Intelligent auditing method, device and equipment for newly-added cultivated land pattern spots and storage medium

Abstract

The invention discloses a newly-added cultivated land pattern spot intelligent auditing method and device, equipment and a storage medium. The method comprises the steps that a land photo set of a target project area is acquired; calculating a pattern spot area covered by the photo shooting range on the land utilization current situation graph based on the land photo set to obtain a photo coverage range; based on the land photo set and a pre-trained ground feature classification model, identifying ground feature categories in the target project area to obtain a ground feature category identification result; and judging whether the target project area meets a new cultivated land condition or not based on the photo coverage range and the ground feature category recognition result. According to the method, automatic auditing of the newly-added cultivated land pattern spots can be carried out, the auditing workload is reduced, and the auditing efficiency and the accuracy of the auditing result are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of land resource management technology, and in particular to a method, device, equipment and storage medium for intelligent review of newly added cultivated land areas. Background Art

[0002] Newly added cultivated land patches refer to land that was not originally cultivated land that was converted into cultivated land and is formed on the current land use map. The specific reasons for the formation of newly added cultivated land patches are as follows:

[0003] 1. Land consolidation project: Comprehensive consolidation of fields, water, roads, forests and villages. Through measures such as leveling the land, improving the soil, and building irrigation and drainage facilities, wasteland, saline-alkali land, sandy land and other non-cultivated land are transformed into arable land. These newly added arable lands are marked with specific spots on the map to form newly added arable land spots;

[0004] 2. High-standard farmland construction: During the implementation of the project, some medium- and low-yield farmlands will be transformed to improve the quality and production capacity of cultivated land. At the same time, through land leveling and merging of scattered plots, the cultivated land area may be increased to form new cultivated land patches;

[0005] 3. Reclamation: Reclamation of abandoned land caused by mining, soil excavation, sand excavation and other activities, as well as damaged land caused by natural disasters, urban and rural construction, etc., to restore them to arable land, thereby creating new arable land patches.

[0006] With the advancement of land consolidation and farmland protection, the review of newly added farmland plots has become increasingly important and faces many challenges. The traditional review method relies on manual judgment, with staff flipping through the photos of newly added farmland taken by field workers one by one to review whether the conditions for newly added farmland are met. The review is inefficient, prone to errors (for example, insufficient photo coverage, other land types in the plot are approved), and the workload is large, making it difficult to meet the growing needs of land management.

[0007] Therefore, in actual work, there is an urgent need for an efficient, accurate and intelligent audit method to improve the quality and efficiency of the audit work of newly added cultivated land areas. Summary of the invention

[0008] In order to solve the above technical problems, the present application provides a method, device, equipment and storage medium for intelligent review of newly added farmland map patches, which can automatically review newly added farmland map patches, reduce the review workload, and effectively improve the review efficiency and the accuracy of the review results.

[0009] The first objective of this application is to provide an intelligent review method for newly added cultivated land areas.

[0010] The above-mentioned application objective 1 of the present application is achieved through the following technical solutions:

[0011] A method for intelligently reviewing newly added cultivated land patches, the method comprising the following steps:

[0012] S1, obtain a collection of land photos of the target project area;

[0013] S2, calculating the area of ​​the patch covered by the photo shooting range on the land use status map based on the land photo collection, and obtaining the photo coverage range;

[0014] S3, identifying the land object category in the target project area based on the land photo collection and the pre-trained land object classification model to obtain a land object category recognition result;

[0015] S4: Based on the coverage of the photos and the results of the identification of the land object categories, it is determined whether the target project area meets the conditions for adding new cultivated land.

[0016] Preferably, the land photo collection includes multiple land photos, and the multiple land photos are taken toward the target project area from different points on the boundary line of the target project area, and the total shooting range of the multiple land photos can cover the target project area.

