Land parcel identification and verification method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the field of artificial intelligence and remote sensing image classification, is applied to the field of intelligent environmental protection, and relates to a land parcel identification and verification method. Preprocessing the to-be-processed remote sensing image to obtain a target remote sensing image; performing land parcel identification processing on the target remote sensing image to obtain an identification result of the target land parcel; obtaining reference data of the target plot based on the longitude and latitude of the target plot; and carrying out comparison verification processing on the identification result of the target land parcel and reference data of the target land parcel to obtain a verification result. The invention further provides a land parcel identification and verification method and device, computer equipment and a storage medium. According to the method, the land parcel crops and the land parcels can be bound, the delimiting precision of the area boundary is effectively improved, the boundary dividing error is reduced, and digital management of large-scale planting and development of popularization related insurance businesses are facilitated.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and remote sensing image classification technology, and in particular to a land parcel identification and verification method, device, computer equipment and storage medium. Background Art

[0002] In traditional plot identification, it is impossible to associate the planted crops with the plots, that is, traditional plot identification cannot divide the plots according to the characteristics of the plot products, and the accuracy of regional boundary demarcation is low, and the error of boundary demarcation is large, which poses a great obstacle to the digital management of large-scale crop planting and the development of related insurance business. Summary of the invention

[0003] The purpose of the embodiments of the present application is to propose a land parcel identification and verification method, apparatus, computer equipment and storage medium to solve the technical problems of low accuracy in identifying the association between land parcel products and land parcels and in delineating regional boundaries, as well as large errors in boundary delineation.

[0004] In order to solve the above technical problems, the present application embodiment provides a land parcel identification and verification method, which adopts the following technical solution:

[0005] Obtain the remote sensing image to be processed of the target plot;

[0006] Preprocessing the remote sensing image to be processed to obtain a target remote sensing image;

[0007] Performing land parcel recognition processing on the target remote sensing image to obtain a recognition result of the target land parcel;

[0008] Determine the reference data of the target plot according to the latitude and longitude of the target plot;

[0009] The recognition result of the target plot is compared and verified with the reference data of the target plot to obtain a verification result.

[0010] Furthermore, the preprocessing includes land boundary demarcation processing and cloud layer analysis processing, and the step of obtaining the remote sensing image to be processed and preprocessing to obtain the target remote sensing image specifically includes:

[0011] Performing the cloud layer analysis on the remote sensing image to be processed to obtain a remote sensing image of the target land;

[0012] The target land remote sensing image is subjected to the land boundary division processing to obtain the target remote sensing image.

[0013] Furthermore, the step of performing the land boundary division processing on the target land remote sensing image to obtain the target remote sensing image specifically includes:

[0014] Obtaining the vegetation index of the target plot;

[0015] Determining the division parameters of the land parcel boundary division process by the vegetation index;

[0016] The target land plot remote sensing image is processed based on the division parameters to obtain the target remote sensing image.

[0017] Furthermore, the step of performing land parcel recognition processing on the target remote sensing image to obtain the recognition result of the target land parcel specifically includes:

[0018] Determine the plot characteristics of the target remote sensing image by using the analytic hierarchy process;

[0019] The plot features are processed in combination with a fuzzy c-means clustering algorithm to obtain the target plot identification result.

[0020] Furthermore, before the step of determining the plot features of the target remote sensing image by using the hierarchical analysis method, the method further includes:

[0021] The target remote sensing image is detected and processed through the instance segmentation framework of the mask r-cnn to obtain all the land objects in the target remote sensing image;

[0022] The plot features of the target remote sensing image are collected through the plot object.

[0023] Furthermore, the reference data of the target plot includes first reference data and second reference data, and the step of determining the reference data of the target plot by the longitude and latitude of the target plot specifically includes:

[0024] Delineating the range of the target plot based on the latitude and longitude of the target plot to obtain the first reference data;

[0025] A watermarked photo of the target land parcel is determined based on the latitude and longitude of the target land parcel to obtain the second reference data.

[0026] Furthermore, the step of comparing and verifying the recognition result of the target land parcel with the reference data of the target land parcel to obtain a verification result specifically includes:

[0027] Obtaining a first verification result by detecting whether the first reference data is within the range of the target land parcel identification result;

[0028] Comparing the second reference data with the image data of the target land parcel recognition result to obtain a second verification result;

[0029] The verification result is determined based on the first verification result and the second verification result.

