Intelligent identification method, device, equipment and storage medium for tea tree diseases and pests

Abstract

The present invention belongs to the field of pest and disease identification technology, and in particular relates to a method, device, equipment, and storage medium for intelligently identifying tea plant pests and diseases. The method comprises the following steps: S1: establishing a tea plant pest and disease feature database; S2: obtaining the type of pest and disease likely to occur in the current tea plant period based on the tea plant period; S3: determining, based on the pest and disease type, the tea plant part where the pest and disease feature is likely to appear; S4: obtaining an image of the corresponding tea plant part based on the tea plant part where the pest and disease feature is likely to appear; S5: obtaining pest and disease feature data for the corresponding part in the corresponding period from the tea plant pest and disease feature database based on the tea plant period and the tea plant part where the pest and disease feature is likely to appear; and S6: identifying the type of tea plant pest and disease based on the pest and disease feature data for the corresponding part in the corresponding period and the image of the tea plant part. The present invention can rapidly detect the type of tea plant pest and disease.

Description

Technical Field

[0001] The present invention relates to the technical field of pest and disease identification, and in particular to a method, device, equipment and storage medium for intelligently identifying pests and diseases on tea trees. Background Art

[0002] Tea trees are a plant that can grow continuously for more than two years and are best cultivated in tropical, subtropical, and warm temperate regions, where warm, humid climates are required. Because tea trees grow densely and lushly, they are extremely susceptible to pests and diseases. This vulnerability is a major factor hindering efficient and high-quality tea production. Over 100 tea plantation diseases are known in tea gardens across my country, of which over 30 are common, primarily tea anthracnose, tea leaf blight, tea ring spot, and tea bud blight. Over 400 tea plantation pests are known, of which over 50 are common, primarily the tea geometrid, tea leaf roller, tea caterpillar, and tea tussock moth. To effectively control tea plantation pests and diseases, identifying their species is crucial. Currently, tea plantation pest detection often relies on image features from relevant parts of the tea plant. However, due to the wide variety of tea plant pests and diseases, current methods for identifying tea plant pests and diseases using image features struggle to quickly and accurately identify the specific pests and diseases affecting tea plants. Summary of the Invention

[0003] In view of this, the embodiments of the present invention provide a method, device, equipment and storage medium for intelligent identification of tea tree pests and diseases, which are used to solve the technical problem that the existing technology is difficult to quickly and accurately detect the types of tea tree pests and diseases.

[0004] The technical solution adopted in the present invention is:

[0005] In a first aspect, the present invention provides a method for intelligently identifying tea plant pests and diseases, the method comprising the following steps:

[0006] S1: Establish a database of tea tree pests and diseases that classifies and stores the characteristics of the tea tree pests and diseases according to the period of occurrence and the parts of the tea tree where the pests and diseases occur;

[0007] S2: Obtain the types of pests and diseases that may occur in the current period according to the current period of the tea tree;

[0008] S3: determining the part of the tea tree where the corresponding pests and diseases are likely to appear according to the pest and disease type;

[0009] S4: Acquire images of corresponding tea tree parts according to the parts of the tea tree where pests and diseases are likely to appear;

[0010] S5: according to the current tea tree period and the tea tree part where the pests and diseases are likely to appear, obtain the pest and disease characteristic data of the corresponding part in the corresponding period from the tea tree pest and disease characteristic database;

[0011] S6: Identify the types of tea tree pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea tree part.

[0012] Preferably, the step S1: establishing a tea tree pest and disease characteristic database for classification and storage according to the period of occurrence of tea tree pests and diseases and the tea tree parts where the pest and disease characteristics appear comprises the following steps:

[0013] S11: Establish a database of tea plant pests and diseases characteristics;

[0014] S12: Classify and store the pest and disease characteristic data in the database according to different periods of pest and disease occurrence;

[0015] S13: The characteristic data of pests and diseases belonging to the same period are further classified and stored according to the parts of the tea trees where the characteristics of the pests and diseases appear.

[0016] Preferably, the method of identifying the types of tea tree pests and diseases based on the pest and disease characteristic data of the corresponding parts in the corresponding period and the images of the tea tree parts also includes the following steps.

[0017] S61: Sort characteristic data of different types of pests and diseases in corresponding parts of corresponding periods according to the probability of occurrence of pests and diseases;

[0018] S62: Comparing and analyzing the pest and disease characteristic data with the image of the tea tree part in order of sorting until an identification result is obtained.

[0019] Preferably, in the step S4 of acquiring an image of a corresponding tea tree part according to a tea tree part where the pest and disease characteristics are likely to appear, if the tea tree part where the pest and disease characteristics are likely to appear is a leaf, the following steps are included:

[0020] S41: Acquire an image of a tea tree to be identified;

[0021] S42: Preprocessing the image of the tea tree to obtain a binary image of the leaves and the trunk;

[0022] S43: performing feature comparison on the binary image of the trunk and the binary image of the leaves according to the growth position relationship between the trunk and the leaves, and extracting a preliminary outline image of the leaves;

[0023] S44: Compare the preliminary leaf contour image with the preset leaf, and extract a complete leaf image based on a clustering algorithm.

