Method for inventory of natural resources assets owned by the whole people based on real-scene 3D model

Abstract

Embodiments of the present application relate to the field of natural resource asset inventory, and specifically to a method for inventorying natural resources assets owned by the whole people based on a real-scene three-dimensional model. The specific implementation of this method includes: dividing the image feature information and the resource area mask division image according to the resource area, generating a local resource area mask image through a resource area segmentation model; generating resource area segmentation information; matching the natural resource asset area information from the natural resource asset database according to the resource area segmentation information and the resource area geographical reference information; collecting real-scene three-dimensional images of the resource area corresponding to the resource area segmentation information; inputting the resource area real-scene three-dimensional model, the resource area segmentation information and the natural resource asset area information into the natural resource asset inventory and recognition model to obtain the resource area asset inventory and recognition information. This implementation method can quickly and accurately identify the resource area assets of each individual resource area within the natural resource asset inventory area.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of natural resource asset inventory, and particularly to a method for inventorying natural resources owned by the whole people based on a real scene three-dimensional model. Background Art

[0002] The inventory of natural resources owned by the whole people is an important way to find out the assets. Based on the existing achievements of various special surveys (inventories) on resource ownership, quantity, quality, use, distribution, etc., the prices, usage rights, revenues, etc. are supplemented through a unified reference time point (period) to estimate the economic value of the assets, and the situation of six types of natural resources owned by the whole people, such as land, minerals, oceans, forests, grasslands, and wetlands, is basically mastered, providing important support for effectively performing the duties of the owner of natural resources owned by the whole people. In the existing natural resource asset inventory programs, the commonly adopted method is to conduct the inventory of natural resource assets through manual statistics. However, the above method often has the following technical problems: Manual statistics takes a long time and there are statistical errors, making it difficult to effectively manage and protect natural resources. Summary of the Invention

[0003] This section of the present application is used to briefly introduce the concepts, which will be described in detail in the following detailed implementation section. This section of the present application is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] Some embodiments of the present application propose a method for inventorying natural resources owned by the whole people based on a real scene three-dimensional model, a computer device, and a computer-readable storage medium to solve one or more of the technical problems mentioned in the above background art section.

[0005] In a first aspect, some embodiments of the present application provide a method for inventorying natural resources assets owned by the whole people based on a real-scene three-dimensional model. The method includes: performing resource area segmentation on the regional remote sensing images of the area to be inventoried for natural resources assets to obtain a set of resource area segmentation images, where there is corresponding resource area geographical reference information for the area to be inventoried for natural resources assets; for each resource area segmentation image in the above set of resource area segmentation images, perform the following recognition steps: generating resource area segmentation information corresponding to the above resource area segmentation image; matching corresponding natural resources asset area information from a pre-established natural resources assets database according to the above resource area segmentation information and the resource area geographical reference information; performing real-scene three-dimensional image acquisition on the resource area corresponding to the above resource area segmentation information to obtain a corresponding set of real-scene three-dimensional images of the resource area, and constructing a real-scene three-dimensional model of the resource area according to the set of real-scene three-dimensional images of the resource area; inputting the above real-scene three-dimensional model of the resource area, the above resource area segmentation information, and the above natural resources asset area information into a pre-trained natural resources assets inventory recognition model to obtain corresponding resource area asset inventory recognition information; and storing each piece of resource area asset inventory recognition information in a corresponding inventory database for natural resources assets owned by the whole people.

[0006] In a second aspect, the present application further provides a computer device. The above computer device includes a processor, a memory, and a computer program stored on the above memory and executable by the above processor. When the above computer program is executed by the above processor, the method described in any implementation manner of the above first aspect is implemented.

[0007] In a third aspect, the present application further provides a computer-readable storage medium. A computer program is stored on the above computer-readable storage medium. When the above computer program is executed by a processor, the method described in any implementation manner of the above first aspect is implemented.