[0030] In order to solve the above technical problems, the embodiment of the present application further provides a land parcel identification and verification device, which adopts the following technical solution:

[0031] An acquisition module is used to acquire the remote sensing image to be processed of the target plot;

[0032] A processing module, used for preprocessing the remote sensing image to be processed to obtain a target remote sensing image;

[0033] An identification module is used to perform land parcel identification processing on the target remote sensing image to obtain an identification result of the target land parcel;

[0034] A determination module, used to determine the reference data of the target plot according to the longitude and latitude of the target plot;

[0035] The verification module is used to compare and verify the recognition result of the target plot with the reference data of the target plot to obtain a verification result.

[0036] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0037] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the land parcel identification and verification method when executing the computer-readable instructions.

[0038] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0039] A computer-readable storage medium, characterized in that computer-readable instructions are stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, the steps of the land parcel identification and verification method are implemented.

[0040] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0041] The present application obtains the target remote sensing image by preprocessing the remote sensing image to be processed, performs plot recognition processing on the target remote sensing image to obtain a recognition result, obtains the reference data of the target plot through the latitude and longitude of the target plot, and compares and verifies the recognition result of the target plot with the reference data of the target plot to achieve binding of the plot crops and the plot, effectively improves the accuracy of demarcation of regional boundaries, reduces errors in boundary division, and helps to realize digital management of large-scale planting and promote the development of related insurance business. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0044] Figure 2 A flowchart of an embodiment of a land parcel identification and verification method according to the present application;

[0045] Figure 3 is a schematic structural diagram of an embodiment of a land parcel identification and verification device according to the present application;

[0046] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0048] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0049] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0050] like Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0051] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0052] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers and desktop computers, etc.

[0053] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0054] It should be noted that the land parcel identification and verification method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the land parcel identification and verification device is generally arranged in the server / terminal device.

[0055] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0056] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for identifying and verifying a plot of land according to the present application. The method for identifying and verifying a plot of land comprises the following steps:

[0057] Step S201, obtaining the remote sensing image to be processed of the target land parcel.

[0058] In this embodiment, the electronic device (eg, Figure 1The server / terminal device shown in the figure can receive the land parcel identification verification request through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0059] In this embodiment, the remote sensing image to be processed of the above-mentioned target plot can be obtained by satellite remote sensing, aerial remote sensing, UAV remote sensing and ground remote sensing. Preferably, in this embodiment, the above-mentioned satellite remote sensing can be used to obtain the remote sensing image to be processed. Specifically, the above-mentioned satellite remote sensing can be a remote sensing technology that uses sensors installed on satellites to obtain ground image information. The above-mentioned sensors can include optical sensors, infrared sensors and radar sensors. The above-mentioned sensors can be used to capture images and data of different bands, and use the above-mentioned images and data of the same band as remote sensing images to be processed. The above-mentioned remote sensing images can include optical images, radar images, thermal infrared images and multi-spectral images. The above-mentioned remote sensing images can be used to record information about surface features, landforms, land use, vegetation, water bodies, meteorology and environment.

[0060] In this embodiment, the to-be-processed remote sensing images of the target plots may include plots for planting and plots for animal husbandry. Specifically, the plots for planting may be land areas used for agricultural planting of crops, such as grains, vegetables, fruits, cotton, and oil crops; the animal husbandry plots may be land areas specifically used for raising and grazing livestock, such as raising cattle, sheep, horses, pigs, poultry, and other livestock for the production of food, dairy products, fur, leather, and other livestock products. The target plots may be plots of flue-cured tobacco crops.

[0061] In a possible embodiment, the multispectral image of the target land parcel can be acquired by an optical sensor on a sentinel-2 satellite to obtain the remote sensing image to be processed. The sentinel-2 satellite is a group of earth observation satellites of the European Space Agency (ESA) for providing high-resolution multispectral remote sensing images for monitoring changes on the earth's surface and resource management.

[0062] Step S202, pre-processing the remote sensing image to be processed to obtain a target remote sensing image.

[0063] In this embodiment, the above-mentioned preprocessing may include image preprocessing and plot division processing. Specifically, the above-mentioned image preprocessing may include the timed downloading of sentinel-2 remote sensing images, band calculation (outlier processing), data splicing, data clipping processing, product generation, etc. Through the built-in crontab scheduled task in Linux, the Python script file can be executed at 5 am every day to obtain the output data product, and the above-mentioned output data product includes the image data of each band of the above-mentioned remote sensing image to be processed; the above-mentioned plot division processing may be to perform plot division processing on the planting plots and animal husbandry plots in the above-mentioned remote sensing image to be processed, so as to obtain the planting plot area remote sensing image and animal husbandry plot area remote sensing image of the above-mentioned remote sensing image to be processed, and the remote sensing image of any one of the above-mentioned planting plot area remote sensing image or the above-mentioned animal husbandry plot area remote sensing image can be used as the above-mentioned target remote sensing image.

