b3| and |b2-b4| represent the pixel length differences between the two opposite edges of the suspected field region v. The closer this difference is to 0, the closer the suspected field region v is to a rectangle. exp(-|b1-b3|) and exp(-| b 2-b4|) represents the similarity between the suspected field area v and the side length of the rectangle. The closer this value is to 1, the closer the suspected field area v is to the rectangle in terms of side length characteristics. The closer this value is to 0, the less the suspected field area v is like a rectangle in terms of side length characteristics. Shape representation X v The closer it is to 1, the higher the possibility that the suspected field area v belongs to the field area; the shape representation X v The closer it is to 0, the lower the possibility that the suspected field area v belongs to the field area.

[0123] Specifically, in some embodiments, the feature detection module 240 can obtain the major diameter c, minor diameter d, and number of pixels A corresponding to the suspected field area. v And the pixel length of the edge of the area (b1, b2, b3, b4), then based on the long diameter c, short diameter d and number of pixels A corresponding to the suspected field area v , calculate the area similarity between the suspected field area and the rectangle Furthermore, the feature detection module 240 can calculate the pixel length differences of the relative edges |b1-b3| and |b2-b4| based on the pixel lengths (b1, b2, b3, b4) of the area edges corresponding to the suspected field area. Finally, the feature detection module 240 can determine the shape representation of the suspected field area based on the aforementioned area similarity and the pixel length differences of the relative edges. For example, in some embodiments, the feature detection module 240 can normalize the pixel length differences of the relative edges and use the product of the normalization results (exp(-|b1-b3|) and exp(-|b2-b4|)) and the aforementioned area similarity as the shape representation of the suspected field area.

[0124] Furthermore, after obtaining the shape representation of each suspected field area through the above steps, the feature detection module 240 can detect the field area based on the shape representation X. v The suspected field area is divided into field area, question area and non-field area. v The suspected field area smaller than the second preset threshold indicates that the possibility of it belonging to the field area is extremely small, and the feature detection module 240 can classify it as a non-field area; similarly, for the shape representation X v The suspected field area greater than the third preset threshold indicates that it is very likely to belong to the field area, and the feature detection module 240 can classify it as a field area; v A suspected field region with a value greater than or equal to the second preset threshold and less than or equal to the third preset threshold indicates that it may be a field region or a non-field region. Feature detection module 240 may classify it as a questionable region and further analyze it in subsequent steps to determine whether it belongs to a field region or a non-field region. In some embodiments of the present specification, the second preset threshold may be 0.3, and the third preset threshold may be 0.7.

[0125] In some embodiments, the feature detection module 240 may determine whether each questionable region belongs to a field area or a non-field area based on the feature performance of each questionable region relative to surrounding adjacent regions.

[0126] For example, in some embodiments, the characteristic representation of the questionable region may be calculated based on the following formula:

[0127]

[0128] Among them, Q O Indicates the characteristic performance of the question area O; l m represents the distance from the center of the adjacent region m (adjacent to the question region O) to the center of the question region O; represents the average distance between the center of each adjacent area (adjacent to the question area O) and the center of the question area O; X m represents the shape performance of the adjacent region m (adjacent to the query region O) (which can be calculated by the calculation method of the shape performance described above), min(X O,t ) represents the minimum value of the shape of the query area O and each adjacent area, max(X O,t ) represents the maximum value of the shape expression of the question area O and each adjacent area; k represents the total number of adjacent areas corresponding to the question area O; exp represents an exponential function with the natural constant e as the base. Its specific function can be referred to above and will not be repeated here.

[0129] It should be noted that, in this specification, the center of each area mentioned above may refer to the geometric center. In the above formula, represents the distance between the adjacent region m (adjacent to the question region O) and other adjacent regions. Specifically, in some embodiments, for the adjacent region m adjacent to the question region O, the feature detection module 240 may calculate the distance l from the center of the adjacent region m to the center of the question region O. m The average of the distances from the center of each adjacent area to the center of the question area O Ratio Then the ratio The smaller the distance between the adjacent region m (adjacent to the question region O) and other adjacent regions, the closer the adjacent region m (adjacent to the question region O) is to the question region O, and the higher the possibility that they belong to the same region.