[0008] The above-mentioned various embodiments of the present application have the following beneficial effects: Through the method for inventorying natural resources assets owned by the whole people based on a real-scene three-dimensional model in some embodiments of the present application, the resource area assets of each individual resource area within the natural resources assets inventory area can be quickly and accurately identified, thereby facilitating management and protection based on the resource area assets of different resource areas. First, obtain the regional remote sensing image corresponding to the natural resources assets inventory area to be inventoried and the resource area geographic reference information corresponding to the above-mentioned natural resources assets inventory area to be inventoried. Thus, data support is provided for identifying the resource area assets of different resource areas. Secondly, perform resource area segmentation on the above-mentioned regional remote sensing image to obtain a set of resource area segmentation images. Thus, individual resource areas can be segmented to facilitate asset differentiation. After that, for each resource area segmentation image in the above-mentioned set of resource area segmentation images, perform the following identification steps: generate the resource area segmentation information corresponding to the above-mentioned resource area segmentation image; match the corresponding natural resources asset area information from the pre-established natural resources assets database according to the above-mentioned resource area segmentation information and the resource area geographic reference information; perform real-scene three-dimensional image acquisition on the resource area corresponding to the above-mentioned resource area segmentation information to obtain the corresponding set of real-scene three-dimensional images of the resource area, and construct a real-scene three-dimensional model of the resource area according to the set of real-scene three-dimensional images of the resource area; input the above-mentioned real-scene three-dimensional model of the resource area, the above-mentioned resource area segmentation information, and the above-mentioned natural resources asset area information into the pre-trained natural resources assets inventory and identification model to obtain the corresponding resource area assets inventory and identification information. Thus, through a multi-level segmentation method, accurate image segmentation of the resource area segmentation image is achieved. Thus, other non-resource areas in the roughly segmented resource area segmentation image can be segmented out. Furthermore, the resource area is inventoried for resource area assets through the pre-trained natural resources assets inventory and identification model. The resource area assets of each individual resource area within the natural resources assets inventory area can be quickly and accurately identified. Finally, store each resource area assets inventory and identification information in the corresponding inventory database of natural resources assets owned by the whole people. Thus, the resource area assets of each individual resource area within the natural resources assets inventory area can be quickly and accurately identified, thereby facilitating management and protection based on the resource area assets of different resource areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present application will become more apparent. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0010] Figure 1 is a flowchart of some embodiments of the method for inventorying natural resources assets owned by the whole people based on a real-scene three-dimensional model according to the present application;

[0011] Figure 2 is a schematic structural diagram of a computer device suitable for implementing some embodiments of the present application;

[0012] Figure 3 is a schematic diagram of the grid resolution of the resource area division image in the method for inventorying natural resources assets owned by the whole people based on the real - scene three - dimensional model of the present application;

[0013] Figure 4 is a schematic diagram of pixel supplementation for the resource area segmentation image in the method for inventorying natural resources assets owned by the whole people based on the real - scene three - dimensional model of the present application. Detailed implementation manners

[0014] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not used to limit the protection scope of the present application.

[0015] In addition, it should be noted that for the sake of convenience of description, only parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence relationship of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "multiple" mentioned in the present application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0020] Figure 1 Shows a process 100 of some embodiments of the method for inventorying natural resources assets owned by the whole people based on the real - scene three - dimensional model according to the present application. The method for inventorying natural resources assets owned by the whole people based on the real - scene three - dimensional model includes the following steps:

[0021] Step 101: Perform resource area segmentation on the regional remote sensing images of the natural resource asset inventory area to obtain a set of resource area segmentation images.

[0022] In some embodiments, the execution entity (e.g., a computing device) of the method for inventorying natural resources assets owned by the whole people based on a real-scene three-dimensional model can perform resource area segmentation on the regional remote sensing images of the natural resource asset inventory area to obtain a set of resource area segmentation images. Among them, there is corresponding resource area geographic reference information for the natural resource asset inventory area to be inventoried.

[0023] For example, the above-mentioned execution entity can obtain the regional remote sensing images corresponding to the natural resource asset inventory area to be inventoried and the resource area geographic reference information corresponding to the above-mentioned natural resource asset inventory area from a pre-constructed database. Among them, the natural resource asset inventory area to be inventoried can be an area where natural resource asset inventory is to be carried out. For example, the natural resource asset inventory area to be inventoried can be an area containing various resources such as land resources, mineral resources, and water resources of each user to be inventoried. The regional remote sensing image can refer to a remote sensing image of the natural resource area taken by a remote sensing satellite technology shooting device. The resource area geographic reference information can be a set of real geographic reference data pre-stored for each different resource area in the natural resource asset inventory area to be inventoried. For example, the resource area geographic reference information can include: vector contour data corresponding to each resource area, elevation data corresponding to each resource area. For example, the resource area in each resource area can refer to the land resource area, forest resource area, or water resource area owned by a certain user. For another example, the resource area in each resource area can refer to a certain mineral area or lake area. For example, the resource area geographic reference information can be a set of multiple resource area key-value pairs composed of each resource area in the natural resource asset inventory area to be inventoried. The key in the resource area key-value pair is the resource area identifier, and the pair in the resource area key-value pair is the geographic reference information corresponding to the resource area. The regional remote sensing images corresponding to the natural resource asset inventory area to be inventoried and the resource area geographic reference information corresponding to the above-mentioned natural resource asset inventory area are pre-stored in the pre-constructed database. The regional remote sensing image can be scaled, and the resolution can be shot according to the specified resolution to ensure image clarity.

[0024] For example, the above-mentioned execution entity can send the regional remote sensing image to an associated image segmentation terminal so that technicians can operate the image segmentation terminal to segment or detect the edges of each individual resource area in the regional remote sensing image to obtain resource area segmentation images of individual resource areas.