[0024] Preferably, after the step S6 of identifying the type of tea plant pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea plant part, the following steps are further included:

[0025] S71: Obtain information from pest control experts related to tea plant diseases and pests;

[0026] S72: expert matching based on the results of intelligent identification of tea plant diseases and pests and information of disease and pest control experts;

[0027] S73: Obtain a network link for online interaction with the matched expert based on the expert matching result.

[0028] Preferably, after the step S6 of identifying the type of tea plant pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea plant part, the following steps are further included:

[0029] S81: Determine the severity of the pests and diseases based on the identified pest and disease type, pest and disease characteristic data, and the image of the tea tree part;

[0030] S82: Based on the type and severity of the pests and diseases, the types and quantities of pest control materials are obtained, including pesticides;

[0031] S83: Generate an order for purchasing the pest control materials according to the type and quantity of the materials and send it to the corresponding merchant.

[0032] Preferably, the step S4 of acquiring images of corresponding tea tree parts according to the characteristics of the pests and diseases that are likely to appear further comprises the following steps:

[0033] S401: If the part of the tea tree where the pest and disease characteristics are likely to appear is the tender shoot and / or bud leaf and / or mature leaf, an image of the tea tree to be identified is obtained by taking aerial photos using a drone;

[0034] S402: If the parts of the tea tree where pest and disease characteristics are likely to appear are the trunk and / or mature leaves, a micro or small drone is used to fly into the tea forest to obtain images of the tea tree to be identified.

[0035] In a second aspect, the present invention further provides a device for intelligently identifying tea plant pests and diseases, the device comprising:

[0036] A database establishment module, the database establishment module is used to establish a tea tree pest and disease characteristic database that is classified and stored according to the period of occurrence of tea tree pests and diseases and the tea tree parts where the pests and diseases characteristics appear;

[0037] A pest and disease type acquisition module, which is used to obtain the types of pests and diseases that may occur in the current period according to the current period of the tea tree;

[0038] A tea tree part determination module, configured to determine, based on the pest type, a part of the tea tree where the corresponding pest characteristics are likely to appear;

[0039] An image acquisition module, the image acquisition module is used to acquire images of corresponding tea tree parts according to the tea tree parts where pests and diseases are likely to appear;

[0040] a pest and disease characteristic data acquisition module, wherein the pest and disease characteristic data acquisition module is used to obtain pest and disease characteristic data of corresponding parts of the corresponding period from a tea tree pest and disease characteristic database according to the current tea tree period and the tea tree parts where pest and disease characteristics are likely to appear;

[0041] The pest and disease type identification module is used to identify the type of tea tree pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea tree part.

[0042] In a third aspect, the present invention also provides a method and device for intelligent identification of tea tree diseases and pests, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, wherein when the computer program instructions are executed by the processor, the method described in the first aspect is implemented.

[0043] In a fourth aspect, the present invention further provides a storage medium having computer program instructions stored thereon, which implement the method described in the first aspect when the computer program instructions are executed by a processor.

[0044] Beneficial effects: The method, device, equipment and storage medium for intelligent identification of tea tree pests and diseases of the present invention first establish a tea tree pest and disease feature database, and classify and store the pest and disease feature data in the database according to the period of occurrence of tea tree pests and diseases and the part of the tea tree where the pest and disease features appear. When identifying pests and diseases, on the one hand, according to the period and the part of the tea tree where the pests and diseases occur, the tea tree pest and disease feature data of the corresponding period and corresponding part can be quickly found from a large amount of pest and disease data. On the other hand, an image of the corresponding tea tree part is obtained. Finally, the image and the screened tea tree pest and disease feature data are compared to identify the type of tea tree pest and disease. The present invention can specifically extract images of tea tree parts and tea tree pest and disease data for comparison, accurately locate the characteristics of the parts where the pests and diseases are located, and there is no need to analyze every part of the tea tree and every type of pest, which greatly reduces the amount of calculation and can quickly and accurately identify the types of tea tree pests and diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work, and these are all within the scope of protection of the present invention.

