Plant disease identification model construction method, device and model construction system

Abstract

This application provides a method, device, and system for constructing a plant disease recognition model. The method includes: creating a deep learning-based hybrid model based on a ResNet18 network model and a DeepLabV3+ network model; training the ResNet18 network model, a first DeepLabV3+ network model, and a second DeepLabV3+ network model in the hybrid model using a training dataset; and testing the trained ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model using a test dataset corresponding to the training dataset to obtain a plant disease recognition model. This method helps improve the accuracy of the constructed model in identifying plant diseases.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for constructing a plant disease identification model and a model construction system. Background Art

[0002] In the agricultural sector, outbreaks of economic tree or crop diseases can easily cause significant economic losses. Traditional plant disease detection relies primarily on manual surveys to detect the occurrence of economic tree or crop diseases. While accurate, this method is time-consuming, labor-intensive, inefficient, and requires a high level of professional experience from the inspectors. Furthermore, the large number of sampling points required makes it unsuitable for large-scale application. In recent years, the use of remote sensing technology combined with deep learning for automated crop disease monitoring has become a trend. However, currently, training is typically performed using a single convolutional neural network. The resulting models still have the potential for misjudgment in identifying plant diseases, and recognition accuracy needs to be improved. Summary of the Invention

[0003] In view of this, the purpose of the embodiments of the present application is to provide a plant disease identification model construction method, device and model construction system, which can improve the problem of low plant disease identification accuracy due to the single structure of the network model.

[0004] To achieve the above technical objectives, the technical solutions adopted in this application are as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for constructing a plant disease identification model, the method comprising:

[0006] Based on the ResNet18 network model and the DeepLabV3+ network model, creating a hybrid model based on deep learning, wherein the hybrid model includes the ResNet18 network model as the backbone network, and a first DeepLabV3+ network model and a second DeepLabV3+ network model connected to the ResNet18 network model;

[0007] The ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model are trained using a training data set, wherein the training data set includes multiple hyperspectral images of target plants, each hyperspectral image is annotated with a first image area representing the target plant and a second image area representing the non-target plant, and each hyperspectral image is also annotated with a first mark representing the presence of a target disease in the target plant, or a second mark representing the absence of the target disease; the first image area and the second image area in the hyperspectral image are used to train the ResNet18 network model and the first DeepLabV3+ network model, and the first mark or the second mark in the hyperspectral image is used to train the second DeepLabV3+ network model;

[0008] The ResNet18 network model, the first DeepLabV3+ network model and the second DeepLabV3+ network model in the trained hybrid model are tested using a test data set corresponding to the training data set, and when the hybrid model meets the preset convergence condition, the tested hybrid model is determined as a plant disease recognition model, which is used to detect whether the target plant in the hyperspectral image has a target disease.

[0009] In combination with the first aspect, in some optional embodiments, before training the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model using a training data set, the method further includes:

[0010] Acquire an initial dataset, the initial dataset comprising a plurality of hyperspectral images of a target plant;

[0011] By using a preset data enhancement algorithm, some or all of the multiple hyperspectral images in the initial data set are horizontally rotated, and / or mirror-flipped, and / or the reflectances of all channels in the hyperspectral images are adjusted to specified values to obtain multiple hyperspectral images after data enhancement;

[0012] All hyperspectral images in the initial data set and all hyperspectral images after data enhancement are used as sample data sets;

[0013] Each hyperspectral image in the sample data set is annotated with a first image region representing a target plant and a second image region representing a non-target plant, and each hyperspectral image is annotated with a first marker representing the presence of a target disease in the target plant or a second marker representing the absence of the target disease, so as to obtain the training data set.

[0014] In combination with the first aspect, in some optional implementations, the hyperspectral images in the training dataset are image data converted into a BIL format.

[0015] In combination with the first aspect, in some optional embodiments, the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model are trained using a training data set, including:

[0016] Using the hyperspectral image having the first image region and the second image region in the training data set to train the ResNet18 network model and the first DeepLabV3+ network model, so that the trained first DeepLabV3+ network model has the function of detecting whether the target plant exists in the hyperspectral image;

[0017] The ResNet18 network model and the second DeepLabV3+ network model are trained using the hyperspectral images with the first label and the second label in the training data set, so that the trained second DeepLabV3+ network model has the function of detecting whether the target disease exists in the hyperspectral image.

