Ecological slope protection landscape greening method

Abstract

The invention discloses an ecological slope protection landscape greening method, and belongs to the technical field of computers. Through the technical scheme provided by the embodiment of the invention, the region image, the region attribute, the road planning and the greening style data of the target region are acquired, and the plurality of candidate vegetation are determined by using the two-dimensional region image and the region attribute. And based on the three-dimensional region image, the road plan, the region attribute and the greening style data, determining a plurality of target vegetations from the plurality of candidate vegetations, and determining a planting position of each target vegetation in the target region. And generating a target region model of the target region based on the plurality of target vegetations, the planting position of each target vegetation in the target region and the three-dimensional region image, thereby performing visual display on the landscape greening effect of the target region, facilitating the related personnel to check the greening effect of the target region so as to perform final selection, and improving the landscape greening effect of the target region. Therefore, low-cost and efficient landscape greening design is realized.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an ecological slope protection and landscaping method. Background Art

[0002] In the field of ecological slope protection landscape greening, the current greening methods are insufficient. The existing ecological slope protection greening work lacks a comprehensive analysis of the target area. In most cases, greening planning only roughly considers factors such as the environment and does not treat the target area as carefully as it should. For example, when designing the ecological slope protection area for greening, the available data is not fully utilized to achieve overall planning.

[0003] Therefore, the prior art often cannot properly determine the appropriate vegetation and their planting positions on the slope protection, and cannot effectively present the visual effect after greening in advance. Summary of the invention

[0004] The embodiment of the present application provides an ecological slope protection landscaping method, which can determine suitable vegetation and the planting position of vegetation, and can also visualize the simulation results. The technical solution is as follows:

[0005] In one aspect, a method for ecological slope protection and landscaping is provided, the method comprising:

[0006] In response to a request for generating a regional model of a target area, a regional image, regional attributes, road planning, and greening style data of the target area are obtained, wherein the target area is an area where a slope protection to be greened is located, the regional image includes a two-dimensional regional image and a three-dimensional regional image, the regional attributes include environmental data and soil data, and the road planning is a road planning of roads around the target area;

[0007] Determining a plurality of candidate vegetation based on the two-dimensional region image and the region attributes;

[0008] Based on the three-dimensional area image, the road planning, the area attributes and the greening style data, determining a plurality of target vegetations from the plurality of candidate vegetations and determining a planting position of each of the target vegetations in the target area;

[0009] Based on the multiple target vegetations, the planting positions of the respective target vegetations in the target area and the three-dimensional area image, a target area model of the target area is generated, and the target area model is used to display the visualization effect of the target area after greening.

[0010] On the one hand, an ecological slope protection and landscaping device is provided, the device comprising:

[0011] an acquisition module, configured to acquire, in response to a request for generating a regional model of a target region, a regional image, regional attributes, road planning, and greening style data of the target region, wherein the target region is a region where a slope protection to be greened is located, the regional image includes a two-dimensional regional image and a three-dimensional regional image, the regional attributes include environmental data and soil data, and the road planning is a road planning of roads around the target region;

[0012] A candidate vegetation determination module, used to determine a plurality of candidate vegetation based on the two-dimensional area image and the area attributes;

[0013] A target vegetation determination module, configured to determine a plurality of target vegetations from the plurality of candidate vegetations and determine a planting position of each of the target vegetations in the target area based on the three-dimensional area image, the road planning, the area attributes and the greening style data;

[0014] A model generation module is used to generate a target area model of the target area based on the multiple target vegetation, the planting position of each target vegetation in the target area and the three-dimensional area image, and the target area model is used to display the visualization effect of the target area after greening.

[0015] In a possible implementation, the candidate vegetation determination module is used to divide the target area into multiple sub-areas based on the two-dimensional area image and the area attributes, and the similarity between any two adjacent sub-areas is less than or equal to a first similarity threshold; based on the sub-area image, sub-area attributes, adjacent sub-areas and position of each sub-area in the target area, determine the sub-area information of each sub-area, the sub-area image belongs to the two-dimensional area image, and the sub-area attributes belong to the area attributes; based on the sub-area information of each sub-area, determine the multiple candidate vegetations from multiple initial vegetations.

[0016] In a possible implementation, the candidate vegetation determination module is used to divide the target area into multiple sub-area elements; obtain the two-dimensional region element image of each of the sub-area elements from the two-dimensional region image and obtain the region element attributes of each of the sub-area elements from the region attributes; determine the region element information of each of the sub-area elements based on the two-dimensional region element image and the region element attributes of each of the sub-area elements; and cluster the multiple sub-area elements based on the region element information of each of the sub-area elements to obtain the multiple sub-areas, wherein one sub-area includes at least one sub-area element.

[0017] In a possible implementation, the candidate vegetation determination module is used to determine first sub-region information of each of the sub-regions based on the sub-region image and sub-region attributes of each of the sub-regions, wherein the first sub-region information is used to represent the own characteristics of the corresponding sub-region; determine second sub-region information of each of the sub-regions based on adjacent sub-regions of each of the sub-regions and the position within the target region, wherein the second sub-region information is used to represent the reference characteristics of the corresponding sub-region; and combine the first sub-region information and the second sub-region information of each of the sub-regions to obtain the sub-region information of each of the sub-regions.

[0018] In a possible implementation, the candidate vegetation determination module is used to determine a plurality of first reference vegetations from the plurality of initial vegetations based on the first sub-area information of each of the sub-areas and the vegetation information of each of the initial vegetations; and to determine the plurality of candidate vegetations from the plurality of first reference vegetations based on the second sub-area information of each of the sub-areas and the vegetation information of each of the first reference vegetations.

[0019] In a possible implementation, the target vegetation determination module is used to determine multiple target vegetations from the multiple candidate vegetations based on the road planning, the greening style data and the vegetation information of each of the candidate vegetations; and to determine the planting position of each of the target vegetations in the target area based on the three-dimensional area image, the greening style data, the area attributes and the vegetation information of each of the target vegetations.

[0020] In a possible implementation, the road planning includes road type, road size and road shape, and the target vegetation determination module is used to determine the degree of road matching between each candidate vegetation and the roads around the target area based on the road type, road size, road shape and vegetation information of each candidate vegetation; determine multiple second reference vegetations from the multiple candidate vegetations based on the degree of road matching between each candidate vegetation and the roads around the target area; and determine multiple target vegetations from the multiple second reference vegetations based on the greening style data and vegetation information of each second reference vegetation.