[0046] Figure 1Schematic diagram of a flow chart of the intelligent identification method for tea tree pests and diseases of the present invention;

[0047] Figure 2 A schematic flow chart of the method for establishing a pest and disease characteristic database according to the present invention;

[0048] Figure 3 A schematic flow chart of the method for identifying pest types according to the present invention;

[0049] Figure 4 A schematic diagram of a flow chart of a method for obtaining images of parts of a tea tree according to the present invention;

[0050] Figure 5 This is a schematic flow chart of a method for acquiring tea tree images using a drone according to the present invention;

[0051] Figure 6 A flow chart of a method for establishing an online communication link with a pest control expert based on pest identification results according to the present invention;

[0052] Figure 7 Schematic diagram of the process of the method for automatically purchasing pest control substances according to the pest identification results of the present invention;

[0053] Figure 8 This is a schematic structural diagram of the device for intelligent identification of tea plant diseases and insect pests according to the present invention;

[0054] Figure 9 This is a structural schematic diagram of the device for intelligent identification of tea tree diseases and insect pests according to the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. In the description of the present invention, it should be understood that the orientation or position relationship indicated by the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like is based on the orientation or position relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further limitations, elements defined by the phrase "comprising..." do not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising the elements. The embodiments of the present invention and the features thereof may be combined with each other if there is no conflict, and all are within the scope of protection of the present invention.

[0056] Example 1

[0057] like Figure 1 As shown, this embodiment provides a method for intelligently identifying tea plant pests and diseases, the method comprising the following steps:

[0058] S1: Establish a database of tea tree pests and diseases that classifies and stores the characteristics of the tea tree pests and diseases according to the period of occurrence and the parts of the tea tree where the pests and diseases occur;

[0059] Due to factors such as temperature, humidity, and daylight hours, tea plant diseases and pests occur at specific times. For example, the tea leafhopper (also known as the tea green leafhopper) typically occurs from May to June; the tea geometrid (also known as the tea geometrid) from June to August; the tea caterpillar (also known as the tea caterpillar) from June to August; and the tea aphid (also known as the tea leaf spot) from March to April. Red leaf spot occurs from July to August.

[0060] When tea trees are attacked by pests and diseases, certain parts of the tea trees will show the characteristics of the pests and diseases. For example, the characteristics of tea anthracnose appear on the mature leaves of the tea trees; the characteristics of tea cloud leaf blight appear on the leaves and fruits of the tea trees; the characteristics of tea ring spot appear on the mature and old leaves of the tea trees; the characteristics of tea branch black spot appear on the mature and old leaves of the tea trees; the characteristics of tea white star disease appear on the mature and old leaves of the tea trees; the characteristics of tea moss disease appear on the branches and trunks of the tea trees; and the characteristics of tea root knot nematode disease appear on the root system of the tea trees. The tea geometrid appears on the leaves and stems of tea plants; the tea leaf roller appears on the leaves; the tea scallop moth appears on the leaves, twigs, and young fruit; the green leafhopper appears on the buds, leaves, and young shoots of tea plants; the tea longhorn beetle appears on the branches, trunks, and roots of tea plants; and the false-eyed green leafhopper appears on the buds, leaves, and young shoots of tea plants. When tea plants are affected by these pests and diseases, the corresponding parts of the plant will show signs of changes in color, shape, and texture.

[0061] like Figure 2 As shown, in this embodiment, the step S1: establishing a tea tree pest and disease feature database for classified storage according to the period of occurrence of tea tree pests and diseases and the tea tree parts where the pest and disease features appear, includes the following steps:

[0062] S11: Establish a database of tea plant pests and diseases characteristics;

[0063] When tea trees are attacked by pests and diseases, corresponding pathological features will appear in certain parts of the tea tree. These pathological features are referred to herein as tea tree pest and disease features. For example, the pest and disease features of tea cake disease include circular lesions with sunken fronts, raised, cake-shaped backs, and small yellowish or reddish spots on the affected areas. Leaf margins may be twisted and deformed, leaf sheaths and petioles may be swollen, and young buds may wither and die. For example, the pest and disease features of tea cake disease include scattered gray-black fine particles on the lesions, twisted infected leaves, browning of young buds and leaves, gray-black, scorched lesions, and disease sites located at the leaf tips or margins. This embodiment collects and organizes pest and disease feature information for various types of tea trees to obtain tea tree pest and disease feature data. For example, information on color changes, shape changes, and texture changes on mature tea leaves caused by anthrax can be collected and organized to obtain tea tree pest and disease feature data for anthrax. Another example is information on color changes, shape changes, and texture changes on mature tea leaves caused by the green leafhopper can be collected and organized to obtain tea tree pest and disease feature data for the green leafhopper. By collecting a large amount of pest and disease characteristic data, we can establish a tea tree pest and disease characteristic database with a full range of pest and disease types and rich pest and disease characteristic information, which will prepare for the subsequent identification of various types of pests and diseases.

[0064] S12: Classify and store the pest and disease characteristic data in the database according to different periods of pest and disease occurrence;

[0065] For example, tea geometrids and tea caterpillars both occur from June to August each year, so the tea tree pest and disease characteristic data corresponding to tea geometrids and tea caterpillars can be classified into one large category for storage.

[0066] S13: The characteristic data of pests and diseases belonging to the same period are further classified and stored according to the parts of the tea trees where the characteristics of the pests and diseases appear.