[0018] In combination with the first aspect, in some optional embodiments, the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the trained hybrid model are tested using a test data set corresponding to the training data set, including:

[0019] Inputting each hyperspectral image in the test data set into the hybrid model to obtain a test result corresponding to each hyperspectral image output by the hybrid model;

[0020] When the test result is different from the first image area and the second image area of the corresponding hyperspectral image, or the first mark or the second mark of the corresponding hyperspectral image, the trained hybrid model is corrected using the first image area and the second image area of the hyperspectral image, or the first mark or the second mark of the hyperspectral image until the hybrid model meets the preset convergence condition.

[0021] In combination with the first aspect, in some optional embodiments, the first mark includes multiple level identifiers characterizing the severity of the target disease, wherein the multiple level identifiers are used to train the second DeepLabV3+ network model to identify the severity of the target disease.

[0022] In conjunction with the first aspect, in some optional implementations, the method further includes:

[0023] Acquire a target image to be identified, where the target image is a hyperspectral image obtained by photographing a target plant;

[0024] The target image is input into the plant disease recognition model to obtain a recognition result of the plant disease recognition model for the target image, wherein the recognition result includes a result indicating whether the target plant has a target disease.

[0025] In combination with the first aspect, in some optional embodiments, the target plant includes a Zanthoxylum bungeanum tree, and the target disease includes Zanthoxylum bungeanum rust.

[0026] In a second aspect, an embodiment of the present application further provides a device for constructing a plant disease identification model, the device comprising:

[0027] A creation unit, configured to create a hybrid model based on deep learning based on a ResNet18 network model and a DeepLabV3+ network model, wherein the hybrid model includes the ResNet18 network model as a backbone network, and a first DeepLabV3+ network model and a second DeepLabV3+ network model connected to the ResNet18 network model;

[0028] A training unit, configured to train the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model using a training data set, wherein the training data set includes multiple hyperspectral images of target plants, each hyperspectral image is annotated with a first image region representing the target plant and a second image region representing the non-target plant, and each hyperspectral image is further annotated with a first marker representing the presence of a target disease in the target plant, or a second marker representing the absence of the target disease; the first image region and the second image region in the hyperspectral image are used to train the ResNet18 network model and the first DeepLabV3+ network model, and the first marker or the second marker in the hyperspectral image is used to train the second DeepLabV3+ network model;

[0029] A testing unit is used to test the ResNet18 network model, the first DeepLabV3+ network model and the second DeepLabV3+ network model in the trained hybrid model using a test data set corresponding to the training data set, and when the hybrid model meets a preset convergence condition, the tested hybrid model is determined as a plant disease recognition model, and the plant disease recognition model is used to detect whether a target plant in a hyperspectral image has a target disease.

[0030] In conjunction with the second aspect, in some optional implementations, the training unit is configured to:

[0031] Using the hyperspectral image having the first image region and the second image region in the training data set to train the ResNet18 network model and the first DeepLabV3+ network model, so that the trained first DeepLabV3+ network model has the function of detecting whether the target plant exists in the hyperspectral image;

[0032] The ResNet18 network model and the second DeepLabV3+ network model are trained using the hyperspectral images with the first label and the second label in the training data set, so that the trained second DeepLabV3+ network model has the function of detecting whether the target disease exists in the hyperspectral image.

[0033] In a third aspect, an embodiment of the present application further provides a model building system, which includes a processor and a memory coupled to each other, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the model building system executes the above method.

[0034] The invention adopting the above technical solution has the following advantages:

[0035] In the technical solution provided in the present application, the ResNet18 network model is used to connect the first DeepLabV3+ network model and the second DeepLabV3+ network model to form a hybrid model. The ResNet18 network model is used as the backbone network to extract image features. The first DeepLabV3+ network model and the second DeepLabV3+ network model are used as two branch networks, which are conducive to introducing multi-scale information to improve the accuracy of recognition. By training and testing each network model in the hybrid model, the first DeepLabV3+ network model can be used to identify target plants in hyperspectral images, and the second DeepLabV3+ network model can identify whether the target plant has a target disease. The combination of each network model in the hybrid model is conducive to improving the accuracy of plant disease identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The present application may be further illustrated by the non-limiting embodiments provided in the accompanying drawings. It should be understood that the following drawings illustrate only certain embodiments of the present application and are therefore not to be construed as limiting the scope of the present application. It is understood that a person skilled in the art can derive other relevant drawings from these drawings without inventive effort.

[0037] Figure 1 A schematic flow chart of the method for constructing a plant disease identification model provided in an embodiment of the present application.