[0025] In an actual application scenario, the above-mentioned execution entity can perform resource area segmentation on the above-mentioned regional remote sensing image through the following steps to obtain a set of resource area segmentation images:

[0026] First, perform calibration processing on the above regional remote sensing image to obtain a calibrated regional remote sensing image. For example, the calibration processing may include: radiometric calibration, atmospheric calibration, and geometric calibration.

[0027] Second, input the above calibrated regional remote sensing image into a pre-trained resource area segmentation model to obtain a resource area segmentation image set. The resource area segmentation model may refer to a neural network model for single independent resource area segmentation based on image recognition technology. For example, the resource area segmentation model may be a YOLO model.

[0028] Furthermore, the resource area segmentation model may be trained through the following steps:

[0029] First, obtain a sample regional remote sensing image.

[0030] Second, determine the network structure of the initial resource area segmentation model. Among them, the above initial resource area segmentation model includes: a convolutional network, a pooling network, and an upsampling layer. For example, the convolutional network may include multiple convolutional layers. The pooling network may include an average pooling layer.

[0031] Third, input the above sample regional remote sensing image into the above initial resource area segmentation model to obtain an initial resource area segmentation image set.

[0032] Fourth, determine the difference value between the above initial resource area segmentation image set and the corresponding sample segmentation label. For example, the difference value between the above initial resource area segmentation image set and the corresponding sample segmentation label can be determined through a preset loss function. The loss function may be a hinge loss function or a cross-entropy loss function.

[0033] Fifth, in response to determining that the above difference value is less than or equal to a preset threshold, determine the above initial resource area segmentation model as the trained resource area segmentation model.

[0034] Step 102, for each resource area segmentation image in the above resource area segmentation image set, perform the following recognition steps:

[0035] Step 1021, generate resource area segmentation information corresponding to the above resource area segmentation image.

[0036] In some embodiments, the above execution subject may generate resource area segmentation information corresponding to the above resource area segmentation image.

[0037] In an actual application scenario, the above execution subject generates resource area segmentation information corresponding to the above resource area segmentation image through the following steps:

[0038] First, generate a set of resource area division image feature information and global resource area segmentation image feature information corresponding to the above-mentioned resource area segmentation image. The resource area division image feature information can represent the image semantic content corresponding to the resource area division image. The resource area division image feature information can be the semantic content corresponding to a partial image area in the resource area segmentation image. The resource area division image feature information can be feature information in vector form. One resource area division image feature information corresponds to one resource area division image. The global resource area segmentation image feature information can be the overall resource area segmentation image feature semantic content corresponding to the resource area segmentation image in vector form.

[0039] It should be clear that the resource area segmentation image is only a remote sensing image of the separately segmented resource areas, and this resource area segmentation image may contain images of other non-resource areas, so further division / segmentation is required.

[0040] For example, the above-mentioned execution entity can generate a set of resource area division image feature information and global resource area segmentation image feature information corresponding to the above-mentioned resource area segmentation image through the following steps:

[0041] First, determine the resolution of the mask image output by the above-mentioned resource area segmentation model as the model resolution. Among them, the input-output and model structure of the resource area segmentation model are determined in advance, and the corresponding model resolution is also set in advance.

[0042] Second, according to the resolution corresponding to the above-mentioned resource area segmentation image and the above-mentioned model resolution, divide the above-mentioned resource area segmentation image to obtain a set of resource area division images. Among them, the resolution corresponding to each resource area division image is the same as the above-mentioned model resolution. For example, the above-mentioned execution entity can determine whether the number of pixel points in the horizontal and vertical directions of the resolution corresponding to the resource area segmentation image on the screen is an integer multiple of the number of pixel points in the horizontal and vertical directions of the model resolution on the screen. Then, if it is an integer multiple, use the area corresponding to the model resolution as a division unit to evenly divide the image corresponding to the resolution to obtain a set of resource area division images. Next, if it is not an integer multiple, perform corresponding direction filling processing on the resource area segmentation image at the above-mentioned resolution so that the resolution of the filled resource area segmentation image in each direction is an integer multiple of the model resolution in each direction. Then, use the area corresponding to the model resolution as a division unit to evenly divide the filled resource area segmentation image to obtain a set of resource area division images.

[0043] Third, input each resource area division image in the above resource area division image set into a vector model to obtain a resource area division image feature information set. Among them, the vector model can be a neural network model that converts an image into a vector form and represents the semantic content of the image features. For example, the vector model can be an Embedding model.

[0044] Fourth, input the above resource area segmentation image into the above vector model to obtain the corresponding global resource area segmentation image feature information.