[0067] For example, the tea looper and tea caterpillar belonging to the same period have their pest and disease characteristics appearing on the leaves. Based on the period of occurrence of pests and diseases, the tea looper and tea caterpillar can be classified into the subcategory of "pest and disease characteristics appearing on the leaves" and stored.

[0068] S2: Obtain the types of pests and diseases that may occur in the current period according to the current period of the tea tree;

[0069] For example, if the current period is June, the types of pests and diseases that may occur in the current period include the false-eyed green leafhopper, tea looper, tea caterpillar, etc.

[0070] S3: Determine, based on the pest type, the part of the tea tree where the corresponding pest characteristics are likely to appear; for example, if the likely pest type is the tea geometrid, the parts of the tea tree where the pest characteristics are likely to appear are the leaves and stems of the tea tree. For example, if the likely pest type is the false-eyed green leafhopper, the parts of the tea tree where the pest characteristics are likely to appear are the buds, leaves, and young shoots of the tea tree.

[0071] S4: Acquire images of corresponding tea tree parts according to the parts of the tea tree where pests and diseases are likely to appear;

[0072] In this step, the image of the part of the tea tree where the pest and disease characteristics are likely to appear is first obtained. For example, if the part where the pest and disease characteristics are likely to appear is the trunk, the image of the trunk is obtained; if the part where the pest and disease characteristics are likely to appear is the leaf, the image of the leaf is obtained. Figure 5 As shown, this embodiment can also use different devices to collect images according to the part of the tea tree that needs to be imaged. The method mainly includes the following steps:

[0073] S401: If the part of the tea tree where the pest and disease characteristics are likely to appear is the tender shoot and / or bud leaf and / or mature leaf, an image of the tea tree to be identified is obtained by taking aerial photos using a drone;

[0074] Young shoots, buds, leaves, etc. are mostly located in the canopy of the tea tree. Using a drone to take aerial photos can quickly obtain images of these parts of the tea tree.

[0075] S402: If the parts of the tea tree where pest and disease characteristics are likely to appear are the trunk and / or mature leaves, a micro or small drone is used to fly into the tea forest to obtain images of the tea tree to be identified.

[0076] Since the trunks and leaves of tea trees are easily obscured by other parts of the trees, a small drone can be used to fly into the tea forest and capture images close to these parts. This embodiment uses a coordinated approach of drone aerial photography and close-up image acquisition by a small drone to improve image acquisition efficiency and ensure that effective images are captured for identifying pests and diseases.

[0077] like Figure 4 As shown, when the part where the tea tree pest and disease characteristics appear is the leaves of the tea tree, the method for obtaining the leaves includes the following steps:

[0078] S41: Acquire an image of a tea tree to be identified;

[0079] In this step, an image of the tea tree is first obtained. The image may be an image of a complete tea tree or an image of a portion of the tea tree. However, the image of the tea tree obtained must include leaves.

[0080] S42: Preprocessing the image of the tea tree to obtain a binary image of the leaves and trunk; after the image is binarized, the pixel values ​​corresponding to the leaves and trunk are 1, and the remaining pixel values ​​are 0. For ease of description, in this article, the binary image of the leaves is referred to as the first intermediate image, and the binary image of the trunk is referred to as the second intermediate image, wherein the first intermediate image contains all the characteristic contours of the leaves and some other interfering background contours, and the second intermediate image contains all the characteristic contours of the trunk and some other interfering background contours.

[0081] S43: performing feature comparison on the binary image of the trunk and the binary image of the leaves according to the growth position relationship between the trunk and the leaves, and extracting a preliminary outline image of the leaves;

[0082] This step can eliminate interfering background contours that do not belong to leaves based on the growth position relationship between the trunk and leaves. The aforementioned growth position relationship is based on common sense. Leaves grow on the trunk, that is, the leaves and the trunk must be connected in outline. This eliminates interfering background contours that are not connected to the trunk, here called pseudo-leaf contours. At the same time, in addition to being able to eliminate pseudo-leaf contours, this method can also eliminate the contours of leaves that have fallen from the trunk, preventing pseudo-leaf contours and the contours of fallen leaves from affecting the subsequent extraction and analysis of leaves.

[0083] In specific implementation, plane coordinates are first established on the first and second intermediate images. Then, the coordinates of the contours with pixel values ​​of 1 in the second intermediate image are located, and the coordinates of these pixels in the plane coordinate system are obtained. The coordinates of the contours in the first intermediate image are compared with the coordinates of the contours in the second intermediate image to extract the contours with the same coordinates as those in the first and second intermediate images. Specifically, the coordinates of the intersection of the trunk and the leaves are obtained. Based on the coordinates of the intersection, whether the leaf is connected to the trunk is determined, thereby determining whether the leaf contour is a true leaf contour, a false leaf contour, or a fallen leaf contour. After this determination is completed, a preliminary contour image of the leaf in the first intermediate image is obtained.