[0038] Figure 2 Schematic diagram of the hyperspectral image before and after recognition provided in an embodiment of the present application.

[0039] Figure 3 This is a block diagram of the plant disease identification model construction device provided in an embodiment of the present application.

[0040] Icon: 200-Plant disease identification model building device; 210-Creation unit; 220-Training unit; 230-Testing unit. DETAILED DESCRIPTION

[0041] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that similar or identical parts in the drawings or descriptions are numbered the same. Implementations not shown or described in the drawings are known to those of ordinary skill in the art. In the description of this application, the terms "first," "second," etc. are used solely to distinguish descriptions and are not to be construed as indicating or implying relative importance.

[0042] Embodiments of the present application provide a model building system. The system may include a processing module and a storage module. The storage module stores a computer program that, when executed by the processing module, enables the model building system to perform the corresponding steps of the plant disease identification model building method described below.

[0043] In this embodiment, the model building system may be a hardware system, for example, a hardware system of a personal computer, a server, or the like.

[0044] The model building system can train a plant disease recognition model, enabling the trained and tested model to identify the presence of a target plant in an image and whether the target plant is infected with a target disease. The target plant may include, but is not limited to, Sichuan pepper trees, wheat, and rice, and the target disease may include, but is not limited to, Sichuan pepper rust, wheat rust, and rice rust. For example, the target plant may be Sichuan pepper trees, and the target disease may be Sichuan pepper rust.

[0045] Please refer to Figure 1 This application also provides a method for constructing a plant disease identification model, which can be applied to the above-mentioned model construction system, and the model construction system executes or implements each step of the method. The method for constructing a plant disease identification model can include the following steps:

[0046] Step 110: creating a hybrid model based on deep learning based on the ResNet18 network model and the DeepLabV3+ network model, wherein the hybrid model includes the ResNet18 network model as a backbone network, and a first DeepLabV3+ network model and a second DeepLabV3+ network model connected to the ResNet18 network model;

[0047] Step 120: Training the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model using a training data set, wherein the training data set includes multiple hyperspectral images of target plants, each hyperspectral image is annotated with a first image region representing the target plant and a second image region representing the non-target plant, and each hyperspectral image is further annotated with a first marker representing the presence of a target disease in the target plant, or a second marker representing the absence of the target disease; the first image region and the second image region in the hyperspectral image are used to train the ResNet18 network model and the first DeepLabV3+ network model, and the first marker or the second marker in the hyperspectral image is used to train the second DeepLabV3+ network model;

[0048] Step 130, testing the ResNet18 network model, the first DeepLabV3+ network model and the second DeepLabV3+ network model in the trained hybrid model through a test data set corresponding to the training data set, and when the hybrid model meets the preset convergence condition, determining the tested hybrid model as a plant disease recognition model, and the plant disease recognition model is used to detect whether the target plant in the hyperspectral image has a target disease.

[0049] The following is a detailed description of the steps in the construction of the plant disease identification model:

[0050] In step 110, the ResNet18 network model and the DeepLabV3+ network model are conventional deep learning network models. The first DeepLabV3+ network model and the second DeepLabV3+ network model have the same network structure, except that the first DeepLabV3+ network model is used to detect the presence of target plants in hyperspectral images, while the second DeepLabV3+ network model is used to detect the presence of target diseases in plants in hyperspectral images.

[0051] In this embodiment, a hybrid model can be constructed using a ResNet18 network model and two DeepLabV3+ network models. In the hybrid model, the input data of the ResNet18 network model can be a hyperspectral image in the training dataset. The output of the ResNet18 network model is connected to the input of the first DeepLabV3+ network model and the second DeepLabV3+ network model.

[0052] The ResNet18 network model is composed of residual blocks, which add skip mapping to directly add the input and output, which helps to replenish the feature information lost by the ResNet18 network model during the convolution process. The ResNet18 network model is used to extract features from hyperspectral images, which can extract richer feature information. During model training, the extracted feature information is used as input data for the first DeepLabV3+ network model and the second DeepLabV3+ network model, so that these two DeepLabV3+ network models can be learned and trained separately.

[0053] The DeepLabv3+ network model consists of an encoder and decoder. The decoder network is primarily based on a DCNN with dilated convolutions, and can employ commonly used classification networks such as ResNet. The decoder network uses the Atrous Spatial Pyramid Pooling (ASPP) module with dilated convolutions to incorporate multi-scale information. Compared to standard convolutions, dilated convolutions increase the receptive field without increasing parameters, thereby improving the recognition accuracy of the trained model.

