CN111832448A - Disease identification method and system for grape orchard - Google Patents
Disease identification method and system for grape orchard Download PDFInfo
- Publication number
- CN111832448A CN111832448A CN202010612798.0A CN202010612798A CN111832448A CN 111832448 A CN111832448 A CN 111832448A CN 202010612798 A CN202010612798 A CN 202010612798A CN 111832448 A CN111832448 A CN 111832448A
- Authority
- CN
- China
- Prior art keywords
- grape
- leaf
- image
- disease
- leaves
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 235000009754 Vitis X bourquina Nutrition 0.000 title claims abstract description 360
- 235000012333 Vitis X labruscana Nutrition 0.000 title claims abstract description 360
- 235000014787 Vitis vinifera Nutrition 0.000 title claims abstract description 360
- 201000010099 disease Diseases 0.000 title claims abstract description 174
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 174
- 238000000034 method Methods 0.000 title claims abstract description 65
- 239000002420 orchard Substances 0.000 title claims abstract description 58
- 240000006365 Vitis vinifera Species 0.000 title 1
- 241000219095 Vitis Species 0.000 claims abstract description 366
- 238000012549 training Methods 0.000 claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 230000002265 prevention Effects 0.000 claims abstract description 5
- 241000233679 Peronosporaceae Species 0.000 claims description 20
- 241000221785 Erysiphales Species 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 12
- 241000123650 Botrytis cinerea Species 0.000 claims description 10
- 238000005562 fading Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 9
- 239000000575 pesticide Substances 0.000 abstract description 9
- 238000005507 spraying Methods 0.000 abstract description 7
- 238000013527 convolutional neural network Methods 0.000 abstract description 3
- 201000004569 Blindness Diseases 0.000 abstract 1
- 241000219094 Vitaceae Species 0.000 abstract 1
- 235000021021 grapes Nutrition 0.000 abstract 1
- 241000607479 Yersinia pestis Species 0.000 description 18
- 241000238631 Hexapoda Species 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 241000196324 Embryophyta Species 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000000877 morphologic effect Effects 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000000447 pesticide residue Substances 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Animal Husbandry (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Agronomy & Crop Science (AREA)
- Evolutionary Biology (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a disease identification method and system for a grape orchard, wherein the method comprises the following steps: obtaining a grape leaf disease image training sample; training a neural network algorithm model by using the grape leaf disease image training sample to obtain a grape disease identification model; and identifying the grape leaf image to be identified by using the grape disease identification model to obtain an identification result. The method is used for the targeted prevention and treatment of grape diseases. The convolutional neural network is used for carrying out feature training on diseased grape leaves, effective features are extracted, common disease features are automatically extracted, and therefore the disease types are accurately identified. By adopting the disease identification method based on deep learning, the diseases of the grapes can be accurately identified, and a basis is provided for spraying specific pesticides, so that the pesticide spraying blindness is reduced, and the quality of agricultural products and the safety of agricultural ecological environment are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of image recognition, in particular to a disease recognition method and system for a grape orchard.
Background
The traditional disease identification method mainly depends on experienced fruit growers or special disease research specialists, and is characterized by long period and strong subjectivity, and the problems of pesticide residue and pesticide resistance of pests are easily caused by blindly spraying pesticides.
Therefore, the technical problem to be solved by the technical staff in the field is to provide a disease identification scheme for a grape orchard, which can accurately identify the disease type of the grape orchard, provide a basis for spraying specific pesticides, administer pesticides according to the symptoms, and improve the quality of agricultural products and the safety of agricultural ecological environment.
Disclosure of Invention
Therefore, the disease identification method and system for the grape orchard can accurately identify the disease of the grape orchard, provide a basis for spraying pesticides, and improve the quality of agricultural products and the safety of agricultural ecological environment.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
in a first aspect, an embodiment of the present invention provides a disease identification method for a grape orchard, including:
obtaining a grape leaf disease image training sample;
training a neural network algorithm model by using the grape leaf disease image training sample to obtain a grape disease identification model;
and identifying the grape leaf images to be identified by using the grape disease identification model to obtain an identification result so as to perform targeted prevention and control according to the identification result.