[0084] S44: Compare the preliminary leaf contour image with the preset leaf, and extract a complete leaf image based on a clustering algorithm.

[0085] The preliminary leaf contour image may also contain some interference images that cannot be removed. For example, the background contour of a similar color to the leaf partially overlaps with the leaf contour. Another example is that two or more leaves partially overlap, resulting in the misidentification of the leaf contour as a single leaf, affecting the accurate extraction of the leaf and the subsequent analysis of leaf pests and diseases. To address this issue, this step further accurately extracts the complete leaf contour from the preliminary leaf contour. The extraction method specifically includes the following steps:

[0086] S441: Compare the number of pixels in the preliminary leaf outline image with the preset leaf pixel threshold; the area of ​​tea leaves will have a certain normal size range, that is, there is an area threshold, and then by determining the image size (resolution) of the preliminary leaf outline image, the image resolution can be directly determined by the shooting equipment, and the pixel threshold of the normal leaf at this resolution can be pre-set.

[0087] S442: If the number of pixels in the preliminary leaf contour image is within the pixel threshold range, the preliminary leaf contour image is extracted as the complete leaf image; when the number of pixels in the preliminary leaf contour image is within the pre-set pixel threshold range, it means that the preliminary leaf contour image is a complete leaf image.

[0088] S443: If the number of pixels in the preliminary leaf contour image is not within the pixel threshold range, then based on the clustering method, the complete leaf image is extracted from the preliminary leaf contour image; when the number of pixels in the preliminary leaf contour image is less than the preset pixel threshold range, it can be said that the contour is not the contour of the leaf, but may be a small dot contour formed by other backgrounds; when the number of pixels in the preliminary leaf contour image is greater than the preset pixel threshold range, it can be said that there are other overlapping contours on the leaf contour, which may be background contours or contours of other leaves on the trunk. Based on the density-based clustering method, the contours belonging to the leaves can be gradually screened out. In the specific operation, first arbitrarily determine a pixel point in the preliminary leaf contour image as the pixel center point C2;

[0089] Then, with the pixel center point C2 as the center of the circle, obtain N radius values ​​Ri within the radius threshold, and calculate the number of pixels corresponding to the N radius values ​​Ri; obtain N radius values ​​Ri, sequentially from small to large, and obtain the radius intervals from large intervals to small intervals, and calculate the number of pixels corresponding to the corresponding radius value range. The reason for using the method of sequentially obtaining radii from small to large and obtaining radius intervals from large intervals to small intervals is that the corresponding radius range can be determined more quickly without calculating all radius values ​​within the radius threshold, thereby reducing the amount of calculation and improving the calculation speed.

[0090] The number of pixels corresponding to the N radius values ​​Ri is then compared with the minimum number of pixels corresponding to the N radius values ​​Ri in the preset leaf. This embodiment allows for simultaneous calculation of the number of pixels within the radius value range and comparison with the minimum number of pixels within the corresponding radius value range in the preset leaf upon obtaining a radius value, to determine whether the number of pixels within the radius value range exceeds the minimum number of pixels in the preset leaf. Furthermore, by obtaining the number of pixels once after obtaining a radius value, the corresponding radius critical value can be calculated immediately. Once the radius critical value is obtained, there is no need to continue the radius acquisition step based on the pixel center point C2, thus saving time, reducing the amount of computation, and improving computational speed.

[0091] If the number of pixels within a certain radius value Ri is greater than or equal to the minimum number of pixels within the radius range corresponding to the radius value Ri in the preset leaf, then mark the pixel center point Q2 as an internal point of the leaf;

[0092] If the number of pixels within a certain radius value Ri is less than the number of pixels within the radius range corresponding to the radius value Ri in the preset leaf, the pixel center point Q2 is marked as an interference pixel point;

[0093] If a certain interfering pixel point is located within the range of a certain internal point of the leaf with the radius value Ri as the radius, then the interfering pixel point is marked as a leaf edge point; otherwise, the interfering pixel point is still the interfering pixel point;

[0094] Repeat the above steps until all pixels in the preliminary leaf contour image are marked.

[0095] S5: according to the current tea tree period and the tea tree part where the pests and diseases are likely to appear, obtain the pest and disease characteristic data of the corresponding part in the corresponding period from the tea tree pest and disease characteristic database;

[0096] For example, if the current period is June and the part of the tea tree where pests and diseases are most likely to appear is the leaves, then the pest and disease characteristic data for which the pest and disease occurrence period is June and the pest and disease occurrence part is the leaves can be obtained from the tea tree pest and disease characteristic database.

[0097] like Figure 3 As shown, S6: identifying the type of tea tree pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea tree part.

