CN112750123A - Rice disease and insect pest monitoring method and system - Google Patents
Rice disease and insect pest monitoring method and system Download PDFInfo
- Publication number
- CN112750123A CN112750123A CN202110088142.8A CN202110088142A CN112750123A CN 112750123 A CN112750123 A CN 112750123A CN 202110088142 A CN202110088142 A CN 202110088142A CN 112750123 A CN112750123 A CN 112750123A
- Authority
- CN
- China
- Prior art keywords
- disease
- image
- pest
- rice
- insect pest
- 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
- 201000010099 disease Diseases 0.000 title claims abstract description 266
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 266
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 259
- 241000238631 Hexapoda Species 0.000 title claims abstract description 178
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 129
- 235000009566 rice Nutrition 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 240000007594 Oryza sativa Species 0.000 title 1
- 241000209094 Oryza Species 0.000 claims abstract description 141
- 238000012545 processing Methods 0.000 claims abstract description 66
- 230000011218 segmentation Effects 0.000 claims description 50
- 238000001914 filtration Methods 0.000 claims description 39
- 230000002265 prevention Effects 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 22
- 241000196324 Embryophyta Species 0.000 claims description 14
- 238000003708 edge detection Methods 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 230000002452 interceptive effect Effects 0.000 claims description 11
- 230000000877 morphologic effect Effects 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 abstract description 6
- 239000013598 vector Substances 0.000 description 12
- 230000003902 lesion Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 238000012706 support-vector machine Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 206010039509 Scab Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000001580 bacterial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a rice disease and insect pest monitoring method and system, wherein the method comprises the following steps: adjusting the position and the angle of the acquisition equipment through a holder bracket; acquiring a rice disease and insect pest position image through acquisition equipment; and processing the rice disease and insect pest position image through embedded end equipment, and determining and displaying the disease and insect pest grade according to the processing result. The scheme can freely adjust the position and the position of the acquisition equipment, so that the acquired rice disease and insect pest part image is clearer and has higher pertinence; the acquired images directly calculate the area of rice diseases and insect pests in real time through the embedded terminal and judge the grade of the diseases and insect pests, so that the instability of the quality of the images to be processed caused by transmission factors is avoided, and the image processing efficiency and the processing quality are improved; subjectivity and errors of artificial judgment of pest and disease damage grades are avoided, and judgment accuracy is improved; through embedded end equipment implementation display, technical personnel of being convenient for in time know the rice plant diseases and insect pests condition, realized intelligent monitoring.
Description
Technical Field
The invention relates to the field of digital agricultural rice disease and insect pest monitoring, in particular to a rice disease and insect pest monitoring method and system.
Background
At present, the intelligent degree of rice disease and insect pest monitoring is lagged behind, the work of identifying and diagnosing the disease and insect pest mainly depends on the experience of basic level testers, the problems of low efficiency, strong subjectivity, large error and the like exist, and the rice high-incidence part which is difficult to reach by human eyes cannot be observed. The disease and insect damage are difficult to distinguish in the early stage of rice disease and insect damage, and are difficult to detect in the disease and insect damage occurrence process, so that the optimal disease and insect damage prevention and control period is easy to miss.
In addition, in the existing crop disease and pest monitoring system applied to the field, the collected tools mainly comprise a digital camera, a mobile phone and a network camera for installing the field ground, the field range monitored by the tools is limited, agricultural basic personnel need to enter a field on-site debugging machine position or change the fixed position regularly, the operation is complicated, the labor amount is large, the global and local positions of crops cannot be well monitored, most of the existing crop disease and pest monitoring systems applied to the field need to acquire images and then upload the images to a PC (personal computer) end for image processing, the transmission speed of image information is difficult to keep at an ideal level due to the influence of external environment (equipment, network and the like), the result feedback process also needs time to wait after the PC end is processed, and the overall detection processing speed is slow. In addition, most of the existing crop disease and insect pest monitoring systems also have the problem that the judgment accuracy rate is not high enough.
Disclosure of Invention
The invention aims to solve the technical problem of providing a rice disease and insect pest monitoring method aiming at the defects of the prior art and solving the problems of low efficiency and low accuracy of the prior rice disease and insect pest monitoring technology.
The technical scheme for solving the technical problems is as follows: a rice pest and disease damage monitoring method comprises the following steps: adjusting the position and the angle of the acquisition equipment through a holder bracket; acquiring a rice disease and insect pest position image through acquisition equipment; and processing the rice disease and insect pest position image through embedded end equipment, and determining and displaying the disease and insect pest grade according to the processing result.