Preferably, the obtaining of the grape leaf disease image training sample includes:
collecting normal grape leaves and diseased grape leaves in a grape orchard;
carrying out image shooting on the normal grape leaves and the diseased grape leaves to obtain original diseased leaf images;
preprocessing the original diseased leaves to obtain standard images in the same form;
and carrying out disease characteristic marking on the standard image to obtain a grape leaf disease image training sample.
Preferably, the diseased grape leaves are classified into 6 types, including: powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mold grape leaves, brown spot grape leaves and anthracnose grape leaves.
Preferably, the characteristic marking of disease on the standard image includes:
carrying out deformation marking on the shape of the blade in the standard image;
fading the leaf color in the standard image;
and carrying out rotting marking on the leaf area in the standard image.
Preferably, the identifying the grape leaf image to be identified by using the grape disease identification model includes:
acquiring a real-time leaf image of a grape plant to be identified as a grape leaf image to be identified;
inputting the to-be-identified grape leaf image into the grape disease identification model for identification to obtain an identification result, and if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the powdery mildew grape leaves, judging that the grape leaves corresponding to the to-be-identified grape leaf image are powdery mildew;
if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the downy mildew grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is downy mildew;
if the attribute characteristics of the grape leaf images to be identified accord with the characteristics of the anthracnose grape leaves, judging that the grape leaves corresponding to the grape leaf images to be identified are anthracnose;
if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the botrytis cinerea grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is botrytis cinerea;
if the attribute characteristics of the grape leaf images to be identified accord with the characteristics of the brown spot grape leaves, judging that the grape leaves corresponding to the grape leaf images to be identified are brown spots;
if the attribute features of the to-be-identified grape leaf image accord with the features of the anthracnose grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is anthracnose;
outputting a recognition result, establishing a corresponding relation between the recognition result and a real-time grape leaf image, and storing the recognition result; wherein the identification result comprises at least one of 6 types of powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mildew grape leaves, brown spot grape leaves and anthracnose grape leaves.
In a second aspect, an embodiment of the present invention provides a disease identification system for a grape orchard, including:
the sample acquisition module is used for acquiring a grape leaf disease image training sample;
the model training module is used for training a neural network algorithm model by utilizing the grape leaf disease image training sample to obtain a grape disease identification model; the grape disease identification model can respectively identify the grape leaves with 6 types of diseases; the diseased grape leaves are divided into 6 types, including: powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mold grape leaves, brown spot grape leaves and anthracnose grape leaves;
and the disease identification module is used for identifying the grape leaf images to be identified by using the grape disease identification model to obtain an identification result so as to perform targeted control according to the identification result.
Preferably, the sample acquiring module comprises:
the blade collecting unit is used for collecting normal grape blades and diseased grape blades in a grape orchard;
the image shooting unit is used for shooting images of the normal grape leaves and the diseased grape leaves to obtain original diseased leaf images;
the pretreatment unit is used for pretreating the original diseased leaves to obtain standard images in the same form;
and the characteristic marking unit is used for carrying out characteristic marking on the disease on the standard image to obtain a grape leaf disease image training sample.
Preferably, the feature marking unit includes:
the deformation marking subunit is used for carrying out deformation marking on the shape of the blade in the standard image;
a fade marking subunit for fade marking a leaf color in the standard image;
and the rotting mark subunit is used for carrying out rotting mark on the leaf area in the standard image.