[0064] In a possible embodiment, by performing image pre-processing on the above-mentioned remote sensing image to be processed, the image data of each band of the above-mentioned remote sensing image to be processed is obtained, and then the above-mentioned plot division processing is performed on the above-mentioned remote sensing image to be processed to obtain the remote sensing image of the planting plot area of ​​the above-mentioned remote sensing image to be processed and the remote sensing image of the livestock plot area of ​​the above-mentioned target plot, and the remote sensing image of the planting plot area of ​​the above-mentioned remote sensing image to be processed is used as the above-mentioned target remote sensing image.

[0065] Step S203, performing land parcel recognition processing on the target remote sensing image to obtain a recognition result of the target land parcel.

[0066] In the present embodiment, the above-mentioned plot recognition processing may be a boundary division processing of the planting plot in the above-mentioned target remote sensing image. Specifically, the output object of the above-mentioned boundary division processing may be a planting product plot in the above-mentioned planting plot, and the above-mentioned planting product plot may be the above-mentioned flue-cured tobacco plot. The above-mentioned planting plot may be subjected to boundary division processing according to the plot characteristics of the above-mentioned flue-cured tobacco plot to obtain the recognition result of the above-mentioned flue-cured tobacco plot, that is, the recognition result of the above-mentioned target plot. The plot characteristics of the above-mentioned flue-cured tobacco plot may be the vegetation growth of the above-mentioned flue-cured tobacco crop. The recognition result of the above-mentioned target plot may include the recognition image of the above-mentioned target plot, the boundary image of the above-mentioned target plot and the boundary range data of the above-mentioned target plot. The boundary range data of the above-mentioned target plot may be represented by the following formula:

[0067] D(f)=Σ y Σ x (|f(x+1,y)-f(x,y)| 2 +|f(x,y+1)-f(x,y)| 2 )

[0068] Wherein, f represents the target remote sensing image, D(f) represents the boundary range, (x, y) represents the above-mentioned target plot, x represents the longitude of the above-mentioned target plot, y represents the latitude of the above-mentioned target plot, and f(x, y) represents the boundary of the plot level (x, y) corresponding to the image f.

[0069] In a possible embodiment, the plot characteristics of the above-mentioned flue-cured tobacco plot are obtained by distinguishing the vegetation growth of the above-mentioned flue-cured tobacco crop from the vegetation growth in non-artificial areas, and the plot recognition processing is performed on the above-mentioned target remote sensing image based on the above-mentioned plot characteristics to obtain the recognition image of the above-mentioned flue-cured tobacco plot, the boundary image of the above-mentioned flue-cured tobacco plot and the boundary range data of the above-mentioned flue-cured tobacco plot, that is, the recognition result of the above-mentioned target plot is obtained.

[0070] Step S204, determining reference data of the target plot according to the longitude and latitude of the target plot.

[0071] In this embodiment, the longitude and latitude of the target plot can be obtained by performing a location processing on the target plot using a global positioning system (GPS) or a geographic information system (GIS) software. Specifically, the longitude and latitude can be a coordinate system of a geographical location, which can be used to describe the location of any point on the earth. The longitude and latitude can include two values, latitude and longitude, which can uniquely determine a location on the earth when combined. The longitude and latitude of the target plot can be the center point within the range of the target plot.

[0072] In this embodiment, the reference data of the target plot may be the field data of the target plot. Specifically, the field data may include image data, soil data, meteorological data, real boundary range data, and vegetation data of the target plot, and the field data may be used to reflect the actual environmental conditions of the target plot.

[0073] In a possible embodiment, the target plot is positioned by a global positioning system (GPS) to obtain the longitude and latitude of the target plot, and the field data of the target plot is retrieved from a plot database by the longitude and latitude of the target plot to reflect the actual environmental conditions of the target plot. The plot database may be a database storing field data of a large number of plots, and the plots include the target plot. The longitude and latitude may be used as a unique primary key to distinguish different plots.

[0074] Step S205 , comparing and verifying the recognition result of the target plot with the reference data of the target plot to obtain a verification result.

[0075] In this embodiment, the comparison and verification process may be to compare and verify the recognition image in the recognition result of the target plot with the picture data in the reference data of the target plot. Specifically, the image content in the recognition image may be compared with the image content in the picture data to determine whether the image content in the recognition image and the image content in the picture data are of the same type. If the determination result is the same type, the verification result shows that the recognition result of the target plot is normal. If they are of different types, the verification result shows that the recognition result of the target plot is abnormal.