[0054] In step 120, the number of hyperspectral images included in the training dataset can be flexibly determined based on actual conditions. Generally speaking, the greater the number of hyperspectral images in the training dataset, the more conducive it is to improving the recognition accuracy of the trained model. For example, the number of hyperspectral images can exceed 1,000.

[0055] In this embodiment, step 120 may include:

[0056] Using the hyperspectral image having the first image region and the second image region in the training data set to train the ResNet18 network model and the first DeepLabV3+ network model, so that the trained first DeepLabV3+ network model has the function of detecting whether the target plant exists in the hyperspectral image;

[0057] The ResNet18 network model and the second DeepLabV3+ network model are trained using the hyperspectral images with the first label and the second label in the training data set, so that the trained second DeepLabV3+ network model has the function of detecting whether the target disease exists in the hyperspectral image.

[0058] In this embodiment, engineers can input the hyperspectral image with the first image area and the second image area into the ResNet18 network model and the first DeepLabV3+ network model to train and learn the ResNet18 network model and the first DeepLabV3+ network model. The trained ResNet18 network model can extract feature information from the hyperspectral image and input it into the trained first DeepLabV3+ network model, so that the trained first DeepLabV3+ network model can initially identify whether the target plant exists in the hyperspectral image.

[0059] Similarly, engineers can input the hyperspectral image with the first label and the second label into the ResNet18 network model and the second DeepLabV3+ network model to train and learn the ResNet18 network model and the second DeepLabV3+ network model. The trained ResNet18 network model can extract feature information from the hyperspectral image and input it into the trained second DeepLabV3+ network model, so that the trained second DeepLabV3+ network model can initially identify whether the target disease exists in the hyperspectral image.

[0060] During training, the hybrid model can use a loss function that combines Dice loss and Cross entropy loss. Adam is used as the optimizer, with an initial learning rate of 0.005 and exponential decay, with each epoch decaying to 0.97 times the previous one. Training is done for 50 epochs. An epoch is a hyperparameter that defines the number of times the learning algorithm works on the entire training dataset.

[0061] During training, engineers can evaluate hybrid models based on metrics such as precision, recall, intersection-over-union (IoU), and F1-score (harmonic mean of precision and recall). The best model can be visually inspected by applying it to the entire image that was not used during model training. The hybrid model can be evaluated using the following formula:

[0062]

[0063]

[0064]

[0065]

[0066] In the above formulas (1)-(4), P refers to the recognition accuracy after the hybrid model training;

[0067] R refers to the recall rate Recall;

[0068] F1 refers to the F1 score;

[0069] I oU Refers to intersection and comparison;

[0070] T P refers to true positive, which means the correctly predicted positive value;

[0071] F P refers to false positive, which means the positive value predicted incorrectly;

[0072] F N Refers to false negative, which means a negative value that is incorrectly predicted;

[0073] A O Area of Overlap refers to the intersection of the actual value and the predicted value of plant diseases;

[0074] A U Area of Union refers to the union of the true value and predicted value of plant diseases.

[0075] It is understandable that engineers can evaluate the reliability of the trained hybrid model based on the above formulas (1)-(4) in a conventional way. In addition, the parameter T P 、F P 、F N The accuracy is based on pixel statistics.

[0076] In step 130, the hyperspectral images in the test dataset have a format similar to that of the hyperspectral images in the training dataset. Specifically, in the test dataset, the hyperspectral images are annotated with a first region representing target plants and a second region representing non-target plants. The hyperspectral images are also annotated with a first marker indicating the presence of a target disease on the target plant, or a second marker indicating the absence of the target disease.

[0077] In this embodiment, step 130 may include:

[0078] Inputting each hyperspectral image in the test data set into the hybrid model to obtain a test result corresponding to each hyperspectral image output by the hybrid model;

[0079] When the test result is different from the first image area and the second image area of the corresponding hyperspectral image, or the first mark or the second mark of the corresponding hyperspectral image, the trained hybrid model is corrected using the first image area and the second image area of the hyperspectral image, or the first mark or the second mark of the hyperspectral image until the hybrid model meets the preset convergence condition.