Preferably, the disease identification module is specifically configured to: acquiring a real-time leaf image of a grape plant to be identified as a grape leaf image to be identified; inputting the to-be-identified grape leaf image into the grape disease identification model for identification, and if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the powdery mildew grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is powdery mildew; if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the downy mildew grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is downy mildew; if the attribute characteristics of the grape leaf images to be identified accord with the characteristics of the anthracnose grape leaves, judging that the grape leaves corresponding to the grape leaf images to be identified are anthracnose; if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the botrytis cinerea grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is botrytis cinerea; if the attribute characteristics of the grape leaf images to be identified accord with the characteristics of the brown spot grape leaves, judging that the grape leaves corresponding to the grape leaf images to be identified are brown spots; if the attribute features of the to-be-identified grape leaf image accord with the features of the anthracnose grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is anthracnose; outputting a recognition result, establishing a corresponding relation between the recognition result and a real-time grape leaf image, and storing the recognition result; wherein the identification result comprises at least one of 6 types of powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mildew grape leaves, brown spot grape leaves and anthracnose grape leaves. In a third aspect, an embodiment of the present invention provides a disease identification apparatus for a grape orchard, including:
a memory for storing a computer program;
a processor for implementing the steps of the disease identification method for a grape orchard as described above when executing the computer program.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the disease identification method for a grape orchard as described above. The embodiment of the invention provides a disease identification method for a grape orchard, which comprises the following steps: obtaining a grape leaf disease image training sample; training a neural network algorithm model by using the grape leaf disease image training sample to obtain a grape disease identification model; and identifying the grape leaf images to be identified by using the grape disease identification model to obtain an identification result so as to perform targeted prevention and control according to the identification result. And (3) performing feature training by using a convolutional neural network, extracting effective features, and automatically extracting common disease features, thereby accurately identifying the disease types. Traditional to crops disease detection and discernment, mostly discern and analyze at the field scene through experienced expert, this kind of artifical mode cycle of guarding of squatting is long, waste time and manpower, and inefficiency, adopt the quick accurate discernment of disease based on degree of depth study, can carry out dynamic monitoring to grape leaf blade disease under the natural condition, one of them or several kinds of diseases of accurate discernment, for spraying specific pesticide provides the technological basis, in order to do benefit to and reduce the blind application of medicine to confirming the disease, realize accurate application of medicine, reduce harm, improve fruit output, increase peasant income, promote agricultural product quality and agricultural ecological environment safety.
The disease identification method and system for the grape orchard provided by the embodiment of the invention have the same beneficial effects, and are not repeated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions that the present invention can be implemented, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the effects and the achievable by the present invention, should still fall within the range that the technical contents disclosed in the present invention can cover.
Fig. 1 is a flowchart of a disease identification method for a grape orchard according to an embodiment of the present invention;
fig. 2 is a flowchart of a disease identification method for a grape orchard according to an embodiment of the present invention;
FIG. 3 is a flow chart of a disease identification method for a grape orchard according to an embodiment of the invention;
FIG. 4 is a flow chart of a disease identification method for a grape orchard according to an embodiment of the invention;
FIG. 5 is an image of normal grape leaves used in a disease identification method for a grape orchard according to an embodiment of the present invention;
FIG. 6 is an image of powdery mildew grape leaves used in a disease identification method for a grape orchard according to an embodiment of the present invention;
FIG. 7 is an image of downy mildew grape leaves used in a disease identification method for a grape orchard according to an embodiment of the invention;
FIG. 8 is an image of anthracnose grape leaves used in a disease identification method for a grape orchard according to an embodiment of the present invention;
FIG. 9 is an image of a botrytis cinerea leaf used in a disease identification method for a grape orchard according to an embodiment of the present invention;
fig. 10 is an image of brown spot grape leaves used in a disease identification method for a grape orchard according to an embodiment of the present invention;
FIG. 11 is an image of a leaf of a grape with anthracnose used in the disease identification method for a grape orchard according to an embodiment of the invention;
fig. 12 is a flowchart of a disease identification system for a grape orchard according to an embodiment of the present invention;
fig. 13 is a schematic structural diagram of a disease identification device for a grape orchard according to a specific embodiment of the invention.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 2, fig. 3 and fig. 4, fig. 1 is a flowchart of a disease identification method for a grape orchard according to an embodiment of the present invention; fig. 2 is a flowchart of a disease identification method for a grape orchard according to an embodiment of the present invention; FIG. 3 is a flow chart of a disease identification method for a grape orchard according to an embodiment of the invention; fig. 4 is a flowchart of a disease identification method for a grape orchard according to an embodiment of the present invention.