[0017] Preferably, in step S2, the calculating of the area of ​​the patch covered by the photo shooting range on the land use status map based on the land photo set to obtain the photo coverage range includes:

[0018] S21, extracting EXIF ​​data of each land photo in the land photo collection;

[0019] S22, parsing the EXIF ​​data of each land photo in the land photo collection to obtain a data parsing result;

[0020] S23, extracting the location information and shooting orientation information of each land photo based on the data analysis result, wherein the shooting orientation information includes the heading angle, pitch angle and roll angle of the camera when shooting the corresponding land photo;

[0021] S24, converting each land photo into a corresponding orthographic projection image using a spatial transformation matrix based on the position information and shooting orientation information of each land photo;

[0022] S25, stitching the orthophoto images corresponding to the land photos to obtain an orthophoto image of the target project area, wherein the area corresponding to the orthophoto image of the target project area is the photo shooting range;

[0023] S26, mapping the orthographic projection image of the target project area onto the current land use map, and obtaining the photo coverage based on the patch area covered by the orthographic projection image of the target project area on the current land use map.

[0024] Preferably, in step S3, identifying the land object category in the target project area based on the land photo collection and the pre-trained land object classification model to obtain the land object category recognition result includes:

[0025] S31, inputting all the land photos in the land photo collection into the pre-trained land object classification model;

[0026] S32, performing supervised classification and identification of the land object categories within the target project area in all the land photos through the pre-trained land object classification model based on a deep learning method to obtain the land object category identification result, wherein the land object category identification result includes the land object type and the corresponding land area.

[0027] Preferably, in step S4, judging whether the target project area meets the conditions for newly added cultivated land based on the photo coverage and the ground object category recognition result includes:

[0028] S41, matching the coverage of the photo with the target project spots on the land use status map, and determining whether the coverage of the photo completely covers the target project spots;

[0029] S42, judging whether the target project area is cultivated land based on the land feature type and the corresponding land area in the land feature category recognition result;

[0030] S43, when the coverage range of the photo completely covers the target project patch, and whether the target project area is cultivated land, determining that the target project area meets the conditions for adding cultivated land;

[0031] S44, determining the target project area as newly added cultivated land, and marking the target project area as a newly added cultivated land area on the land use status map.

[0032] The second purpose of this application is to provide an intelligent audit device for newly added cultivated land areas.

[0033] The second application objective of the present application is achieved through the following technical solutions:

[0034] A newly added cultivated land area intelligent audit device, comprising:

[0035] Photo acquisition module, used to obtain a set of land photos of the target project area;

[0036] A coverage range calculation module calculates the area of ​​the patch covered by the photo shooting range on the land use status map based on the land photo set to obtain the photo coverage range;

[0037] A land object classification and recognition module, used to identify the land object category in the target project area based on the land photo collection and the pre-trained land object classification model to obtain a land object category recognition result;

[0038] The newly added cultivated land review module determines whether the target project area meets the conditions for newly added cultivated land based on the photo coverage and the ground feature category recognition results.

[0039] Preferably, the land photo collection includes multiple land photos, and the multiple land photos are taken toward the target project area from different points on the boundary line of the target project area, and the total shooting range of the multiple land photos can cover the target project area.

[0040] Preferably, the coverage calculation module includes:

[0041] A data extraction unit, used for extracting EXIF ​​data of each land photo in the land photo collection;

[0042] A data parsing unit, used for parsing the EXIF ​​data of each land photo in the land photo collection to obtain a data parsing result;

[0043] An information extraction unit, configured to extract the location information and shooting orientation information of each land photo based on the data analysis result, wherein the shooting orientation information includes the heading angle, pitch angle and roll angle of the camera when shooting the corresponding land photo;

[0044] An image conversion unit, used to convert each land photo into a corresponding orthographic projection image using a space transformation matrix based on the position information and shooting orientation information of each land photo;

[0045] An image stitching unit is used to stitch the orthographic projection images corresponding to the land photos to obtain an orthographic projection image of the target project area, wherein the area corresponding to the orthographic projection image of the target project area is the photo shooting range;

[0046] The photo coverage range calculation unit is used to map the orthographic projection image of the target project area onto the land use status map, and obtain the photo coverage range based on the map area covered by the orthographic projection image of the target project area on the land use status map.

[0047] Preferably, the ground object classification and identification module includes:

[0048] A photo input unit, used for inputting all land photos in the land photo collection into the pre-trained land feature classification model;

[0049] A land object classification and identification unit is used to perform supervised classification and identification of land object categories within the target project area in all the land photos based on a deep learning method using the pre-trained land object classification model to obtain the land object category identification result, wherein the land object category identification result includes the land object type and the corresponding area.