[0045] As Figure 3 shown, the resolution of the resource area segmentation image is 512*512 and the model resolution can be 256*256. The resource area segmentation image can be divided into a grid, divided into 4 pieces, and the resolution of each corresponding grid is 256*256.

[0046] As Figure 4 shown, the resolution of the resource area segmentation image is 1920*1080 and the model resolution can be 256*256. 1920 and 1080 cannot be divided evenly by 256. Therefore, padding pixels are added to the resource area segmentation image to obtain a padded image of 2048*1280. Then, the padded image of 2048*1280 is evenly divided to obtain a resource area division image set in which each resource area division image is 256*256.

[0047] Second step, according to the above global resource area segmentation image feature information, use a pre-trained resource area segmentation model to generate a global resource area mask image.

[0048] For example, the above execution entity can use a pre-trained resource area segmentation model to generate a global resource area mask image according to the above global resource area segmentation image feature information. Among them, the global resource area mask image can be an image representing the mask position information of the resource area in the resource area segmentation image. The image area where the resource area is located in the global resource area mask image is set to black, and the image area where the non-resource area is located is set to yellow. Among them, the resource area segmentation model can be a neural network model for segmenting the resource area in the image. For example, the resource area segmentation model can be an encoding and decoding model. For example, the resource area segmentation model can be a U-net model. The resolution of the global resource area mask image is the same as the resolution of the resource area division image. For example, in response to determining that the resource area segmentation model is a non-interactive segmentation model, the execution entity can input the global resource area segmentation image feature information into the resource area segmentation model to obtain the global resource area mask image.

[0049] For another example, the resource area segmentation model is an interactive segmentation model. Among them, the interactive segmentation model can be a neural network model for image segmentation based on interactive information. For example, the interactive segmentation model can be the SAM (SegmentAnything Model). Input the above-mentioned overall image feature information and resource area image marking information into the above-mentioned interactive segmentation model to obtain a global resource area mask image. Among them, the interactive segmentation model includes: an encoding model (Encoder) and a decoding model (Dencoder). Among them, the resource area image marking information can be the positive example set and negative example set corresponding to the image content in the resource area segmentation image. The positive example set and negative example set can be set on the resource area segmentation image, and the corresponding quantity can be calibrated successively by observing the segmentation effect. For example, a positive example can be that the corresponding point (mask area) is on the resource area in the resource area segmentation image. A negative example can be that the corresponding point is not on the resource area in the resource area segmentation image.

[0050] In the third step, according to the division method corresponding to the resource area division image set, divide the above-mentioned global resource area mask image to obtain a resource area mask division image set. Among them, the division method can be the division method for dividing the resource area segmentation image into the resource area division image set. One resource area mask division image corresponds to one resource area division image. The resource area mask division image can be an image representing the mask position information of the resource area in the resource area division image. As an example, the division method is specifically as follows: The above-mentioned execution entity can determine whether the number of pixel points of the global resource area mask image corresponding to the resolution in the horizontal and vertical directions of the screen is an integer multiple of the number of pixel points of the model resolution in the horizontal and vertical directions of the screen. Then, if it is an integer multiple, use the area corresponding to the model resolution as a division unit to uniformly divide the image corresponding to the resolution to obtain a resource area mask division image set. Then, if it is not an integer multiple, perform corresponding direction filling processing on the global resource area mask image at the above-mentioned resolution so that the resolution of the filled global resource area mask image in each direction is an integer multiple of the model resolution in each direction. Then, use the area corresponding to the model resolution as a division unit to uniformly divide the filled global resource area mask image to obtain a resource area mask division image set.

[0051] Fourthly, for each resource area division image feature information in the above resource area division image feature information set, according to the above resource area division image feature information and the corresponding resource area mask division image, through the above resource area segmentation model, a local resource area mask image corresponding to the above resource area division image feature information is generated. Among them, for resource area division images with corresponding positional relationships in the resource area division image feature information, there are also resource area mask division images with corresponding positional relationships. Among them, the local resource area mask image can be an image of the mask position information where the resource area is located in the resource area division image corresponding to the resource area division image feature information. The resolution of the local resource area mask image is equal to the resolution of the corresponding resource area division image. Performing segmentation of the resource area based on the overall image content can be a global segmentation of the image content corresponding to the resource area. The area content related to the resource area in the resource area can all be segmented out. For example, the above resource area division image feature information and the corresponding resource area mask division image can be input into the resource area segmentation model to obtain the corresponding local resource area mask image.

[0052] In a practical application scenario, the above execution subject can generate the local resource area mask image corresponding to the above resource area division image feature information through the following steps:

[0053] First, generate image marking information corresponding to the above resource area mask division image.

[0054] Second, input the above resource area mask division image into a vector model to obtain resource area mask image feature information.

[0055] Third, input the above resource area mask image feature information, the above resource area division image feature information, and the above image marking information into the above resource area segmentation model to obtain the corresponding local resource area mask image.