[0021] In a possible implementation, the target vegetation determination module is used to determine the sub-region terrain of multiple sub-regions of the target region based on the three-dimensional region image; determine the target vegetation type of each sub-region based on the greening style data and the sub-region terrain of each sub-region; determine the planting position of each target vegetation in the target region based on the target vegetation type of each sub-region, sub-region attributes and vegetation information of each target vegetation, and the sub-region attributes belong to the region attributes.

[0022] In a possible implementation, the target vegetation determination module is used to determine, for any target vegetation among the multiple target vegetations, the degree of matching between the target vegetation and the multiple sub-areas based on the vegetation information of the target vegetation, the target vegetation type of each of the sub-areas, and the sub-area attributes; and determine the planting position of the target vegetation in the target area based on the degree of matching between the target vegetation and the multiple sub-areas.

[0023] In a possible implementation, the model generation module is used to generate a vegetation model of each target vegetation based on the vegetation information of the multiple target vegetations; generate a terrain model of the target area based on the three-dimensional area image; and add the vegetation model of each target vegetation to the terrain model based on the planting position of each target vegetation in the target area to obtain a target area model of the target area.

[0024] On the one hand, a computer device is provided, which includes one or more processors and one or more memories, wherein at least one computer program is stored in the one or more memories, and the computer program is loaded and executed by the one or more processors to implement the ecological slope protection and landscaping method.

[0025] On the one hand, a computer-readable storage medium is provided, in which at least one computer program is stored, and the computer program is loaded and executed by a processor to implement the ecological slope protection and landscaping method.

[0026] On the one hand, a computer program product or computer program is provided, which includes a program code, and the program code is stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the above-mentioned ecological slope protection and landscaping method.

[0027] Through the technical solution provided by the embodiment of the present application, the regional image, regional attributes, road planning and greening style data of the target area are obtained, and multiple candidate vegetations are determined using the two-dimensional regional image and the regional attributes, thereby realizing the preliminary screening of vegetation. Based on the three-dimensional regional image, the road planning, the regional attributes and the greening style data, multiple target vegetations are determined from the multiple candidate vegetations and the planting positions of each target vegetation in the target area are determined, thereby determining the target vegetation to be used in the end, and the planting position of the target vegetation can also be determined, thereby realizing automated landscape greening design, that is, being able to determine suitable vegetation and the planting position of vegetation. Based on the multiple target vegetations, the planting position of each target vegetation in the target area and the three-dimensional regional image, a target area model of the target area is generated, thereby visually displaying the landscape greening effect of the target area, so that relevant personnel can view the greening effect of the target area to make a final selection, thereby realizing low-cost and efficient landscape greening design. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 It is a schematic diagram of an implementation environment of an ecological slope protection and landscaping method provided in an embodiment of the present application;

[0030] Figure 2 This is a flow chart of an ecological slope protection and landscaping method provided in an embodiment of the present application;

[0031] Figure 3 This is another flow chart of an ecological slope protection and landscaping method provided in an embodiment of the present application;

[0032] Figure 4 It is a structural schematic diagram of an ecological slope protection and landscaping device provided in an embodiment of the present application;

[0033] Figure 5 It is a structural diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0035] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with basically the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on quantity and execution order.

[0036] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain better results.

[0037] Machine Learning (ML) is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge sub-models to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning.

[0038] Ecological slope protection: By planting vegetation (trees, shrubs, turf, etc.) on the bank slope, the mechanical effect (deep root anchoring and shallow root reinforcement) and hydrological effect (reducing pore pressure, weakening splash erosion and controlling runoff) of the well-developed root system of plants are used to protect the slope and consolidate the soil, prevent soil erosion, and create landscape while meeting the needs of the ecological environment.

[0039] Landscape greening: Landscape greening refers to the activities of creating a beautiful natural environment and recreational space within a certain area by planting plants, transforming terrain, constructing buildings and arranging garden paths.

[0040] Three-dimensional simulation: Three-dimensional simulation refers to the use of computer technology to generate a realistic virtual environment with multiple senses such as sight, hearing, touch, and taste. Users can use various sensor devices through natural skills to interact with entities in the virtual environment. In the embodiment of the present application, the three-dimensional simulation is to provide users with a preview after greening.

[0041] In the related art, the landscaping of ecological slope protection is usually designed by designers, and the effect of the design depends on the experience and level of the designers. At the same time, it takes a lot of time to communicate with the designers and modify the design plan, resulting in low design efficiency and possible poor results.

[0042] With the vigorous development of machine learning technology, the technical solution provided in the embodiment of the present application can utilize machine learning technology to automatically generate design solutions through collected data, that is, to generate a target area model for people to view, which can improve the design efficiency of landscape greening and reduce design costs.

[0043] Figure 1 This is a schematic diagram of the implementation environment of an ecological slope protection and landscaping method provided in the embodiment of the present application, see Figure 1 , the implementation environment may include a terminal 110 and a server 140.

[0044] The terminal 110 is connected to the server 140 via a wireless network or a wired network. Optionally, the terminal 110 is a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal 110 is installed and runs an application program that supports ecological slope protection and landscaping.

[0045] The server 140 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, distribution networks (Content Delivery Network, CDN) and big data and artificial intelligence platforms. The server 140 can provide background services for applications running on the terminal 110. In the embodiment of the present application, the server is also referred to as an online modeling platform or simulation platform.

[0046] The following is a description of the ecological slope protection and landscaping method provided in the embodiments of the present application. Figure 2 This is a flow chart of an ecological slope protection and landscaping method provided in an embodiment of the present application, see Figure 2 Taking the execution subject as a server as an example, the method includes the following steps.

[0047] 201. In response to a request for generating a regional model of a target area, the server obtains a regional image, regional attributes, road planning, and greening style data of the target area. The target area is an area where an ecological slope protection to be greened is located. The regional image includes a two-dimensional regional image and a three-dimensional regional image. The regional attributes include environmental data and soil data. The road planning is a road planning for roads around the target area.

[0048] The regional model generation request is sent by the terminal to the server. The target area is the area where the slope protection to be landscaped is located. The two-dimensional regional image is used to represent the plane situation of the target area, and the three-dimensional regional image is used to represent the three-dimensional situation of the target area. The environmental data is used to represent the environmental situation of the target area, and the soil data is used to represent the soil situation of the target area. The greening style data is provided by relevant personnel according to needs, usually in text form.