In a specific implementation manner of the present invention, an embodiment of the present invention provides a disease identification method for a grape orchard, including:
step S11: obtaining a grape leaf disease image training sample;
step S12: training a neural network algorithm model by using the grape leaf disease image training sample to obtain a grape disease identification model;
step S13: and identifying the grape leaf images to be identified by using the grape disease identification model to obtain an identification result so as to perform targeted prevention and control according to the identification result.
Firstly, the embodiment of the invention needs to use a neural network for training, so that a sample needs to be trained, images of various grape leaves can be collected as the sample, and the grape leaves can comprise a large number of different leaves, including grape leaves with different angles, different humidity, different temperatures, different illumination and different meteorological conditions. The grape leaf disease image training method comprises the steps of classifying grape leaves in an artificial mode, shooting pictures, and marking the images by using marking software, so that a grape leaf disease image training sample is obtained.
In one embodiment, specifically, in order to obtain a grape leaf disease image training sample, the following steps may be performed:
step S21: collecting normal grape leaves and diseased grape leaves in a grape orchard;
step S22: carrying out image shooting on the normal grape leaves and the diseased grape leaves to obtain original diseased leaf images;
step S23: preprocessing the original diseased leaves to obtain standard images in the same form;
step S24: and carrying out disease characteristic marking on the standard image to obtain a grape leaf disease image training sample.
Firstly, a large amount of normal grape leaves and diseased grape leaves can be collected in different seasons and aiming at different disease occurrence periods.
As shown in fig. 5, 6, 7, 8, 9, 10 and 11, fig. 5 is an image of normal grape leaves used in a disease identification method for a grape orchard according to an embodiment of the present invention; FIG. 6 is an image of powdery mildew grape leaves used in a disease identification method for a grape orchard according to an embodiment of the present invention; FIG. 7 is an image of downy mildew grape leaves used in a disease identification method for a grape orchard according to an embodiment of the invention; FIG. 8 is an image of anthracnose grape leaves used in a disease identification method for a grape orchard according to an embodiment of the present invention; FIG. 9 is an image of a botrytis cinerea leaf used in a disease identification method for a grape orchard according to an embodiment of the present invention; fig. 10 is an image of brown spot grape leaves used in a disease identification method for a grape orchard according to an embodiment of the present invention; fig. 11 is an image of a leaf of a anthracnose grape used in the disease identification method for a grape orchard according to the embodiment of the present invention. Specifically, the collected diseased grape leaves comprise: powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mold grape leaves, brown spot grape leaves and anthracnose grape leaves.
Obtaining an original disease leaf image by performing pendulum shooting on the collected grape leaves; of course, the grape leaves on the grape plants can also be directly photographed, and the collected grape leaves are photographed in the embodiment for the convenience of photographing. After shooting, the original diseased leaves can be preprocessed to obtain standard images in the same form. For example, the original disease leaf images can be normalized by using a preset formula to obtain normalized images; deleting images which do not accord with the training conditions from the normalized images to obtain screened images; and further carrying out noise reduction processing on the screened image to obtain a standard image. In addition, data enhancement can be carried out on the original diseased leaf image; the data enhancement specifically includes: and performing one or more of the following processes on the standard image: rotating an image, cropping an image, changing image color differences, distorting image features, changing image size, enhancing image noise. And finally, carrying out disease characteristic marking on the standard image to obtain a grape leaf disease image training sample.
Specifically, in practice, in order to perform characteristic marking of diseases on the standard image, the following steps may be adopted:
step S31: carrying out deformation marking on the shape of the blade in the standard image;
step S32: fading the leaf color in the standard image;
step S33: and carrying out rotting marking on the leaf area in the standard image.
That is to say: when a grape plant is infected with a disease, the physiological structure and morphological characteristics can be changed, such as deformation, fading, rot and the like, so that the grape leaf disease image is taken as an object, the physiological structure and morphological characteristics are taken as characteristics, and different physiological structures and morphological characteristics corresponding to different diseases can be used for training a neural network model to identify the grape disease.