[0050] Preferably, the newly added cultivated land review module includes:

[0051] A range judgment unit matches the coverage range of the photo with the target project spots on the land use status map to judge whether the coverage range of the photo completely covers the target project spots;

[0052] A cultivated land judging unit, judging whether the target project area is cultivated land based on the land feature type and the corresponding land area in the land feature category recognition result;

[0053] The newly added cultivated land determination unit determines that the target project area meets the conditions for newly added cultivated land when the coverage of the photo completely covers the target project area and whether the target project area is cultivated land, determines that the target project area is newly added cultivated land, and marks the target project area as a newly added cultivated land area on the land use status map.

[0054] The third object of the present application is to provide an electronic device.

[0055] The third application objective of this application is achieved through the following technical solutions:

[0056] An electronic device, comprising:

[0057] A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method for intelligent review of newly added cultivated land areas as described in any one of the first objectives of the present application.

[0058] The fourth object of this application is to provide a computer-readable storage medium.

[0059] The fourth application objective of this application is achieved through the following technical solutions:

[0060] A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the method for intelligent review of newly added cultivated land areas as described in any one of the first objectives of the present application.

[0061] In summary, the present application discloses a method, device, equipment and storage medium for intelligent review of newly added cultivated land spots, which obtains a land photo set of the target project area; calculates the spot area covered by the photo shooting range on the land use status map based on the land photo set to obtain the photo coverage; identifies the land object category in the target project area based on the land photo set and the pre-trained land object classification model to obtain the land object category recognition result; and determines whether the target project area meets the conditions for newly added cultivated land based on the photo coverage and land object category recognition results. The present application can automatically review newly added cultivated land spots, reduce the review workload, and effectively improve the review efficiency and the accuracy of the review results. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A schematic diagram of a process of a newly added cultivated land patch intelligent review method in an embodiment of the present application;

[0064] Figure 2 This is a structural schematic diagram of a newly added intelligent review device for cultivated land patches in an embodiment of the present application;

[0065] Figure 3 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0067] In the embodiments provided in the present application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely schematic. For example, the division of units and modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or modules can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0068] In addition, all functional units in the embodiments of the present application may be integrated into one processor, or each unit may be a separate device, or two or more units may be integrated into one device; each functional unit in the embodiments of the present application may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0069] A person skilled in the art can understand that all or part of the steps of the following method embodiments can be completed by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, the steps of the following method embodiments are executed; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a magnetic disk or an optical disk, and other media that can store program codes.

[0070] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "multiple" and "several" mean two or more, unless otherwise clearly and specifically defined.

[0071] like Figure 1 As shown, the embodiment of the present application provides a method for intelligently reviewing newly added cultivated land patches, which may include the following steps:

[0072] S1, obtain a collection of land photos of the target project area;

[0073] Through land consolidation, high-standard farmland construction, reclamation and other land type change projects, non-cultivated land in the target project area can be converted into cultivated land. After the land change, the newly added cultivated land will be reviewed. If the review is passed, the corresponding map of the target project area on the land use status map will be marked as a newly added cultivated land map. When reviewing the newly added cultivated land, you first need to obtain a land photo set of the target project area.

[0074] Specifically, the land photo set of the target project area can be composed of photos corresponding to the target area taken by field workers using cameras and other field photo collection equipment; it can also be remote sensing images taken by drones, remote sensing satellites, etc.

[0075] Since the target project area is usually large in area and has complex boundaries, when field workers are employed to photograph the target area to obtain a land photo collection, it is difficult to capture the entire target project area in one photo. In this embodiment, the land photo collection includes multiple land photos, which are obtained by field workers using a camera to photograph the target project area at different points on the boundary line of the target project area, and the total shooting range of the multiple land photos can cover the target project area. That is, when field workers take land photos of the target area, they start from a preset starting point, advance in a preset direction along the boundary line of the target project area, and stand at different positions on the boundary line to take photos toward the target area during the advance process, so that multiple land photos can be obtained, and the multiple land photos are packaged to form a land photo collection of the target area.