[0098] This step extracts the characteristic data of the pests and diseases that belong to the same period and the same part and compares them with the images of the tea tree parts collected in the previous step to identify the types of tea tree pests and diseases.

[0099] S61: Sort the characteristic data of different types of pests and diseases at corresponding parts of the plant during corresponding periods according to the probability of occurrence of the pests and diseases. For example, if there are three types of pests and diseases occurring on leaves in July, namely Type A, Type B, and Type C, and the probability of occurrence of these three pests and diseases is P1, P2, and P3, respectively, and P3 ≥ P1 ≥ P2, then the characteristic data of the pests and diseases corresponding to Type C is sorted first, the characteristic data of the pests and diseases corresponding to Type A is sorted after Type C, and the characteristic data of the pests and diseases corresponding to Type B is sorted last.

[0100] S62: Comparing and analyzing the pest and disease characteristic data with the image of the tea tree part in order of sorting until an identification result is obtained.

[0101] In this step, the pest signature data corresponding to the pest with the highest probability of occurrence is first compared with the image of the tea plant. If the pest type cannot be determined, the pest signature data corresponding to the pest with the second highest probability of occurrence is then compared with the image of the tea plant. This process is repeated until the pest type is determined or all pest signatures for the corresponding period and location have been compared. This method of performing comparative analysis in order of probability of occurrence helps shorten the time required to identify the pest type.

[0102] When identifying pests and diseases, we can first extract disease feature parameters from images of the corresponding disease type to create a dataset. This dataset can then be trained using a specific algorithm (such as a support vector machine or BP neural network) to identify pests and diseases with different characteristics. Because there are many algorithms for identifying pests and diseases, some algorithms have higher accuracy rates for certain pests and diseases. Therefore, we can also select a pest and disease recognition algorithm based on the specific time and location, thereby improving the accuracy of pest and disease recognition.

[0103] In order to improve the accuracy of recognition, this embodiment can also use hyperspectral images for recognition. First, the relative spectral reflectance of the sensitive band of the area of ​​interest is extracted from the image of the tea tree part as the spectral feature, and the second component image after the secondary principal component analysis is used as the feature image. Then, the color features and texture features of the feature image are extracted based on the color moment and gray-level co-occurrence matrix. Finally, the BP neural network optimized by the genetic algorithm is used to test the fusion data of the color, texture and spectral feature vectors.

[0104] like Figure 6 As shown, this embodiment further includes the following steps after S6: identifying the type of tea plant pests and diseases based on the pest and disease feature data of the corresponding part in the corresponding period and the image of the tea plant part:

[0105] S71: Obtain information from pest control experts related to tea plant diseases and pests;

[0106] S72: Expert matching is performed based on the results of intelligent identification of tea tree pests and diseases and information of pest and disease control experts.

[0107] After identifying the type of tea plant pests and diseases, this embodiment can obtain information about pest control experts related to the identified pest and disease type. This information can be stored in a database along with the pest and disease characteristic data, or can be searched by pest and disease type using a search engine. The pest and disease control expert information may include the pest control expert's areas of expertise, relevant work experience, and relevant research results. Based on the identified pest and disease type, the expert with the most expertise or experience in the relevant pest and disease control field can then be found.

[0108] S73: Obtain a network link for online interaction with the matched expert based on the expert matching result.

[0109] When a suitable expert is matched, a relevant web link can be pushed to the user. After clicking the web link, the user can communicate online with the matched expert, consult the expert for professional and standardized pest and disease control measures, and send the collected relevant pest and disease image information to the matched expert.

[0110] like Figure 7 As shown, in addition, this embodiment further includes the following steps after S6: identifying the type of tea plant pests and diseases based on the pest and disease feature data of the corresponding part in the corresponding period and the image of the tea plant part:

[0111] S81: Determine the severity of the pests and diseases based on the identified pest and disease type, pest and disease characteristic data, and the image of the tea tree part;

[0112] After identifying the types of pests and diseases, this embodiment can further identify the severity of the pests and diseases based on the collected images of the tea tree parts.

[0113] S82: Based on the type and severity of the pests and diseases, the types and quantities of pest control materials are obtained, including medicines for pest control;

[0114] This embodiment can obtain corresponding pest control methods after knowing the type and severity of the pest. If the corresponding pest control method requires pesticides, tools, or other materials, these required materials and their quantity information are extracted. Pest control materials include, but are not limited to, sticky traps, traps, pesticides, and pesticide spraying tools.

[0115] S83: Generate an order for purchasing the pest control materials according to the type and quantity of the materials and send it to the corresponding merchant.

[0116] This embodiment can directly send orders to merchants selling the substances according to the types and quantities of the substances required for preventing and treating the identified pests and diseases, which can greatly facilitate users.