The rice disease and pest location image acquisition device has the advantages that the left and right deflection of the camera, the up and down inclination angle of the camera and the position of the camera can be freely adjusted through the holder bracket, so that the acquired rice disease and pest location image is clearer and has higher pertinence; the acquired images directly calculate the area of rice diseases and insect pests in real time through the embedded terminal and judge the grade of the diseases and insect pests, so that the instability of the quality of the images to be processed caused by transmission factors is avoided, and the image processing efficiency and the processing quality are improved; subjectivity and errors of artificial judgment of pest and disease damage grades are avoided, and judgment accuracy is improved; through embedded end equipment implementation display, technical personnel of being convenient for in time know the rice plant diseases and insect pests condition, realized intelligent monitoring.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, in the above technical solution, the processing the rice plant disease and insect pest location image through the embedded terminal device, and determining the grade of the plant disease and insect pest according to the processing result, includes: carrying out Gaussian filtering denoising and gray level transformation on the rice disease and insect pest position image to obtain a first image; carrying out binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation on the first image to separate disease spots of the rice disease and pest part image to obtain a second image; and calculating the area of the disease spot according to the second image and determining the grade of the disease and insect pests according to a preset disease spot area judgment criterion.
The further scheme has the advantages that the image denoising can be carried out on the rice disease and insect pest position image through Gaussian filtering denoising and gray level transformation, and the disease spots of the rice disease and insect pest position image can be accurately separated through binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation, so that the accuracy of disease and insect pest grade discrimination is improved.
Further, in the above technical solution, the method further includes: sending the rice disease and pest position image to a remote device; processing the rice disease and insect pest position image through remote equipment to determine the disease and insect pest type, determining a prevention and control measure corresponding to the disease and insect pest type according to the disease and insect pest type, and sending the prevention and control measure back to the embedded end for displaying.
The method has the advantages that the remote equipment is used for processing the rice plant disease and insect pest position image to determine the type of the plant disease and insect pest and determine the prevention and treatment measures, so that accurate suggestions for preventing and treating the plant disease and insect pest can be conveniently and quickly provided for users, the plant disease and insect pest type judgment and prevention measures are matched and placed at the remote end, resources of the embedded end equipment are saved, and the monitoring efficiency of the embedded end equipment can be improved.
Further, in the above technical solution, the determining the type of the pest by processing the rice pest position image with the remote device includes: carrying out Gaussian filtering denoising on the rice disease and insect pest position image through the remote equipment to obtain a third image; performing super-color threshold segmentation and significance threshold segmentation on the third image to separate disease spots of the rice disease and insect pest position image to obtain a fourth image; and performing morphological filtering, feature extraction and classification training on the fourth image to determine the type of the plant diseases and insect pests.
The method has the advantages that the rice disease and insect pest part image can be denoised through Gaussian filtering denoising, the scabs of the rice disease and insect pest part image can be accurately separated through super-color threshold segmentation and significance threshold segmentation, and the type of the disease and insect pest can be accurately determined by performing morphological filtering, feature extraction and classification training on the fourth image.
Further, in the above technical solution, determining a control measure corresponding to the type of the pest according to the type of the pest includes: uploading the pest and disease damage types to an expert suggestion library through remote equipment, and acquiring control measures corresponding to the pest and disease damage types through the expert suggestion library.
The beneficial effect of adopting the above preferred scheme is that the determined control measures can be more accurate by using the expert advice library.
In order to solve the technical problem, the invention also provides a rice disease and insect pest monitoring system, which comprises a holder bracket, acquisition equipment and embedded end equipment; the holder bracket is characterized in that: the device is used for adjusting the position and the angle of the acquisition equipment; the acquisition equipment comprises: the method is used for collecting rice disease and insect pest position images; the embedded end equipment comprises: the method is used for processing the rice disease and insect pest position image, determining the disease and insect pest grade according to the processing result and displaying the disease and insect pest grade.
The beneficial effect of the scheme is that the left and right deflection of the camera, the up and down inclination angle of the camera and the position of the camera can be freely adjusted through the holder bracket, so that the collected rice disease and insect pest position image is clearer and has higher pertinence; the acquired images directly calculate the area of rice diseases and insect pests in real time through the embedded terminal and judge the grade of the diseases and insect pests, so that the instability of the quality of the images to be processed caused by transmission factors is avoided, and the image processing efficiency and the processing quality are improved; subjectivity and errors of artificial judgment of pest and disease damage grades are avoided, and judgment accuracy is improved; through embedded end equipment implementation display, technical personnel of being convenient for in time know the rice plant diseases and insect pests condition, realized intelligent monitoring.