[0080] Understandably, during the testing process, engineers can input hyperspectral images from the test dataset into the hybrid model. The ResNet18 network model extracts feature information from the hyperspectral images. The first and second DeepLabV3+ network models then perform dilated convolution on the extracted feature information and output test results. The test results can include markers indicating the presence and absence of target plants in the hyperspectral images, as well as the presence of target diseases on the target plants. The test results are then compared with the pre-set first and second regions, and the first or second markers, of the hyperspectral images. If any discrepancies are found, the hybrid model is calibrated based on the pre-set first and second regions, and the first or second markers. If no discrepancies are found, the hybrid model is tested on additional hyperspectral images until all hyperspectral images in the test dataset are tested, or until the hybrid model meets the preset convergence criteria. The preset convergence criteria can be flexibly determined based on actual conditions. For example, the preset convergence criteria could be that the hybrid model's test accuracy exceeds 90%, indicating convergence.

[0081] Understandably, using the test data set to test the trained hybrid model can improve the accuracy and reliability of the trained hybrid model in hyperspectral image recognition.

[0082] As an optional implementation, before training the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model using a training data set, the method further includes:

[0083] Acquire an initial dataset, the initial dataset comprising a plurality of hyperspectral images of a target plant;

[0084] By using a preset data enhancement algorithm, some or all of the multiple hyperspectral images in the initial data set are horizontally rotated, and / or mirror-flipped, and / or the reflectances of all channels in the hyperspectral images are adjusted to specified values to obtain multiple hyperspectral images after data enhancement;

[0085] All hyperspectral images in the initial data set and all hyperspectral images after data enhancement are used as sample data sets;

[0086] Each hyperspectral image in the sample data set is annotated with a first image region representing a target plant and a second image region representing a non-target plant, and each hyperspectral image is annotated with a first marker representing the presence of a target disease in the target plant or a second marker representing the absence of the target disease, so as to obtain the training data set.

[0087] In this embodiment, the hyperspectral images in the training dataset or initial dataset are converted to the BIL (Band Interleaved by Line) format. That is, if the hyperspectral images are not in the BIL format, they must be converted. BIL is a data format for remote sensing images. The BIL format conversion method is conventional and will not be detailed here.

[0088] The preset data enhancement algorithm can be flexibly determined according to actual conditions, and can have one or more of the following functions: horizontally rotating the hyperspectral image, mirror flipping, and adjusting the reflectance of all channels in the hyperspectral image to a specified value.

[0089] The horizontal rotation angle can be flexibly set based on the actual situation, for example, ±30°. The specified reflectance value can also be flexibly determined based on the actual situation. For example, for all initial hyperspectral images, the reflectance of all channels can be adjusted to any non-1 multiple in the range [0.5, 1.5] with a probability of 0.5. After data augmentation, multiple new hyperspectral images can be obtained. All hyperspectral images in the initial dataset and all new hyperspectral images serve as the sample dataset.

[0090] After obtaining a sample dataset through data augmentation, engineers can use the vector image drawing function of ArcGIS tools to annotate the hyperspectral images in the sample dataset. Specifically, each hyperspectral image in the sample dataset is annotated with a first region representing the target plant and a second region representing the non-target plant. Furthermore, each hyperspectral image is annotated with a first marker indicating the presence of the target disease on the target plant or a second marker indicating the absence of the target disease.

[0091] Furthermore, to enhance the refinement of model recognition, the first marker includes multiple level identifiers representing the severity of the target disease. For example, the first marker may include three level identifiers: a first level identifier representing severe diseases, a second level identifier representing common diseases, and a third level identifier representing mild diseases. Hyperspectral images with different level identifiers can be used to train the second DeepLabV3+ network model to identify the severity of the target disease.

[0092] As an optional implementation, the method may further include:

[0093] Acquire a target image to be identified, where the target image is a hyperspectral image obtained by photographing a target plant;

[0094] The target image is input into the plant disease recognition model to obtain a recognition result of the plant disease recognition model for the target image, wherein the recognition result includes a result indicating whether the target plant has a target disease.

[0095] Please refer to Figure 2 The target image can be a hyperspectral image (usually a color image) obtained by shooting the pepper tree planting area using a drone. The target image can be as follows Figure 2 (a). The method for acquiring the target image can be flexibly determined based on the actual situation. For example, the model building system can obtain a pre-prepared target image from a personal computer or server.

[0096] After acquiring the target image, the model building system can input the target image into the trained and tested plant disease recognition model. The first DeepLabV3+ network model in the plant disease recognition model can classify the pepper trees and background images in the target image. The second DeepLabV3+ network model can classify the healthy pepper trees and those suffering from pepper rust. The plant disease recognition model can further analyze the preliminary recognition results of the target image based on the first DeepLabV3+ network model and the second DeepLabV3+ network model to obtain the final recognition result. The recognition result can be as follows Figure 2 As shown in (b), Figure 2 (b) is a schematic diagram of retaining only the area of the Zanthoxylum bungeanum tree in the target image, and the light color represents the healthy Zanthoxylum bungeanum tree, and the dark color represents the Zanthoxylum bungeanum tree suffering from Zanthoxylum bungeanum rust.