[0056] Among them, inputting the above resource area mask image feature information, the above resource area division image feature information, and the above image marking information into the above resource area segmentation model to obtain the corresponding local resource area mask image includes:

[0057] First, determine the resource area division image corresponding to the above resource area division image feature information as the target resource area division image.

[0058] Second, select at least one resource region division image that has an adjacent relationship with the above-mentioned target resource region division image from the above-mentioned resource region division image set as the adjacent resource region division image group. Among them, the adjacent resource region division image can be the image content in the above-mentioned target resource region division image that has a position adjacent relationship with the target resource region division image.

[0059] Third, combine the above-mentioned adjacent resource region division image group and the above-mentioned target resource region division image to obtain a combined resource region division image.

[0060] Fourth, generate the image marking information and the subset of resource region division image feature information corresponding to the above-mentioned combined resource region division image, and use the image marking information and the subset of resource region division image feature information as the alternative image marking information and the target resource region division image subset respectively.

[0061] Fifth, input the above-mentioned target resource region division image subset and the above-mentioned alternative image marking information into the above-mentioned resource region segmentation model to generate a combined resource region mask image.

[0062] Sixth, select the sub-resource region mask image corresponding to the above-mentioned target resource region division image from the above-mentioned combined resource region mask image. For example, first, the corresponding image splitting method can be determined according to the image combination method corresponding to the adjacent resource region division image group and the target resource region division image. Then, according to the image splitting method, select the sub-resource region mask image corresponding to the above-mentioned target resource region division image from the above-mentioned combined resource region mask image.

[0063] Seventh, input the image feature information corresponding to the above-mentioned sub-resource region mask image, the above-mentioned resource region mask image feature information, the above-mentioned resource region division image feature information, and the above-mentioned image marking information into the above-mentioned resource region segmentation model to obtain the corresponding local resource region mask image. For example, the resource region mask image feature information represents the mask content corresponding to the resource region division image feature information after the resource region segmentation of the resource region segmentation image.

[0064] Thus, inputting the regional mask feature centered on the target resource region division image into the resource region segmentation model can enable the model to learn a mask content of higher quality relative to the mask image feature information, making the subsequent local mask image more accurate.

[0065] Step 5: Generate the resource area segmentation information corresponding to the above-mentioned resource area segmentation image according to each local resource area mask image. The resource area segmentation information may be the image position information of the resource area in the resource area segmentation image, or the image after semantic segmentation of the resource area. For example, first, the local resource area mask images can be combined according to the division method to generate a combined resource area mask image. Then, according to the above-mentioned combined resource area mask image, generate the resource area segmentation information corresponding to the resource area.

[0066] Step 1022: Match the corresponding natural resource asset area information from the pre-established natural resource asset database according to the above-mentioned resource area segmentation information and the resource area geographic reference information.

[0067] In some embodiments, the above-mentioned execution subject may match the corresponding natural resource asset area information from the pre-established natural resource asset database according to the above-mentioned resource area segmentation information and the resource area geographic reference information. The natural resource asset database may be pre-established and correspond to the databases of each resource area within the area to be inventoried of natural resource assets. The natural resource asset area information may represent the asset area information of the resource area corresponding to the above-mentioned resource area segmentation information and the resource area geographic reference information. For example, the natural resource asset area information may include: natural resource area name, natural resource type, natural resource output, natural resource unit value sequence (unit price). The natural resource unit value sequence may represent the value change sequence of the natural resource. For example, on January 1st, the value is A; on January 2nd, the value is B...

[0068] Step 1023: Collect real-scene three-dimensional images of the resource area corresponding to the above-mentioned resource area segmentation information to obtain the corresponding real-scene three-dimensional image set of the resource area, and construct a real-scene three-dimensional model of the resource area according to the real-scene three-dimensional image set of the resource area.

[0069] In some embodiments, the above-mentioned execution subject may collect real-scene three-dimensional images of the resource area corresponding to the above-mentioned resource area segmentation information to obtain the corresponding real-scene three-dimensional image set of the resource area, and construct a real-scene three-dimensional model of the resource area according to the real-scene three-dimensional image set of the resource area. For example, a drone carrying a panoramic three-dimensional camera / 3D camera can be used to collect real-scene three-dimensional images of the resource area corresponding to the above-mentioned resource area segmentation information to obtain the corresponding real-scene three-dimensional image set of the resource area. Among them, the real-scene three-dimensional image set of the resource area can comprehensively represent the set of three-dimensional images of the corresponding resource area. Among them, the real-scene three-dimensional images in the real-scene three-dimensional image set of the resource area have a sequential order.