Further, in the above technical solution, the embedded end device includes an embedded end processing module; the embedded end processing module: the method is used for processing the rice disease and insect pest position image and determining the disease and insect pest grade according to the processing result, and comprises the following steps: carrying out Gaussian filtering denoising and gray level transformation on the rice disease and insect pest position image to obtain a first image; and carrying out binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation on the first image to separate disease spots of the rice disease and pest part image to obtain a second image.
The scheme has the advantages that the image denoising can be carried out on the rice disease and insect pest position image through Gaussian filtering denoising and gray level transformation, and the disease spots of the rice disease and insect pest position image can be accurately separated through binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation, so that the accuracy of disease and insect pest grade discrimination is improved.
Further, in the above technical solution, the remote device further includes: the embedded terminal equipment is also used for sending the rice disease and pest position image to remote equipment; the remote device: the method is used for processing the rice disease and insect pest position image to determine the disease and insect pest type, determining the prevention and treatment measures corresponding to the disease and insect pest type according to the disease and insect pest type, and sending the prevention and treatment measures back to the embedded end equipment for displaying.
The method has the advantages that the rice disease and insect pest position image is processed through the remote equipment to determine the disease and insect pest type and determine the prevention and treatment measures, so that accurate suggestions for preventing and treating the disease and insect pest can be conveniently and quickly provided for users, the disease and insect pest type judgment and prevention and treatment measures are matched and placed at the remote end, resources of the embedded end equipment are saved, and the monitoring efficiency of the embedded end equipment can be improved.
Further, in the above technical solution, the remote device includes a remote processing module; the remote processing module: the Gaussian filtering denoising method is used for carrying out Gaussian filtering denoising on the rice disease and insect pest position image to obtain a third image; performing super-color threshold segmentation and significance threshold segmentation on the third image to separate disease spots of the rice disease and insect pest position image to obtain a fourth image; and performing morphological filtering, feature extraction and classification training on the fourth image to determine the type of the plant diseases and insect pests.
The scheme has the advantages that the rice disease and insect pest position image can be denoised through Gaussian filtering denoising, the disease spots of the rice disease and insect pest position image can be accurately separated through super-color threshold segmentation and significance threshold segmentation, and the type of the disease and insect pest can be accurately determined by performing morphological filtering, feature extraction and classification training on the fourth image.
Further, in the above technical solution, the remote device includes a control measure determining module: the control measure determination module: and the system is used for uploading the pest and disease damage types to an expert suggestion library and acquiring control measures corresponding to the pest and disease damage types through the expert suggestion library.
The beneficial effect of adopting the above preferred scheme is that the determined control measures can be more accurate by using the expert advice library.
Drawings
FIG. 1 is a schematic flow chart of a rice disease and pest monitoring method provided by an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another rice disease and pest monitoring method provided by the embodiment of the invention;
FIG. 3 is a schematic diagram of determining pest grade in a rice pest monitoring method according to an embodiment of the present invention;
fig. 4 is a schematic view of a rice disease and pest monitoring system provided by an embodiment of the invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Example one
As shown in fig. 1, fig. 1 is a schematic flow chart of a rice pest monitoring method provided by an embodiment of the present invention, and the method includes:
s101: adjusting the position and the angle of the acquisition equipment through a holder bracket;
s102: acquiring a rice disease and insect pest position image through acquisition equipment;
s103: and processing the rice disease and insect pest position image through embedded end equipment, and determining and displaying the disease and insect pest grade according to the processing result.
In this embodiment, the available cloud platform support that image acquisition equipment connected of agricultural staff adjusts collection equipment like the camera, and cloud platform support is connected with collection equipment. The staff only need control the pan tilt support through embedded end equipment or pan tilt support's control button thereby control the control camera about deflect, the upper and lower inclination of camera and the position of camera to reach clearer and pertinence collection, the acquisition equipment has accessed embedded end equipment development board, can be at the position picture that embedded end equipment real-time supervision camera was gathered.
The embedded terminal equipment carries a display screen, and after the acquired image directly calculates the area of rice plant diseases and insect pests in real time through the embedded terminal and judges the grade of the plant diseases and insect pests, the display screen displays the image, so that the instability of the quality of the image to be processed due to transmission factors is avoided, and the image processing efficiency and the processing quality are improved; subjectivity and errors of artificial judgment of pest and disease damage grades are avoided, and judgment accuracy is improved; through embedded end equipment implementation display, technical personnel of being convenient for in time know the rice plant diseases and insect pests condition, realized intelligent monitoring.
The method for processing the rice disease and insect pest position image through the embedded terminal equipment specifically comprises the following steps: carrying out image denoising on the rice disease and insect pest image, separating disease spots from a background, and calculating the area of the extracted disease spots;
the pest and disease damage grade can be determined according to the average area ratio of the lesion area of a single leaf to the whole leaf of local rice calculated by the embedded end equipment, and can also be determined according to the ratio of the lesion area on the leaf to the total area of the leaf.