[0049] 202. The server determines a plurality of candidate vegetations based on the two-dimensional region image and the region attributes.

[0050] The candidate vegetation is the vegetation that is more closely matched with the target area, and the candidate vegetation may be subsequently selected as the target vegetation to be planted in the target area.

[0051] 203. The server determines a plurality of target vegetations from the plurality of candidate vegetations and determines a planting position of each target vegetation in the target area based on the three-dimensional area image, the road planning, the area attributes and the greening style data.

[0052] The target vegetation is the candidate vegetation selected to be planted in the target area.

[0053] 204. The server generates a target area model of the target area based on the multiple target vegetations, the planting position of each target vegetation in the target area, and the three-dimensional area image. The target area model is used to display a visualization effect of the target area after greening.

[0054] The target area model is a model showing the effect of greening the target area in a determined manner. The target area model is used to facilitate relevant personnel to view the greening effect of the target area and make a final selection.

[0055] Through the technical solution provided by the embodiment of the present application, the regional image, regional attributes, road planning and greening style data of the target area are obtained, and multiple candidate vegetations are determined using the two-dimensional regional image and the regional attributes, thereby realizing the preliminary screening of vegetation. Based on the three-dimensional regional image, the road planning, the regional attributes and the greening style data, multiple target vegetations are determined from the multiple candidate vegetations and the planting positions of each target vegetation in the target area are determined, thereby determining the target vegetation to be used in the end, and the planting position of the target vegetation can also be determined, thereby realizing automated landscape greening design, that is, being able to determine suitable vegetation and the planting position of vegetation. Based on the multiple target vegetations, the planting position of each target vegetation in the target area and the three-dimensional regional image, a target area model of the target area is generated, thereby visually displaying the landscape greening effect of the target area, so that relevant personnel can view the greening effect of the target area to make a final selection, thereby realizing low-cost and efficient landscape greening design.

[0056] The above steps 201-204 are a brief introduction to the ecological slope protection and landscaping method provided in the embodiment of the present application. The following will combine some examples to more clearly illustrate the ecological slope protection and landscaping method provided in the embodiment of the present application. Figure 3 Taking the execution subject as a server as an example, the method includes the following steps.

[0057] 301. In response to a request for generating a regional model of a target area, the server obtains a regional image, regional attributes, road planning, and greening style data of the target area. The target area is an area where an ecological slope protection to be greened is located. The regional image includes a two-dimensional regional image and a three-dimensional regional image. The regional attributes include environmental data and soil data. The road planning is a road planning for roads around the target area.

[0058] Among them, the regional model generation request is sent by the terminal to the server, which is used to request the generation of the target regional model of the target region, and the target regional model is used to display the visualization effect of the target region after greening. The target region is the area where the slope protection to be landscaped is located. The two-dimensional regional image is used to represent the plane situation of the target region, and the three-dimensional regional image is used to represent the three-dimensional situation of the target region. The biggest difference between the two-dimensional regional image and the three-dimensional regional image is that the three-dimensional regional image carries height information. Environmental data is used to represent the environmental conditions of the target region. For example, environmental data includes climate data, air quality and weather data. Soil data is used to represent the soil conditions of the target region. For example, soil data includes soil type, soil texture, soil organic matter and soil pH value. Greening style data is provided by relevant personnel according to needs, usually in text form. Of course, in other embodiments, greening style data is also a combination of text and image.

[0059] In some embodiments, the regional image of the target area is collected by a drone, that is, the two-dimensional regional image and the three-dimensional regional image of the target area are obtained by a drone. The regional attributes are obtained from a regional attribute database, which stores regional attributes of multiple regions. The road planning is obtained from a planning database, which stores road planning corresponding to multiple regions. The greening style data is uploaded by the terminal, that is, the greening style data is carried in the regional model generation request.

[0060] It should be noted that the regional images, regional attributes and road planning of the above-mentioned target areas are obtained, collected and used after approval by relevant departments, and the process of acquisition, collection and use strictly complies with the requirements of relevant laws and regulations.

[0061] 302. The server determines a plurality of candidate vegetations based on the two-dimensional region image and the region attributes.

[0062] The candidate vegetation is the vegetation that is more closely matched with the target area, and the candidate vegetation may be subsequently selected as the target vegetation to be planted in the target area.

[0063] In a possible implementation, the server divides the target area into a plurality of sub-areas based on the two-dimensional area image and the area attribute, and the similarity between any two adjacent sub-areas is less than or equal to a first similarity threshold. The server determines the sub-area information of each sub-area based on the sub-area image, the sub-area attribute, the adjacent sub-area, and the position in the target area of ​​each sub-area, the sub-area image belongs to the two-dimensional area image, and the sub-area attribute belongs to the area attribute. The server determines the plurality of candidate vegetations from the plurality of initial vegetations based on the sub-area information of each sub-area.

[0064] Among them, multiple sub-regions constitute the target area. The similarity between any two adjacent sub-regions is less than or equal to the first similarity threshold, which means that any two adjacent sub-regions are dissimilar sub-regions. The first similarity threshold is set by the technician according to the actual situation, and the embodiment of the present application does not limit this. The adjacent sub-region of the sub-region refers to other sub-regions adjacent to the sub-region in the target area. Multiple initial vegetations are all vegetation that can be selected. The sub-region image belongs to the two-dimensional region image, which means that the sub-region image is part of the two-dimensional region image. The sub-region attribute belongs to the region attribute, which means that the sub-region attribute can be directly obtained from the region attribute.

[0065] In order to explain the above implementation more clearly, the above implementation is explained in several parts below.

[0066] In the first part, the server divides the target area into a plurality of sub-areas based on the two-dimensional area image and the area attributes.

[0067] In a possible implementation, the server divides the target area into a plurality of sub-area elements. The server obtains a two-dimensional area element image of each sub-area element from the two-dimensional area image and obtains an area element attribute of each sub-area element from the area attribute. The server determines area element information of each sub-area element based on the two-dimensional area element image and the area element attribute of each sub-area element. The server clusters the plurality of sub-area elements based on the area element information of each sub-area element to obtain the plurality of sub-areas, wherein each sub-area includes at least one sub-area element.