[0070] In an actual application scenario, the above-mentioned execution subject can construct a real-scene three-dimensional model of the resource area through the following steps:

[0071] First, based on the above-mentioned resource area division image feature information set and the global resource area segmentation image feature information, an initial resource area real-scene three-dimensional model corresponding to the above-mentioned resource area segmentation image is generated. For example, through a three-dimensional modeling tool, based on the above-mentioned resource area division image feature information set and the global resource area segmentation image feature information, an initial resource area real-scene three-dimensional model corresponding to the above-mentioned resource area segmentation image can be constructed. For example, the three-dimensional modeling tool can be: Maya, 3Dmax, Zbrush. It should be noted that through these image feature information, the edge features and three-dimensional features required to represent the initial resource area real-scene three-dimensional model can be used.

[0072] Second, based on the above-mentioned resource area real-scene three-dimensional image set, the above-mentioned initial resource area real-scene three-dimensional model is subjected to resource area real-scene three-dimensional image filling processing to obtain a filled initial resource area real-scene three-dimensional model, which is used as the resource area real-scene three-dimensional model. For example, the Substance Painter tool can be used to fill the above-mentioned resource area real-scene three-dimensional image set into the initial resource area real-scene three-dimensional model in sequence; then, the edge areas of each resource area real-scene three-dimensional image in the filled initial resource area real-scene three-dimensional model are optimized, that is, the same three-dimensional image edge pixel points are removed. Thus, the resource area real-scene three-dimensional model is obtained. It should be noted that the resource area real-scene three-dimensional model can refer to the constructed three-dimensional image model corresponding to the resource area.

[0073] Step 1024: Input the above-mentioned resource area real-scene three-dimensional model, the above-mentioned resource area segmentation information, and the above-mentioned natural resource asset area information into a pre-trained natural resource asset inventory and identification model to obtain corresponding resource area asset inventory and identification information.

[0074] In some embodiments, the above-mentioned execution subject can input the above-mentioned resource area real-scene three-dimensional model, the above-mentioned resource area segmentation information, and the above-mentioned natural resource asset area information into a pre-trained natural resource asset inventory and identification model to obtain corresponding resource area asset inventory and identification information. The natural resource asset inventory and identification model can be a neural network model used to estimate and identify the natural resource asset results of the corresponding resource area. For example, the natural resource asset inventory and identification model can be a Transformer deep learning model, or a resource-capability-value model (RCV model), a CA-Markov model, a FLUS model, an InVEST model. The resource area asset inventory and identification information can represent the estimated asset value of the resource area. For example, if resource area A is a mining area, the resource area asset inventory and identification information can represent a value of XX yuan. For another example, if resource area A is reservoir No. 001, the resource area asset inventory and identification information can represent a value of YY yuan.

[0075] Further, the natural resource asset inventory and identification model can be obtained through the following steps:

[0076] In the first step, obtain the sample data of natural resource assets.

[0077] In the second step, based on the sample data of natural resource assets and the causal model in the initial natural resource asset inventory and identification model, determine the causal coefficients of the factors affecting the value of natural resource assets. Among them, the above-mentioned sample data of natural resource assets includes the characteristic data sequences under various data dimensions, as well as the sample labels of the sample natural resource asset values at different times and different data dimensions. Among them, the causal model can include a linear causal model (Linear DML (Double Machine Learning)), a tree series causal model (Causal Forest DML), etc. For example, the execution entity can determine the causal coefficients of the factors affecting the value of natural resource assets based on the sample data of natural resource assets and the causal model in the initial natural resource asset inventory and identification model.

[0078] Among them, the above-mentioned second step can include:

[0079] 1. Determine the appropriate causal model according to the data characteristics of different characteristic data sequences in the sample data of natural resource assets. For example, for different data characteristics, a suitable causal model can be selected. For example, if it shows linear data, a linear causal model can be selected; and if it shows hierarchical data, a tree series causal model can be selected.

[0080] 2. Based on the above-mentioned sample data of natural resource assets and the determined causal model, generate the causal effects of the factors affecting the value of natural resource assets. For example, the execution entity can input the sample data of natural resource assets into the determined causal model, and analyze the sample data through the causal model, so as to obtain the causal effects of the factors affecting the value of natural resource assets. For example, the execution entity can perform transformation processing on the causal effects of each factor to obtain the causal coefficients of each factor.

[0081] 3. Perform transformation processing on the causal effects of each factor to obtain the causal coefficients of each factor. The execution entity can perform exponential transformation on the causal effects of each factor to obtain the transformed causal coefficients.

[0082] Among them, performing transformation processing on the causal effects of each factor to obtain the causal coefficients of each factor includes:

[0083] 1. Perform exponential transformation on the causal effects of each factor to obtain the transformed causal coefficients.

[0084] 2. Evaluate the transformed causal coefficients and determine the causal coefficients of each factor as the causal coefficients that pass the evaluation.

