Farmland soil analysis method, device and equipment and storage medium

Abstract

The invention relates to the technical field of agricultural management, in particular to a farmland soil analysis method, device and equipment and a storage medium, and the method comprises the steps: shooting a farmland soil image through an unmanned aerial vehicle when the unmanned aerial vehicle flies at a relatively low height from farmland soil; the farmland soil image is analyzed and recognized, and when it is analyzed and recognized that the farmland soil image contains an insect image, the insect image in the farmland soil image is separated from the background by using an image segmentation algorithm; based on a filling or repairing algorithm, filling an area shielded by insects in the farmland soil image after the insect image and the background are separated; and the filled farmland soil image is analyzed based on the visual neural network, so that the fertility and the water content of the farmland soil are judged, accurate analysis and evaluation of the farmland soil are realized under the condition that insects interfere with the unmanned aerial vehicle to shoot the farmland soil image, and more effective farmland management suggestions are provided for farmers.

Description

Technical Field

[0001] The present invention relates to the field of agricultural management technology, and in particular to a farmland soil analysis method, device, equipment and storage medium. Background Art

[0002] In the current agricultural field, using drones to capture farmland soil images has become an important technical means. By analyzing these images through visual neural networks, it is possible to accurately assess soil fertility and water content, and provide farmers with effective fertilization and irrigation recommendations, thereby improving farmland production efficiency and crop quality. However, with the development of drone photography technology, some challenges have gradually emerged. For example, when shooting at a low altitude from the farmland soil, it may be interfered by insects flying over or blocking the lens, thus affecting the quality and availability of the image. This interference makes the soil features unclear, which in turn affects the accuracy of soil analysis and farmland management.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and storage medium for analyzing farmland soil, aiming to solve the technical problem that when existing drones are shooting at a low altitude from farmland soil, they may be interfered by insects flying over or blocking the lens, thereby affecting the quality and usability of the image. This interference makes the soil characteristics unclear, which in turn affects the accuracy of soil analysis and farmland management.

[0005] To achieve the above object, the present invention provides a method for analyzing farmland soil, the method comprising:

[0006] When the drone is flying at a relatively low altitude from the farmland soil, the drone is used to take images of the farmland soil;

[0007] Analyzing and identifying the farmland soil image, and when the farmland soil image is identified to contain an insect image, using an image segmentation algorithm to separate the insect image from the background in the farmland soil image;

[0008] Filling the area blocked by insects in the farmland soil image after the insect image is separated from the background based on a filling or repair algorithm;

[0009] The filled farmland soil image is analyzed based on a visual neural network to determine the fertility and water content of the farmland soil.

[0010] Optionally, the filling or repairing algorithm is used to fill in the area blocked by the insects in the farmland soil image after the insect image is separated from the background, including:

[0011] Acquire a farmland soil image that does not contain an insect image and is closest to the farmland soil image that contains an insect image;

[0012] Determine a virtual insect background image in the farmland soil image not containing the insect image based on the insect position in the farmland soil image containing the insect image;

[0013] Based on the virtual insect background image, the area blocked by the insects in the farmland soil image after the insect image is separated from the background is filled by a filling or repair algorithm.

[0014] Optionally, the acquiring of the farmland soil image not containing the insect image that is closest to the farmland soil image containing the insect image comprises:

[0015] Acquire farmland soil images within a preset frame time before and after the farmland soil image containing the insect image;

[0016] The farmland soil image not containing the insect image and closest to the farmland soil image containing the insect image is obtained from the farmland soil images within the preset frame time length before and after.

[0017] Optionally, after acquiring the farmland soil image within a preset frame time length before and after the farmland soil image containing the insect image, the method further includes:

[0018] When no farmland soil image that does not contain an insect image is detected in the farmland soil images within the preset frame time before and after, adjusting the shooting angle or height of the drone;

[0019] Reacquiring the farmland soil image within a second preset frame time before and after the farmland soil image containing the insect image based on the adjusted shooting angle or height of the drone;

[0020] Correspondingly, the step of obtaining the farmland soil image not containing the insect image which is closest to the farmland soil image containing the insect image from the farmland soil images within the preset frame time lengths before and after the farmland soil images includes:

[0021] The farmland soil image not containing the insect image and closest to the farmland soil image containing the insect image is obtained from the farmland soil images within the second preset frame time length before and after.