On the basis of the foregoing embodiment, in this embodiment, in order to identify a grape leaf image to be identified by using the grape disease identification model, the following steps may be specifically performed:
step S41: acquiring a real-time leaf image of a grape plant to be identified as a grape leaf image to be identified;
step S42: inputting the grape leaf image to be identified into the grape disease identification model for identification;
step S43: and outputting the recognition result. And establishing a corresponding relation between the recognition result and the real-time grape leaf image, and storing.
In the specific implementation process, the grape leaf diseases can be identified in real time, for example, the electronic equipment running the grape disease identification model can be used for acquiring a real-time leaf image of a grape plant to be identified in a grape orchard in real time, namely, the image shooting is carried out through the arranged camera, then the grape leaf image to be identified is input into the grape disease identification model for identification, the identification result is output, the corresponding relation between the identification result and the real-time leaf image is established, and the identification result and the real-time leaf image are stored, so that a worker can conveniently know the disease information of each plant.
The embodiment of the invention provides a disease identification method for a grape orchard, which is used for carrying out feature training by applying a convolutional neural network, extracting effective features and automatically extracting common disease features so as to accurately identify disease types. Traditional to crops disease detection and discernment, mostly discern and analyze at the field scene through experienced expert, this kind of artifical mode cycle of squatting to watch on is long, waste time and manpower, and inefficiency, adopt the quick accurate discernment of disease based on degree of depth study, can carry out dynamic monitoring to grape leaf disease under the natural condition, one kind or several kinds of diseases in accurate discernment period, in order to do benefit to and carry out accurate institute to confirming the disease, reduce harm, improve fruit output, increase peasant income, can accurately discern the disease in grape orchard, provide the basis for spraying pesticides, promote agricultural product quality and agricultural ecological environment safety.
In the embodiment of the invention, when the grape leaves to be identified have diseases and insect pests, the position of the image of the grape leaves and the image of the healthy leaves in the disease and insect pest area is obviously different, for example, the common diseases and insect pests such as downy mildew and gray mold can have mildew-like substances in the characteristics of the grape leaves, namely various mildew layers generated at the disease-sensitive part have large changes in shape, color, texture, structure and the like. In the specific implementation process, the target images of the grape leaves with diseases and insect pests can be fused, analyzed and calculated through a deep learning algorithm to generate the image characteristics of the grape leaf diseases and insect pests, and the specific implementation process can comprise the following steps: the method comprises the steps of extracting image features of grape leaves with diseases and insect pests by adopting an HOG feature extraction method, dividing a target image of the grape leaves with the diseases and insect pests into a plurality of connected regions, namely cell units, collecting direction histograms of gradients or edges of all pixel points in the cell units, and combining the histograms of the gradients or the edges to form the image features of the grape leaf diseases and insect pests; furthermore, the species of the grape leaf disease and insect pest image features can be subdivided by using a network-based WaveCluster clustering algorithm, so that the images with similar features are classified into one class, and are correspondingly marked to generate class labels; and classifying and predicting the category labels by using a decision tree classification algorithm, obtaining an identification result through feature selection, decision tree generation and decision tree pruning, and outputting a pest and disease identification result of the grape leaves, wherein the identification result may be at least one of 6 types of powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mildew grape leaves, brown spot grape leaves and anthracnose grape leaves. It should be noted that the HOG feature is also called as a Histogram of Oriented Gradient (HOG) feature, and it constitutes a feature by calculating and counting a Histogram of Gradient orientations of local regions of an image, and a common method is to combine the HOG feature with an SVM to perform image recognition and classification. In an image, the appearance and shape (appearance and shape) of a local object can be well described by the direction density distribution of a gradient or an edge, the essence is to detect the edge of the image, and the edge is mainly represented by the statistical information of the gradient.