[0085] In the third step, select the causal coefficient of the target factor from the determined causal coefficients of each factor. Here, the above target factor is the factor corresponding to the target time and target dimension. The target time and target dimension here are usually the time and dimension in which the value of the resource area to be predicted is located. During the model training process, the target time and target dimension are usually the time and data dimension in the natural resource asset sample data. The executing entity can select the factor coefficient that matches the prediction date and granularity.

[0086] In the fourth step, according to the above natural resource asset sample data and the basic natural resource asset identification model in the above initial natural resource asset inventory and identification model, obtain the basic natural resource asset identification result. Among them, the above basic natural resource asset identification model is used to identify the value of natural resource assets at the above target time. The basic natural resource asset identification model can adopt the natural resource asset value prediction models commonly used in related technologies, such as the Transformer deep learning model. Here, the executing entity can input the natural resource asset sample data into the basic natural resource asset identification model to obtain the preliminary prediction result of the value of natural resource assets at the above target time and target dimension.

[0087] In the fifth step, generate the initial natural resource asset identification value output by the above initial natural resource asset inventory and identification model according to the causal coefficient of the above target factor and the above basic natural resource asset identification result. For example, the causal coefficient of the target factor can be multiplied by the basic natural resource asset identification result, and the obtained result can be used as the initial natural resource asset identification value output by the initial natural resource asset inventory and identification model.

[0088] In the sixth step, adjust the above initial natural resource asset inventory and identification model according to the above initial natural resource asset identification value and the corresponding sample label to continue training the adjusted initial natural resource asset inventory and identification model. For example, the loss value between the initial natural resource asset identification value and the corresponding sample label can be determined through a preset loss function. Finally, the above initial natural resource asset inventory and identification model can be adjusted by means of gradient descent.

[0089] In the seventh step, in response to determining that the training of the initial natural resource asset inventory and identification model is completed, determine the trained initial natural resource asset inventory and identification model as the natural resource asset inventory and identification model.

[0090] Step 103: Store each resource area asset inventory and identification information in the corresponding inventory database of natural resources owned by the whole people.

[0091] In some embodiments, the above-mentioned execution entity may store the inventory identification information of each resource area asset in the corresponding national natural resource asset inventory database. The national natural resource asset inventory database may be a pre-established database for storing the inventory identification information of the resource areas that have completed the inventory.

[0092] Figure 2 FIG. is a schematic block diagram of the structure of a computer device provided by an embodiment of the present disclosure. The computer device may be a terminal.

[0093] As Figure 2 shown, the computer device includes a processor, a memory, and a network interface connected by a system bus. Among them, the memory may include a non-volatile storage medium and an internal memory.

[0094] The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions, which when executed, may cause the processor to execute any one of the methods for inventorying national natural resource assets based on a real-scene three-dimensional model.

[0095] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0096] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, it may cause the processor to execute any one of the methods for inventorying national natural resource assets based on a real-scene three-dimensional model.

[0097] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 2 the structure shown in FIG. is only a block diagram of some structures related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0098] It should be understood that the processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0099] Among them, in one embodiment, the above-mentioned processor is used to run a computer program stored in the memory to implement the following steps: perform resource area segmentation on the regional remote sensing image of the natural resource asset inventory area to obtain a set of resource area segmentation images, where there is corresponding resource area geographic reference information for the natural resource asset inventory area; for each resource area segmentation image in the above set of resource area segmentation images, perform the following recognition steps: generate resource area segmentation information corresponding to the above resource area segmentation image; match the corresponding natural resource asset area information from the pre-established natural resource asset database according to the above resource area segmentation information and the resource area geographic reference information; perform real-scene three-dimensional image acquisition on the resource area corresponding to the above resource area segmentation information to obtain a corresponding set of resource area real-scene three-dimensional images, and construct a resource area real-scene three-dimensional model according to the set of resource area real-scene three-dimensional images; input the above resource area real-scene three-dimensional model, the above resource area segmentation information, and the above natural resource asset area information into a pre-trained natural resource asset inventory recognition model to obtain corresponding resource area asset inventory recognition information; store each resource area asset inventory recognition information in the corresponding national natural resource asset inventory database.

[0100] The embodiments of the present disclosure also provide a computer-readable storage medium. A computer program is stored on the above computer-readable storage medium. The computer program includes program instructions. The method implemented when the above program instructions are executed may refer to the various embodiments of the method for national natural resource asset inventory based on the real-scene three-dimensional model of the present disclosure.

[0101] Among them, the above computer-readable storage medium may be an internal storage unit of the computer device in the foregoing embodiments, such as the hard disk or memory of the computer device. The above computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device.

[0102] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or system including the element.

[0103] The serial numbers of the above embodiments of the present disclosure are only for description and do not represent the superiority or inferiority of the embodiments. The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for checking all natural resources assets owned by the whole people based on a real-life three-dimensional model, characterized in that: include: Perform resource region segmentation on the regional remote sensing image of the area to be investigated for natural resource assets, and obtain a resource region segmentation image set, wherein the area to be investigated for natural resource assets has corresponding resource region geographic reference information; For each resource region segmentation image in the resource region segmentation image set, the following identification steps are performed: Generating resource region segmentation information corresponding to the resource region segmentation image; According to the resource area segmentation information and the resource area geographic reference information, matching corresponding natural resource asset area information from a pre-established natural resource asset database; Performing real-scene 3D image acquisition on the resource area corresponding to the resource area segmentation information to obtain a corresponding real-scene 3D image set of the resource area, and constructing a real-scene 3D model of the resource area according to the real-scene 3D image set of the resource area; Inputting the resource area real-scene three-dimensional model, the resource area segmentation information and the natural resource asset area information into a pre-trained natural resource asset inventory identification model to obtain corresponding resource area asset inventory identification information; The asset inventory identification information of each resource area is stored in the corresponding national natural resource asset inventory database; The step of generating resource region segmentation information corresponding to the resource region segmentation image includes: Generate a resource region partition image feature information set and global resource region segmentation image feature information corresponding to the resource region segmentation image; Generate a global resource region mask image based on the global resource region segmentation image feature information and using a pre-trained resource region segmentation model; Performing image division on the global resource region mask image according to the division mode corresponding to the resource region division image set to obtain the resource region mask division image set; For each resource region partition image feature information in the resource region partition image feature information set, generating a local resource region mask image corresponding to the resource region partition image feature information through the resource region segmentation model according to the resource region partition image feature information and the corresponding resource region mask partition image; Generating resource region segmentation information corresponding to the resource region segmentation image according to each local resource region mask image; The step of generating a resource region partition image feature information set and global resource region partition image feature information corresponding to the resource region segmentation image includes: Determining the resolution of the mask image output by the resource region segmentation model as the model resolution; According to the resolution corresponding to the resource region segmentation image and the model resolution, the resource region segmentation image is divided to obtain a resource region segmentation image set, wherein the resolution corresponding to each resource region segmentation image is the same as the model resolution; Inputting each resource area division image in the resource area division image set into a vector model to obtain a resource area division image feature information set; The resource region segmentation image is input into the vector model to obtain corresponding global resource region segmentation image feature information.

2. The method for checking the natural resources assets owned by all people based on the real-life three-dimensional model according to claim 1 is characterized in that: The method of constructing a real-scene three-dimensional model of the resource area according to the real-scene three-dimensional image set of the resource area includes: Generate an initial resource region real-scene three-dimensional model corresponding to the resource region segmentation image according to the resource region segmentation image feature information set and the global resource region segmentation image feature information; According to the resource area real-scene 3D image set, the initial resource area real-scene 3D model is filled with resource area real-scene 3D images to obtain a filled initial resource area real-scene 3D model as the resource area real-scene 3D model.

3. The method for checking the natural resources assets owned by all people based on the real-life three-dimensional model according to claim 1 is characterized in that: The method of generating a local resource region mask image corresponding to the resource region partition image feature information according to the resource region partition image feature information and the corresponding resource region mask partition image through the resource region segmentation model includes: Generate image marking information corresponding to the resource region mask partition image; Inputting the resource region mask partition image into a vector model to obtain resource region mask image feature information; The resource region mask image feature information, the resource region partition image feature information and the image tag information are input into the resource region segmentation model to obtain a corresponding local resource region mask image.

4. The method for checking the natural resource assets owned by all people based on the real-life three-dimensional model according to claim 1 is characterized in that: The resource region segmentation is performed on the regional remote sensing image of the area to be natural resource asset inventory to obtain a resource region segmentation image set, including: Performing correction processing on the regional remote sensing image to obtain a corrected regional remote sensing image; The correction area remote sensing image is input into a pre-trained resource area segmentation model to obtain a resource area segmentation image set.

5. The method for checking the natural resources assets owned by all people based on the real-life three-dimensional model according to claim 4 is characterized in that: Before inputting the correction area remote sensing image into a pre-trained resource area segmentation model to obtain a resource area segmentation image set, the method further includes: Acquire remote sensing images of the sample area; Determine a network structure of an initial resource region segmentation model, wherein the initial resource region segmentation model includes: a convolutional network, a pooling network, and an upsampling layer; Inputting the sample area remote sensing image into the initial resource area segmentation model to obtain an initial resource area segmentation image set; Determine a difference value between the initial resource region segmentation image set and the corresponding sample segmentation label; In response to determining that the difference value is less than or equal to a preset threshold, the initial resource region segmentation model is determined as a trained resource region segmentation model.

6. A computer device, characterized in that: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images