[0117] Example 2

[0118] See also Figure 8 This embodiment provides a method and device for intelligently identifying tea plant pests and diseases, the device comprising:

[0119] A database establishment module, the database establishment module is used to establish a tea tree pest and disease characteristic database that is classified and stored according to the period of occurrence of tea tree pests and diseases and the tea tree parts where the pests and diseases characteristics appear;

[0120] A pest and disease type acquisition module, which is used to obtain the types of pests and diseases that may occur in the current period according to the current period of the tea tree;

[0121] A tea tree part determination module, configured to determine, based on the pest type, a part of the tea tree where the corresponding pest characteristics are likely to appear;

[0122] An image acquisition module, the image acquisition module is used to acquire images of corresponding tea tree parts according to the tea tree parts where pests and diseases are likely to appear;

[0123] a pest and disease characteristic data acquisition module, wherein the pest and disease characteristic data acquisition module is used to obtain pest and disease characteristic data of corresponding parts of the corresponding period from a tea tree pest and disease characteristic database according to the current tea tree period and the tea tree parts where pest and disease characteristics are likely to appear;

[0124] The pest and disease type identification module is used to identify the type of tea tree pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea tree part.

[0125] The image acquisition module also includes:

[0126] A tea tree image acquisition submodule, wherein the tea tree image acquisition submodule is used to acquire an image of a tea tree to be identified;

[0127] An image preprocessing submodule, the image preprocessing submodule is used to preprocess the image of the tea tree to obtain a binary image of the leaves and the trunk;

[0128] A leaf preliminary contour extraction submodule is used to perform feature comparison on the binary image of the trunk and the binary image of the leaf according to the growth position relationship between the trunk and the leaf, and extract a preliminary contour image of the leaf;

[0129] The leaf image extraction submodule is used to compare the preliminary leaf contour image with the preset leaf, and extract a complete leaf image based on a clustering algorithm.

[0130] Example 3

[0131] In addition, combined Figure 9 The tea tree pest and disease intelligent identification method of the aforementioned embodiment of the present invention can be implemented by the tea tree pest and disease intelligent identification method device of this embodiment. Figure 9 A schematic diagram of the hardware structure of the intelligent identification method and equipment for tea tree pests and diseases provided by an embodiment of the present invention is shown.

[0132] The tea tree pest and disease intelligent identification method and device of this embodiment may include a processor 401 and a memory 402 storing computer program instructions.

[0133] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0134] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be inside or outside the data processing device. In a specific embodiment, memory 402 is a non-volatile solid-state memory. In a specific embodiment, memory 402 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0135] The processor 401 reads and executes computer program instructions stored in the memory 402 to implement the data addressing method of any one of the regional random tea tree pest and disease intelligent identification methods in the above embodiments.

[0136] In one example, the tea plant pest and disease intelligent identification method and device of this embodiment may further include a communication interface 403 and a bus 410. Figure 9 As shown, the processor 401 , the memory 402 , and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0137] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiment of the present invention.

[0138] Bus 410 includes hardware, software or both, and the parts for the output of small multiples of ink volume are coupled to each other.For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the embodiment of the present invention describes and shows specific bus, the present invention considers any suitable bus or interconnection.

[0139] Example 4

[0140] In addition, in conjunction with the tea plant pest and disease intelligent identification method in the above embodiments, embodiments of the present invention may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when executed by a processor, the computer program instructions implement any of the tea plant pest and disease intelligent identification methods in the above embodiments.

[0141] The above is a detailed introduction to the method, device, equipment and storage medium for intelligent identification of tea tree pests and diseases provided by the embodiments of the present invention.

[0142] It should be understood that the present invention is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted. In the above embodiments, several specific steps are described and illustrated as examples. However, the method of the present invention is not limited to the specific steps described and illustrated. Those skilled in the art may make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present invention.

[0143] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in unit, a function card or the like. When implemented in software, the elements of the present invention are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0144] It should also be noted that the exemplary embodiments described herein describe methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the steps described above. In other words, the steps may be performed in the order described in the embodiments, or in a different order, or several steps may be performed simultaneously.

[0145] The above description is only a specific embodiment of the present invention. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention.

Claims

1. An intelligent identification method for tea plant diseases and insect pests, characterized in that: The method comprises the following steps: S1: Establish a database of tea tree pests and diseases that classifies and stores the characteristics of the tea tree pests and diseases according to the period of occurrence and the parts of the tea tree where the pests and diseases occur; S2: Obtain the types of pests and diseases that may occur in the current period according to the current period of the tea tree; S3: determining the part of the tea tree where the corresponding pests and diseases are likely to appear according to the pest and disease type; S4: Acquire images of corresponding tea tree parts according to the parts of the tea tree where pests and diseases are likely to appear; S5: according to the current tea tree period and the tea tree part where the pests and diseases are likely to appear, obtain the pest and disease characteristic data of the corresponding part in the corresponding period from the tea tree pest and disease characteristic database; S6: Identify the types of tea tree pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea tree part.