The grape leaf disease and insect pest image feature expression is analyzed and calculated through the deep learning network, a grape leaf disease and insect pest identification model based on the deep learning network is generated, and the specific implementation process can comprise the following steps: constructing and training a deep learning network model, wherein the deep learning network model can be composed of a convolution layer, two full-connection flows and a pest classification layer, and the two full-connection flows are positioned behind the convolution layer; each full-connection flow is composed of at least one full-connection layer; the number of the neurons of the last layer of the full-connection layer is the same as the number of the types of the corresponding grape disease and insect pest leaf images and the number of the types of the normal plant leaf images; the pest classification layer is positioned behind the two full-connection flows; each type in the pest classification layer corresponds to a plant pest; training normal grape leaf images by using a deep learning network model and generating model parameters; and transferring the model parameters to a new deep learning network model to obtain a grape disease identification model based on the deep learning network.
Inputting the to-be-identified grape leaf image into the grape disease identification model for identification, and if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the powdery mildew grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is powdery mildew; if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the downy mildew grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is downy mildew; if the attribute characteristics of the grape leaf images to be identified accord with the characteristics of the anthracnose grape leaves, judging that the grape leaves corresponding to the grape leaf images to be identified are anthracnose; if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the botrytis cinerea grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is botrytis cinerea; if the attribute characteristics of the grape leaf images to be identified accord with the characteristics of the brown spot grape leaves, judging that the grape leaves corresponding to the grape leaf images to be identified are brown spots; and if the attribute features of the to-be-identified grape leaf image accord with the features of the anthracnose grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is anthracnose. Finally, an identification result is output, the identification result may be at least one of 6 types of powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mold grape leaves, brown spot grape leaves, and anthracnose grape leaves.
Referring to fig. 12, fig. 12 is a flowchart of a disease identification system for a grape orchard according to an embodiment of the present invention.
In another embodiment of the present invention, the embodiment of the present invention provides a disease identification system 1200 for a grape orchard, including:
the sample acquisition module 1210 is used for acquiring a grape leaf disease image training sample;
the model training module 1220 is used for training a neural network algorithm model by using the grape leaf disease image training sample to obtain a grape disease identification model;
and the disease identification module 1230 is used for identifying the grape leaf image to be identified by using the grape disease identification model to obtain an identification result, so as to perform targeted control according to the identification result.
Preferably, the sample acquiring module comprises:
the blade collecting unit is used for collecting normal grape blades and diseased grape blades in a grape orchard;
the image shooting unit is used for shooting images of the normal grape leaves and the diseased grape leaves to obtain original diseased leaf images;
the pretreatment unit is used for pretreating the original diseased leaves to obtain standard images in the same form;
and the characteristic marking unit is used for carrying out characteristic marking on the disease on the standard image to obtain a grape leaf disease image training sample.
Preferably, the feature marking unit includes:
the deformation marking subunit is used for carrying out deformation marking on the shape of the blade in the standard image;
a fade marking subunit for fade marking a leaf color in the standard image;
and the rotting mark subunit is used for carrying out rotting mark on the leaf area in the standard image.
Referring to fig. 13, fig. 13 is a schematic structural diagram of a disease identification apparatus for a grape orchard according to an embodiment of the present invention.
The embodiment of the invention provides a disease identification device 1300 for a grape orchard, which comprises:
a memory 1310 for storing a computer program;
a processor 1320 for implementing the steps of any disease identification method for a grape orchard as described in any of the above embodiments when the computer program is executed.
The embodiment of the invention provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the disease identification method for a grape orchard according to any one of the embodiments are realized.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (10)
1. A disease identification method for a grape orchard is characterized by comprising the following steps:
obtaining a grape leaf disease image training sample;
training a neural network algorithm model by using the grape leaf disease image training sample to obtain a grape disease identification model;
and identifying the grape leaf images to be identified by using the grape disease identification model to obtain an identification result so as to perform targeted prevention and control according to the identification result.