[0068] Among them, the sub-region element is the smallest unit that constitutes the sub-region, and the size of the sub-region element is set by the technicians according to the actual situation, and the embodiment of the present application does not limit this.

[0069] For example, the server divides the target area into multiple sub-region elements in a preset manner. The server obtains the two-dimensional region element image of each sub-region element from the two-dimensional region image and obtains the region element attribute of each sub-region element from the region attribute. The server combines the two-dimensional region element image and the region element attribute of each sub-region element to obtain the region element information of each sub-region element. The server extracts features from the region element information of each sub-region element to obtain the region element features of each sub-region element. The server randomly determines multiple initial cluster centers among the multiple sub-region elements. Starting from the multiple initial cluster centers, the server clusters adjacent sub-region elements among the multiple sub-region elements using the region element features of each sub-region element to obtain multiple sub-regions.

[0070] Wherein, the number of the initial cluster centers is set by the technician according to the actual situation, and the embodiment of the present application does not limit this. In the process of clustering, multiple rounds of iterations will be performed, and the cluster centers will be replaced in each iteration to perform re-clustering until the cluster centers no longer change or the number of iterations reaches the number threshold, and the embodiment of the present application does not limit this. In addition, in the process of clustering, clustering will be started from the sub-region elements adjacent to the cluster centers, so as to avoid non-adjacent sub-region elements from being divided into the same cluster. In addition, in the embodiment of the present application, the cluster centers can be merged, that is, when the feature similarity between the regional element features of any two adjacent cluster centers is greater than or equal to the second similarity threshold, the two cluster centers are directly merged into one cluster center. The second similarity threshold is set by the technician according to the actual situation, and the embodiment of the present application does not limit this.

[0071] In the second part, the server determines the sub-region information of each sub-region based on the sub-region image, sub-region attributes, adjacent sub-regions and the position in the target region of each sub-region.

[0072] In a possible implementation, the server determines first subregion information of each subregion based on the subregion image and subregion attribute of each subregion, and the first subregion information is used to represent the corresponding subregion's own characteristics. The server determines second subregion information of each subregion based on the adjacent subregions of each subregion and the position in the target region, and the second subregion information is used to represent the reference characteristics of the corresponding subregion. The server combines the first subregion information and the second subregion information of each subregion to obtain the subregion information of each subregion.

[0073] The self-characteristics are characteristics that are independent of other sub-regions and / or locations, and can be regarded as characteristics that are only related to the sub-region itself. The reference characteristics are characteristics that are related to other sub-regions and / or locations, and are used as references for sub-region information, and are therefore defined as reference characteristics.

[0074] For example, the server extracts features of the sub-region image and sub-region attributes of each sub-region to obtain sub-region image features and sub-region attribute features of each sub-region. The server fuses the sub-region image features and sub-region attribute features of each sub-region to obtain sub-region fusion features of each sub-region. The server performs multiple rounds of iterative decoding on the sub-region fusion features of each sub-region to obtain first sub-region information of each sub-region.

[0075] The process of extracting features from sub-region images and sub-region attributes is the process of encoding sub-region images and sub-region attributes based on the attention mechanism. Encoding based on the attention mechanism can make full use of the contextual information in the sub-region images and sub-region attributes to obtain more accurate results. Correspondingly, decoding based on the attention mechanism can also utilize the contextual information in the sub-region fusion features to obtain the first sub-region information with stronger expression ability.

[0076] Part three: the server determines the plurality of candidate vegetations from the plurality of initial vegetations based on the sub-region information of each sub-region.

[0077] In a possible implementation, the server determines a plurality of first reference vegetations from the plurality of initial vegetations based on the first sub-region information of each sub-region and the vegetation information of each initial vegetation. The server determines the plurality of candidate vegetations from the plurality of first reference vegetations based on the second sub-region information of each sub-region and the vegetation information of each first reference vegetation.

[0078] The vegetation information is used to describe the characteristics of the vegetation, for example, the vegetation information includes vegetation type, vegetation habit, vegetation appearance, and vegetation planting requirements. The first reference vegetation is selected based on the first sub-region information and vegetation information, so the first reference vegetation is vegetation that matches the sub-region itself. The second reference vegetation is selected based on the second sub-region information and vegetation information, so the second reference vegetation is vegetation that matches other sub-regions and sub-region positions related to the sub-region.

[0079] For example, the server performs feature extraction on the first sub-region information of each sub-region and the vegetation information of each initial vegetation to obtain the first sub-region feature of each sub-region and the vegetation feature of each initial vegetation. The server determines the feature similarity between the first sub-region feature of each sub-region and the vegetation feature of each initial vegetation. The server determines the initial vegetation whose corresponding feature similarity is greater than or equal to the third similarity threshold as the first reference vegetation to obtain the multiple first reference vegetations. The server performs feature extraction on the second sub-region information of each sub-region and the vegetation information of each first reference vegetation to obtain the second sub-region feature of each sub-region. The server determines the feature similarity between the second sub-region feature of each sub-region and the vegetation feature of each first reference vegetation. The server determines the first reference vegetation whose corresponding feature similarity is greater than or equal to the fourth similarity threshold as the candidate vegetation to obtain the multiple candidate vegetations.

[0080] Among them, the third similarity threshold and the fourth similarity threshold are set by technical personnel according to actual conditions, and the embodiments of the present application do not limit this. The initial vegetation whose corresponding feature similarity is greater than or equal to the third similarity threshold refers to the initial vegetation whose feature similarity between the vegetation feature and the first sub-region feature of any sub-region is greater than or equal to the third similarity threshold, and accordingly, the first reference vegetation whose corresponding feature similarity is greater than or equal to the fourth similarity threshold refers to the first reference vegetation whose feature similarity between the vegetation feature and the second sub-region feature of any sub-region is greater than or equal to the fourth similarity threshold.

[0081] In order to more clearly illustrate the technical solution provided by the above example, the method of extracting features of vegetation information of the initial vegetation in the above example is described below.

[0082] In some embodiments, the server obtains first sub-vegetation information corresponding to the first sub-region information from the vegetation information of the initial vegetation, and uses a first feature extractor to perform feature extraction on the first sub-vegetation information to obtain vegetation features of the initial vegetation.

[0083] The correspondence between the first sub-vegetation information and the first sub-region information is set by a technician according to actual conditions, and the embodiment of the present application does not limit this. The first feature extractor is used to perform low-dimensional feature extraction, that is, to perform feature extraction at a faster speed, so as to quickly determine the first reference vegetation.

[0084] In order to more clearly illustrate the technical solution provided by the above example, the method of extracting features from the vegetation information of the first reference vegetation in the above example is described below.

[0085] In some embodiments, the server obtains second sub-vegetation information corresponding to the second sub-region information from the vegetation information of the first reference vegetation, and uses a second feature extractor to perform feature extraction on the second sub-vegetation information to obtain vegetation features of the first reference vegetation.

[0086] The correspondence between the second sub-vegetation information and the second sub-region information is set by the technician according to the actual situation, and the embodiment of the present application does not limit this. The second feature extractor is used for feature extraction of the ongoing dimension, that is, in the feature extraction process, the speed of feature extraction and the expression ability of the obtained features are taken into account. The dimension of the vegetation feature of the first reference vegetation is higher than the vegetation feature of the initial vegetation.

[0087] 303. The server determines a plurality of target vegetations from the plurality of candidate vegetations based on the road planning, the greening style data, and the vegetation information of each candidate vegetation.

[0088] The target vegetation is the candidate vegetation selected to be planted in the target area.

[0089] In a possible implementation, the road planning includes road type, road size, and road shape, and the server determines the road matching degree between each candidate vegetation and the road around the target area based on the road type, road size, road shape, and vegetation information of each candidate vegetation. The server determines a plurality of second reference vegetations from the plurality of candidate vegetations based on the road matching degree between each candidate vegetation and the road around the target area. The server determines a plurality of target vegetations from the plurality of second reference vegetations based on the greening style data and vegetation information of each second reference vegetation.

[0090] In order to explain the above implementation more clearly, the above implementation is explained in several parts below.

[0091] In the first part, the server determines the road matching degree between each candidate vegetation and the roads around the target area based on the road type, road size, road shape and vegetation information of each candidate vegetation.

[0092] In a possible implementation, the server extracts features of the road type, road size, road shape, and vegetation information of each candidate vegetation to obtain road type features of the road type, road size features of the road size, road shape features of the road shape, and vegetation features of each candidate vegetation. The server fuses the road type features, road size features, and road shape features to obtain fused road features. The server determines the feature similarity between the fused road features and the vegetation features of each candidate vegetation to obtain the road matching degree between each candidate vegetation and the roads around the target area, and the road matching degree is the feature similarity between the fused road features and the vegetation features of each candidate vegetation.

[0093] In order to more clearly illustrate the technical solution provided by the above example, the method of extracting features of vegetation information of candidate vegetation in the above example is described below.

[0094] In some embodiments, the server obtains the third sub-vegetation information corresponding to the road planning from the vegetation information of the candidate vegetation, and uses a third feature extractor to extract features from the third sub-vegetation information to obtain vegetation features of the candidate vegetation.

[0095] The correspondence between the third sub-vegetation information and the road planning is set by the technician according to the actual situation, and the embodiment of the present application does not limit this. The third feature extractor is used to perform high-dimensional feature extraction, that is, to extract features with stronger expression capabilities. The dimension of the vegetation feature of the candidate vegetation is higher than the vegetation feature of the first reference vegetation.

[0096] In the second part, the server determines a plurality of second reference vegetations from the plurality of candidate vegetations based on the degree of road matching between each candidate vegetation and the roads around the target area.

[0097] In a possible implementation, the server determines, among multiple candidate vegetations, candidate vegetations whose corresponding road matching degree is greater than or equal to a matching degree threshold as second reference vegetations to obtain the multiple second reference vegetations.

[0098] Among them, when the road matching degree is the feature similarity between the fused road feature and the vegetation features of each candidate vegetation, the road matching degree is greater than or equal to the matching degree threshold, which means that the feature similarity is greater than or equal to the fifth similarity threshold. The fifth similarity threshold is set by technical personnel according to actual conditions, and the embodiments of the present application do not limit this.

[0099] Part three: the server determines a plurality of target vegetations from the plurality of second reference vegetations based on the greening style data and the vegetation information of each second reference vegetation.

[0100] In a possible implementation, the server performs feature extraction on the greening style data and the vegetation information of each second reference vegetation to obtain the greening style features of the greening style data and the vegetation features of each second reference vegetation. The server determines the feature similarity between the greening style features and the vegetation features of each second reference vegetation. The server determines the second reference vegetation whose corresponding feature similarity is greater than or equal to the sixth similarity threshold as the target vegetation to obtain the multiple target vegetations.

[0101] Among them, the sixth similarity threshold is set by technical personnel according to actual conditions, and the embodiments of the present application do not limit this.

[0102] In order to more clearly illustrate the technical solution provided by the above example, the method of extracting features from the vegetation information of the second reference vegetation in the above example is described below.

[0103] In some embodiments, the server obtains fourth sub-vegetation information corresponding to the greening style data from the vegetation information of the second reference vegetation, and uses a third feature extractor to perform feature extraction on the fourth sub-vegetation information to obtain vegetation features of the second reference vegetation.

[0104] Among them, the correspondence between the fourth sub-vegetation information and the greening style data is set by technical personnel according to actual conditions, and the embodiment of the present application does not limit this. The dimension of the vegetation characteristics of the second reference vegetation is the same as the vegetation characteristics of the candidate vegetation.

[0105] 304. The server determines a planting position of each target vegetation in the target area based on the three-dimensional area image, the greening style data, the area attributes, and the vegetation information of each target vegetation.

[0106] In a possible implementation, the server determines the sub-region terrains of the multiple sub-regions of the target region based on the three-dimensional region image. The server determines the target vegetation type of each sub-region based on the greening style data and the sub-region terrain of each sub-region. The server determines the planting position of each target vegetation in the target region based on the target vegetation type of each sub-region, the sub-region attribute, and the vegetation information of each target vegetation, and the sub-region attribute belongs to the region attribute.

[0107] Among them, the sub-region terrain is used to describe the topography of the sub-region. Since the three-dimensional regional map carries height information, the sub-region terrain can be determined using the three-dimensional regional map. The target vegetation type refers to the vegetation type that matches the greening style and regional terrain. In the embodiment of the present application, determining the planting location of the target vegetation is to determine the sub-region corresponding to the target vegetation.

[0108] In order to explain the above implementation more clearly, the above implementation is explained in several parts below.