[0022] Optionally, when no farmland soil image containing no insect image is detected in the farmland soil images within the preset frame time before and after, adjusting the shooting angle or height of the drone includes:

[0023] When no farmland soil image containing no insect image is detected in the farmland soil images within the preset frame time before and after, detecting the number of surrounding insects by using the drone infrared sensor;

[0024] When the number of insects is greater than a preset number of insects, controlling the drone to release a colorless insect repellent to drive away surrounding insects;

[0025] When the number of insects is not greater than a preset number of insects, the shooting angle or height of the drone is adjusted.

[0026] Optionally, when the number of insects is not greater than a preset number of insects, adjusting the shooting angle or height of the drone includes:

[0027] When the number of insects is not greater than a preset number of insects, determining the angle and distance between the surrounding insects and the drone;

[0028] The shooting angle or height of the drone is adjusted by a preset adjustment algorithm based on the angle and distance between the surrounding insects and the drone.

[0029] Optionally, when the number of insects is greater than a preset number of insects, controlling the drone to release a colorless insect repellent to drive away surrounding insects includes:

[0030] When the number of insects is greater than a preset number of insects, determining the types of insects around the drone by using image recognition technology;

[0031] Based on the types of insects around the drone, the drone is controlled to release corresponding colorless insect repellent to drive away the surrounding insects.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also provides a farmland soil analysis device, the farmland soil analysis device comprising:

[0033] An image shooting module is used to shoot images of farmland soil by the drone when the drone is flying at a relatively low altitude from the farmland soil;

[0034] An image separation module is used to analyze and identify the farmland soil image, and when the farmland soil image is analyzed and identified to contain an insect image, separate the insect image from the background in the farmland soil image using an image segmentation algorithm;

[0035] A region filling module is used to fill the region blocked by insects in the farmland soil image after the insect image is separated from the background based on a filling or repair algorithm;

[0036] The farmland judgment module is used to analyze the filled farmland soil image based on the visual neural network, so as to judge the fertility and water content of the farmland soil.

[0037] In addition, to achieve the above-mentioned purpose, the present invention also provides a farmland soil analysis device, which includes: a memory, a processor, and a farmland soil analysis program stored in the memory and executable on the processor, wherein the farmland soil analysis program is configured to implement the steps of the farmland soil analysis method as described in any one of the above texts.

[0038] In addition, to achieve the above-mentioned purpose, the present invention also provides a storage medium, on which a farmland soil analysis program is stored. When the farmland soil analysis program is executed by a processor, the steps of the farmland soil analysis method as described in any one of the above items are implemented.

[0039] The present invention provides a farmland soil analysis method, which comprises: when the unmanned aerial vehicle is flying at a relatively low altitude from the farmland soil, photographing a farmland soil image by the unmanned aerial vehicle; analyzing and identifying the farmland soil image, and when it is analyzed and identified that the farmland soil image contains an insect image, using an image segmentation algorithm to separate the insect image from the background in the farmland soil image; filling in the area blocked by insects in the farmland soil image after the insect image is separated from the background based on a filling or repairing algorithm; analyzing the filled farmland soil image based on a visual neural network, so as to determine the fertility and water content of the farmland soil, so as to achieve accurate analysis and evaluation of the farmland soil when insects interfere with the unmanned aerial vehicle photographing of the farmland soil image, and provide farmers with more effective farmland management suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of the structure of a farmland soil analysis device in the hardware operating environment involved in the embodiment of the present invention;

[0041] Figure 2 This is a schematic diagram of the process of the first embodiment of the farmland soil analysis method of the present invention;

[0042] Figure 3 This is a schematic diagram of the flow chart of the second embodiment of the farmland soil analysis method of the present invention;

[0043] Figure 4 This is a schematic diagram of the process of the third embodiment of the farmland soil analysis method of the present invention;

[0044] Figure 5 It is a structural block diagram of the first embodiment of the farmland soil analysis device of the present invention.