2. The disease identification method for a vineyard according to claim 1,
the training sample for obtaining the grape leaf disease image comprises the following steps:
collecting normal grape leaves and diseased grape leaves in a grape orchard;
carrying out image shooting on the normal grape leaves and the diseased grape leaves to obtain original diseased leaf images;
preprocessing the original diseased leaves to obtain standard images in the same form;
and carrying out disease characteristic marking on the standard image to obtain a grape leaf disease image training sample.
3. The disease identification method for a vineyard according to claim 2,
the diseased grape leaves are divided into 6 types, including: powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mold grape leaves, brown spot grape leaves and anthracnose grape leaves.
4. The disease identification method for a vineyard according to claim 2,
the characteristic marking of the disease on the standard image comprises the following steps:
carrying out deformation marking on the shape of the blade in the standard image;
fading the leaf color in the standard image;
and carrying out rotting marking on the leaf area in the standard image.
5. The disease identification method for a grape orchard according to claim 3, wherein the identification of the grape leaf image to be identified by using the grape disease identification model comprises:
acquiring a real-time leaf image of a grape plant to be identified as a grape leaf image to be identified;
inputting the to-be-identified grape leaf image into the grape disease identification model for identification, and if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the powdery mildew grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is powdery mildew;
if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the downy mildew grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is downy mildew;
if the attribute characteristics of the grape leaf images to be identified accord with the characteristics of the anthracnose grape leaves, judging that the grape leaves corresponding to the grape leaf images to be identified are anthracnose;
if the attribute characteristics of the to-be-identified grape leaf image accord with the characteristics of the botrytis cinerea grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is botrytis cinerea;
if the attribute characteristics of the grape leaf images to be identified accord with the characteristics of the brown spot grape leaves, judging that the grape leaves corresponding to the grape leaf images to be identified are brown spots;
if the attribute features of the to-be-identified grape leaf image accord with the features of the anthracnose grape leaf, judging that the grape leaf corresponding to the to-be-identified grape leaf image is anthracnose;
outputting a recognition result, establishing a corresponding relation between the recognition result and a real-time grape leaf image, and storing the recognition result; wherein the identification result comprises at least one of 6 types of powdery mildew grape leaves, downy mildew grape leaves, anthracnose grape leaves, gray mildew grape leaves, brown spot grape leaves and anthracnose grape leaves.
6. A disease identification system for a vineyard, comprising:
the sample acquisition module is used for acquiring a grape leaf disease image training sample;
the model training module is used for training a neural network algorithm model by utilizing the grape leaf disease image training sample to obtain a grape disease identification model;
and the disease identification module is used for identifying the grape leaf images to be identified by using the grape disease identification model to obtain an identification result so as to perform targeted control according to the identification result.
7. The disease identification system for a vineyard according to claim 6,
the sample acquisition module comprises:
the blade collecting unit is used for collecting normal grape blades and diseased grape blades in a grape orchard;
the image shooting unit is used for shooting images of the normal grape leaves and the diseased grape leaves to obtain original diseased leaf images;
the pretreatment unit is used for pretreating the original diseased leaves to obtain standard images in the same form;
and the characteristic marking unit is used for carrying out characteristic marking on the disease on the standard image to obtain a grape leaf disease image training sample.
8. The disease identification system for a vineyard according to claim 7,
the feature labeling unit includes:
the deformation marking subunit is used for carrying out deformation marking on the shape of the blade in the standard image;
a fade marking subunit for fade marking a leaf color in the standard image;
and the rotting mark subunit is used for carrying out rotting mark on the leaf area in the standard image.
9. A disease identification equipment for grape orchard, characterized by comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for disease identification for vineyards according to any one of claims 1 to 5 when said computer program is executed.