[0130] In the above formula, represents the difference in shape performance of the adjacent region m (adjacent to the question region O) relative to all adjacent regions surrounding the question region O. Specifically, in some embodiments, for the adjacent region m adjacent to the question region O, the feature detection module 240 may calculate the shape performance X of the adjacent region m. m The minimum value min(X O,t ) of the first difference (X m -min(X O,t )), and the shape representation maximum value max(X O,t ) and minimum value min(X O,t )'s second difference (max(X O,t )-min(H O,t )), and the ratio of the first difference to the second difference The shape expression difference of the adjacent region m is used. The smaller the shape expression difference, the more similar the shape of the adjacent region m is to the shape of the question region O, and the greater the possibility that the adjacent region m and the question region O belong to the same region. The larger the shape expression difference, the less similar the shape of the adjacent region m and the question region O are, and the less likely the adjacent region m and the question region O belong to the same region.

[0131] Specifically, in some embodiments of the present specification, the feature detection module 240 may identify the surrounding area of the question area in the following manner, and determine whether the question area is a field area or a non-field area based on the conditions of the adjacent areas around the question area:

[0132] First, the feature detection module 240 may determine the surrounding area of the question area. In this specification, the surrounding area of the question area may refer to an area whose minimum distance to the question area is less than a preset threshold (eg, 20 pixels).

[0133] Then, for each question area, the feature detection module 240 can obtain the distance performance of each adjacent area relative to other adjacent areas based on the distance from the center of each adjacent area to the center of the question area and the average of the distances from the centers of each adjacent area to the center of the question area.

[0134] Furthermore, the feature detection module 240 can obtain the shape performance difference of each adjacent area relative to the surrounding adjacent areas of the question area based on the shape performance of each adjacent area and the maximum and minimum values of the shape performance corresponding to all adjacent areas adjacent to the question area.

[0135] Furthermore, the feature detection module 240 can obtain the normalized feature value corresponding to each adjacent region (i.e., ).

[0136] Furthermore, the feature detection module 240 can calculate the mean of the normalized feature values corresponding to all adjacent regions adjacent to the question region. Get the characteristic representation Q of the question area O The characteristic representation of the question area Q O The larger it is, the more fields there are around the question area O, and the greater the possibility that the question area O belongs to a field.

[0137] Finally, the feature detection module 240 may mark the query area with a feature greater than or equal to a fourth preset threshold as a field area, and mark the query area with a feature less than the fourth preset threshold as a non-field area. In some embodiments, the fourth preset threshold may be 0.5.

[0138] Through the above steps, all questionable regions can be analyzed to determine whether they belong to farmland or non-farmland areas. After completing the analysis of all questionable regions, all regions in the remote sensing image corresponding to the target region that may belong to farmland can be obtained. Furthermore, feature detection module 240 can exclude the farmland regions identified through the above process from the remote sensing image corresponding to the target region, thereby obtaining a third image to be processed.

[0139] Step 350 , performing classification based on the third image to be processed to obtain a wetland area. In some embodiments, step 350 may be performed by the classification module 250 .

[0140] In some embodiments, classification module 250 may employ an iterative self-organizing clustering method to classify the third image to be processed, excluding the field interference, thereby classifying various ground features in the remote sensing image corresponding to the target area to determine the wetland area in the remote sensing image. The specific process of using the iterative self-organizing clustering method to determine the wetland area from the remote sensing image is considered prior art and will not be discussed in detail in this specification.

[0141] It can be understood that in this specification, by excluding the field areas in the remote sensing image through the above steps, it is possible to avoid including the field areas in the wetland range during the classification process using the iterative self-organizing clustering method, thereby improving the accuracy of the wetland range identification results and reducing the interference of the field areas on the identification of wetland restoration status.

[0142] Step 360 : Determine the wetland restoration status of the target area based on the range change of the wetland area. In some embodiments, step 360 may be performed by the wetland restoration status determination module 260 .

[0143] Specifically, in some embodiments, the wetland restoration status determination module 260 can determine the wetland restoration status of the target area by comparing the wetland area ranges in remote sensing images collected at different time points. For example, the wetland area range obtained through the aforementioned process can be compared with a reference range or a wetland range obtained in a previous identification.

[0144] Specifically, in some embodiments, an acquisition cycle can be set (for example, it can be set to one week), and then a remote sensing image corresponding to the target area is acquired once through GF-2 in each acquisition cycle, and a binary image of the wetland area in the remote sensing image corresponding to several acquisition cycles is obtained according to the above method (for example, the wetland area determined by the above method is converted to black, and the remaining ground objects are converted to white).