[0045] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0047] Reference Figure 1 , Figure 1 A schematic diagram of the structure of a farmland soil analysis device in the hardware operating environment involved in an embodiment of the present invention.

[0048] like Figure 1 As shown, the farmland soil analysis equipment may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The wired interface of the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable memory (Non-volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0049] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the farmland soil analysis equipment, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0050] like Figure 1 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a farmland soil analysis program.

[0051] exist Figure 1 In the farmland soil analysis device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to peripherals; the farmland soil analysis device calls the farmland soil analysis program stored in the memory 1005 through the processor 1001, and executes the farmland soil analysis method provided by the embodiment of the present invention.

[0052] Based on the above hardware structure, an embodiment of the farmland soil analysis method of the present invention is proposed.

[0053] Reference Figure 2 , Figure 2 It is a flow chart of the first embodiment of the farmland soil analysis method of the present invention, and provides the first embodiment of the farmland soil analysis method of the present invention.

[0054] In a first embodiment, the farmland soil analysis method comprises the following steps:

[0055] S10: When the UAV is flying at a relatively low altitude from the farmland soil, the UAV is used to photograph the farmland soil image.

[0056] It should be noted that the executor of this embodiment can be an electronic device that can acquire farmland soil images and analyze and evaluate the farmland soil images. The electronic device can be installed in a drone, or other electronic devices that can achieve the above functions. This embodiment does not limit this.

[0057] It should be noted that the height and angle of the drone relative to the soil need to be determined before flight to ensure that a comprehensive and clear soil image can be obtained. Adjust the camera equipment on the drone, including the camera parameter settings, such as exposure time, focal length, etc., and the selection of shooting mode, such as single shooting or continuous shooting, to meet the needs of soil images. Design a suitable flight path to ensure that the drone can cover the farmland soil area that needs to be photographed, and avoid overlap or omission to obtain complete soil image data. During the flight, monitor the working status and shooting effect of the camera equipment in real time, and adjust the flight height, speed or angle in time to ensure the quality of the soil image captured. Store and organize the captured farmland soil image data to ensure the integrity and accuracy of the data for subsequent analysis and processing. The implementation method of this step involves the operation technology of the aircraft and the setting adjustment of the photographic equipment, which needs to be implemented in conjunction with advanced flight control systems and camera technology. The effect is to obtain clear and complete farmland soil images, providing a reliable data basis for subsequent soil analysis and evaluation.

[0058] S20: Analyze and identify the farmland soil image. When it is identified that the farmland soil image contains an insect image, use an image segmentation algorithm to separate the insect image from the background in the farmland soil image.

[0059] It should be noted that before image analysis, it is usually necessary to preprocess the image, such as removing noise and enhancing contrast, to improve the accuracy of subsequent algorithms. Use target detection algorithms, such as convolutional neural networks (CNNs) based on deep learning or traditional feature extraction and classification algorithms to identify and locate insects in soil images. Use image segmentation algorithms, such as semantic segmentation or instance segmentation, to separate insect images from the background. This can be done by using pixel-level segmentation methods to assign each pixel in the image to different categories, thereby achieving accurate separation of insects from the background. Optimize and post-process the segmentation results, such as removing small areas or isolated pixels in the segmentation results and filling blank areas at the segmentation boundaries to improve the accuracy and completeness of the separation of insects from the background. Quantitatively and qualitatively evaluate the segmentation results, such as calculating indicators such as accuracy, recall rate and F1 score, or visually evaluating the separation effect of insects from the background by visualizing the segmentation results. The implementation methods of these steps can use relevant algorithms and technologies in the fields of image processing and machine learning, such as deep learning models, image segmentation algorithms, feature extraction and classification technologies, etc. The effect of this step is to achieve accurate separation of insects and background in farmland soil images, providing clear image data for subsequent restoration and analysis.

[0060] S30: Filling the area blocked by insects in the farmland soil image after the insect image is separated from the background based on a filling or repair algorithm.