[0076] In this embodiment, the comparison and verification process may be to compare and verify the boundary range data in the recognition result of the target plot with the real boundary range data in the reference data of the target plot. Specifically, the verification result may be determined by comparing the range size of the boundary range data with the range size of the real boundary range data. If the range of the boundary range data is larger than the range of the real boundary range data, the verification result shows that the recognition result of the target plot is normal. If the range of the boundary range data is smaller than the range of the real boundary range data, the verification result shows that the recognition result of the target plot is abnormal.

[0077] In this embodiment, the above verification results can be displayed through a mobile phone, a computer, a monitoring display screen, etc.

[0078] The present application obtains the target remote sensing image by preprocessing the remote sensing image to be processed, performs plot recognition processing on the target remote sensing image to obtain a recognition result, obtains the reference data of the target plot through the latitude and longitude of the target plot, and compares and verifies the recognition result of the target plot with the reference data of the target plot to achieve binding of the plot crops and the plot, effectively improves the accuracy of demarcation of regional boundaries, reduces errors in boundary division, and helps to realize digital management of large-scale planting and promote the development of related insurance business.

[0079] In some optional implementations, step S202 includes the following steps:

[0080] Perform cloud layer analysis on the remote sensing image to be processed to obtain the remote sensing image of the target land;

[0081] The remote sensing image of the target plot is processed by dividing the plot boundaries to obtain the target remote sensing image.

[0082] In this embodiment, the cloud layer analysis and processing may include extracting classification parameters of cloud coverage areas in the remote sensing image to be processed; classifying the remote sensing image to be processed according to the classification parameters; extracting thick cloud areas in the cloud coverage areas according to the classification results and performing mask processing and mask cropping; supplementing the thick cloud areas with areas with normal cloud layer impact from other data sources during the same period through an image fusion method to obtain the remote sensing image of the target land plot.

[0083] Specifically, the cloud coverage area may be an area covered or obscured by clouds in the target plot, and the cloud coverage area may be divided into a thick cloud area and a thin cloud area. The classification parameter may be a cloud thickness parameter, and the cloud thickness parameter may be used to determine the type of cloud coverage area of ​​the target plot. When the value of the cloud thickness parameter of the target plot is greater than the thick cloud threshold, the cloud coverage area type of the target plot is judged to be a thick cloud area; when the value of the cloud thickness parameter of the target plot is less than the thick cloud threshold, the cloud coverage area type of the target plot is judged to be a thin cloud area. The mask processing may be a mask processing in a geographic information system (GIS), and the mask may be used to clip geographic data and cover areas of no interest. The mask processing may refer to the use of a mask layer (also called a mask or mask layer) to limit the display, analysis or operation range of geographic data. The image fusion method may be an image processing method such as weighted average fusion, wavelet transform fusion, multi-scale fusion, and principal component analysis (PCA) fusion.

[0084] In a possible embodiment, the sentinel-2 remote sensing image is sequentially processed with radiation correction, atmospheric correction, image fusion, geometric correction, etc. Among them, for the land area blocked by clouds, 30-meter Landsat data is downloaded from the USGS website or the geospatial data cloud to supplement it, the threshold of the cloud coverage area in the sentinel-2 remote sensing image is extracted, the image is classified, the thick cloud area is extracted and masked, and the data with less cloud influence in the same period is cropped by masking and fused to supplement the cloud-covered area, so as to obtain the remote sensing image of the target land.

[0085] In a possible embodiment, by performing image pre-processing on the above-mentioned target plot remote sensing image, image data of each band of the above-mentioned remote sensing image to be processed is obtained, and then the above-mentioned plot boundary division processing is performed on the above-mentioned target plot remote sensing image to obtain the above-mentioned planting plot area remote sensing image and the above-mentioned livestock plot area remote sensing image of the above-mentioned target plot remote sensing image. The remote sensing image of either the above-mentioned planting plot area remote sensing image or the above-mentioned livestock plot area remote sensing image can be used as the above-mentioned target remote sensing image.

[0086] This application processes the cloud-covered area in the above-mentioned remote sensing image to be processed to reduce the impact of cloud-obstructed land area on land identification.

[0087] In some optional implementations, the above step of performing land boundary demarcation processing on the target land remote sensing image to obtain the target remote sensing image includes the following steps:

[0088] Get the vegetation index of the target plot;

[0089] Determine the demarcation parameters of the land parcel boundary demarcation process through vegetation index;

[0090] The target land remote sensing image is processed based on the division parameters to obtain the target remote sensing image.