2. The method for intelligently identifying tea plant diseases and insect pests according to claim 1, wherein: Said S1: establishing a tea tree pest and disease characteristic database for classification and storage according to the period of occurrence of tea tree pests and diseases and the tea tree parts where the pest and disease characteristics appear, comprises the following steps: S11: Establish a database of tea plant pests and diseases characteristics; S12: Classify and store the pest and disease characteristic data in the database according to different periods of pest and disease occurrence; S13: The characteristic data of pests and diseases belonging to the same period are further classified and stored according to the parts of the tea trees where the characteristics of the pests and diseases appear.

3. The intelligent identification method for tea plant diseases and insect pests according to claim 1, characterized in that: Identifying the types of tea plant diseases and insect pests based on the disease and insect pest characteristic data of the corresponding parts of the corresponding period and the image of the tea plant part also includes the following steps: S61: Sort characteristic data of different types of pests and diseases in corresponding parts of corresponding periods according to the probability of occurrence of pests and diseases; S62: Comparing and analyzing the pest and disease characteristic data with the image of the tea tree part in order of sorting until an identification result is obtained.

4. The intelligent identification method for tea plant diseases and insect pests according to claim 1, characterized in that: In the step S4 of acquiring an image of a corresponding tea tree part according to a tea tree part where pest and disease characteristics are likely to appear, if the tea tree part where pest and disease characteristics are likely to appear is a leaf, the following steps are included: S41: Acquire an image of a tea tree to be identified and preset leaf parameters; S42: Preprocessing the image of the tea tree to obtain a binary image of the leaves and the trunk; S43: performing feature comparison on the binary image of the trunk and the binary image of the leaves according to the growth position relationship between the trunk and the leaves, and extracting a preliminary outline image of the leaves; S44: Compare the preliminary leaf contour image with the preset leaf to extract a complete leaf image.

5. The intelligent identification method for tea plant diseases and insect pests according to claim 1, characterized in that: The step S4 of obtaining images of corresponding tea tree parts according to the parts of the tea tree where pests and diseases are likely to appear further comprises the following steps: S401: If the part of the tea tree where the pest and disease characteristics are likely to appear is the tender shoot and / or bud leaf and / or mature leaf, an image of the tea tree to be identified is obtained by taking aerial photos using a drone; S402: If the parts of the tea tree where pest and disease characteristics are likely to appear are the trunk and / or mature leaves, a micro or small drone is used to fly into the tea forest to obtain images of the tea tree to be identified.

6. The intelligent identification method for tea plant diseases and insect pests according to any one of claims 1 to 5, characterized in that: After the step S6 of identifying the type of tea plant pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea plant part, the following steps are also included: S71: Obtain information from pest control experts related to tea plant diseases and pests; S72: expert matching based on the results of intelligent identification of tea plant diseases and pests and information of disease and pest control experts; S73: Obtain a network link for online interaction with the matched expert based on the expert matching result.

7. The intelligent identification method for tea plant diseases and insect pests according to any one of claims 1 to 5, characterized in that: After the step S6 of identifying the type of tea plant pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea plant part, the following steps are also included: S81: Determine the severity of the pests and diseases based on the identified pest and disease type, pest and disease characteristic data, and the image of the tea tree part; S82: Obtaining the type and quantity of pest control supplies based on the type and severity of the pests, including medicines; S83: Generate an order for purchasing the pest control materials according to the type and quantity of the materials and send it to the corresponding merchant.

8. Tea tree pest and disease intelligent identification device, characterized in that: The device comprises: A database establishment module, the database establishment module is used to establish a tea tree pest and disease characteristic database that is classified and stored according to the period of occurrence of tea tree pests and diseases and the tea tree parts where the pests and diseases characteristics appear; A pest and disease type acquisition module, which is used to obtain the types of pests and diseases that may occur in the current period according to the current period of the tea tree; A tea tree part determination module, configured to determine, based on the pest type, a part of the tea tree where the corresponding pest characteristics are likely to appear; An image acquisition module, the image acquisition module is used to acquire images of corresponding tea tree parts according to the tea tree parts where pests and diseases are likely to appear; a pest and disease characteristic data acquisition module, wherein the pest and disease characteristic data acquisition module is used to obtain pest and disease characteristic data of corresponding parts of the corresponding period from a tea tree pest and disease characteristic database according to the current tea tree period and the tea tree parts where pest and disease characteristics are likely to appear; The pest and disease type identification module is used to identify the type of tea tree pests and diseases based on the pest and disease characteristic data of the corresponding part in the corresponding period and the image of the tea tree part.

9. Tea tree pest and disease intelligent identification equipment, characterized by: include: At least one processor, at least one memory, and computer program instructions stored in the memory, which implement the method according to any one of claims 1 to 7 when the computer program instructions are executed by the processor.

10. A storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images