[0061] It should be noted that first, it is necessary to determine which areas are blocked by insects and need to be filled. This can be determined by the results of insect and background segmentation. Select a suitable filling or repair algorithm, such as an image repair algorithm based on texture synthesis, a content filling algorithm based on deep learning, etc. These algorithms can infer the content of the blocked area based on the information of surrounding pixels and fill it. Use the pixel information around the area blocked by insects, including features such as color and texture, as the input of the filling algorithm. This information can help the algorithm predict the content of the blocked area more accurately. Apply the selected filling algorithm to the blocked area and generate the filling result based on the information of the surrounding pixels. The algorithm will automatically fill the blocked area to restore the image to its original state. Evaluate the quality of the filled image, such as comparing it with the original image, checking the consistency of the filled area with the surrounding environment, and whether the filling result is consistent with visual perception. This can be done through visual inspection or quantitative evaluation. The specific implementation method of the filling algorithm may involve related technologies in the fields of image processing and machine learning, such as texture synthesis, generative adversarial network (GAN), etc. The effect of this step is to restore the area blocked by insects to a complete soil image through the filling algorithm, providing an accurate data basis for subsequent soil analysis.

[0062] S40: Analyze the filled farmland soil image based on a visual neural network to determine the fertility and water content of the farmland soil.

[0063] It should be noted that the padded farmland soil image data is prepared, and the corresponding soil fertility and water content annotation data is provided. These data can be obtained through field collection and experiments. Design and build a visual neural network model suitable for soil fertility and water content judgment. This may include convolutional neural networks (CNNs) or other deep learning architectures. The padded soil images are preprocessed, including size standardization, color space conversion, etc., and feature extraction to extract image features that are helpful for fertility and water content judgment. The constructed neural network model is trained using the prepared data set. During the training process, the model will learn the relationship between the soil image and its fertility and water content. The trained model is verified using the validation set and its performance in fertility and water content judgment is evaluated. This may involve the calculation of indicators such as accuracy, recall rate, F1 score, etc. The trained model is applied to the new padded soil image, and the soil fertility and water content are judged through model prediction. The model will output the corresponding prediction results. The implementation methods of these steps involve knowledge and techniques in the field of deep learning, such as neural network architecture design, data preprocessing, model training and tuning, etc. The effect of this step is that the visual neural network is used to automatically judge the fertility and water content of the filled soil image, providing an important reference for soil management and agricultural production.

[0064] The present embodiment provides a farmland soil analysis method, which includes: when the drone is flying at a relatively low altitude from the farmland soil, taking a farmland soil image by the drone; analyzing and identifying the farmland soil image, and when the farmland soil image is analyzed and identified to contain an insect image, using an image segmentation algorithm to separate the insect image from the background in the farmland soil image; filling the area blocked by insects in the farmland soil image after the insect image is separated from the background based on a filling or repair algorithm; analyzing the filled farmland soil image based on a visual neural network to determine the fertility and water content of the farmland soil, thereby achieving accurate analysis and evaluation of the farmland soil in the event that insects interfere with the drone taking the farmland soil image, and providing farmers with more effective farmland management suggestions.

[0065] Reference Figure 3 , Figure 3 The flowchart of the second embodiment of the farmland soil analysis method of the present invention is as follows. In the second embodiment, the filling or repairing algorithm is used to fill the area blocked by insects in the farmland soil image after the insect image is separated from the background, including:

[0066] S301: Acquire a farmland soil image that does not contain an insect image and is closest to a farmland soil image that contains an insect image.

[0067] It should be noted that, first, a method for measuring image similarity needs to be defined, such as the structural similarity index (SSIM) or the peak signal-to-noise ratio (PSNR). These indicators can help measure the similarity between two images. Traverse the farmland soil image library and find images with high similarity to the images containing insect images as candidates. Check the candidate images to ensure that they do not contain insect images. This can be achieved through the results of the previous insect image detection and segmentation steps. Calculate the distance between each candidate image and the image containing insect images. This can use Euclidean distance, Manhattan distance or other distance measurement methods. Select the image with the closest distance to the image containing insect images from the candidate images that do not contain insect images as the final selection. The implementation methods of these steps can involve relevant technologies in the fields of image processing and computer vision, such as image similarity calculation, image detection, distance calculation, etc. The effect of this step is to find the most similar farmland soil image that does not contain insect images for further analysis and comparison, thereby helping farmland management and insect monitoring.