[0091] In this embodiment, the vegetation index can be obtained by methods such as normalized vegetation index, normalized difference water index and simplified vegetation index. Specifically, the vegetation index can be used to distinguish the boundaries of the planting plots and the livestock plots in the remote sensing image of the target plot. More specifically, a distinction threshold can be set by the vegetation index to distinguish the planting plots and the livestock plots. Usually, the vegetation index of the planting plots is higher, while the vegetation index of the livestock plots is lower. When the vegetation index of a part of the target plot is greater than the distinction threshold, it is judged as the planting plot, otherwise it is judged as the livestock plot. The distinction threshold may vary depending on the region, season and vegetation type.

[0092] In this embodiment, in the step of determining the division parameters of the plot boundary division processing by the vegetation index, specifically, the above-mentioned distinction threshold can be determined as the division parameter of the above-mentioned plot boundary division processing, and the above-mentioned target plot remote sensing image is divided by the above-mentioned division parameters to obtain the planting plot area remote sensing image, the animal husbandry plot area remote sensing image, the above-mentioned planting plot boundary range and the animal husbandry plot boundary range in the above-mentioned target plot remote sensing image.

[0093] The present application determines the division parameters for the plot boundary division processing through the vegetation index, and then processes the remote sensing image of the target plot based on the above division parameters to obtain the target remote sensing image, thereby reducing the reliance on the traditional manual drawing method of the plot range, thereby reducing the time consumption, and the extraction result of the plot boundary is high in accuracy and the plot boundary extraction is complete.

[0094] In some optional implementations, step S203 includes the following steps:

[0095] Determine the plot characteristics of the target remote sensing image through the analytic hierarchy process;

[0096] The plot features are processed with the fuzzy c-means clustering algorithm to obtain the target plot recognition result.

[0097] In this embodiment, the plot features of the target remote sensing image may be the plot features of the target plot. Specifically, the plot features of the target plot may be the plot features of the flue-cured tobacco plot, and the plot features of the flue-cured tobacco plot may be flue-cured tobacco planting characteristics, which may include the shape of ridges, a clear sense of boundaries, and the difference between the growth of the flue-cured tobacco crops and the growth of non-flue-cured tobacco crops at different times. The flue-cured tobacco planting characteristics may be used to conveniently extract the planting range of flue-cured tobacco crops, and use them as the plot features of the flue-cured tobacco plot to further identify the plot boundaries of the target plot.

[0098] In this embodiment, the target remote sensing image can be the regional remote sensing image of the planting plot. Since the planting plot usually contains multiple planting products, that is, there can be multiple plot features in the regional remote sensing image of the planting plot, all plot features can be screened by the analytic hierarchy process to determine the plot features of the target plot. Specifically, the analytic hierarchy process can be divided into the following steps: first, the screening criteria need to be defined, and the screening criteria can be the above-mentioned tobacco planting characteristics; list all the available plot features; decompose the screening criteria into multiple levels, and the levels can be the evaluation criteria such as the growth cycle of the planted crops, the shape of the planted crops, and the color of the planted crops; establish a judgment matrix to compare the plot features in pairs, and obtain the weight value of each plot feature; finally, perform weighted summation according to the weight value to obtain the score of each plot feature, and determine the plot feature with the highest score as the plot feature of the target plot, that is, the plot feature of the target remote sensing image. The above-mentioned hierarchical analysis method can fully mine the rich spectral, geometric and texture information of high-resolution remote sensing images based on feature screening of geological knowledge, and combine the three information to improve the accuracy of classification results.

[0099] In this embodiment, the fuzzy c-means clustering algorithm can be a clustering method based on fuzzy logic, and the fuzzy c-means clustering algorithm allows data points to belong to multiple clusters instead of just one cluster. Specifically, by processing the plot features of the target plot in combination with the fuzzy c-means clustering algorithm, the target plot recognition result can generally have multiple aspects, including the recognition image, boundary image, and boundary range data of the target plot. The fuzzy c-means clustering algorithm can combine multiple features to form a more comprehensive plot classification.

[0100] This application determines the plot characteristics of the target remote sensing image through the hierarchical analysis method, which helps to more accurately determine the plot characteristics of the above-mentioned target remote sensing image, and processes the plot characteristics in combination with the fuzzy c-means clustering algorithm to obtain the target plot identification result, which helps to better understand and utilize the plot data.

[0101] In some optional implementations, before the step of determining the plot features of the target remote sensing image by using the hierarchical analysis method, the following steps are also included:

[0102] The target remote sensing image is detected and processed through the instance segmentation framework of Mask R-CNN to obtain all the land objects in the target remote sensing image;

[0103] The plot features of the target remote sensing image are collected through the plot object.