[0097] Of course, in other embodiments, healthy and diseased Zanthoxylum bungeanum trees can be rendered and displayed differently using different colors. For example, healthy Zanthoxylum bungeanum trees can be rendered green, and diseased Zanthoxylum bungeanum trees can be rendered red. The plant disease recognition model can calculate the severity of the disease based on the area ratio of diseased Zanthoxylum bungeanum trees to all Zanthoxylum bungeanum trees. The calculation method of the severity of the disease can be flexibly determined according to the actual situation and will not be repeated here.

[0098] When the second DeepLabV3+ network model identifies an area of the target image as suffering from pepper rust and there is an overlapping area with the area of the target image identified as a pepper tree in the first DeepLabV3+ network model, the overlapping area is confirmed as the area of the pepper tree suffering from pepper rust. Similarly, when the second DeepLabV3+ network model identifies an area of the target image as healthy pepper trees and there is an overlapping area with the area of the target image identified as a pepper tree in the first DeepLabV3+ network model, the overlapping area is confirmed as the area of the healthy pepper tree.

[0099] Understandably, because the color characteristics of the exposed soil in the image are similar to those of a Zanthoxylum bungeanum tree infected with Zanthoxylum bungeanum rust, the area of the exposed soil in the image is easily misidentified as an area infected with Zanthoxylum bungeanum rust by a conventional deep learning model. In this embodiment, by combining the first DeepLabV3+ network model with the second DeepLabV3+ network model, the accuracy and reliability of Zanthoxylum bungeanum rust identification are improved, and misidentification due to a single model structure can be avoided.

[0100] Please refer to Figure 3 The present application also provides a plant disease identification model construction device 200. The plant disease identification model construction device 200 includes at least one software function module that can be stored in a storage module in the form of software or firmware or embedded in an operating system (OS). The processing module is configured to execute executable modules stored in the storage module, such as the software function modules and computer programs included in the plant disease identification model construction device 200.

[0101] The plant disease identification model construction device 200 includes a creation unit 210, a training unit 220, and a testing unit 230. The functions of each unit may be as follows:

[0102] A creation unit 210 is configured to create a hybrid model based on deep learning based on a ResNet18 network model and a DeepLabV3+ network model, wherein the hybrid model includes the ResNet18 network model as a backbone network, and a first DeepLabV3+ network model and a second DeepLabV3+ network model connected to the ResNet18 network model;

[0103] A training unit 220 is used to train the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model using a training data set, wherein the training data set includes multiple hyperspectral images of target plants, each hyperspectral image is annotated with a first image area representing the target plant and a second image area representing the non-target plant, and each hyperspectral image is further annotated with a first mark representing the presence of a target disease in the target plant, or a second mark representing the absence of the target disease; the first image area and the second image area in the hyperspectral image are used to train the ResNet18 network model and the first DeepLabV3+ network model, and the first mark or the second mark in the hyperspectral image is used to train the second DeepLabV3+ network model;

[0104] The testing unit 230 is used to test the ResNet18 network model, the first DeepLabV3+ network model and the second DeepLabV3+ network model in the trained hybrid model through a test data set corresponding to the training data set, and when the hybrid model meets the preset convergence condition, the tested hybrid model is determined as a plant disease recognition model, and the plant disease recognition model is used to detect whether the target plant in the hyperspectral image has a target disease.

[0105] Optionally, the plant disease identification model construction device 200 may further include:

[0106] a first acquisition unit, configured to acquire an initial data set, wherein the initial data set includes a plurality of hyperspectral images of a target plant;

[0107] a data enhancement unit, configured to horizontally rotate and / or mirror-flip some or all of the multiple hyperspectral images in the initial data set and / or adjust the reflectance of all channels in the hyperspectral images to specified values using a preset data enhancement algorithm, so as to obtain multiple hyperspectral images after data enhancement;

[0108] a combining unit, configured to use all hyperspectral images in the initial data set and all hyperspectral images after data enhancement as a sample data set;

[0109] A labeling unit is used to label each hyperspectral image in the sample data set with a first image region representing a target plant and a second image region representing a non-target plant, and to label each hyperspectral image with a first label representing the presence of a target disease in the target plant or a second label representing the absence of the target disease, so as to obtain the training data set.