[0076] Specifically, in this embodiment, a land photo set of the target project area can be obtained from the photographing equipment of the field workers.

[0077] S2, based on the land photo collection, calculate the area of ​​the patch covered by the photo shooting range on the land use status map to obtain the photo coverage;

[0078] After obtaining the land photo set, it is necessary to calculate the coverage of the photos on the land use status map, that is, to calculate the map area covered by the photo shooting range on the land use status map based on the land photo set to obtain the photo coverage.

[0079] Specifically, in this embodiment, the specific method for calculating the patch area covered by the photo shooting range on the land use status map based on the land photo set to obtain the photo coverage range is as follows:

[0080] S21, extracting EXIF ​​data of each land photo in the land photo collection;

[0081] EXIF (Exchangeable Image File Format) data is a series of information collected by digital cameras during the shooting process. It is specially set for digital camera photos and can record the attribute information and shooting data of digital photos. EXIF ​​can be attached to JPEG, TIFF, RIFF and other files to add content related to digital camera shooting information and index map or version information of image processing software.

[0082] EXIF data mainly includes various information related to the photography conditions at the time, such as aperture, shutter, ISO, time, camera brand and model, sound recorded during shooting, location information when taking the photo, shooting direction information, etc.

[0083] S22, parsing the EXIF ​​data of each land photo in the land photo collection to obtain a data parsing result;

[0084] After the EXIF ​​data of each land photo in the land photo collection is extracted, the EXIF ​​data of each land photo extracted is further parsed to obtain a data parsing result. Specifically, the parsing result may include information such as the time, location, and orientation of the photo.

[0085] S23, extracting the location information and shooting orientation information of each land photo based on the data analysis result, wherein the shooting orientation information includes the heading angle, pitch angle and roll angle of the camera when taking the corresponding land photo;

[0086] Next, the location information and shooting azimuth information of each land photo are extracted from the data analysis results. Specifically, the location information of the land photo refers to the longitude and latitude of the camera when the land photo was taken, and the shooting azimuth information of the land photo refers to the heading angle, pitch angle and roll angle of the camera when the corresponding land photo was taken.

[0087] S24, converting each land photo into a corresponding orthographic projection image using a spatial transformation matrix based on the location information and shooting orientation information of each land photo;

[0088] After extracting the location information and shooting orientation information of each land photo, the spatial transformation matrix is ​​used to convert each land photo into a corresponding orthographic projection image, thereby unifying the coordinates of each pixel on the land photo with the pixel coordinates on the land use status map to facilitate subsequent operations.

[0089] Specifically, the process of converting each photo into a corresponding orthographic projection image using a spatial transformation matrix according to the location information and shooting orientation information of the photo is actually the projection transformation of the pixel points of the image. This image conversion method belongs to the prior art and will not be described in detail here.

[0090] S25, stitching the orthophoto images corresponding to the land photos to obtain an orthophoto image of the target project area, wherein the area corresponding to the orthophoto image of the target project area is the photo shooting range;

[0091] After obtaining the orthographic projection images of each land photo through image conversion, the orthographic projection images are stitched to obtain the orthographic projection image of the entire target project area, and the area corresponding to the orthographic projection image of the entire target project area is the photo shooting range.

[0092] The specific method of image stitching can adopt existing image matching algorithms such as phase correlation method or time domain-based method, which will not be described in detail here.

[0093] S26. Map the orthophoto projection image of the target project area onto the current land use map, and obtain the photo coverage based on the patch area covered by the orthophoto projection image of the target project area on the current land use map.

[0094] Finally, the orthophoto image of the target project area is mapped onto the current land use map through the image mapping method. That is, the orthophoto image of the target project area and the corresponding area of ​​the current land use map are matched and the pixels are aligned based on the position coordinates of each pixel point. After the mapping is completed, the area covered by the orthophoto image of the target project area on the current land use map is the photo coverage.

[0095] S3, identifying the types of objects in the target project area based on the land photo collection and the pre-trained object classification model to obtain the object classification results;

[0096] After obtaining the land photo collection, it is also necessary to classify and identify the land objects in the photos in the land photo collection, that is, to identify the land object categories in the target project area based on the land photo collection and the pre-trained land object classification model, so as to obtain the land object category recognition results.