10. A computer-readable storage medium, characterized in that it has stored thereon a computer program which, when being executed by a processor, carries out the steps of a method for disease identification for vineyards according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010612798.0A CN111832448A (en) | 2020-06-30 | 2020-06-30 | Disease identification method and system for grape orchard |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010612798.0A CN111832448A (en) | 2020-06-30 | 2020-06-30 | Disease identification method and system for grape orchard |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111832448A true CN111832448A (en) | 2020-10-27 |
Family
ID=72900804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010612798.0A Pending CN111832448A (en) | 2020-06-30 | 2020-06-30 | Disease identification method and system for grape orchard |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111832448A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471747A (en) * | 2022-08-30 | 2022-12-13 | 广东省农业科学院环境园艺研究所 | AI (artificial intelligence) rapid identification method for camellia diseases and insect pests and physiological diseases and application |
| CN115527109A (en) * | 2022-08-29 | 2022-12-27 | 邯郸市亿润工程咨询有限公司 | Underwater concrete disease monitoring method and device, underwater robot and medium |
| CN115936267A (en) * | 2023-03-10 | 2023-04-07 | 浪潮云洲(山东)工业互联网有限公司 | Internet of things-based grape disease prediction method and equipment |
-
2020
- 2020-06-30 CN CN202010612798.0A patent/CN111832448A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115527109A (en) * | 2022-08-29 | 2022-12-27 | 邯郸市亿润工程咨询有限公司 | Underwater concrete disease monitoring method and device, underwater robot and medium |
| CN115471747A (en) * | 2022-08-30 | 2022-12-13 | 广东省农业科学院环境园艺研究所 | AI (artificial intelligence) rapid identification method for camellia diseases and insect pests and physiological diseases and application |
| CN115936267A (en) * | 2023-03-10 | 2023-04-07 | 浪潮云洲(山东)工业互联网有限公司 | Internet of things-based grape disease prediction method and equipment |
| CN115936267B (en) * | 2023-03-10 | 2023-06-27 | 浪潮云洲(山东)工业互联网有限公司 | Grape disease prediction method and device based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | An AIoT based smart agricultural system for pests detection | |
| Farjon et al. | Detection and counting of flowers on apple trees for better chemical thinning decisions | |
| JP2019520631A (en) | Weed recognition in the natural environment | |
| CN111832448A (en) | Disease identification method and system for grape orchard | |
| Sharma et al. | RETRACTED ARTICLE: SVM-based compliance discrepancies detection using remote sensing for organic farms | |
| Sarkate et al. | Application of computer vision and color image segmentation for yield prediction precision | |
| Tiwari et al. | An experimental set up for utilizing convolutional neural network in automated weed detection | |
| CN114818909B (en) | Weed detection method and device based on crop growth characteristics | |
| CN111753646A (en) | Agricultural pest detection and classification method fusing population season growth and elimination information | |
| CN109344738A (en) | The recognition methods of crop diseases and pest crop smothering and device | |
| Jawade et al. | Disease prediction of mango crop using machine learning and IoT | |
| CN112465038A (en) | Method and system for identifying disease and insect pest types of fruit trees | |
| WO2021154624A1 (en) | System and method for performing machine vision recognition of dynamic objects | |
| CN112329506A (en) | Fruit identification method and system, and positioning method and system of wolfberry picking robot | |
| Schieck et al. | Comparison of deep learning methods for grapevine growth stage recognition | |
| Tripathy et al. | Image processing techniques aiding smart agriculture | |
| Jogi et al. | CNN based Synchronal recognition of Weeds in Farm Crops | |
| Balram et al. | Crop field monitoring and disease detection of plants in smart agriculture using internet of things | |
| Rony et al. | BottleNet18: Deep Learning-Based Bottle Gourd Leaf Disease Classification | |
| CN114022717A (en) | Blade disease identification method and system based on image identification | |
| Harsha et al. | Comparative Analysis of Smart Pesticide Recommendation System sing ML/AI | |
| Dahiya et al. | An Effective Detection of Litchi Disease using Deep Learning | |
| Sornalakshmi et al. | A technical survey on deep learning and AI solutions for plant quality and health indicators monitoring in agriculture | |
| Uzun | An intelligent system for detecting Mediterranean fruit fly [Medfly; Ceratitis capitata (Wiedemann)] | |
| Patil et al. | GRAPE QUALITY PREDICTION WITH PRE-POST HARVESTING USING FUSION DEEP LEARNING |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |