CN107862682A - A kind of determination method and apparatus of the santal blade graywall extent of injury - Google Patents
A kind of determination method and apparatus of the santal blade graywall extent of injury Download PDFInfo
- Publication number
- CN107862682A CN107862682A CN201711068076.8A CN201711068076A CN107862682A CN 107862682 A CN107862682 A CN 107862682A CN 201711068076 A CN201711068076 A CN 201711068076A CN 107862682 A CN107862682 A CN 107862682A
- Authority
- CN
- China
- Prior art keywords
- image
- santal
- graywall
- injury
- extent
- 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
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment provides a kind of determination method and apparatus of the santal blade graywall extent of injury, and the prediction to the graywall extent of injury can be achieved.Methods described, including：Obtain whole tree Image；Split leaf image from whole tree Image；Color characteristic and textural characteristics are determined according to leaf image；The graywall extent of injury is determined according to santal blade graywall extent of injury prediction model, color characteristic and textural characteristics.Described device includes：Acquiring unit, cutting unit, obtaining unit and determining unit.The technique effect of the present invention can estimate the santal blade graywall extent of injury for operator by image that field servo instrument is passed back, the disease incidence for judging every almug of science, and implement different therapeutic schemes according to the difference of Disaster degree, while controlling and treating disease, accomplish the physics and chemistry injury minimum to almug, and then ensure the survival rate and growth quality of santal.
Description
Technical field
The present invention relates to belong to forest management and orest management field, more particularly to a kind of determination of the graywall extent of injury
Method and apparatus.
Background technology
In forest management and orest management field, there are many forest disease and pests leaf can be caused to change, e.g., in forest
During insect pest, leaf can be eaten up by insect, and during forest disease, leaf can wither.In a word, because forest often occurs
Pest and disease damage, and need to be predicted pest and disease damage degree, corresponding preventing and treating could be taken to arrange according to the pest and disease damage degree of prediction
Apply.
For example, santal is rare tree, its wooden uniform and smooth, there is the fragrance of uniqueness again, always given in terms of perfume is made
For treasure.Due to the high economic value of santal and medical value, the ground such as south China has obtained a large amount of plants in recent years.Santal is one
Kind of semiparasite aiphyllium, and when temperature or environment are unsuitable, santal be vulnerable to endanger root seedling blight,
Root rot and endanger the leaf graywall of blade, powdery mildew, Ramulus Taxilli white butterfly, chafer and the control of Zeuzera coffeae Nietner for endangering stem
Harm, its middle period graywall is more universal and influences photosynthesis, and then seriously endangers the growth of santal, so, monitoring in real time
Santal blade graywall and to take corresponding measure in time be the important means for being related to santal failure in operation.
Although prior art can obtain substantial amounts of view data, but without method according to these view data to leaf greyness
The extent of injury of disease is made and estimated, thus how the danger according to the view data of the santal blade under complex background to leaf graywall
It is current problem anxious to be resolved that evil degree, which is made and estimated,.
The content of the invention
The embodiment provides a kind of determination method and apparatus of the santal blade graywall extent of injury, can be achieved
Prediction to the graywall extent of injury.
The embodiment provides a kind of determination method of the santal blade graywall extent of injury, including：
Obtain whole tree Image；
Split leaf image from whole tree Image；
Color characteristic and textural characteristics are determined according to leaf image；
Determine that graywall endangers journey according to santal blade graywall extent of injury prediction model, color characteristic and textural characteristics
Degree.
Whole tree Image of the acquisition includes：The view data of every almug is obtained using field servo instrument, during shooting
Using tight shot and large aperture is used, from 06:00—18:00, an image is obtained per hour, and is real-time transmitted to service
Device.
The leaf image of splitting from whole tree Image specifically includes：
Gauss high-pass filtering is carried out to image；
Binary map is obtained using Otsu methods；
The circular configuration element that medium filtering and actionradius with reference to 7 × 7 templates are 2 carries out morphological erosion and swollen
Swollen computing obtains mask image；
Mask image is multiplied to obtain to the santal leaf image containing limb under complex background with artwork；
Image is transformed into Lab systems, L * component is extracted, binary map is obtained using Otsu methods；
It is smoothed using the medium filtering of 7 × 7 templates, the circular configuration element that then actionradius is 2 corrodes
Expand each 2 times；
Above-mentioned image is multiplied to obtain to the santal leaf image that limb is free of under complex background with original image.
It is described to determine that color characteristic and textural characteristics specifically include according to leaf image：
Color characteristic is determined from leaf image, the color characteristic includes G averages/(R average+G average+B averages), L
Component average, b component averages；
The textural characteristics include correlation mean value component.
During performing step and determining color characteristic and textural characteristics according to leaf image, step is also performed：By image
Gray-scale compression be 16 grades, step-length selection 1, direction be 0 °, 45 °, 90 ° and 135 °；Calculate four direction upper average and
Variance obtains 8 dimension texture feature vectors.
It is described to determine that greyness is critically ill according to santal blade graywall extent of injury prediction model, color characteristic and textural characteristics
The step of evil degree, specifically includes：
Santal blade graywall extent of injury prediction model is：
Y=a1x1+a2x2+a3lnx3+a4lnx4+a5,
Wherein, Y represents the graywall extent of injury, x1For G averages/(R average+G average+B averages), x2For L * component average,
x3For b component averages, x4For the correlation average in textural characteristics；In the model, a1=16.736, a2=-0.042, a3=
0.294, a4=0.124, a5=2.343.
Embodiments of the invention additionally provide a kind of determining device of the santal blade graywall extent of injury, including：
Acquiring unit, for whole tree Image；
Cutting unit, for splitting leaf image from whole tree Image；
Obtaining unit, for determining color characteristic and textural characteristics according to leaf image；
Determining unit, for true according to santal blade graywall extent of injury prediction model, color characteristic and textural characteristics
Determine the santal blade graywall extent of injury.
The acquiring unit is field servo instrument, and every field servo instrument includes camera, and camera can enter in the horizontal direction
360 ° of rotations of row, vertical direction can carry out 180 ° of rotations.
The solution have the advantages that operator can estimate santal blade ash by image that field servo instrument is passed back
The pinta extent of injury, the disease incidence for judging every almug of science, and different control is implemented according to the difference of Disaster degree
Treatment scheme, while controlling and treating disease, accomplish physics and chemistry injury minimum to almug, and then ensure santal
Survival rate and growth quality.The method realizes the estimation of santal greyness degree of disease from graphical analysis angle, and speed is fast, precision
Height, it is extremely applicable to the cultivation of santal rare tree.
Brief description of the drawings
When considered in conjunction with the accompanying drawings, by referring to following detailed description, can more completely more fully understand the present invention with
And easily learn many of which with the advantages of, but accompanying drawing described herein be used for a further understanding of the present invention is provided,
The part of the present invention is formed, schematic description and description of the invention is used to explain the present invention, do not formed to this hair
Bright limitation, wherein：
Fig. 1 is the flow chart of the determination method of the graywall extent of injury of the embodiment of the present invention；
Fig. 2 is the flow that leaf image is extracted from whole tree Image of the embodiment of the present invention.
Embodiment
Understand for the ease of persons skilled in the art and realize the present invention, describe the implementation of the present invention in conjunction with accompanying drawing
Example.
Obviously, those skilled in the art belong to the guarantor of the present invention based on many modifications and variations that spirit of the invention is done
Protect scope.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is individual ", " described " and "the" may also comprise plural form.Those skilled in the art of the present technique are appreciated that unless otherwise defined, here
All terms (including technical term and scientific terminology) used have with the those of ordinary skill's in art of the present invention
It is commonly understood by identical meaning.
Embodiment one
The it is proposed of Internet of Things provides conveniently with developing into all trades and professions, and forestry technology of Internet of things also monitors in real time for forestry
Provide new method.Experiment is in northern six counties and cities (Yunlong, Longzhou, maple, dragon's fountain, culture and education, Wenchang) plant wingceltis in Hainan Province
Lay Duo Tai fields servo instrument in fragrant woods, the camera in every equipment can carry out 360 ° of rotations, Vertical Square in the horizontal direction
Rotated to 180 ° can be carried out, meanwhile, every field server is by air temperature sensor, air humidity sensor, soil temperature
The composition such as sensor and wireless local pessimistic concurrency control is spent, from 06:00—18:00, an image, and real-time Transmission are obtained per hour
To server.Tight shot is used during shooting and uses large aperture, image size is 1024 × 768 pixels.
In image processing field, the emphasis and difficult point of image segmentation always image understanding, and computer vision skill
The basis of art, by the development of decades, image Segmentation Technology has numerous algorithms, but totally can be classified as four classes：Threshold segmentation
Algorithm, space clustering partitioning algorithm, the partitioning algorithm based on region and the partitioning algorithm based on movable contour model.Although image
Partitioning algorithm has a lot, but santal growing environment is complicated, and segmentation of the host plant to background causes large effect, institute
It is only on the one hand, on the other hand also the hardware facility for obtaining image to be adjusted with optimized algorithm.
As shown in figure 1, embodiments of the invention illustrate the determination side of the santal blade graywall extent of injury by taking santal as an example
Method and device., can be with Accurate Prediction santal by the determination method and apparatus of the santal blade graywall extent of injury of the present invention
The blade graywall extent of injury, so as to which science is prevented and treated for each almug, and then ensure the survival rate of santal with
Growth quality.
The determination method of the santal blade graywall extent of injury includes：It (is single with whole tree to obtain santal tree Image
Position)；Split santal leaf image from santal tree Image；Determine that the graywall extent of injury is pre- according to the santal leaf image of segmentation
Parameter is surveyed, the parameter includes color characteristic and textural characteristics；Determined according to santal blade graywall extent of injury prediction model
The graywall extent of injury.With reference to the determination method of the santal blade graywall extent of injury of the figure description present invention：
Step 101：Santal tree Image is obtained, it is specifically included：
Lay Duo Tai fields servo instrument in the woods of plant santal, the camera in every equipment can be carried out in the horizontal direction
360 ° of rotations, vertical direction can carry out 180 ° of rotations, meanwhile, every field server is wet by air temperature sensor, air
The composition such as sensor, soil temperature sensor and wireless local pessimistic concurrency control is spent, from 06:00—18:00, obtain per hour once
Image, and it is real-time transmitted to server.Tight shot is used during shooting and uses large aperture, image size is 1024 × 768 pictures
Element.
Step 102, split santal leaf image from santal tree Image, it specifically comprises the following steps：
Gauss high-pass filtering is carried out to image；
Binary map is obtained using Otsu methods；
The circular configuration element that medium filtering and actionradius with reference to 7 × 7 templates are 2 carries out morphological erosion and swollen
Swollen computing obtains mask image；
Mask image is multiplied to obtain to the santal leaf image containing limb with artwork；
Image is transformed into Lab systems, L * component is extracted, binary map is obtained using Otsu methods；
It is smoothed using the medium filtering of 7 × 7 templates, the circular configuration element that then actionradius is 2 corrodes
Expand each 2 times；
Above-mentioned image is multiplied with original image to obtain the santal leaf image without limb；
Step 103, graywall forecast of damage parameter determined according to the santal leaf image of segmentation, the parameter includes
Color characteristic and textural characteristics, it is specifically included：
Calculate color feature value；
Calculate texture eigenvalue；
Color characteristic and textural characteristics and the correlation of the extent of damage are analyzed, carry out Variable Selection；
Scab removal is carried out to image using Photoshop softwares, calculates the pixel count p1 after scab removes and complete leaf
Ratio between the pixel count p2 of piece, as loss percentage.
The calculating color feature value specifically includes：
Color characteristic, including three kinds of color systems, RGB, HSI and Lab are calculated to the santal leaf image of acquisition.Calculate each
The color average of passage, wherein, because RGB color system is bigger by illumination effect, so calculating R averages/(R averages+G is equal
Value+B averages), G averages/(R average+G average+B averages), B averages/(R average+G average+B averages) replace each components of RGB it is equal
Value, finally gives 9 dimension color characteristics.
Wherein
I=(R+G+B)/3
L=116 × (Y/Y0)1/3-16
A=500 × [(X/X0)1/3-(Y/Y0)1/3]
B=200 × [(Y/Y0)1/3-(Z/Z0)1/3]
Wherein：X=0.5164R+0.2789G+0.1792B
Y=0.2963R+0.6192G+0.0845B
Z=0.0339R+0.1426G+1.0166B
In formula：R, G, B value are 0~100, X0、Y0、Z0For standard sources D65 three primary colours values, its value is X0
=95.045, Y0=100, Z0=108.255.
The calculating texture eigenvalue specifically includes：
Gray level co-occurrence matrixes can extract 14 kinds of textural characteristics, and respectively texture second order is away from, texture entropy, texture comparison
Degree, texture uniformity, texture are related, unfavourable balance point away from, maximum probability, texture variance, symbiosis and average, symbiosis and variance, symbiosis
With entropy, symbiosis difference average, symbiosis difference variance, symbiosis difference entropy.These textural characteristics are tested, finally select preferable energy
Four kinds of value, entropy, contrast, correlation textural characteristics are as the parameter further studied.
When calculating characteristic value using gray level co-occurrence matrixes, coloured image is converted into gray scale first using MATLAB instruments
Image, then carries out gray level rarefaction and parametric texture calculates.Because the amount of calculation of gradation of image co-occurrence matrix is by image
Gray level and image size determine, and test choose sampled pixel size immobilize, so not influenceing line
Need gray level being compressed on the premise of reason feature, generally by 256 grades of 8 grades or 16 grades of boil down tos, compress in this application
To 16 grades.After being pre-processed to image, the calculating of gray level co-occurrence matrixes characteristic value is carried out.Extraction does not have 4 kinds of synteny
Textural characteristics, respectively energy, entropy, contrast and correlation；To reduce amount of calculation in extraction process, by the gray level of image
16 grades of boil down to, step-length selection 1, direction are 0 °, 45 °, 90 ° and 135 °；The upper average and variance for calculating four direction obtain 8
Tie up texture feature vector；
The analysis color characteristic and textural characteristics and the correlation of the extent of damage, carry out Variable Selection and specifically include：
By significance test, select in the significantly correlated variable in 0.01 horizontal both sides, and carry out initial fitting (including line
Property, the type of index numbers, logarithm type, power function type), filter out variable of the coefficient correlation more than 0.8：G averages/(R averages+G
Average+B averages), L * component average, b components average and correlation average.
Step 104, the graywall extent of injury determined according to santal blade graywall extent of injury prediction model：
Using the color characteristic extracted in above-mentioned steps and textural characteristics as independent variable, the graywall extent of injury as because
Variable establishes graywall extent of injury model, and sample number is assumed to be 50；
The form of model is:
Y=a1x1+a2x2+a3lnx3+a4lnx4+a5
Wherein Y represents the graywall extent of injury, x1Represent G averages/(R average+G average+B averages), x2It is equal to represent L * component
Value, x3Represent b component averages, x4Represent correlation average.
In the model, a1=16.736, a2=-0.042, a3=0.294, a4=0.124, a5=2.343.Use the model
Obtained coefficient correlation can reach 0.969, have higher fitting degree.
30 samples of random selection are tested to model, and the coefficient correlation of gained test sample is 0.92, and root mean square misses
Difference is 0.04632, illustrates that the availability of model is higher；
As shown in Fig. 2 the method that santal leaf image is obtained under complex background is present embodiments provided, including following step
Suddenly：
Step 201, Gauss high-pass filtering is carried out to image；
Step 202, using Otsu methods obtain binary map；
The circular configuration element that step 203, the medium filtering with reference to 7 × 7 templates and actionradius are 2 carries out morphology
Corrosion and dilation operation obtain mask image；
Step 204, mask image is multiplied to obtain to the santal leaf image containing limb under complex background with artwork；
Step 205, image is transformed into Lab systems, extracts L * component, binary map is obtained using Otsu methods；
Step 206, it is smoothed using the medium filtering of 7 × 7 templates, then actionradius is 2 circular configuration
Each 2 times of element corrosion expansion；
Step 207, above-mentioned image is multiplied to obtain to the santal leaf image that limb is free of under complex background with original image；
Above-mentioned each step is introduced separately below.
In step 201-204, the image segmentation of the santal blade with limb is completed.Gauss is carried out to image first
High-pass filtering.Because the image acquiring device of field servo instrument is arranged to large aperture, obtained blurred background, so using Gauss
High-pass filtering can fall the background removal of low frequency.Otsu methods and medium filtering, morphological erosion and dilation operation are by burr
Remove and obtain mask image, mask image is multiplied to obtain to the santal blade containing limb with artwork.
In step 205-207, the removal of limb is completed.Lab systems are smaller by illumination effect, while limb and blade exist
L * channel (brightness) shows difference, so image is transformed into Lab systems, extracts L * component, binary map is obtained using Otsu methods,
Equally, burr is removed and obtains mask image by medium filtering, morphological erosion and dilation operation, most at last mask image with it is former
Figure, which is multiplied, obtains the santal blade without limb.
Embodiment two
A kind of determining device of the santal blade graywall extent of injury is present embodiments provided, including：
Acquiring unit, for whole tree Image；
Cutting unit, for splitting leaf image from whole tree Image；
Obtaining unit, for determining color characteristic and textural characteristics according to leaf image；
Determining unit, (graywall extent of injury model is built according to the color characteristic of santal blade and textural characteristics, so as to
Determine the graywall extent of injury.).
The acquiring unit is field servo instrument, and every field servo instrument includes camera, and camera can enter in the horizontal direction
360 ° of rotations of row, vertical direction can carry out 180 ° of rotations.
The operation principle of the unit of the present embodiment can be found in the description of embodiment one.
Although depicting the present invention by embodiment, it will be appreciated by the skilled addressee that not departing from the present invention's
In the case of spirit and essence, so that it may the present invention is had many deformations and change, the scope of the present invention is by appended claim
To limit.
Claims (8)
- A kind of 1. determination method of the santal blade graywall extent of injury, it is characterised in that including：Obtain whole tree Image；Split leaf image from whole tree Image；Color characteristic and textural characteristics are determined according to leaf image；The graywall extent of injury is determined according to santal blade graywall extent of injury prediction model, color characteristic and textural characteristics.
- 2. according to the method for claim 1, it is characterised in that whole tree Image of the acquisition includes：Use field servo Instrument obtains the view data of every almug, using tight shot and large aperture is used during shooting, from 06:00—18:00, per small When obtain an image, and be real-time transmitted to server.
- 3. according to the method for claim 1, it is characterised in that the leaf image of splitting from whole tree Image specifically wraps Include：Gauss high-pass filtering is carried out to image；Binary map is obtained using Otsu methods；The circular configuration element that medium filtering and actionradius with reference to 7 × 7 templates are 2 carries out morphological erosion and expansion is transported Calculation obtains mask image；Mask image is multiplied to obtain to the santal leaf image containing limb under complex background with artwork；Image is transformed into Lab systems, L * component is extracted, binary map is obtained using Otsu methods；It is smoothed using the medium filtering of 7 × 7 templates, the circular configuration element corrosion expansion that then actionradius is 2 Each 2 times；Above-mentioned image is multiplied to obtain to the santal leaf image that limb is free of under complex background with original image.
- 4. according to the method for claim 1, it is characterised in that described to determine that color characteristic and texture are special according to leaf image Sign specifically includes：Color characteristic is determined from leaf image, the color characteristic includes G averages/(R average+G average+B averages), L * component Average, b component averages；The computational methods of wherein average are：Travel through the color value n of each pixelij(i is line number, and j is row Number),(m is the total line number of image, and n is the total columns of image)；The textural characteristics include correlation mean value component.
- 5. according to the method for claim 4, it is characterised in that perform step according to leaf image determine color characteristic and During textural characteristics, step is also performed：It it is 16 grades by the gray-scale compression of image, step-length selection 1, direction is 0 °, 45 °, 90 ° With 135 °；The upper average and variance for calculating four direction obtain 8 dimension texture feature vectors.
- 6. according to the method for claim 1, it is characterised in that described step specifically includes：Santal blade graywall extent of injury prediction model is：Y=a1x1+a2x2+a3lnx3+a4lnx4+a5,Wherein, Y represents the graywall extent of injury, x1For G averages/(R average+G average+B averages), x2For L * component average, x3For b Component average, x4For the correlation average in textural characteristics；In the model, a1=16.736, a2=-0.042, a3=0.294, a4 =0.124, a5=2.343.
- A kind of 7. determining device of the santal blade graywall extent of injury, it is characterised in that including：Acquiring unit, for whole tree Image；Cutting unit, for splitting leaf image from whole tree Image；Obtaining unit, for determining color characteristic and textural characteristics according to leaf image；Determining unit, for determining wingceltis according to santal blade graywall extent of injury prediction model, color characteristic and textural characteristics The spiceleaf piece graywall extent of injury.
- 8. the determining device of the santal blade graywall extent of injury according to claim 7, it is characterised in that the acquisition Unit is field servo instrument, and every field servo instrument includes camera, and camera can carry out 360 ° of rotations, Vertical Square in the horizontal direction Rotated to 180 ° can be carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711068076.8A CN107862682A (en) | 2017-11-03 | 2017-11-03 | A kind of determination method and apparatus of the santal blade graywall extent of injury |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711068076.8A CN107862682A (en) | 2017-11-03 | 2017-11-03 | A kind of determination method and apparatus of the santal blade graywall extent of injury |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107862682A true CN107862682A (en) | 2018-03-30 |
Family
ID=61700650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711068076.8A Pending CN107862682A (en) | 2017-11-03 | 2017-11-03 | A kind of determination method and apparatus of the santal blade graywall extent of injury |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107862682A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934833A (en) * | 2019-04-18 | 2019-06-25 | 东华大学 | Plant growth detection system based on computer vision |
| CN113409253A (en) * | 2021-06-02 | 2021-09-17 | 南京公诚节能新材料研究院有限公司 | Agricultural condition monitoring key technical method |
| CN114190213A (en) * | 2021-09-01 | 2022-03-18 | 南开大学 | System and method for comprehensively preventing and treating crop diseases and insect pests by using sensor |
| CN117456214A (en) * | 2023-11-06 | 2024-01-26 | 江苏省农业科学院 | Tomato leaf spot identification method, system and electronic equipment |
| CN117456214B (en) * | 2023-11-06 | 2024-05-31 | 江苏省农业科学院 | Tomato leaf spot identification method, system and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559511A (en) * | 2013-11-20 | 2014-02-05 | 天津农学院 | Automatic identification method of foliar disease image of greenhouse vegetable |
| CN104050668A (en) * | 2014-06-17 | 2014-09-17 | 安徽农业大学 | Object recognition method applied to green tea tender shoots and based on binocular vision technology |
| CN106910214A (en) * | 2017-02-09 | 2017-06-30 | 中国林业科学研究院资源信息研究所 | A kind of santal trunk insect pest degree of injury level images method of discrimination |
-
2017
- 2017-11-03 CN CN201711068076.8A patent/CN107862682A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559511A (en) * | 2013-11-20 | 2014-02-05 | 天津农学院 | Automatic identification method of foliar disease image of greenhouse vegetable |
| CN104050668A (en) * | 2014-06-17 | 2014-09-17 | 安徽农业大学 | Object recognition method applied to green tea tender shoots and based on binocular vision technology |
| CN106910214A (en) * | 2017-02-09 | 2017-06-30 | 中国林业科学研究院资源信息研究所 | A kind of santal trunk insect pest degree of injury level images method of discrimination |
Non-Patent Citations (3)
| Title |
|---|
| 张桂喜等: "《预测与决策概论 第3版》", 30 August 2013 * |
| 翟治芳等: "基于朴素贝叶斯分类器的棉花盲椿象危害等级识别", 《农业工程学报》 * |
| 胡敏等: "基于颜色和纹理特征的黄瓜病害识别算法", 《电子测量与仪器学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934833A (en) * | 2019-04-18 | 2019-06-25 | 东华大学 | Plant growth detection system based on computer vision |
| CN113409253A (en) * | 2021-06-02 | 2021-09-17 | 南京公诚节能新材料研究院有限公司 | Agricultural condition monitoring key technical method |
| CN114190213A (en) * | 2021-09-01 | 2022-03-18 | 南开大学 | System and method for comprehensively preventing and treating crop diseases and insect pests by using sensor |
| CN117456214A (en) * | 2023-11-06 | 2024-01-26 | 江苏省农业科学院 | Tomato leaf spot identification method, system and electronic equipment |
| CN117456214B (en) * | 2023-11-06 | 2024-05-31 | 江苏省农业科学院 | Tomato leaf spot identification method, system and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107194937B (en) | Traditional Chinese medicine tongue picture image segmentation method in open environment | |
| CN107862682A (en) | A kind of determination method and apparatus of the santal blade graywall extent of injury | |
| CN108764176A (en) | A kind of action sequence recognition methods, system and equipment and storage medium | |
| CN110232445B (en) | Cultural relic authenticity identification method based on knowledge distillation | |
| CN109242092B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN109284761A (en) | A kind of image characteristic extracting method, device, equipment and readable storage medium storing program for executing | |
| CN109389569A (en) | Based on the real-time defogging method of monitor video for improving DehazeNet | |
| CN112215217B (en) | Digital image recognition method and device for simulating doctor to read film | |
| CN106910214A (en) | A kind of santal trunk insect pest degree of injury level images method of discrimination | |
| CN104299241A (en) | Remote sensing image significance target detection method and system based on Hadoop | |
| CN115457451B (en) | Constant temperature and humidity test box monitoring method and device based on Internet of things | |
| Liu et al. | Development of a mobile application for identification of grapevine (Vitis vinifera L.) cultivars via deep learning | |
| Suo et al. | Casm-amfmnet: A network based on coordinate attention shuffle mechanism and asymmetric multi-scale fusion module for classification of grape leaf diseases | |
| CN116385819A (en) | Water quality evaluation method, device and equipment based on neural network model | |
| CN107578448A (en) | Blending surfaces number recognition methods is included without demarcation curved surface based on CNN | |
| Kalkan et al. | Cloudy/clear weather classification using deep learning techniques with cloud images | |
| CN115849202B (en) | Intelligent crane operation target identification method based on digital twin technology | |
| CN106845554A (en) | A kind of image of santal plant strain growth soil iron content determines method and system | |
| CN103761530B (en) | Hyperspectral image unmixing method based on relevance vector machine | |
| CN105139361B (en) | A kind of image super-resolution rebuilding method of the FPM algorithms based on nonlinear optimization | |
| CN106845512A (en) | Beasts shape recognition method and system based on fractal parameter | |
| Li et al. | Development of a single-leaf disease severity automatic grading system based on image processing | |
| Mohammad et al. | Classification of fresh N36 pineapple crop using image processing technique | |
| CN109740109A (en) | A kind of PolSAR image broad object decomposition method based on unitary transformation | |
| CN112783949B (en) | Human body data prediction method, device, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180330 |