[0110] Optionally, the training unit 220 may be configured to:

[0111] Using the hyperspectral image having the first image region and the second image region in the training data set to train the ResNet18 network model and the first DeepLabV3+ network model, so that the trained first DeepLabV3+ network model has the function of detecting whether the target plant exists in the hyperspectral image;

[0112] The ResNet18 network model and the second DeepLabV3+ network model are trained using the hyperspectral images with the first label and the second label in the training data set, so that the trained second DeepLabV3+ network model has the function of detecting whether the target disease exists in the hyperspectral image.

[0113] Optionally, the testing unit 230 may be used to:

[0114] Inputting each hyperspectral image in the test data set into the hybrid model to obtain a test result corresponding to each hyperspectral image output by the hybrid model;

[0115] When the test result is different from the first image area and the second image area of the corresponding hyperspectral image, or the first mark or the second mark of the corresponding hyperspectral image, the trained hybrid model is corrected using the first image area and the second image area of the hyperspectral image, or the first mark or the second mark of the hyperspectral image until the hybrid model meets the preset convergence condition.

[0116] Optionally, the plant disease identification model construction device 200 may further include:

[0117] A second acquisition unit is used to acquire a target image to be identified, where the target image is a hyperspectral image obtained by photographing a target plant;

[0118] The recognition unit is used to input the target image into the plant disease recognition model to obtain a recognition result of the plant disease recognition model for the target image, wherein the recognition result includes a result indicating whether the target plant has a target disease.

[0119] In this embodiment, the processing module can be an integrated circuit chip with signal processing capabilities. The above-mentioned processing module can be a general-purpose processor. For example, the processor can be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0120] The storage module can be, but is not limited to, random access memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, etc. In this embodiment, the storage module can be used to store hyperspectral images, recognition results, preset data augmentation algorithms, ResNet18 network models, and DeepLabV3+ network models. Of course, the storage module can also be used to store programs, which the processing module executes after receiving execution instructions.

[0121] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the model building system described above can refer to the corresponding processes of each step in the aforementioned method, and will not be elaborated here.

[0122] The present application also provides a computer-readable storage medium that stores a computer program, which, when executed on a computer, causes the computer to execute the plant disease identification model construction method described in the above embodiment.

[0123] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a model building system, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0124] In summary, the embodiments of the present application provide a method, device and model construction system for constructing a plant disease recognition model. In this solution, the ResNet18 network model is used to connect the first DeepLabV3+ network model and the second DeepLabV3+ network model to form a hybrid model. The ResNet18 network model is used as the backbone network to extract image features. The first DeepLabV3+ network model and the second DeepLabV3+ network model are used as two branch networks, which are conducive to introducing multi-scale information to improve the accuracy of recognition. By training and testing each network model in the hybrid model, the first DeepLabV3+ network model can be used to identify target plants in hyperspectral images, and the second DeepLabV3+ network model can identify whether the target plant has the target disease. The combination of each network model in the hybrid model is conducive to improving the accuracy of plant disease recognition.

[0125] In the embodiments provided in the present application, it should be understood that the disclosed devices, systems and methods can also be implemented in other ways. The device, system and method embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of code, and a part of the module, program segment or code includes one or more executable instructions for implementing the specified logical function. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, the functional modules in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0126] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for constructing a plant disease identification model, characterized in that: The method comprises: Based on the ResNet18 network model and the DeepLabV3+ network model, creating a hybrid model based on deep learning, wherein the hybrid model includes the ResNet18 network model as the backbone network, and a first DeepLabV3+ network model and a second DeepLabV3+ network model connected to the ResNet18 network model; The ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model are trained using a training data set, wherein the training data set includes multiple hyperspectral images of target plants, each hyperspectral image is annotated with a first image area representing the target plant and a second image area representing the non-target plant, and each hyperspectral image is also annotated with a first mark representing the presence of a target disease in the target plant, or a second mark representing the absence of the target disease; the first image area and the second image area in the hyperspectral image are used to train the ResNet18 network model and the first DeepLabV3+ network model, and the first mark or the second mark in the hyperspectral image is used to train the second DeepLabV3+ network model; The ResNet18 network model, the first DeepLabV3+ network model and the second DeepLabV3+ network model in the trained hybrid model are tested using a test data set corresponding to the training data set, and when the hybrid model meets the preset convergence condition, the tested hybrid model is determined as a plant disease recognition model, which is used to detect whether the target plant in the hyperspectral image has a target disease.