[0104] In this embodiment, the instance segmentation framework of the mask r-cnn can be a deep learning framework for instance segmentation tasks, which can simultaneously realize target detection and semantic segmentation, and generate an accurate segmentation mask for each detected target. Specifically, by subjecting the target remote sensing image to target detection through the instance segmentation framework of the mask r-cnn, all the plot objects in the target remote sensing image are obtained. The target remote sensing image can be the regional remote sensing image of the planting plot. Since the planting plot usually contains a variety of planting products, all the planting products detected by the target in the planting plot can be used as all the plot objects, and the instance segmentation task is performed on all the plot objects to obtain the plot features of the target remote sensing image.

[0105] This application uses the instance segmentation framework of Mask R-CNN to perform detection processing to obtain all the land objects in the target remote sensing image, so that the final depicted land map is spatially complete and efficient detection of objects in the image is achieved.

[0106] In some optional implementations, step S204 includes the following steps:

[0107] Delineating the range of the target plot based on the latitude and longitude of the target plot to obtain first reference data;

[0108] The watermark photo of the target land parcel is determined based on the latitude and longitude of the target land parcel to obtain the second reference data.

[0109] In the present embodiment, the above-mentioned target plot range can be obtained by plot delineation technology. Specifically, the above-mentioned plot delineation technology can refer to the technology of identifying, extracting and delineating the range of different plots or land use areas in remote sensing images or geographic information system (GIS) data. Specifically, the actual longitude and latitude information of the four corner points on the above-mentioned target plot can be obtained through the global positioning system (GPS), and the actual longitude and latitude information can be used to record and quickly delineate the real boundary range data of the above-mentioned target plot on the map, and the real boundary range data of the above-mentioned target plot can be used as the above-mentioned target plot range. The above-mentioned first reference data can include the real boundary range data of the above-mentioned target plot and the actual longitude and latitude information of the above-mentioned target plot.

[0110] In this embodiment, the watermarked photo may be a picture with watermark information. Specifically, the watermark information of the watermarked photo may include the longitude and latitude of the shooting location, shooting time, shooting equipment information, etc. The watermarked photo may be used to identify the ownership, geographic location, date and other information of the picture. The second reference data may include the image data of the watermarked photo and all information data of the watermark information.

[0111] In a possible embodiment, the target land parcel may be photographed in real life through a watermark camera to obtain a plurality of watermarked photos, each of which carries the actual longitude and latitude of the watermark camera at the shooting location. The plurality of watermarked photos are uploaded to the land parcel database, and the actual longitude and latitude may be used as a unique primary key to distinguish different watermarked photos.

[0112] This application obtains the target plot range and the watermarked photo of the target plot based on the actual latitude and longitude of the target plot, thereby providing authentic and reliable reference data for subsequent verification processing operations and improving the effectiveness of the verification results.

[0113] In some optional implementations, step S205 includes the following steps:

[0114] Obtaining a first verification result by detecting whether the first reference data is within the range of the target land parcel identification result;

[0115] Comparing the second reference data with the image data of the target land parcel recognition result to obtain a second verification result;

[0116] A verification result is determined based on the first verification result and the second verification result.

[0117] In this embodiment, the first verification result is obtained by detecting whether the first reference data is within the range of the target land parcel identification result. Specifically, the first verification result is determined by detecting whether the real boundary range data of the first reference data is within the boundary range data of the target land parcel identification result. If the real boundary range data of the first reference data is within the boundary range data of the target land parcel identification result, the first verification result is successfully verified. If the real boundary range data of the first reference data is not within the boundary range data of the target land parcel identification result, the first verification result fails.

[0118] The image data in the recognition result of the target plot may be the recognition image, and the second verification result may be obtained by comparing the image data of the watermark photo in the second reference data with the recognition image. Specifically, the image data and the recognition image may be subjected to crop recognition using image recognition processing technology to obtain the real planted crops in the image data and the target planted crops in the recognition image. The image recognition processing technology may be based on openCV, SURF (Speeded-Up Robust Features) accelerated robust feature algorithm or ORB (Oriented FAST and Rotated BRIEF) algorithm to accurately identify the real planted crops in the image data of the watermark photo, and determine whether the real planted crops and the target planted crops are of the same type. If the determination result is that they are of the same type, the second verification result is a successful verification, and if they are of different types, the second verification result is a failed verification.

[0119] The present application performs a double verification on the target plot identification result through the first reference data and the second reference data, thereby improving the accuracy of the target plot identification result.

[0120] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0121] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning. This application can be applied to the field of smart environmental protection, thereby promoting the construction of smart cities.

