An orchard field image acquisition method and system based on cloud edge-end cooperation

Abstract

The application provides an orchard field image acquisition method and system based on cloud edge-end cooperation, and relates to the technical field of agricultural planting. The method comprises the following steps: obtaining historical planting information of an orchard through a cloud server, and obtaining yield distribution results of the orchard according to the historical planting information; dividing and sorting the regions of the orchard according to the yield distribution results to obtain corresponding division and sorting results; determining the number of image acquisition devices of each division region according to the division and sorting results, and completing image acquisition. The application combines the advantages of cloud computing, edge computing and terminal devices, and aims to provide comprehensive data support and intelligent decision-making schemes for the management of orchards.

Description

Technical Field

[0001] This invention relates to the field of agricultural planting technology, and more specifically to a method and system for acquiring orchard field images based on cloud-edge-device collaboration. Background Technology

[0002] Currently, an orchard refers to a plot of land planted with fruit trees. Fruit trees should be planted in designated areas for easier management, and the quality and industrialization level of the corresponding fruits are constantly developing and improving. The fruit industry has become the third largest agricultural industry after grain and vegetables, and is a highlight of economic development in many places and one of the pillar industries for farmers to become wealthy.

[0003] However, due to the long growth cycle and high dependence on weather conditions of certain fruit varieties, as well as their popularity in the market, the corresponding requirements for fruit yield are high. In addition, the orchard area is large, and conventional image acquisition methods cannot guarantee the image acquisition accuracy and coverage, which affects the accuracy of yield prediction and subsequent adjustments. Furthermore, the subsequent image processing has not achieved basic cloud-edge-device collaboration, resulting in low data processing efficiency.

[0004] Therefore, how to provide a method for acquiring orchard field images that can solve the above problems is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, the present invention provides a method and system for orchard field image acquisition based on cloud-edge-device collaboration, which combines the advantages of cloud computing, edge computing and terminal devices, and aims to provide comprehensive data support and intelligent decision-making solutions for orchard management.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A method for acquiring orchard field images based on cloud-edge-device collaboration includes the following steps: The historical planting information of the orchard is obtained through a cloud server, and the yield distribution of the orchard is obtained based on the historical planting information. Based on the yield distribution results, the orchard areas are divided and sorted to obtain the corresponding division and sorting results; Based on the division and sorting results, determine the number of image acquisition devices for each divided region, and complete the image acquisition.

[0007] Preferred options also include: Match the corresponding edge computing nodes based on the partitioning and sorting results; The edge computing nodes are used to process the acquired orchard images to obtain the orchard image processing results for each region.

[0008] Preferred options also include: The historical planting information includes: geographical location information, historical image information, and historical yield information; Obtain the current production demand and compare it with the historical production information; When the comparison result exceeds the preset threshold, the area to be adjusted is determined based on the division and sorting results and the orchard image processing results of each area. Adjust the planting parameters for the area to be adjusted.

[0009] Preferably, the specific process for determining the area to be adjusted includes: Extract the historical image corresponding to the area to be adjusted from the historical image information, and process the historical image to obtain the corresponding historical image processing result; The historical image processing results are matched with the orchard image processing results. When the two cannot be matched, the area is identified as the area to be adjusted.

[0010] Preferably, the specific process of matching the historical image processing results with the orchard image processing results includes: The historical images and the orchard images are preprocessed separately. The preprocessed historical images and orchard images are used to extract features to obtain the corresponding historical features and image features. Calculate the similarity between the historical features and the image features, and match the historical image processing results with the orchard image processing results based on the similarity calculation results.

[0011] Preferably, the specific process of matching the historical image processing results with the orchard image processing results based on the similarity calculation results includes: The similarity calculation result is compared with a preset threshold. When the similarity calculation result is less than or equal to the preset threshold, the area corresponding to the orchard image processing result is determined as the area to be adjusted.

[0012] Preferably, the specific process of adjusting the planting parameters of the area to be adjusted includes: Obtain current weather information and current planting parameters for the orchard; A decision-making model for adjusting planting parameters is constructed, and the current meteorological information, current planting parameters, and orchard image are input into the decision-making model for processing to obtain the corresponding processing results. A corresponding adjustment plan is generated based on the processing results; The planting parameters are adjusted according to the adjustment plan.

[0013] This invention also provides an orchard field image acquisition system based on cloud-edge-device collaboration, comprising: The acquisition module is used to acquire historical planting information of the orchard through a cloud server and obtain the yield distribution results of the orchard based on the historical planting information. The sorting module is used to divide and sort the orchard areas according to the yield distribution results, and obtain the corresponding division and sorting results; The acquisition module is used to determine the number of image acquisition devices in each divided region based on the division and sorting results, and to complete image acquisition. The processing module is used to match the corresponding edge computing nodes according to the division and sorting results, and use the edge computing nodes to process the acquired orchard images to obtain the orchard image processing results for each region.