Further, in this embodiment, the processing the rice plant disease and insect pest location image through the embedded terminal device, and determining the plant disease and insect pest grade according to the processing result includes:
carrying out Gaussian filtering denoising and gray level transformation on the rice disease and insect pest position image to obtain a first image; carrying out binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation on the first image to separate disease spots of the rice disease and pest part image to obtain a second image; and calculating the area of the disease spot according to the second image and determining the grade of the disease and insect pests according to a preset disease spot area judgment criterion.
The gaussian filtering is a linear smooth filtering, and is suitable for eliminating gaussian noise, and is widely applied to a noise reduction process of image processing, in popular terms, the gaussian filtering is a process of weighted averaging of the whole image, the value of each pixel point is obtained by weighting averaging itself and other pixel values in the neighborhood, and the specific operation of the gaussian filtering is as follows: each pixel in the image is scanned using a template (or convolution, mask), and the weighted average gray value of the pixels in the neighborhood determined by the template is used to replace the value of the pixel in the center of the template.
The gray level transformation specifically comprises the step of changing the gray level value of each pixel in a source image point by point according to a certain transformation relation according to a target condition, so as to improve the image quality and enable the display effect of the image to be clearer.
The binarization of the image is to set the gray value of a pixel point on the image to be 0 or 255, that is, the whole image has an obvious visual effect of only black and white, and the image can be simply segmented.
The edge detection utilizes a canny edge detection algorithm, and the background and the target can be separated by combining HSV space threshold segmentation and Grab cut interaction segmentation. The area calculation uses the contourArea function in OpenCV to perform the area calculation.
The specific process of determining the pest and disease damage grade according to the preset lesion area judgment criterion is shown in the flow chart 3, namely determining the pest and disease damage grade according to the preset lesion area judgment criterion.
The preset lesion area judgment criterion may be: when the ratio of the lesion area of a single leaf to the average area of the whole leaves of the local rice is less than 0.3 (judgment range 1), the pest grade is mild, when the ratio is 0.3-0.6 (judgment range 2), the pest grade is moderate, and when the ratio is more than 0.6 (judgment range 3), the pest grade is severe; obviously, the above ranges can be adjusted based on the actual situation, and do not limit the invention.
The image denoising can be carried out on the rice disease and insect pest part image through Gaussian filtering denoising and gray level transformation, and the disease spots of the rice disease and insect pest part image can be accurately separated through binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation, so that the accuracy of disease and insect pest grade discrimination is improved.
Example two
As shown in fig. 2, the method for monitoring rice diseases and pests provided by this embodiment includes:
s101: adjusting the position and the angle of the acquisition equipment through a holder bracket;
s102: acquiring a rice disease and insect pest position image through acquisition equipment;
s103: processing the rice disease and insect pest position image through embedded end equipment, determining the disease and insect pest grade according to the processing result and displaying;
s104: sending the rice disease and pest position image to a remote device;
s105: processing the rice disease and insect pest position image through remote equipment to determine the disease and insect pest type, determining a prevention and control measure corresponding to the disease and insect pest type according to the disease and insect pest type, and sending the prevention and control measure back to the embedded end for displaying.
The control measures corresponding to the pest types are determined according to the pest types, the control measures corresponding to different types of diseases can be recorded according to pre-stored data, and a database or a system for obtaining the corresponding control measures by inputting the pest types can also be used.
The remote equipment is used for processing the rice disease and insect pest position image to determine the disease and insect pest type and determine the prevention and treatment measures, so that accurate suggestions for preventing and treating the disease and insect pest can be conveniently and quickly provided for a user, the disease and insect pest type judgment and the prevention and treatment measures are matched and placed at the remote end, the resources of the embedded end equipment are saved, and the monitoring efficiency of the embedded end equipment can be improved.
Further, in this embodiment, the determining the type of the pest by processing the rice pest position image through the remote device includes: the remote equipment performs Gaussian filtering denoising on the rice disease and insect pest position image to obtain a third image; performing super-color threshold segmentation and significance threshold segmentation on the third image to separate disease spots of the rice disease and insect pest position image to obtain a fourth image; and performing morphological filtering, feature extraction and classification training on the fourth image to determine the type of the plant diseases and insect pests.
For super-color segmentation, most of background areas in rice pest images collected on agricultural sites are mainly green and are background areas needing to be removed, so that the sphere ranges taking (R, g and b) as the center and R as the radius are all background areas close to green, and the sphere ranges are expressed as formula 1.1:
equation 1.1: (x-r)2+(y-g)2+(z-b)2≤R2
The specific steps of the hypercolor segmentation are as follows: calculating an RGB histogram of the pest and disease damage image, and respectively calculating peak probabilities of three color components; setting the segmentation threshold to R according to equation 1.12For the pest image s (i, j),
wherein g (i, j) ═ f ((x-r)2+(y-g)2+(z-b)2)。
The high-green background noise of the rice disease and insect pest image can be removed through the high-color segmentation algorithm, and the disease area can be reserved as far as possible.
For saliency segmentation, which may also be referred to as visual saliency detection, a frequency domain saliency detection algorithm (FT), a histogram contrast based saliency detection algorithm (HC), a global contrast based LC detection algorithm, a region contrast and map based saliency detection algorithm (RC), a residual spectrum based saliency detection algorithm (SR), and the like may be adopted, and salient regions in an image may be segmented by saliency segmentation.
In addition, the scab image noise separated from the rice plant disease and insect pest position image can be eliminated through morphological filtering, and the outline is smoothed.
For feature extraction, feature extraction is performed through a gray level co-occurrence matrix and a color histogram.
For classification training, the classification training specifically refers to classification training of an SVM (support vector machine), classification of multiple types of diseases is achieved by using a one-to-many method in the classification training of the SVM, a classifier is trained for each type, after training is completed, for a feature vector to be classified, the probability of the feature vector being classified in the type is calculated by using each classifier, and then the type with the highest probability is selected as the type of the feature vector. In detail, in the one-over-rest (OVR SVMs for short), during training, samples of a certain class are sequentially classified into one class, and other remaining samples are classified into another class, so that k SVMs are constructed from samples of k classes. The classification classifies the unknown sample as the class having the largest classification function value. If four disease types are to be divided (namely 4 Label), namely A (sheath blight disease), B (rice blast disease), C (streak disease) and D (bacterial leaf blight disease), respectively extracting the vector corresponding to the A in the step (1) as a positive set and the vectors corresponding to the B, C and D as a negative set when the training set is extracted; (2) the vector corresponding to B is used as a positive set, and the vectors corresponding to A, C and D are used as a negative set; (3) the vector corresponding to C is used as a positive set, and the vectors corresponding to A, B and D are used as a negative set; (4) the vector corresponding to D is used as a positive set, and the vectors corresponding to A, B and C are used as a negative set; and respectively training by using the four training sets to obtain four training result files. And during testing, testing the corresponding test vectors by using the four training result files respectively. Each of the final tests has a result f1(x), f2(x), f3(x), f4(x), the final result being the largest of these four values as the classification result, so that the pest can be classified to determine the type of pest.
After the disease and insect pest types are obtained through classification training, the disease and insect pest types can be compared with data of a disease and insect pest image information base, the disease and insect pest image information base can be a database in which various disease and insect pest types and corresponding pictures are recorded, or other disease and insect pest image recognition systems, and if the determined disease and insect pest types are the same, a remote result is directly output; if the difference is not the same, the result is further uploaded to an expert suggestion library, and a rice disease and pest expert performs further identification.
Further, in this embodiment, determining the control measure corresponding to the type of pest according to the type of pest may include: uploading the pest and disease damage types to an expert suggestion library through remote equipment, and acquiring control measures corresponding to the pest and disease damage types through the expert suggestion library.
By using a library of expert advice, the determined control measures can be made more accurate. The expert suggestion library is an intelligent query system covering various rice disease and insect pest types and corresponding prevention measures, the received rice disease and insect pest types are used as input, the corresponding prevention measures can be queried in real time, and then the prevention measures are fed back to a far end.
As shown in fig. 4, the embodiment further provides a rice disease and pest monitoring system, which includes a cradle head support, a collection device and an embedded terminal device;
the holder bracket is characterized in that: the device is used for adjusting the position and the angle of the acquisition equipment;
the acquisition equipment comprises: the method is used for collecting rice disease and insect pest position images;
the embedded end equipment comprises: the method is used for processing the rice disease and insect pest position image, determining the disease and insect pest grade according to the processing result and displaying the disease and insect pest grade.
Wherein, the agricultural staff can adjust the acquisition equipment such as camera with the cloud platform support that the peripheral hardware image acquisition equipment is connected, and cloud platform support is connected with the acquisition equipment. The staff only need control the pan tilt support through embedded end equipment or pan tilt support's control button thereby control the control camera about deflect, the upper and lower inclination of camera and the position of camera to reach clearer and pertinence collection, the acquisition equipment has accessed embedded end equipment development board, can be at the position picture that embedded end equipment real-time supervision camera was gathered.
The embedded end equipment carries a display screen, can intelligently monitor rice plant diseases and insect pests through an embedded technology, and can directly calculate the area of the rice plant diseases and insect pests in real time and judge the grade of the plant diseases and insect pests by the embedded end after an image is collected;
the embedded terminal equipment carries a display screen, and after the acquired image directly calculates the area of rice plant diseases and insect pests in real time through the embedded terminal and judges the grade of the plant diseases and insect pests, the display screen displays the image, so that the instability of the quality of the image to be processed due to transmission factors is avoided, and the image processing efficiency and the processing quality are improved; subjectivity and errors of artificial judgment of pest and disease damage grades are avoided, and judgment accuracy is improved; through embedded end equipment implementation display, technical personnel of being convenient for in time know the rice plant diseases and insect pests condition, realized intelligent monitoring.
The pest and disease damage grade can be determined according to the average area ratio of the lesion area of a single leaf to the whole leaf of local rice calculated by the embedded end equipment, and can also be determined according to the ratio of the lesion area on the leaf to the total area of the leaf.
Further, in this embodiment, the embedded end device includes an embedded end processing module; the embedded end processing module: the method is used for processing the rice disease and insect pest position image and determining the disease and insect pest grade according to the processing result, and comprises the following steps: carrying out Gaussian filtering denoising and gray level transformation on the rice disease and insect pest position image to obtain a first image; carrying out binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation on the first image to separate disease spots of the rice disease and pest part image to obtain a second image; and calculating the area of the disease spot according to the second image and determining the grade of the disease and insect pests according to a preset disease spot area judgment criterion.
The image denoising can be carried out on the rice disease and insect pest part image through Gaussian filtering denoising and gray level transformation, and disease spots of the rice disease and insect pest part image can be accurately separated through binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation, so that the accuracy of disease and insect pest grade discrimination is improved;
the embedded end processing module performs gaussian filtering denoising, gray level transformation, binarization, edge detection, HSV space threshold segmentation, and Grab cut interactive segmentation, and the like, as described in the above embodiments of the rice disease and pest monitoring method, and are not described in detail herein.
As shown in fig. 4, the rice disease and pest monitoring system provided in this embodiment further includes a remote device, and the embedded terminal device is further configured to send the rice disease and pest position image to the remote device; the remote device: the method is used for processing the rice disease and insect pest position image to determine the disease and insect pest type, determining the prevention and treatment measures corresponding to the disease and insect pest type according to the disease and insect pest type, and sending the prevention and treatment measures back to the embedded end equipment for displaying.
The remote equipment can be a pc, a mobile phone, a server and other equipment, the remote equipment and the embedded equipment are wirelessly transmitted, rice disease and insect pest position images are processed through the remote equipment to determine disease and insect pest types and determine prevention measures, so that accurate suggestions for preventing and treating diseases and insect pests can be conveniently and rapidly provided for users, the disease and insect pest types are judged, the prevention measures are matched and placed at the remote end, resources of the embedded equipment are saved, and the monitoring efficiency of the embedded equipment can be improved.
Further, in this embodiment, the remote device includes a remote processing module; the remote processing module: the Gaussian filtering denoising method is used for carrying out Gaussian filtering denoising on the rice disease and insect pest position image to obtain a third image; performing super-color threshold segmentation and significance threshold segmentation on the third image to separate disease spots of the rice disease and insect pest position image to obtain a fourth image; and performing morphological filtering, feature extraction and classification training on the fourth image to determine the type of the plant diseases and insect pests.
The contents of gaussian filtering denoising, hypercolor threshold segmentation, significance threshold segmentation, morphological filtering, feature extraction, classification training and the like are as described in the embodiments of the rice disease and pest monitoring method, and are not described in detail herein;
the rice disease and insect pest position image can be denoised through Gaussian filtering denoising, disease spots of the rice disease and insect pest position image can be accurately separated through super-color threshold segmentation and significance threshold segmentation, and the disease and insect pest type can be accurately determined by performing morphological filtering, feature extraction and classification training on the fourth image.
Further, in this embodiment, the remote device includes a control measure determining module, where the control measure determining module: and the system is used for uploading the pest and disease damage types to an expert suggestion library and acquiring control measures corresponding to the pest and disease damage types through the expert suggestion library.
The expert suggestion library is an intelligent query system covering various rice disease and insect pest type corresponding control measures, and the determined control measures can be more accurate by using the expert suggestion library. The expert suggestion library is an intelligent query system covering various rice disease and insect pest types and corresponding prevention measures, the received rice disease and insect pest types are used as input, the corresponding prevention measures can be queried in real time, and then the prevention measures are fed back to a far end.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A rice disease and pest monitoring method is characterized by comprising the following steps:
adjusting the position and the angle of the acquisition equipment through a holder bracket;
acquiring a rice disease and insect pest position image through acquisition equipment;
and processing the rice disease and insect pest position image through embedded end equipment, and determining and displaying the disease and insect pest grade according to the processing result.
2. A rice pest monitoring method according to claim 1, wherein the step of processing the rice pest location image through the embedded terminal device and determining the pest grade according to the processing result comprises:
carrying out Gaussian filtering denoising and gray level transformation on the rice disease and insect pest position image to obtain a first image;
carrying out binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation on the first image to separate disease spots of the rice disease and pest part image to obtain a second image;
and calculating the area of the disease spot according to the second image and determining the grade of the disease and insect pests according to a preset disease spot area judgment criterion.
3. A rice pest monitoring method according to claim 1 further comprising:
sending the rice disease and pest position image to a remote device;
processing the rice disease and insect pest position image through remote equipment to determine the disease and insect pest type, determining a prevention and control measure corresponding to the disease and insect pest type according to the disease and insect pest type, and sending the prevention and control measure back to the embedded end for displaying.
4. A rice pest monitoring method according to claim 3 wherein processing the rice pest map image by a remote facility to determine the type of pest comprises:
carrying out Gaussian filtering denoising on the rice disease and insect pest position image through the remote equipment to obtain a third image;
performing super-color threshold segmentation and significance threshold segmentation on the third image to separate disease spots of the rice disease and insect pest position image to obtain a fourth image;
and performing morphological filtering, feature extraction and classification training on the fourth image to determine the type of the plant diseases and insect pests.
5. A rice pest monitoring method according to claim 3 or claim 4 wherein determining a control measure corresponding to the type of pest based on the type of pest includes:
uploading the pest and disease damage types to an expert suggestion library through remote equipment, and acquiring control measures corresponding to the pest and disease damage types through the expert suggestion library.
6. A rice disease and pest monitoring system is characterized by comprising a holder bracket, a collecting device and an embedded end device;
the holder bracket is characterized in that: the device is used for adjusting the position and the angle of the acquisition equipment;
the acquisition equipment comprises: the method is used for collecting rice disease and insect pest position images;
the embedded end equipment comprises: the method is used for processing the rice disease and insect pest position image, determining the disease and insect pest grade according to the processing result and displaying the disease and insect pest grade.
7. A rice pest monitoring system according to claim 6 wherein the embedded end device includes an embedded end processing module;
the embedded end processing module: the method is used for processing the rice disease and insect pest position image and determining the disease and insect pest grade according to the processing result, and comprises the following steps:
carrying out Gaussian filtering denoising and gray level transformation on the rice disease and insect pest position image to obtain a first image;
carrying out binarization, edge detection, HSV space threshold segmentation and Grab cut interactive segmentation on the first image to separate disease spots of the rice disease and pest part image to obtain a second image;
and calculating the area of the disease spot according to the second image and determining the grade of the disease and insect pests according to a preset disease spot area judgment criterion.
8. A rice pest monitoring system according to claim 6 further including a remote device:
the embedded terminal equipment is also used for sending the rice disease and pest position image to remote equipment;
the remote device: the method is used for processing the rice disease and insect pest position image to determine the disease and insect pest type, determining the prevention and treatment measures corresponding to the disease and insect pest type according to the disease and insect pest type, and sending the prevention and treatment measures back to the embedded end equipment for displaying.
9. A rice pest monitoring system according to claim 8 wherein the remote apparatus includes a remote processing module;
the remote processing module: the Gaussian filtering denoising method is used for carrying out Gaussian filtering denoising on the rice disease and insect pest position image to obtain a third image;
performing super-color threshold segmentation and significance threshold segmentation on the third image to separate disease spots of the rice disease and insect pest position image to obtain a fourth image;
and performing morphological filtering, feature extraction and classification training on the fourth image to determine the type of the plant diseases and insect pests.