2. The method according to claim 1, characterized in that Before training the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model using a training data set, the method further includes: Acquire an initial dataset, the initial dataset comprising a plurality of hyperspectral images of a target plant; By using a preset data enhancement algorithm, some or all of the multiple hyperspectral images in the initial data set are horizontally rotated, and / or mirror-flipped, and / or the reflectances of all channels in the hyperspectral images are adjusted to specified values to obtain multiple hyperspectral images after data enhancement; All hyperspectral images in the initial data set and all hyperspectral images after data enhancement are used as sample data sets; Each hyperspectral image in the sample data set is annotated with a first image region representing a target plant and a second image region representing a non-target plant, and each hyperspectral image is annotated with a first marker representing the presence of a target disease in the target plant or a second marker representing the absence of the target disease, so as to obtain the training data set.

3. The method according to claim 2, characterized in that The hyperspectral images in the training dataset are image data converted into BIL format.

4. The method according to claim 1, wherein The ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model are trained using a training data set, including: Using the hyperspectral image having the first image region and the second image region in the training data set to train the ResNet18 network model and the first DeepLabV3+ network model, so that the trained first DeepLabV3+ network model has the function of detecting whether the target plant exists in the hyperspectral image; The ResNet18 network model and the second DeepLabV3+ network model are trained using the hyperspectral images with the first label and the second label in the training data set, so that the trained second DeepLabV3+ network model has the function of detecting whether the target disease exists in the hyperspectral image.

5. The method according to claim 1, wherein Testing the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the trained hybrid model using a test data set corresponding to the training data set, including: Inputting each hyperspectral image in the test data set into the hybrid model to obtain a test result corresponding to each hyperspectral image output by the hybrid model; When the test result is different from the first image area and the second image area of the corresponding hyperspectral image, or the first mark or the second mark of the corresponding hyperspectral image, the trained hybrid model is corrected using the first image area and the second image area of the hyperspectral image, or the first mark or the second mark of the hyperspectral image until the hybrid model meets the preset convergence condition.

6. The method according to claim 1, characterized in that The first mark includes multiple level identifiers that characterize the severity of the target disease, wherein the multiple level identifiers are used to train the second DeepLabV3+ network model to identify the severity of the target disease.

7. The method according to any one of claims 1 to 6, characterized in that The target plants include Zanthoxylum bungeanum trees, and the target diseases include Zanthoxylum bungeanum rust.

8. A plant disease identification model construction device, characterized in that: The device comprises: A creation unit, configured to create a hybrid model based on deep learning based on a ResNet18 network model and a DeepLabV3+ network model, wherein the hybrid model includes the ResNet18 network model as a backbone network, and a first DeepLabV3+ network model and a second DeepLabV3+ network model connected to the ResNet18 network model; A training unit, configured to train the ResNet18 network model, the first DeepLabV3+ network model, and the second DeepLabV3+ network model in the hybrid model using a training data set, wherein the training data set includes multiple hyperspectral images of target plants, each hyperspectral image is annotated with a first image region representing the target plant and a second image region representing the non-target plant, and each hyperspectral image is further annotated with a first marker representing the presence of a target disease in the target plant, or a second marker representing the absence of the target disease; the first image region and the second image region in the hyperspectral image are used to train the ResNet18 network model and the first DeepLabV3+ network model, and the first marker or the second marker in the hyperspectral image is used to train the second DeepLabV3+ network model; A testing unit is used to test the ResNet18 network model, the first DeepLabV3+ network model and the second DeepLabV3+ network model in the trained hybrid model using a test data set corresponding to the training data set, and when the hybrid model meets a preset convergence condition, the tested hybrid model is determined as a plant disease recognition model, and the plant disease recognition model is used to detect whether a target plant in a hyperspectral image has a target disease.

9. The device according to claim 8, characterized in that The training unit is used to: Using the hyperspectral image having the first image region and the second image region in the training data set to train the ResNet18 network model and the first DeepLabV3+ network model, so that the trained first DeepLabV3+ network model has the function of detecting whether the target plant exists in the hyperspectral image; The ResNet18 network model and the second DeepLabV3+ network model are trained using the hyperspectral images with the first label and the second label in the training data set, so that the trained second DeepLabV3+ network model has the function of detecting whether the target disease exists in the hyperspectral image.

10. A model building system, characterized in that: The model building system includes a processor and a memory coupled to each other, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the model building system executes the method according to any one of claims 1 to 7.

Images