[0014] As can be seen from the above technical solution, compared with the prior art, the present invention discloses a method and system for orchard field image acquisition based on cloud-edge-device collaboration, which has the following beneficial effects: 1. This invention acquires and analyzes historical planting information of orchards through cloud servers, which can accurately understand the yield distribution of orchards. Based on the yield distribution results, the orchards are divided and sorted by region, which can ensure the targeting and efficiency of image acquisition, and at the same time facilitate the adjustment and optimization of subsequent planting parameters. 2. This invention determines the number of image acquisition devices for each area based on the division and sorting results, avoiding resource waste and over-acquisition, and reducing orchard management costs; by processing the acquired orchard images through edge computing nodes, the latency and bandwidth consumption of data transmission to the cloud are reduced, and processing efficiency is improved. 3. When the comparison between the current yield demand and historical yield information exceeds a preset threshold, this invention can automatically determine the area to be adjusted and generate an adjustment plan, thus realizing the intelligent and automated management of orchards. By constructing a decision model for adjusting planting parameters, and comprehensively considering current meteorological information, planting parameters, and orchard images, a more scientific and reasonable planting strategy can be formulated to improve the yield and quality of orchards.

[0015] In summary, the method provided by this invention not only improves the level of intelligence in orchard management, but also achieves a dual improvement in orchard yield and quality through precise adjustment of planting parameters and image acquisition; and provides strong support for the sustainable development of orchards by optimizing resource allocation and reducing management costs. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0017] Figure 1 The overall flowchart of an orchard field image acquisition method based on cloud-edge-device collaboration provided by the present invention; Figure 2 The present invention provides a structural principle block diagram of an orchard field image acquisition system based on cloud-edge-device collaboration. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] See Figure 1 As shown in the figure, this invention discloses a method for acquiring orchard field images based on cloud-edge-device collaboration, including the following steps: Historical planting information of the orchard is obtained through a cloud server, and the yield distribution of the orchard is obtained based on the historical planting information. The orchard areas were divided and sorted according to the yield distribution results, and the corresponding division and sorting results were obtained. The number of image acquisition devices for each divided area is determined based on the division and sorting results, and image acquisition is completed.

[0020] In one specific embodiment, it also includes: Match the corresponding edge computing nodes based on the partitioning and sorting results; Edge computing nodes are used to process the acquired orchard images to obtain the orchard image processing results for each region.

[0021] In one specific embodiment, it also includes: Historical planting information includes: geographical location information, historical image information, and historical yield information; Obtain the current production demand and compare it with historical production information; When the comparison results exceed the preset threshold, the area to be adjusted is determined based on the division and sorting results and the orchard image processing results of each region. Adjust the planting parameters for the area to be adjusted.

[0022] Specifically, the process of determining the number of image acquisition devices for each segmented region based on the segmentation and sorting results includes: Determine the maximum area that can be monitored, the installation height and angle of the image acquisition equipment to determine the corresponding coverage area, and at the same time determine whether the orchard area is an area to be adjusted. If so, the required number should be determined based on the ratio of the coverage area to the coverage region. At the same time, the corresponding key areas should be determined based on actual management needs and actual environmental meteorological parameters. The number of image acquisition devices should be increased appropriately, and the acquisition areas should be overlapped appropriately according to actual management needs during the deployment process to improve the image acquisition accuracy and provide richer raw data sources for subsequent image processing.

[0023] In one specific embodiment, the process of determining the region to be adjusted includes: Extract the historical image corresponding to the area to be adjusted from the historical image information, process the historical image, and obtain the corresponding historical image processing result; The historical image processing results are matched with the orchard image processing results. When the two cannot be matched, the area is identified as the area to be adjusted.

[0024] In one specific embodiment, the process of matching historical image processing results with orchard image processing results includes: The historical images and orchard images are preprocessed separately. The preprocessing process may include image filtering, binarization, etc. Feature extraction is performed on the preprocessed historical images and orchard images to obtain the corresponding historical features and image features; Calculate the similarity between historical features and image features, and match the historical image processing results with the orchard image processing results based on the similarity calculation results.

[0025] In a specific embodiment, the process of matching the historical image processing result with the orchard image processing result based on the similarity calculation result includes: The similarity calculation result is compared with the preset threshold. When the similarity calculation result is less than or equal to the preset threshold, the area corresponding to the orchard image processing result is determined as the area to be adjusted.