[0122] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0123] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0124] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a land parcel identification and verification device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0125] like Figure 3 As shown, the land parcel identification and verification device 300 described in this embodiment includes: an acquisition module 301, a processing module 302, an identification module 303, a determination module 304 and a verification module 305. Among them:

[0126] The acquisition module 301 is used to acquire the remote sensing image to be processed of the target land parcel;

[0127] The processing module 302 is used to pre-process the remote sensing image to be processed to obtain a target remote sensing image;

[0128] The recognition module 303 is used to perform land parcel recognition processing on the target remote sensing image to obtain the recognition result of the target land parcel;

[0129] A determination module 304 is used to determine the reference data of the target plot according to the longitude and latitude of the target plot;

[0130] The verification module 305 is used to compare and verify the recognition result of the target plot with the reference data of the target plot to obtain a verification result.

[0131] This embodiment obtains a target remote sensing image by preprocessing the remote sensing image to be processed of the target plot, performs plot recognition processing on the target remote sensing image to obtain a recognition result, obtains reference data of the target plot through the latitude and longitude of the target plot, and compares and verifies the recognition result of the target plot with the reference data of the target plot to obtain a verification result.

[0132] The plot identification and verification device proposed in this embodiment effectively binds the plot crops to the plot, effectively improves the accuracy of regional boundary demarcation, reduces boundary demarcation errors, and helps to realize digital management of large-scale planting and promote the development of related insurance business.

[0133] In some optional implementations of this embodiment, the processing module 302 includes: a first processing submodule and a second processing submodule, wherein:

[0134] The first processing submodule is used to perform the cloud layer analysis on the remote sensing image to be processed to obtain a remote sensing image of the target land;

[0135] The second processing submodule is used to perform the land boundary division processing on the target land remote sensing image to obtain the target remote sensing image.

[0136] This application processes the cloud-covered area in the above-mentioned remote sensing image to be processed to reduce the impact of cloud-obstructed land area on land identification.

[0137] In some optional implementations of this embodiment, the second processing submodule includes: an acquisition unit, a first processing unit, and a second processing unit, wherein:

[0138] An acquisition unit, used for acquiring the vegetation index of the target plot;

[0139] A first processing unit, used for determining the division parameters of the land parcel boundary division processing according to the vegetation index;

[0140] The second processing unit is used to process the target land plot remote sensing image based on the division parameters to obtain the target remote sensing image.

[0141] The present application determines the division parameters for the plot boundary division processing through the vegetation index, and then processes the remote sensing image of the target plot based on the above division parameters to obtain the target remote sensing image, thereby reducing the reliance on the traditional manual drawing method of the plot range, thereby reducing the time consumption, and the extraction result of the plot boundary is high in accuracy and the plot boundary extraction is complete.

[0142] In some optional implementations of this embodiment, the identification module 303 includes: a first determination submodule and a third processing submodule, wherein:

[0143] The first determination submodule is used to determine the plot characteristics of the target remote sensing image by using a hierarchical analysis method;

[0144] The third processing submodule is used to process the plot features in combination with the fuzzy c-means clustering algorithm to obtain the target plot identification result.

[0145] This application determines the plot characteristics of the target remote sensing image through the hierarchical analysis method, which helps to more accurately determine the plot characteristics of the above-mentioned target remote sensing image, and processes the plot characteristics in combination with the fuzzy c-means clustering algorithm to obtain the target plot identification result, which helps to better understand and utilize the plot data.

[0146] In some optional implementations of this embodiment, before the first determination submodule, the first detection submodule and the acquisition submodule are also included, wherein:

[0147] The first detection submodule is used to detect and process the target remote sensing image through the instance segmentation framework of Mask R-CNN to obtain all the land objects in the target remote sensing image;

[0148] The acquisition submodule is used to acquire the land parcel features of the target remote sensing image through all the land parcel objects.

[0149] This application uses the instance segmentation framework of Mask R-CNN to perform detection processing to obtain all the land objects in the target remote sensing image, so that the final depicted land map is spatially complete and efficient detection of objects in the image is achieved.

[0150] In some optional implementations of this embodiment, the determination module 304 further includes: a delineation submodule and a second determination submodule, wherein:

[0151] A delineation submodule, configured to delineate the range of the target plot based on the latitude and longitude of the target plot to obtain the first reference data;

[0152] The second determination submodule is used to determine the watermark photo of the target land parcel based on the longitude and latitude of the target land parcel to obtain the second reference data.

[0153] This application obtains the target plot range and the watermarked photo of the target plot based on the actual latitude and longitude of the target plot, thereby providing authentic and reliable reference data for subsequent verification processing operations and improving the effectiveness of the verification results.

[0154] In some optional implementations of this embodiment, the verification module 305 further includes: a second detection submodule, a comparison submodule and a third determination submodule, wherein:

[0155] A second detection submodule, configured to obtain a first verification result by detecting whether the first reference data is within the range of the target land parcel identification result;

[0156] A comparison submodule, used for comparing the second reference data with the image data of the target land parcel recognition result to obtain a second verification result;

[0157] A third determination submodule is configured to determine the verification result based on the first verification result and the second verification result.

[0158] The present application performs a double verification on the target plot identification result through the first reference data and the second reference data, thereby improving the accuracy of the target plot identification result.

[0159] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0160] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0161] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0162] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the land parcel identification and verification method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0163] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the land parcel identification and verification method.

[0164] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0165] The computer device proposed in this embodiment can effectively bind plots of crops to plots of land, effectively improve the accuracy of demarcation of regional boundaries, reduce errors in boundary demarcation, and help realize digital management of large-scale planting and promote the development of related insurance business.

[0166] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the land parcel identification and verification method as described above.

[0167] The computer-readable storage medium proposed in this embodiment can effectively bind the crops on the plots to the plots, effectively improve the accuracy of demarcation of regional boundaries, and reduce boundary divisions, which is conducive to the digital management of large-scale planting and the promotion of the development of related insurance business.

[0168] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0169] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A land parcel identification and verification method, characterized in that: The steps include: Obtain the remote sensing image to be processed of the target plot; Preprocessing the remote sensing image to be processed to obtain a target remote sensing image; Performing land parcel recognition processing on the target remote sensing image to obtain a recognition result of the target land parcel; Determine the reference data of the target plot according to the latitude and longitude of the target plot; The recognition result of the target plot is compared and verified with the reference data of the target plot to obtain a verification result.

2. The land parcel identification and verification method according to claim 1, characterized in that: The preprocessing includes land boundary demarcation processing and cloud layer analysis processing. The step of obtaining the remote sensing image to be processed and performing preprocessing to obtain the target remote sensing image specifically includes: Performing the cloud layer analysis on the remote sensing image to be processed to obtain a remote sensing image of the target land; The target land remote sensing image is subjected to the land boundary division processing to obtain the target remote sensing image.

3. The land parcel identification and verification method according to claim 2, characterized in that: The step of performing the land boundary division processing on the target land remote sensing image to obtain the target remote sensing image specifically includes: Obtaining the vegetation index of the target plot; Determining the division parameters of the land parcel boundary division process by the vegetation index; The target land plot remote sensing image is processed based on the division parameters to obtain the target remote sensing image.

4. The land parcel identification and verification method according to claim 1, characterized in that: The step of performing land parcel recognition processing on the target remote sensing image to obtain the recognition result of the target land parcel specifically includes: Determine the plot characteristics of the target remote sensing image by using the analytic hierarchy process; The plot features are processed in combination with a fuzzy c-means clustering algorithm to obtain the target plot identification result.

5. The land parcel identification and verification method according to claim 4, characterized in that: Before the step of determining the plot features of the target remote sensing image by using the hierarchical analysis method, the method further includes: The target remote sensing image is detected and processed through the instance segmentation framework of the mask r-cnn to obtain all the land objects in the target remote sensing image; The plot features of the target remote sensing image are collected through all the plot objects.

6. The land parcel identification and verification method according to claim 1, characterized in that: The reference data of the target plot includes first reference data and second reference data. The step of determining the reference data of the target plot by the longitude and latitude of the target plot specifically includes: Delineating the range of the target plot based on the latitude and longitude of the target plot to obtain the first reference data; A watermarked photo of the target land parcel is determined based on the latitude and longitude of the target land parcel to obtain the second reference data.

7. The land parcel identification and verification method according to any one of claim 6, characterized in that: The step of comparing and verifying the recognition result of the target land parcel with the reference data of the target land parcel to obtain a verification result includes: Obtaining a first verification result by detecting whether the first reference data is within the range of the target land parcel identification result; Comparing the second reference data with the image data of the target land parcel recognition result to obtain a second verification result; The verification result is determined based on the first verification result and the second verification result.

8. A land parcel identification and verification device, characterized in that: include: An acquisition module is used to acquire the remote sensing image to be processed of the target plot; A processing module, used for preprocessing the remote sensing image to be processed to obtain a target remote sensing image; An identification module is used to perform land parcel identification processing on the target remote sensing image to obtain an identification result of the target land parcel; A determination module, used to determine the reference data of the target plot according to the longitude and latitude of the target plot; The verification module is used to compare and verify the recognition result of the target plot with the reference data of the target plot to obtain a verification result.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the land parcel identification and verification method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the land parcel identification and verification method as described in any one of claims 1 to 7.

Images