[0145] Furthermore, the wetland restoration status determination module 260 can determine the area of the actual remote sensing area corresponding to a pixel point in the remote sensing image based on the internal and external parameters of GF-2 (such as resolution, orbital height, etc.), and then calculate the actual area of the wetland area in each period by combining the binary image of the wetland area obtained for each period and the area of the remote sensing area corresponding to each image pixel point. Finally, by comparing the changes in the wetland area of the current period with the wetland area of the previous periods, the wetland restoration status of the target area can be determined. If the wetland range in the remote sensing image continues to increase, it means that the wetland restoration effect is good. On the contrary, if the wetland range in the remote sensing image continues to decrease, it means that the wetland is still deteriorating and the protection of the wetland ecological environment needs to be further strengthened.

[0146] In summary, the beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) In the wetland restoration status identification method and system based on remote sensing technology provided in some embodiments of this specification, by excluding the field area in the remote sensing image and then performing wetland identification on the remaining image, the interference of the field in the remote sensing image on the wetland classification can be effectively reduced, thereby improving the accuracy of wetland restoration status identification; (2) In the wetland restoration status identification method and system based on remote sensing technology provided in some embodiments of this specification, by identifying the field area in the remote sensing image based on color features, shape features and the conditions of the surrounding adjacent areas, the field area in the remote sensing image can be accurately and effectively identified.

[0147] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0148] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0149] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0150] In addition, it will be understood by those skilled in the art that various aspects of this specification may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of this specification may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of this specification may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0151] A computer storage medium may include a propagated data signal embodying the computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, or any suitable combination thereof. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium that can be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transfer the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of these.

[0152] The computer program codes required for the operation of the various parts of this specification can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages such as C, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages. The program code can be run entirely on the user's computer, or as a separate software package on the user's computer, or partly on the user's computer and partly on a remote computer, or entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0153] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some embodiments of the invention that are currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing processing device or mobile device.

[0154] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0155] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values are as accurate as possible within the feasible range.

[0156] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0157] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A wetland restoration status identification method based on remote sensing technology, characterized in that: include: Acquiring a remote sensing image corresponding to a target area, wherein the remote sensing image is acquired within a specified time period; Preprocessing the remote sensing image to obtain a first image to be processed; Performing edge detection on the first image to be processed, and recording each closed area formed by an edge as a detected area, to obtain a second image to be processed; performing feature detection on the second image to be processed, identifying a field area in the remote sensing image, and excluding the field area from the remote sensing image to obtain a third image to be processed; The method for identifying a field area in a remote sensing image comprises: detecting color features of the area to be detected to obtain a suspected field area; dividing the suspected field area into a field area, a question area, and a non-field area based on edge shape features of the suspected field area; obtaining a distance representation of each adjacent area relative to other adjacent areas based on the distance from the center of each adjacent area to the center of the question area and the average of the distances from the center of each adjacent area to the center of the question area; obtaining a shape representation difference of each adjacent area relative to surrounding adjacent areas of the question area based on the shape representation of each adjacent area and the maximum and minimum values of the shape representations corresponding to all adjacent areas adjacent to the question area; obtaining a normalized eigenvalue corresponding to each adjacent area based on the distance representation of each adjacent area relative to other adjacent areas and the shape representation difference of each adjacent area relative to surrounding adjacent areas of the question area; calculating the average of the normalized eigenvalues corresponding to all adjacent areas adjacent to the question area to obtain a feature representation of the question area; marking a question area whose feature representation is greater than or equal to a fourth preset threshold as a field area, and marking a question area whose feature representation is less than the fourth preset threshold as a non-field area; Performing classification based on the third image to be processed to obtain a wetland area; The wetland restoration status of the target area is determined based on the changes in the scope of the wetland area.

2. The wetland restoration status identification method based on remote sensing technology according to claim 1, characterized in that: The detecting the color characteristics of the area to be detected to obtain a suspected field area includes: For each area to be measured, the total number of pixels in the area to be measured and the grayscale value of each pixel are obtained; Calculating the similarity of each pixel in the area to be measured to the overall color of the area to be measured; Based on the similarity, calculating the color consistency within the area to be measured; The area to be tested with color consistency greater than a first preset threshold is marked as a suspected field area.