[0026] In a specific embodiment, the process of adjusting the planting parameters of the area to be adjusted includes: Obtain current weather information and current planting parameters for the orchard; A decision-making model for adjusting planting parameters was constructed, and current meteorological information, current planting parameters, and orchard images were input into the decision-making model for processing to obtain the corresponding processing results. Generate corresponding adjustment plans based on the processing results; The planting parameters were adjusted according to the adjustment plan.

[0027] Specifically, the decision-making model for adjusting planting parameters can be a fusion model of neural networks and random forests. The neural network can be a BP neural network or a convolutional neural network. The adjustment plan can include the suggested planting parameters, expected effects and possible risks, and provide visualization charts for easy understanding.

[0028] See Figure 2 As shown, this embodiment of the invention also provides a system for orchard field image acquisition based on cloud-edge-device collaboration using any of the above embodiments, comprising: The acquisition module is used to obtain historical planting information of the orchard through the cloud server and obtain the yield distribution results of the orchard based on the historical planting information; The sorting module is used to divide and sort the orchard areas based on the yield distribution results, and obtain the corresponding division and sorting results; The acquisition module is used to determine the number of image acquisition devices in each divided area based on the division and sorting results, and to complete the image acquisition. The processing module is used to match the corresponding edge computing nodes according to the division and sorting results, and use the edge computing nodes to process the acquired orchard images to obtain the orchard image processing results for each region.

[0029] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0030] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for acquiring orchard field images based on cloud-edge-device collaboration, characterized in that, Includes the following steps: The historical planting information of the orchard is obtained through a cloud server, and the yield distribution of the orchard is obtained based on the historical planting information. Based on the yield distribution results, the orchard areas are divided and sorted to obtain the corresponding division and sorting results; Based on the division and sorting results, determine the number of image acquisition devices for each divided region, and complete the image acquisition.

2. The orchard field image acquisition method based on cloud-edge-device collaboration according to claim 1, characterized in that, Also includes: Match the corresponding edge computing nodes based on the partitioning and sorting results; The edge computing nodes are used to process the acquired orchard images to obtain the orchard image processing results for each region.

3. The orchard field image acquisition method based on cloud-edge-device collaboration according to claim 2, characterized in that, Also includes: The historical planting information includes: geographical location information, historical image information, and historical yield information; Obtain the current production demand and compare it with the historical production information; When the comparison result exceeds the preset threshold, the area to be adjusted is determined based on the division and sorting results and the orchard image processing results of each area. Adjust the planting parameters for the area to be adjusted.

4. The orchard field image acquisition method based on cloud-edge-device collaboration according to claim 3, characterized in that, The specific process of determining the area to be adjusted includes: Extract the historical image corresponding to the area to be adjusted from the historical image information, and process the historical image to obtain the corresponding historical image processing result; The historical image processing results are matched with the orchard image processing results. When the two cannot be matched, the area is identified as the area to be adjusted.

5. The orchard field image acquisition method based on cloud-edge-device collaboration according to claim 4, characterized in that, The specific process of matching the historical image processing results with the orchard image processing results includes: The historical images and the orchard images are preprocessed separately. The preprocessed historical images and orchard images are used to extract features to obtain the corresponding historical features and image features. Calculate the similarity between the historical features and the image features, and match the historical image processing results with the orchard image processing results based on the similarity calculation results.

6. The orchard field image acquisition method based on cloud-edge-device collaboration according to claim 5, characterized in that, The specific process of matching the historical image processing results with the orchard image processing results based on the similarity calculation results includes: The similarity calculation result is compared with a preset threshold. When the similarity calculation result is less than or equal to the preset threshold, the area corresponding to the orchard image processing result is determined as the area to be adjusted.

7. The orchard field image acquisition method based on cloud-edge-device collaboration according to claim 4, characterized in that, The specific process of adjusting the planting parameters of the area to be adjusted includes: Obtain current weather information and current planting parameters for the orchard; A decision-making model for adjusting planting parameters is constructed, and the current meteorological information, current planting parameters, and orchard image are input into the decision-making model for processing to obtain the corresponding processing results. A corresponding adjustment plan is generated based on the processing results; The planting parameters are adjusted according to the adjustment plan.

8. A system utilizing the cloud-edge-device collaborative orchard field image acquisition method according to any one of claims 1-7, characterized in that, include: The acquisition module is used to acquire historical planting information of the orchard through a cloud server and obtain the yield distribution results of the orchard based on the historical planting information. The sorting module is used to divide and sort the orchard areas according to the yield distribution results, and obtain the corresponding division and sorting results; The acquisition module is used to determine the number of image acquisition devices in each divided region based on the division and sorting results, and to complete image acquisition. The processing module is used to match the corresponding edge computing nodes according to the division and sorting results, and use the edge computing nodes to process the acquired orchard images to obtain the orchard image processing results for each region.

Images