[0097] Specifically, in this embodiment, the ground object category in the target project area is identified based on the land photo collection and the pre-trained ground object classification model, and the specific method for obtaining the ground object category identification result is as follows:

[0098] S31, inputting all land photos in the land photo set into a pre-trained land object classification model;

[0099] S32, using a pre-trained feature classification model to perform supervised classification and identification of the feature categories in the target project area in all land photos based on a deep learning method, to obtain a feature category identification result, wherein the feature category identification result includes the feature type and the corresponding area.

[0100] There may be gravel, trees, weeds, fruit trees, vegetables, rice and other types of land features on the land, while the types of land features on cultivated land are mainly vegetables, rice and other crops. Therefore, the types of land features in the target project area are identified in order to accurately determine whether the land is cultivated land.

[0101] Specifically, in this embodiment, the pre-trained land feature classification model can be obtained by training the land feature classification model with a priori common land feature models.

[0102] S4: Based on the photo coverage and the object category recognition results, determine whether the target project area meets the conditions for adding new arable land.

[0103] Finally, the coverage of the photos and the results of the object category recognition can be used to determine whether the target project area meets the conditions for adding new arable land.

[0104] Specifically, in this embodiment, based on the coverage of the photos and the results of the object category recognition, the specific method for determining whether the target project area meets the conditions for the newly added cultivated land is as follows:

[0105] S41, matching the coverage of the photo with the target project spots on the land use status map, and determining whether the coverage of the photo completely covers the target project spots;

[0106] S42, judging whether the target project area is cultivated land based on the land feature type and the corresponding land area in the land feature category recognition result;

[0107] Specifically, when the land features in the target project area are land features planted on cultivated land such as vegetables and rice, and the total area of ​​land features planted on cultivated land is greater than a preset threshold (e.g., 98%) to the area of ​​the target project area, the target project area is determined to be cultivated land. Specifically, the preset threshold is determined according to industry standards.

[0108] S43, when the coverage of the photo completely covers the target project patch and whether the target project area is cultivated land, it is determined that the target project area meets the conditions for adding cultivated land;

[0109] S44, determining the target project area as newly added cultivated land, and marking the target project area as a newly added cultivated land area on the land use status map, thereby completing the review of the newly added cultivated land area.

[0110] In summary, the intelligent review method for newly added cultivated land patches in the above-mentioned embodiment first obtains a land photo set of the target project area; then, based on the land photo set, the patch area covered by the photo shooting range on the land use status map is calculated to obtain the photo coverage; then, based on the land photo set and the pre-trained land object classification model, the land object category in the target project area is identified to obtain the land object category recognition result; finally, based on the photo coverage and the land object category recognition result, it is judged whether the target project area meets the conditions for newly added cultivated land. The embodiment of the present application can automatically review newly added cultivated land patches, reduce the review workload, effectively improve the review efficiency, and judge the newly added cultivated land by combining the photo coverage and the land object category recognition results, effectively improving the accuracy of the review results.

[0111] It should be noted that, in the above embodiment, the execution order of steps S2 and S3 is only an example. In the actual execution process, they are not necessarily executed in the order of S2 and S3. That is to say, the step of calculating the photo coverage range of S2 can be executed first, or the step of identifying the ground object category of S3 can be executed first, or S2 and S3 can be executed in parallel at the same time.

[0112] like Figure 2 As shown, the embodiment of the present application provides an intelligent review device for newly added cultivated land spots, which may include:

[0113] The photo acquisition module 201 is used to acquire a land photo set of the target project area;

[0114] The coverage calculation module 202 calculates the area of ​​the patch covered by the photo shooting range on the land use status map based on the land photo collection to obtain the photo coverage;

[0115] The ground object classification and recognition module 203 is used to recognize the ground object categories in the target project area based on the land photo collection and the pre-trained ground object classification model to obtain the ground object category recognition result;

[0116] The newly added cultivated land review module 204 determines whether the target project area meets the conditions for newly added cultivated land based on the coverage of the photos and the results of the recognition of the land object categories.

[0117] In one embodiment, the land photo set includes multiple land photos, which are taken from different points on the boundary line of the target project area toward the target project area, and the total shooting range of the multiple land photos can cover the target project area.

[0118] In one embodiment, the coverage calculation module 202 includes:

[0119] A data extraction unit, used for extracting EXIF ​​data of each land photo in the land photo collection;

[0120] A data parsing unit, used for parsing the EXIF ​​data of each land photo in the land photo collection to obtain a data parsing result;

[0121] An information extraction unit, used to extract the location information and shooting orientation information of each land photo based on the data analysis result, wherein the shooting orientation information includes the heading angle, pitch angle and roll angle of the camera when shooting the corresponding land photo;

[0122] An image conversion unit, used to convert each land photo into a corresponding orthographic projection image using a space transformation matrix based on the position information and shooting orientation information of each land photo;

[0123] An image stitching unit is used to stitch the orthophoto images corresponding to the land photos to obtain an orthophoto image of the target project area, wherein the area corresponding to the orthophoto image of the target project area is the photo shooting range;

[0124] The photo coverage calculation unit is used to map the orthophoto projection image of the target project area onto the land use status map, and obtain the photo coverage based on the image patch area covered by the orthophoto projection image of the target project area on the land use status map.

[0125] In one embodiment, the object classification and identification module 203 includes:

[0126] A photo input unit, used for inputting all land photos in the land photo collection into the pre-trained land object classification model;

[0127] The land object classification and recognition unit is used to perform supervised classification and recognition of land object categories in the target project area in all land photos based on a deep learning method using a pre-trained land object classification model to obtain land object category recognition results, wherein the land object category recognition results include land object types and corresponding land areas.

[0128] In one embodiment, the newly added cultivated land review module 204 includes:

[0129] The range judgment unit matches the coverage of the photo with the target project spots on the land use status map to determine whether the coverage of the photo completely covers the target project spots;

[0130] A cultivated land judgment unit, which judges whether the target project area is cultivated land based on the land feature type and the corresponding land area in the land feature category recognition result;

[0131] A new cultivated land determination unit is added. When the photo coverage completely covers the target project map and whether the target project area is cultivated land, it is determined that the target project area meets the conditions for newly added cultivated land, and the target project area is determined to be newly added cultivated land, and the target project map is marked as a newly added cultivated land on the land use status map.

[0132] It should be noted that the intelligent audit device for newly added cultivated land map patches in the above embodiment has the same working principle and technical effect as the intelligent audit method for newly added cultivated land map patches in the above embodiment, which will not be repeated here.

[0133] like Figure 3As shown, an embodiment of the present application provides an electronic device 3, which includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and executable on the processor 302, wherein the memory 301 and the processor 302 communicate with each other via a bus 304, and when the processor 302 executes the computer program 303, the steps of the newly added intelligent review method of cultivated land areas as described in the above-mentioned method embodiment of the present application are implemented.

[0134] Specifically, the electronic device 3 may be an intelligent device with a memory and a processor, such as an industrial computer, a PC, or an intelligent mobile terminal, or may be a computer component with a memory and a processor, such as a CPU or a GPU.

[0135] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method for intelligent review of newly added cultivated land areas in the above-mentioned method embodiment of the present application.

[0136] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0137] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0138] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, software modules executed by a processor, or a combination of the two. The software modules may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0139] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent review of newly added cultivated land patches, characterized in that: The method comprises the following steps: S1, obtain a collection of land photos of the target project area; S2, calculating the area of ​​the patch covered by the photo shooting range on the land use status map based on the land photo collection, and obtaining the photo coverage range; S3, identifying the land object category in the target project area based on the land photo collection and the pre-trained land object classification model to obtain a land object category recognition result; S4: Based on the coverage of the photos and the results of the identification of the land object categories, it is determined whether the target project area meets the conditions for adding new cultivated land.

2. The intelligent audit method for newly added cultivated land patches according to claim 1 is characterized in that: The land photo collection includes multiple land photos, which are taken from different points on the boundary line of the target project area toward the target project area, and the total shooting range of the multiple land photos can cover the target project area.