10. A rice pest monitoring system according to claim 8 or claim 9 wherein: the remote device includes a control measure determination module:
the control measure determination module: and the system is used for uploading the pest and disease damage types to an expert suggestion library and acquiring control measures corresponding to the pest and disease damage types through the expert suggestion library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110088142.8A CN112750123A (en) | 2021-01-22 | 2021-01-22 | Rice disease and insect pest monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110088142.8A CN112750123A (en) | 2021-01-22 | 2021-01-22 | Rice disease and insect pest monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112750123A true CN112750123A (en) | 2021-05-04 |
Family
ID=75652897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110088142.8A Pending CN112750123A (en) | 2021-01-22 | 2021-01-22 | Rice disease and insect pest monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112750123A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435252A (en) * | 2021-05-27 | 2021-09-24 | 广西壮族自治区烟草公司百色市公司 | Tobacco pest and disease monitoring and early warning method and system based on remote sensing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514459A (en) * | 2013-10-11 | 2014-01-15 | 中国科学院合肥物质科学研究院 | Method and system for identifying crop diseases and pests based on Android mobile phone platform |
| CN108111614A (en) * | 2017-12-27 | 2018-06-01 | 北京工业大学 | Agriculture and forestry pest and disease monitoring manages system |
| CN109101891A (en) * | 2018-07-17 | 2018-12-28 | 哈尔滨理工大学 | A kind of rice pest detection system and its detection method merging artificial intelligence |
| CN110517311A (en) * | 2019-08-30 | 2019-11-29 | 北京麦飞科技有限公司 | Pest and disease monitoring method based on leaf spot lesion area |
| US20200311915A1 (en) * | 2017-11-29 | 2020-10-01 | Optim Corporation | Growth status prediction system and method and computer-readable program |
-
2021
- 2021-01-22 CN CN202110088142.8A patent/CN112750123A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514459A (en) * | 2013-10-11 | 2014-01-15 | 中国科学院合肥物质科学研究院 | Method and system for identifying crop diseases and pests based on Android mobile phone platform |
| US20200311915A1 (en) * | 2017-11-29 | 2020-10-01 | Optim Corporation | Growth status prediction system and method and computer-readable program |
| CN108111614A (en) * | 2017-12-27 | 2018-06-01 | 北京工业大学 | Agriculture and forestry pest and disease monitoring manages system |
| CN109101891A (en) * | 2018-07-17 | 2018-12-28 | 哈尔滨理工大学 | A kind of rice pest detection system and its detection method merging artificial intelligence |
| CN110517311A (en) * | 2019-08-30 | 2019-11-29 | 北京麦飞科技有限公司 | Pest and disease monitoring method based on leaf spot lesion area |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435252A (en) * | 2021-05-27 | 2021-09-24 | 广西壮族自治区烟草公司百色市公司 | Tobacco pest and disease monitoring and early warning method and system based on remote sensing |
| CN113435252B (en) * | 2021-05-27 | 2023-09-29 | 广西壮族自治区烟草公司百色市公司 | Remote sensing-based tobacco pest monitoring and early warning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10943346B2 (en) | Multi-sample whole slide image processing in digital pathology via multi-resolution registration and machine learning | |
| CN111474701B (en) | Pathological microscopic image real-time acquisition and analysis system, method, device and medium | |
| WO2021139258A1 (en) | Image recognition based cell recognition and counting method and apparatus, and computer device | |
| CN111368643B (en) | Escherichia coli dynamic growth monitoring method | |
| CN111275041B (en) | Endoscope image display method and device, computer equipment and storage medium | |
| US10395091B2 (en) | Image processing apparatus, image processing method, and storage medium identifying cell candidate area | |
| CN110766656B (en) | Method, device, equipment and storage medium for screening fundus macular region abnormality | |
| KR102155381B1 (en) | Method, apparatus and software program for cervical cancer decision using image analysis of artificial intelligence based technology | |
| CN111931751B (en) | Deep learning training method, target object identification method, system and storage medium | |
| US20210090248A1 (en) | Cervical cancer diagnosis method and apparatus using artificial intelligence-based medical image analysis and software program therefor | |
| CN110736748A (en) | Immunohistochemical nuclear plasma staining section diagnosis method and system | |
| CN113781455B (en) | Cervical cell image anomaly detection method, device, equipment and medium | |
| CN112801049B (en) | Image classification method, device and equipment | |
| CN109886170B (en) | Intelligent detection, identification and statistics system for oncomelania | |
| CN104198325A (en) | Method for measuring ratio of cut stem to cut tobacco based on computer vision | |
| CN112580671A (en) | Automatic detection method and system for multiple development stages of rice ears based on deep learning | |
| WO2021117013A1 (en) | Determination of medical condition risk using thermographic images | |
| CN112750123A (en) | Rice disease and insect pest monitoring method and system | |
| CN111862118B (en) | Pressure sore staging training method, staging method and staging system | |
| CN115953690B (en) | Lodging crop identification method for unmanned harvester travel calibration | |
| KR20210033902A (en) | Method, apparatus and software program for cervical cancer diagnosis using image analysis of artificial intelligence based technology | |
| CN109658405B (en) | Image data quality control method and system in crop live-action observation | |
| Abdullah et al. | A portable rice disease diagnosis tool basedon bi-level color image thresholding | |
| Aleynikov et al. | Automated diseases detection of plant diseases in space greenhouses | |
| KR102220574B1 (en) | Method, apparatus and computer program for calculating quality score threshold for filtering image data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210504 |
|
| RJ01 | Rejection of invention patent application after publication |