[0068] S302: Determine a virtual insect background image in the farmland soil image that does not contain an insect image based on the insect position in the farmland soil image that contains an insect image.

[0069] It should be noted that the insect detection and segmentation algorithm is used to determine the position and boundaries of the insects in the farmland soil image containing the insects. This can be done using computer vision techniques such as target detection or semantic segmentation. A background area corresponding to the insect position is extracted from the farmland soil image that does not contain the insect image. This can be achieved by sampling the soil background around the insect position to ensure that the generated virtual insect background is similar to the real background. The virtual insect background generated in the above steps is synthesized with the farmland soil image that does not contain the insect image. This can involve image superposition, fusion or blending techniques to ensure that the virtual insect background is naturally connected to the soil image. The synthesized image is quality evaluated to check whether the synthesized insect background matches the real background and whether the synthesis result is natural and realistic. This can be done through visual inspection or image quality evaluation indicators. The implementation methods of these steps involve relevant technologies in the fields of image processing and computer vision, such as target detection, image synthesis, image fusion, etc. The effect of this step is to generate a farmland soil image with a virtual insect background, which can be used for subsequent analysis and processing without being restricted by the real insect position.

[0070] S303: Filling the area blocked by insects in the farmland soil image after the insect image is separated from the background through a filling or repair algorithm based on the virtual insect background image.

[0071] It should be noted that the insect image and the background are separated by an image segmentation algorithm to obtain an insect image and a background image. According to the separation results of the insect image and the background image, the area blocked by the insect is determined, that is, the area that needs to be filled or repaired. Select an appropriate image filling or repair algorithm, such as a pixel-based filling algorithm (such as a mean, median or Gaussian weighted average based on neighborhood pixels), a filling algorithm based on texture synthesis (such as a filling algorithm based on local texture), a filling algorithm based on deep learning, etc. Fill or repair the area blocked by the insect. The algorithm will synthesize appropriate pixel values ​​based on the surrounding background information or the overall image features, so that the filled area blends naturally with the surrounding environment. The quality of the filled or repaired image is evaluated to check whether the filled area is seamlessly connected with the surrounding environment and whether the filling effect is natural and realistic. This can be done through visual inspection or image quality evaluation indicators. The implementation methods of these steps involve relevant technologies in the fields of image processing and computer vision, such as image segmentation, image filling, and repair algorithms. The effect of this step is to successfully fill or repair the area blocked by the insect, making the soil image more complete and accurate in subsequent analysis.

[0072] Reference Figure 4 , Figure 4 The flowchart of the third embodiment of the farmland soil analysis method of the present invention is as follows. In the third embodiment, the step of obtaining the farmland soil image that does not contain an insect image and is closest to the farmland soil image that contains an insect image comprises:

[0073] S3011: Acquire farmland soil images within a preset frame time before and after the farmland soil image containing the insect image;

[0074] S3012: Acquire, from the farmland soil images within the preset frame time before and after, a farmland soil image that does not contain an insect image and is closest to the farmland soil image that contains an insect image.

[0075] It should be noted that the purpose of obtaining farmland soil images within the preset frame duration before and after the farmland soil image containing the insect image is to ensure that relevant information in the continuous frames is obtained, so as to better understand the distribution and activities of insects in the soil. The preset frame duration before and after refers to an interval set on the time axis to determine the time span of the continuous frames before and after the farmland soil image containing the insect image. For example, if the preset frame duration before and after is set to 10 minutes, it means that the system will obtain farmland soil images within 10 minutes before and after the farmland soil image containing the insect image.

[0076] Specifically, first, a time window needs to be set, including farmland soil images within the preset frame duration before and after, to ensure that the continuous frames before and after the farmland soil image containing the insect image are considered. The farmland soil images within the preset frame duration before and after are traversed, and the image that is closest to the farmland soil image containing the insect image and does not contain the insect image is selected as the final selection. This can be achieved by calculating the similarity or distance between images. The effect of this step is to successfully find the closest farmland soil image that does not contain the insect image for subsequent analysis and comparison, which helps to accurately identify the insect situation in the farmland soil and make corresponding farmland management decisions.

[0077] It should be understood that the purpose of limiting a time range is to ensure that the acquired farmland soil images are relevant and continuous, so as to more accurately capture the changes in insect activities and the evolution of the soil environment. This helps to reduce the confusion and clutter of the data and improve the accuracy and reliability of the analysis. At the same time, limiting the time range can also effectively control the amount of data, making subsequent processing more efficient and manageable.

[0078] Furthermore, in this embodiment, after acquiring the farmland soil image within a preset frame time length before and after the farmland soil image containing the insect image, the method further includes:

[0079] When no farmland soil image that does not contain an insect image is detected in the farmland soil images within the preset frame time before and after, adjusting the shooting angle or height of the drone;

[0080] Reacquiring the farmland soil image within a second preset frame time before and after the farmland soil image containing the insect image based on the adjusted shooting angle or height of the drone;

[0081] Correspondingly, the step of obtaining the farmland soil image not containing the insect image which is closest to the farmland soil image containing the insect image from the farmland soil images within the preset frame time lengths before and after the farmland soil images includes:

[0082] The farmland soil image not containing the insect image and closest to the farmland soil image containing the insect image is obtained from the farmland soil images within the second preset frame time length before and after.

[0083] It should be noted that adjusting the shooting angle or height of the drone and reacquiring images can help fill the gaps in farmland soil images where no insect images are detected, ensuring that more comprehensive and accurate image data is obtained. The second preset frame duration refers to the time length of the two preset frames before and after the process of re-adjusting the drone shooting angle or height and reacquiring images when farmland soil images that do not contain insect images are not detected. This time length can be set according to specific circumstances and needs, and usually refers to a pre-set period of time, such as a few seconds or minutes.

[0084] Further, in this embodiment, when no farmland soil image that does not contain an insect image is detected in the farmland soil images within the preset frame time before and after, adjusting the shooting angle or height of the drone includes:

[0085] When no farmland soil image containing no insect image is detected in the farmland soil images within the preset frame time before and after, detecting the number of surrounding insects by using the drone infrared sensor;

[0086] It should be noted that detecting the number of surrounding insects through the drone's infrared sensor means that within the preset frame time before and after, when no insect image is detected in the farmland soil image taken by the drone, the infrared sensor on the drone is used to scan the number of surrounding insects to detect the number of surrounding insects.

[0087] Specifically, infrared sensors can measure the heat distribution of insects, as insects usually generate tiny amounts of heat. The sensors transmit the collected data to the control system on the drone for analysis and processing to determine the number of insects around.

[0088] When the number of insects is greater than a preset number of insects, the drone is controlled to release colorless insect repellent to drive away surrounding insects.

[0089] It should be noted that when the number of surrounding insects is detected to be greater than the preset value, the system will control the drone to release colorless insect repellent to drive away the surrounding insects, thereby obtaining a farmland soil image that does not contain insect images, where the preset number of insects refers to the expected number of insects in the farmland soil image that is set in advance.

[0090] When the number of insects is not greater than a preset number of insects, the shooting angle or height of the drone is adjusted.

[0091] It should be noted that when the number of surrounding insects detected does not exceed the preset value, the system will automatically adjust the shooting angle or height of the drone to ensure that the farmland soil image without insects is obtained. The flight control system can be used to adjust the flight parameters of the drone, such as attitude control or altitude control, to ensure that the angle or height of the camera shooting is sufficient to cover the entire farmland and exclude the interference of insects. Ensure that the camera carried by the drone has a high enough resolution and wide angle to capture the widest possible land area and ensure the quality and accuracy of the soil image.

[0092] Further, in this embodiment, when the number of insects is not greater than a preset number of insects, adjusting the shooting angle or height of the drone includes:

[0093] When the number of insects is not greater than a preset number of insects, determining the angle and distance between the surrounding insects and the drone;

[0094] The shooting angle or height of the drone is adjusted by a preset adjustment algorithm based on the angle and distance between the surrounding insects and the drone.

[0095] It should be noted that by using sensors or visual systems, the system can detect the relative position and distance between the surrounding insects and the drone. The system uses a preset adjustment algorithm to automatically adjust the drone's shooting angle or height based on the angle and distance between the detected surrounding insects and the drone. This may involve changing the flight attitude, altitude or route.

[0096] Specifically, the flight control system and corresponding algorithms can be used to achieve adjustments by controlling the flight attitude or altitude of the drone. For example, according to the relative position of the insects, the flight direction or altitude can be adjusted to ensure that the camera can capture images of the land without insects. Through such adjustments, it is possible to ensure that images of farmland soil without insect interference are obtained, improving the clarity and accuracy of the images.

[0097] Further, in this embodiment, when the number of insects is greater than a preset number of insects, controlling the drone to release a colorless insect repellent to drive away surrounding insects includes:

[0098] When the number of insects is greater than a preset number of insects, determining the types of insects around the drone by using image recognition technology;

[0099] Based on the types of insects around the drone, the drone is controlled to release corresponding colorless insect repellent to drive away the surrounding insects.

[0100] It should be noted that the system can use image recognition technology to analyze the types and numbers of insects around. This can be done by capturing images with the camera onboard the drone and analyzing and identifying them through algorithms. According to the identified insect species, the corresponding colorless insect repellent can be accurately released. These insect repellents can be chemicals or other technologies that can effectively repel insects when they are colorless, while not causing damage to the soil or crops. By releasing colorless insect repellents, the number of surrounding insects can be quickly and effectively reduced, thereby ensuring that the drone can capture undisturbed soil images. This method can improve the quality and accuracy of farmland soil images and provide more reliable data support for agricultural management and decision-making. At the same time, due to the use of colorless insect repellents, there will be no harmful effects on the farmland environment, which meets the requirements of environmental protection and sustainable agriculture.

[0101] In addition, an embodiment of the present invention further proposes a storage medium, on which a farmland soil analysis program is stored. When the farmland soil analysis program is executed by a processor, the steps of the farmland soil analysis method described above are implemented.

[0102] In addition, refer to Figure 5 The embodiment of the present invention further provides a farmland soil analysis device, the farmland soil analysis device comprising:

[0103] The image shooting module 10 is used to shoot farmland soil images by the drone when the drone is flying at a relatively low altitude from the farmland soil;

[0104] An image separation module 20 is used to analyze and identify the farmland soil image, and when the farmland soil image is analyzed and identified to contain an insect image, separate the insect image from the background in the farmland soil image using an image segmentation algorithm;

[0105] A region filling module 30 is used to fill the region blocked by insects in the farmland soil image after the insect image is separated from the background based on a filling or repair algorithm;

[0106] The farmland judgment module 40 is used to analyze the filled farmland soil image based on a visual neural network, so as to judge the fertility and water content of the farmland soil.

[0107] Other embodiments or specific implementations of the farmland soil analysis device of the present invention can refer to the above-mentioned method embodiments and will not be described in detail here.

[0108] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0109] The serial numbers of the embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. In a unit claim that lists several means, several of these means may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order and these words may be interpreted as names.

[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal user device (which can be a mobile phone, a computer, a server, an air conditioner, or a network user device, etc.) to execute the methods described in each embodiment of the present invention.

[0111] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for analyzing farmland soil, characterized in that: The method comprises: When the drone is flying at a relatively low altitude from the farmland soil, the drone is used to take images of the farmland soil; Analyzing and identifying the farmland soil image, and when the farmland soil image is identified to contain an insect image, using an image segmentation algorithm to separate the insect image from the background in the farmland soil image; Filling the area blocked by insects in the farmland soil image after the insect image is separated from the background based on a filling or repair algorithm; The filled farmland soil image is analyzed based on a visual neural network to determine the fertility and water content of the farmland soil.

2. The farmland soil analysis method according to claim 1, characterized in that: The method of filling the area blocked by insects in the farmland soil image after the insect image is separated from the background based on the filling or repair algorithm includes: Acquire a farmland soil image that does not contain an insect image and is closest to the farmland soil image that contains an insect image; Determine a virtual insect background image in the farmland soil image not containing the insect image based on the insect position in the farmland soil image containing the insect image; Based on the virtual insect background image, the area blocked by the insects in the farmland soil image after the insect image is separated from the background is filled by a filling or repair algorithm.

3. The farmland soil analysis method according to claim 2, characterized in that: The step of obtaining a farmland soil image that is closest to the farmland soil image that contains the insect image and does not contain the insect image comprises: Acquire farmland soil images within a preset frame time length before and after the farmland soil image containing the insect image; The farmland soil image not containing the insect image and closest to the farmland soil image containing the insect image is obtained from the farmland soil images within the preset frame time length before and after.

4. The farmland soil analysis method according to claim 3, characterized in that: After acquiring the farmland soil image within a preset frame time length before and after the farmland soil image containing the insect image, the method further includes: When no farmland soil image that does not contain an insect image is detected in the farmland soil images within the preset frame time before and after, adjusting the shooting angle or height of the drone; Reacquiring the farmland soil image within a second preset frame time before and after the farmland soil image containing the insect image based on the adjusted shooting angle or height of the drone; Correspondingly, the step of obtaining the farmland soil image not containing the insect image which is closest to the farmland soil image containing the insect image from the farmland soil images within the preset frame time lengths before and after the farmland soil images includes: The farmland soil image not containing the insect image and closest to the farmland soil image containing the insect image is obtained from the farmland soil images within the second preset frame time length before and after.

5. The farmland soil analysis method according to claim 4, characterized in that: When no farmland soil image containing no insect image is detected in the farmland soil images within the preset frame time length before and after, adjusting the shooting angle or height of the drone includes: When no farmland soil image containing no insect image is detected in the farmland soil images within the preset frame time before and after, detecting the number of surrounding insects by using the drone infrared sensor; When the number of insects is greater than a preset number of insects, controlling the drone to release a colorless insect repellent to drive away surrounding insects; When the number of insects is not greater than a preset number of insects, the shooting angle or height of the drone is adjusted.

6. The farmland soil analysis method according to claim 5, characterized in that: When the number of insects is not greater than a preset number of insects, adjusting the shooting angle or height of the drone includes: When the number of insects is not greater than a preset number of insects, determining the angle and distance between the surrounding insects and the drone; The shooting angle or height of the drone is adjusted by a preset adjustment algorithm based on the angle and distance between the surrounding insects and the drone.

7. The farmland soil analysis method according to claim 5, characterized in that: When the number of insects is greater than a preset number of insects, controlling the drone to release a colorless insect repellent to drive away surrounding insects includes: When the number of insects is greater than a preset number of insects, determining the types of insects around the drone by using image recognition technology; Based on the types of insects around the drone, the drone is controlled to release corresponding colorless insect repellent to drive away the surrounding insects.

8. A farmland soil analysis device, characterized in that: The farmland soil analysis device comprises: An image shooting module is used to shoot images of farmland soil by the drone when the drone is flying at a relatively low altitude from the farmland soil; An image separation module is used to analyze and identify the farmland soil image, and when the farmland soil image is analyzed and identified to contain an insect image, separate the insect image from the background in the farmland soil image using an image segmentation algorithm; A region filling module is used to fill the region blocked by insects in the farmland soil image after the insect image is separated from the background based on a filling or repair algorithm; The farmland judgment module is used to analyze the filled farmland soil image based on the visual neural network, so as to judge the fertility and water content of the farmland soil.

9. A farmland soil analysis device, characterized in that: The device comprises: a memory, a processor, and a farmland soil analysis program stored in the memory and executable on the processor, wherein the farmland soil analysis program is configured to implement the steps of the farmland soil analysis method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a farmland soil analysis program, and when the farmland soil analysis program is executed by the processor, the steps of the farmland soil analysis method according to any one of claims 1 to 7 are implemented.

Images