[0109] In the first part, the server determines sub-region terrains of multiple sub-regions of the target region based on the three-dimensional region image.

[0110] In a possible implementation, the server segments the three-dimensional region image to obtain three-dimensional region images corresponding to each sub-region. The server determines the sub-region terrain of each sub-region based on the three-dimensional region images corresponding to each sub-region.

[0111] For example, the server segments the three-dimensional region image to obtain three-dimensional region images corresponding to each sub-region. For any sub-region among the multiple sub-regions, the server determines the sub-region terrain of the sub-region based on the three-dimensional region image of the sub-region and the three-dimensional region images of other sub-regions adjacent to the sub-region among the multiple sub-regions.

[0112] In order to more clearly illustrate the technical solution provided by the above example, the method of determining the sub-region terrain of the sub-region based on the three-dimensional region image of the sub-region and the three-dimensional region images of other sub-regions adjacent to the sub-region in the multiple sub-regions in the above example is explained below.

[0113] In some embodiments, the server generates an initial sub-region terrain of the sub-region based on the three-dimensional region image of the sub-region. The server uses three-dimensional region images of other sub-regions adjacent to the sub-region to correct the edge of the initial sub-region terrain of the sub-region to obtain the sub-region terrain of the sub-region.

[0114] The initial sub-region terrain and the sub-region terrain are both in text form.

[0115] For example, the server extracts features from the three-dimensional region image of the sub-region to obtain the three-dimensional region features of the sub-region. The server performs multiple rounds of iterative decoding on the three-dimensional region features to obtain the initial sub-region terrain of the sub-region. The server extracts features from the three-dimensional region images of other sub-regions adjacent to the sub-region to obtain reference three-dimensional region features of other adjacent sub-regions. The server uses the reference three-dimensional region features and the adjacent relationship between other sub-regions and the sub-region to correct the initial sub-region terrain to obtain the sub-region terrain of the sub-region.

[0116] In the second part, the server determines the target vegetation type of each sub-area based on the greening style data and the sub-area terrain of each sub-area.

[0117] In a possible implementation, for any sub-region among the multiple sub-regions, the server extracts features of the greening style data and the sub-region terrain of the sub-region to obtain the greening style features of the greening style data and the regional terrain features of the sub-region. The server fuses the greening style features with the regional terrain features to obtain vegetation type determination features. The server performs multiple rounds of iterative decoding on the vegetation type determination features to obtain the target vegetation type of the sub-region.

[0118] For example, for any sub-region among the multiple sub-regions, the server encodes the greening style data and the sub-region terrain of the sub-region based on the attention mechanism to obtain the greening style features of the greening style data and the regional terrain features of the sub-region. The server performs weighted fusion of the greening style features and the regional terrain features to obtain vegetation type determination features. The server performs multiple rounds of iterative decoding on the vegetation type determination features based on the attention mechanism to obtain the target vegetation type of the sub-region.

[0119] Among them, the weights for weighted fusion of the greening style features and the terrain features of the region are set by technical personnel according to actual conditions, and the embodiments of the present application do not limit this.

[0120] In the third part, the server determines the planting position of each target vegetation in the target area based on the target vegetation type of each sub-area, the sub-area attribute and the vegetation information of each target vegetation.

[0121] In a possible implementation, for any target vegetation among the multiple target vegetations, the server determines the degree of matching between the target vegetation and the multiple sub-regions based on the vegetation information of the target vegetation, the target vegetation type of each sub-region, and the sub-region attributes. The server determines the planting position of the target vegetation in the target region based on the degree of matching between the target vegetation and the multiple sub-regions.

[0122] For example, for any target vegetation among the multiple target vegetations, the server performs feature extraction on the vegetation information of the target vegetation to obtain the vegetation features of the target vegetation. The server performs feature extraction on the target vegetation type and sub-region attributes of each sub-region to obtain the target sub-region features of each sub-region. The server determines the degree of match between the target vegetation and the multiple sub-regions based on the vegetation features of the target vegetation and the target sub-region features of each sub-region. The server determines the sub-region with the highest degree of match with the target vegetation among the multiple sub-regions as the planting position of the target vegetation in the target region.

[0123] 305. The server generates a target area model of the target area based on the multiple target vegetations, the planting positions of the respective target vegetations in the target area, and the three-dimensional area image. The target area model is used to display a visualization effect of the target area after greening.

[0124] The target area model is a model showing the effect of greening the target area in a determined manner. The target area model is used to facilitate relevant personnel to view the greening effect of the target area and make a final selection.

[0125] In a possible implementation, the server generates a vegetation model of each target vegetation based on the vegetation information of the multiple target vegetations. The server generates a terrain model of the target area based on the three-dimensional area image. The server adds the vegetation model of each target vegetation to the terrain model based on the planting position of each target vegetation in the target area to obtain a target area model of the target area.

[0126] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0127] Through the technical solution provided by the embodiment of the present application, the regional image, regional attributes, road planning and greening style data of the target area are obtained, and multiple candidate vegetations are determined using the two-dimensional regional image and the regional attributes, thereby realizing the preliminary screening of vegetation. Based on the three-dimensional regional image, the road planning, the regional attributes and the greening style data, multiple target vegetations are determined from the multiple candidate vegetations and the planting positions of each target vegetation in the target area are determined, thereby determining the target vegetation to be used in the end, and the planting position of the target vegetation can also be determined, thereby realizing automated landscape greening design, that is, being able to determine suitable vegetation and the planting position of vegetation. Based on the multiple target vegetations, the planting position of each target vegetation in the target area and the three-dimensional regional image, a target area model of the target area is generated, thereby visually displaying the landscape greening effect of the target area, so that relevant personnel can view the greening effect of the target area to make a final selection, thereby realizing low-cost and efficient landscape greening design.

[0128] Figure 4 This is a schematic diagram of the structure of an ecological slope protection and landscaping device provided in an embodiment of the present application, see Figure 4 The device includes: an acquisition module 401, a candidate vegetation determination module 402, a target vegetation determination module 403 and a model generation module 404.

[0129] The acquisition module 401 is used to respond to a request for generating a regional model of a target area and obtain the regional image, regional attributes, road planning and greening style data of the target area. The target area is the area where the slope protection to be greened is located. The regional image includes a two-dimensional regional image and a three-dimensional regional image. The regional attributes include environmental data and soil data. The road planning is the road planning of the roads around the target area.

[0130] The candidate vegetation determination module 402 is used to determine a plurality of candidate vegetation based on the two-dimensional region image and the region attributes.

[0131] The target vegetation determination module 403 is used to determine multiple target vegetations from the multiple candidate vegetations and determine the planting position of each target vegetation in the target area based on the three-dimensional area image, the road planning, the area attributes and the greening style data.

[0132] The model generation module 404 is used to generate a target area model of the target area based on the multiple target vegetations, the planting position of each target vegetation in the target area and the three-dimensional area image. The target area model is used to display the visualization effect of the target area after greening.

[0133] In a possible implementation, the candidate vegetation determination module 402 is used to divide the target area into multiple sub-areas based on the two-dimensional area image and the area attribute, and the similarity between any two adjacent sub-areas is less than or equal to a first similarity threshold. Based on the sub-area image, sub-area attribute, adjacent sub-areas and position of each sub-area in the target area, the sub-area information of each sub-area is determined, the sub-area image belongs to the two-dimensional area image, and the sub-area attribute belongs to the area attribute. Based on the sub-area information of each sub-area, the multiple candidate vegetations are determined from multiple initial vegetations.

[0134] In a possible implementation, the candidate vegetation determination module 402 is used to divide the target area into a plurality of sub-area elements. A two-dimensional area element image of each sub-area element is obtained from the two-dimensional area image and a region element attribute of each sub-area element is obtained from the region attribute. Region element information of each sub-area element is determined based on the two-dimensional area element image and the region element attribute of each sub-area element. Based on the region element information of each sub-area element, the plurality of sub-area elements are clustered to obtain the plurality of sub-areas, wherein one of the sub-areas includes at least one sub-area element.

[0135] In a possible implementation, the candidate vegetation determination module 402 is used to determine first subregion information of each subregion based on the subregion image and subregion attributes of each subregion, where the first subregion information is used to represent the corresponding subregion's own characteristics. Second subregion information of each subregion is determined based on adjacent subregions of each subregion and the position in the target region, where the second subregion information is used to represent the reference characteristics of the corresponding subregion. The first subregion information and the second subregion information of each subregion are combined to obtain the subregion information of each subregion.

[0136] In a possible implementation, the candidate vegetation determination module 402 is configured to determine a plurality of first reference vegetations from the plurality of initial vegetations based on the first sub-region information of each sub-region and the vegetation information of each initial vegetation, and to determine the plurality of candidate vegetations from the plurality of first reference vegetations based on the second sub-region information of each sub-region and the vegetation information of each first reference vegetation.

[0137] In a possible implementation, the target vegetation determination module 403 is used to determine multiple target vegetations from the multiple candidate vegetations based on the road planning, the greening style data, and the vegetation information of each candidate vegetation. Based on the three-dimensional area image, the greening style data, the area attributes, and the vegetation information of each target vegetation, determine the planting position of each target vegetation in the target area.

[0138] In a possible implementation, the road planning includes road type, road size and road shape, and the target vegetation determination module 403 is used to determine the road matching degree between each candidate vegetation and the road around the target area based on the road type, road size, road shape and vegetation information of each candidate vegetation. Based on the road matching degree between each candidate vegetation and the road around the target area, multiple second reference vegetations are determined from the multiple candidate vegetations. Based on the greening style data and the vegetation information of each second reference vegetation, multiple target vegetations are determined from the multiple second reference vegetations.

[0139] In a possible implementation, the target vegetation determination module 403 is used to determine the sub-region terrain of multiple sub-regions of the target region based on the three-dimensional region image. Based on the greening style data and the sub-region terrain of each sub-region, the target vegetation type of each sub-region is determined. Based on the target vegetation type of each sub-region, the sub-region attribute and the vegetation information of each target vegetation, the planting position of each target vegetation in the target region is determined, and the sub-region attribute belongs to the region attribute.

[0140] In a possible implementation, the target vegetation determination module 403 is used to determine, for any target vegetation among the multiple target vegetations, the matching degree between the target vegetation and the multiple sub-regions based on the vegetation information of the target vegetation, the target vegetation type of each sub-region, and the sub-region attributes. Based on the matching degree between the target vegetation and the multiple sub-regions, determine the planting position of the target vegetation in the target region.

[0141] In a possible implementation, the model generation module 404 is used to generate a vegetation model of each target vegetation based on the vegetation information of the multiple target vegetations. Based on the three-dimensional area image, a terrain model of the target area is generated. Based on the planting position of each target vegetation in the target area, the vegetation model of each target vegetation is added to the terrain model to obtain a target area model of the target area.

[0142] It should be noted that: when the ecological slope protection and landscaping device provided in the above embodiment generates a model, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the ecological slope protection and landscaping device provided in the above embodiment and the ecological slope protection and landscaping method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0143] Through the technical solution provided by the embodiment of the present application, the regional image, regional attributes, road planning and greening style data of the target area are obtained, and multiple candidate vegetations are determined using the two-dimensional regional image and the regional attributes, thereby realizing the preliminary screening of vegetation. Based on the three-dimensional regional image, the road planning, the regional attributes and the greening style data, multiple target vegetations are determined from the multiple candidate vegetations and the planting positions of each target vegetation in the target area are determined, thereby determining the target vegetation to be used in the end, and the planting position of the target vegetation can also be determined, thereby realizing automated landscape greening design, that is, being able to determine suitable vegetation and the planting position of vegetation. Based on the multiple target vegetations, the planting position of each target vegetation in the target area and the three-dimensional regional image, a target area model of the target area is generated, thereby visually displaying the landscape greening effect of the target area, so that relevant personnel can view the greening effect of the target area to make a final selection, thereby realizing low-cost and efficient landscape greening design.

[0144] Figure 5This is a schematic diagram of the structure of a server provided in an embodiment of the present application. The server 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 501 and one or more memories 502, wherein at least one computer program is stored in the one or more memories 502, and the at least one computer program is loaded and executed by the one or more processors 501 to implement the methods provided in the above-mentioned various method embodiments. Of course, the server 500 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The server 500 may also include other components for implementing device functions, which will not be described in detail here.

[0145] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including a computer program, and the computer program can be executed by a processor to complete the ecological slope protection and landscaping method in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0146] In an exemplary embodiment, a computer program product or a computer program is also provided, which includes a program code, and the program code is stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the above-mentioned ecological slope protection and landscaping method.

[0147] In some embodiments, the computer program involved in the embodiments of the present application may be deployed and executed on a computer device, or on multiple computer devices located at one location, or on multiple computer devices distributed at multiple locations and interconnected by a communication network. Multiple computer devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.

[0148] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0149] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. An ecological slope protection and landscaping method, characterized in that: The method comprises: In response to a request for generating a regional model of a target area, a regional image, regional attributes, road planning, and greening style data of the target area are obtained, wherein the target area is an area where a slope protection to be greened is located, the regional image includes a two-dimensional regional image and a three-dimensional regional image, the regional attributes include environmental data and soil data, and the road planning is a road planning of roads around the target area; Determining a plurality of candidate vegetation based on the two-dimensional region image and the region attributes; Based on the three-dimensional area image, the road planning, the area attributes and the greening style data, determining a plurality of target vegetations from the plurality of candidate vegetations and determining a planting position of each of the target vegetations in the target area; A target area model of the target area is generated based on the multiple target vegetations, the planting positions of the respective target vegetations in the target area, and the three-dimensional area image, wherein the target area model is used to display a visualization effect of the target area after greening.

2. The method according to claim 1, characterized in that: The determining of a plurality of candidate vegetation based on the two-dimensional regional image and the regional attributes includes: Based on the two-dimensional region image and the region attribute, the target region is divided into a plurality of sub-regions, and the similarity between any two adjacent sub-regions is less than or equal to a first similarity threshold; Determine subregion information of each of the subregions based on a subregion image, a subregion attribute, an adjacent subregion, and a position within the target region of each of the subregions, wherein the subregion image belongs to the two-dimensional region image, and the subregion attribute belongs to the region attribute; Based on the sub-region information of each of the sub-regions, the plurality of candidate vegetations are determined from a plurality of initial vegetations.

3. The method according to claim 2, characterized in that The step of dividing the target area into a plurality of sub-areas based on the two-dimensional area image and the area attribute comprises: Dividing the target area into a plurality of sub-area elements; Acquire a two-dimensional region element image of each of the sub-region elements from the two-dimensional region image and acquire a region element attribute of each of the sub-region elements from the region attribute; Determining the region element information of each of the sub-region elements based on the two-dimensional region element image and the region element attribute of each of the sub-region elements; Based on the region element information of each of the sub-region elements, the multiple sub-region elements are clustered to obtain the multiple sub-regions, and one of the sub-regions includes at least one sub-region element.

4. The method according to claim 2, characterized in that: Determining the subregion information of each of the subregions based on the subregion image, the subregion attribute, the adjacent subregion and the position within the target region of each of the subregions includes: Determine first subregion information of each of the subregions based on the subregion image and the subregion attribute of each of the subregions, where the first subregion information is used to represent the corresponding subregion's own characteristics; Determine second sub-region information of each of the sub-regions based on an adjacent sub-region and a position within the target region, where the second sub-region information is used to represent a reference characteristic of the corresponding sub-region; The first sub-region information and the second sub-region information of each of the sub-regions are combined to obtain the sub-region information of each of the sub-regions.

5. The method according to claim 4, characterized in that The determining the plurality of candidate vegetations from the plurality of initial vegetations based on the sub-region information of each of the sub-regions comprises: Determine a plurality of first reference vegetations from the plurality of initial vegetations based on the first sub-region information of each of the sub-regions and the vegetation information of each of the initial vegetations; The plurality of candidate vegetations are determined from the plurality of first reference vegetations based on the second sub-region information of each of the sub-regions and the vegetation information of each of the first reference vegetations.

6. The method according to claim 1, characterized in that The determining of a plurality of target vegetations from the plurality of candidate vegetations and determining a planting position of each of the target vegetations in the target area based on the three-dimensional area image, the road planning, the area attributes and the greening style data includes: Determine a plurality of target vegetations from the plurality of candidate vegetations based on the road planning, the greening style data and the vegetation information of each of the candidate vegetations; Based on the three-dimensional area image, the greening style data, the area attributes and the vegetation information of each of the target vegetations, the planting position of each of the target vegetations in the target area is determined.

7. The method according to claim 6, characterized in that The road planning includes road type, road size and road shape, and the determining of multiple target vegetations from the multiple candidate vegetations based on the road planning, the greening style data and the vegetation information of each candidate vegetation includes: Determining the degree of road matching between each of the candidate vegetation and the roads around the target area based on the road type, road size, road shape and vegetation information of each of the candidate vegetation; Determining a plurality of second reference vegetations from the plurality of candidate vegetations based on a road matching degree between each of the candidate vegetations and a road around the target area; Based on the greening style data and the vegetation information of each of the second reference vegetations, a plurality of target vegetations are determined from the plurality of second reference vegetations.

8. The method according to claim 6, characterized in that The determining the planting position of each target vegetation in the target area based on the three-dimensional area image, the greening style data, the area attribute and the vegetation information of each target vegetation includes: Determining sub-region topography of a plurality of sub-regions of the target region based on the three-dimensional region image; Determining a target vegetation type for each of the sub-areas based on the greening style data and the sub-area terrain of each of the sub-areas; Based on the target vegetation type of each sub-region, the sub-region attribute and the vegetation information of each target vegetation, the planting position of each target vegetation in the target region is determined, and the sub-region attribute belongs to the region attribute.

9. The method according to claim 8, characterized in that The step of determining the planting position of each target vegetation in the target area based on the target vegetation type of each sub-area, the sub-area attribute and the vegetation information of each target vegetation includes: For any target vegetation among the multiple target vegetations, determining a matching degree between the target vegetation and the multiple sub-areas based on vegetation information of the target vegetation, target vegetation types of each of the sub-areas, and sub-area attributes; Based on the matching degree between the target vegetation and the multiple sub-areas, a planting position of the target vegetation in the target area is determined.

10. The method according to claim 1, characterized in that The generating a target area model of the target area based on the multiple target vegetations, the planting positions of the respective target vegetations in the target area, and the three-dimensional area image comprises: Based on the vegetation information of the multiple target vegetations, generating a vegetation model of each of the target vegetations; Based on the three-dimensional regional image, generating a terrain model of the target area; Based on the planting position of each target vegetation in the target area, the vegetation model of each target vegetation is added to the terrain model to obtain a target area model of the target area.

Images