3. The wetland restoration status identification method based on remote sensing technology according to claim 2, characterized in that: The similarity of each pixel in the area to be measured to the overall color of the area to be measured, and the color consistency in the area to be measured are obtained based on the following method: Calculate the average grayscale value in the area to be measured; Obtaining a first parameter based on a ratio of a grayscale value of each pixel in the area to be measured to the average grayscale value; Normalizing the first parameter to obtain a similarity between each pixel and the overall color of the area to be measured; The average value of the similarity of all pixels in the area to be measured relative to the overall color of the area to be measured is calculated to obtain the color consistency of the area to be measured.

4. The wetland restoration status identification method based on remote sensing technology according to claim 3 is characterized in that: The step of dividing the suspected field area into a field area, a questionable area, and a non-field area according to the edge shape characteristics of the suspected field area includes: Obtaining the major diameter, minor diameter, number of pixels, and pixel length of the edge of the suspected field area; Calculating the area similarity between the suspected field area and the rectangle based on the major diameter, minor diameter, and number of pixels corresponding to the suspected field area; Calculating a pixel length difference of a relative edge based on the pixel length of the edge of the region corresponding to the suspected field region; determining a shape representation of the suspected field area according to the area similarity and the pixel length difference of the relative edges; The suspected field area whose shape performance is less than the second preset threshold is divided into a non-field area; the suspected field area whose shape performance is greater than the third preset threshold is divided into a field area; the suspected field area whose shape performance is greater than or equal to the second preset threshold and less than or equal to the third preset threshold is divided into a questionable area.

5. The wetland restoration status identification method based on remote sensing technology according to claim 4 is characterized in that: The determining of the shape of the suspected field area according to the area similarity and the pixel length difference of the relative edges includes: The pixel length differences of the relative edges are normalized, and the product of the normalization result and the area similarity is used as the shape representation of the suspected field area.

6. The wetland restoration status identification method based on remote sensing technology according to claim 4 is characterized in that: The distance representation of the adjacent area relative to other adjacent areas is obtained based on the following method: For questionable areas O Adjacent adjacent areas m , calculate the adjacent area m The center of the question area O The distance from the center and the centers of each adjacent region to the question region O The average distance from the center of Ratio ; The ratio As the adjacent area m The distance relative to other adjacent areas.

7. The wetland restoration status identification method based on remote sensing technology according to claim 4, characterized in that: The shape difference between the adjacent region and the surrounding adjacent regions of the question region is obtained based on the following method: For questionable areas O Adjacent adjacent areas m , calculate the adjacent area m Shape performance With respect to the question area O The minimum value of the shape corresponding to all adjacent adjacent areas The first difference, and the question area O The shape corresponding to all adjacent adjacent areas shows the maximum value and minimum value The second difference of The ratio of the first difference to the second difference is used as the adjacent area m The shape shows the difference.

8. A wetland restoration status identification system based on remote sensing technology, characterized in that: include: An acquisition module is used to acquire a remote sensing image corresponding to a target area, wherein the remote sensing image is acquired within a specified time period; A preprocessing module, configured to preprocess the remote sensing image to obtain a first image to be processed; an edge detection module, configured to perform edge detection on the first image to be processed, and record each closed area formed by an edge as a detected area, to obtain a second image to be processed; a feature detection module, configured to perform feature detection on the second image to be processed, identify a field area in the remote sensing image, and exclude the field area from the remote sensing image to obtain a third image to be processed; The method for identifying a field area in a remote sensing image comprises: detecting color features of the area to be detected to obtain a suspected field area; dividing the suspected field area into a field area, a question area, and a non-field area based on edge shape features of the suspected field area; obtaining a distance representation of each adjacent area relative to other adjacent areas based on the distance from the center of each adjacent area to the center of the question area and the average of the distances from the center of each adjacent area to the center of the question area; obtaining a shape representation difference of each adjacent area relative to surrounding adjacent areas of the question area based on the shape representation of each adjacent area and the maximum and minimum values of the shape representations corresponding to all adjacent areas adjacent to the question area; obtaining a normalized eigenvalue corresponding to each adjacent area based on the distance representation of each adjacent area relative to other adjacent areas and the shape representation difference of each adjacent area relative to surrounding adjacent areas of the question area; calculating the average of the normalized eigenvalues corresponding to all adjacent areas adjacent to the question area to obtain a feature representation of the question area; marking a question area whose feature representation is greater than or equal to a fourth preset threshold as a field area, and marking a question area whose feature representation is less than the fourth preset threshold as a non-field area; a classification module, configured to perform classification based on the third image to be processed to obtain a wetland area; The wetland restoration status determination module is used to determine the wetland restoration status of the target area according to the range change of the wetland area.

Images