3. The intelligent audit method for newly added cultivated land patches according to claim 2 is characterized in that: In step S2, the area of ​​the patch covered by the photo shooting range on the land use status map is calculated based on the land photo set, and the photo coverage range is obtained, including: S21, extracting EXIF ​​data of each land photo in the land photo collection; S22, parsing the EXIF ​​data of each land photo in the land photo collection to obtain a data parsing result; S23, extracting the location information and shooting orientation information of each land photo based on the data analysis result, wherein the shooting orientation information includes the heading angle, pitch angle and roll angle of the camera when shooting the corresponding land photo; S24, converting each land photo into a corresponding orthographic projection image using a spatial transformation matrix based on the position information and shooting orientation information of each land photo; S25, stitching the orthophoto images corresponding to the land photos to obtain an orthophoto image of the target project area, wherein the area corresponding to the orthophoto image of the target project area is the photo shooting range; S26, mapping the orthographic projection image of the target project area onto the current land use map, and obtaining the photo coverage based on the patch area covered by the orthographic projection image of the target project area on the current land use map.

4. The intelligent audit method for newly added cultivated land area according to claim 2 is characterized in that: In step S3, the ground object category in the target project area is identified based on the land photo collection and the pre-trained ground object classification model, and the ground object category identification result obtained includes: S31, inputting all the land photos in the land photo collection into the pre-trained land object classification model; S32, performing supervised classification and identification of the land object categories within the target project area in all the land photos through the pre-trained land object classification model based on a deep learning method to obtain the land object category identification result, wherein the land object category identification result includes the land object type and the corresponding land area.

5. The intelligent audit method for newly added cultivated land area according to claim 4 is characterized in that: In step S4, judging whether the target project area meets the conditions for newly added cultivated land based on the coverage of the photo and the result of the recognition of the land object category includes: S41, matching the coverage of the photo with the target project spots on the land use status map, and determining whether the coverage of the photo completely covers the target project spots; S42, judging whether the target project area is cultivated land based on the land feature type and the corresponding land area in the land feature category recognition result; S43, when the coverage of the photo completely covers the target project map, and whether the target project area is cultivated land, determine that the target project area meets the conditions for newly added cultivated land, determine the target project area as newly added cultivated land, and mark the target project map as a newly added cultivated land map on the land use status map.

6. A newly added cultivated land area intelligent audit device, characterized in that: include: Photo acquisition module, used to obtain a set of land photos of the target project area; A coverage range calculation module calculates the area of ​​the patch covered by the photo shooting range on the land use status map based on the land photo set to obtain the photo coverage range; A land object classification and recognition module, used to identify the land object category in the target project area based on the land photo collection and the pre-trained land object classification model to obtain a land object category recognition result; The newly added cultivated land review module determines whether the target project area meets the conditions for newly added cultivated land based on the photo coverage and the ground feature category recognition results.

7. The intelligent audit device for newly added cultivated land patches according to claim 1 is characterized in that: The land photo collection includes multiple land photos, which are taken from different points on the boundary line of the target project area toward the target project area, and the total shooting range of the multiple land photos can cover the target project area.

8. The intelligent audit device for newly added cultivated land area according to claim 7 is characterized in that: The coverage calculation module includes: A data extraction unit, used for extracting EXIF ​​data of each land photo in the land photo collection; A data analysis unit, used for analyzing the EXIF ​​data of each land photo in the land photo collection to obtain a data analysis result; An information extraction unit, configured to extract the location information and shooting orientation information of each land photo based on the data analysis result, wherein the shooting orientation information includes the heading angle, pitch angle and roll angle of the camera when shooting the corresponding land photo; An image conversion unit, used to convert each land photo into a corresponding orthographic projection image using a space transformation matrix based on the position information and shooting orientation information of each land photo; An image stitching unit is used to stitch the orthographic projection images corresponding to the land photos to obtain an orthographic projection image of the target project area, wherein the area corresponding to the orthographic projection image of the target project area is the photo shooting range; The photo coverage range calculation unit is used to map the orthographic projection image of the target project area onto the land use status map, and obtain the photo coverage range based on the map area covered by the orthographic projection image of the target project area on the land use status map.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the newly added cultivated land map intelligent review method as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the newly added cultivated land map intelligent review method as described in any one of claims 1-5 are implemented.

Images