CN108901540A - Fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm - Google Patents
Fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm Download PDFInfo
- Publication number
- CN108901540A CN108901540A CN201810689327.2A CN201810689327A CN108901540A CN 108901540 A CN108901540 A CN 108901540A CN 201810689327 A CN201810689327 A CN 201810689327A CN 108901540 A CN108901540 A CN 108901540A
- Authority
- CN
- China
- Prior art keywords
- image
- fruit
- formula
- circle
- fitness
- 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
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G17/00—Cultivation of hops, vines, fruit trees, or like trees
- A01G17/005—Cultivation methods
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G7/00—Botany in general
- A01G7/04—Electric or magnetic or acoustic treatment of plants for promoting growth
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G7/00—Botany in general
- A01G7/06—Treatment of growing trees or plants, e.g. for preventing decay of wood, for tingeing flowers or wood, for prolonging the life of plants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P60/00—Technologies relating to agriculture, livestock or agroalimentary industries
- Y02P60/14—Measures for saving energy, e.g. in green houses
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Environmental Sciences (AREA)
- Multimedia (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Botany (AREA)
- Forests & Forestry (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Wood Science & Technology (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to the methods of a kind of light filling based on artificial bee colony fuzzy clustering algorithm and fruit thinning, belong to agricultural technology field.Including S1：Image is acquired, by the module transfers such as wireless device or Bluetooth transmission to image pick-up card either image receiver module；S2：Illumination patterns figure is obtained using maximum stable extremal region and layering edge analysis algorithm；S3：Fruit is split using artificial bee colony fuzzy clustering algorithm is improved, and judges its size；S4：Light filling and fruit thinning are carried out to fruit tree.This method is by image processing application in agricultural production, agricultural producer can be helped to complete the monitoring of large-scale plantation in farm, judge the growth of Tree Fruit, be illuminated by the light situation situation, agricultural producer is assisted to be managed and trim fruit tree, fruit tree is made to generate higher economic value.
Description
Technical field
The invention belongs to agricultural technology field, it is related to a kind of fruit tree light filling based on artificial bee colony fuzzy clustering algorithm and dredges
Fruit method.
Background technique
In agriculture field, efficiently obtaining agriculture situation for the peasant under large-scale cropping pattern, when high is
Important link in agricultural production management, by artificial acquisition and detection information be unable to satisfy modern agriculture it is high when efficiently want
It asks.Therefore by image processing application in agricultural production, agricultural producer can be helped to complete the prison of large-scale plantation in farm
It surveys, judges the growth of Tree Fruit, is illuminated by the light situation situation, assist agricultural producer to be managed and trim fruit tree, make fruit
Tree generates higher economic value.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of fruit tree light filling based on artificial bee colony fuzzy clustering algorithm and
Fruit thinning method carries out maximum stable extremal region and layering edge analysis algorithm to fruit tree image using the method for image procossing
It obtains illumination patterns figure and fruit is split using artificial bee colony fuzzy clustering algorithm is improved, and judge its size；To
Light filling and fruit thinning are carried out to fruit tree.
In order to achieve the above objectives, the present invention provides the following technical solutions：
A kind of fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm, this approach includes the following steps：
S1：Image is acquired, is adopted image and transmission of video to image by wireless device or Bluetooth communication modules
In truck either image receiver module；
S2：Illumination patterns figure is obtained using maximum stable extremal region and layering edge analysis algorithm；
S3：Fruit is split using artificial bee colony fuzzy clustering algorithm is improved, and judges its size；
S4：Light filling and fruit thinning are carried out to fruit tree.
Further, in step s 2, the maximum stable extremal region and layering edge analysis algorithm include the following steps：
S21：The acquisition of image RGB component, obtains green component：Color image is divided into the image of tri- components of RGB, point
Not Biao Shi Red Green Blue component image, each component is 256 grades, obtains the image of three kinds of components of red, green, blue
Afterwards, retain green component；
S22：Gradation conversion：True color image is converted into gray level image using rgb2gray function；
S23：Wiener filtering：Wiener filtering is carried out using 3 × 3 filter window and filters out the Gaussian noise in image；
S24：Maximum stable extremal region algorithm detects area-of-interest：For piece image, the threshold value pair of alternation is utilized
Image carries out binarization segmentation, and threshold value t takes 0~255 totally 256 numerical value, thus obtains 256 width bianry images；In threshold value t by 0
Constantly increase or by 255 it is ever-reduced during, have some connected regions in larger range threshold value shape keep stablize, this
A little regions are maximum stable extremal region；
S25：Region shape analysis carries out preliminary screening：Oval mesh is carried out for each maximum stable extremal region profile
Mark fitting carries out shape analysis to area results are extracted, and preliminary screening provides the maximum stable extremal area of suitable shape feature
Domain；
P maximum stable extremal region is extracted using maximum stable extremal region algorithm, wherein i-th of extremal region is quasi-
Close the ellipse target E come outiParameter is
Ei={ xi,yi,ai,bi,θi},i∈[1,P]
(x in formulai,yi) it is center coordinate, ai、biRespectively long axis and minor axis length, θiFor transverse inclination angle；According to this
Oval eccentricity eiRemoval is invalid oval：
T in formula4For eccentricity threshold value；
S26：It is layered edge analysis：The distinctive illumination patterns mode of fruit surface is detected with layering method for profile analysis,
It obtains by center outer layers LM,LM-1,LM-23 grades of contour lines；
S27：Hough transformation circle fitting：For the outer profile of three-level contour, it is utilized respectively round Hough transformation and is justified
Detection；Every grade of contour line of each fruit target fits a circle, thus fits multiple approximate concentric circles, as fruit mesh
Target is layered contour feature；Finally, nested analysis is carried out to multistage contour line according to following formula and obtains final target circle：
Wherein RiWith RjRespectively indicate round CiWith circle CjRadius, dijIndicate the distance in two centers of circle；When two round centers of circle
When distance is close enough, then it is assumed that circle CiBelong to round CjA part, therefore only retain circle Cj；The last one finally remained
Circle target uniquely corresponds to a fruit；
S28：It obtains a result.
Further, in step s3, the improvement artificial bee colony fuzzy clustering algorithm includes：
S31：Original image is read in, the H-I color model statistic histogram of image is generated；
S32：Initialization of population inputs threshold value L, maximum cycle M, fuzzy membership exponent m；Initialize degree of membership square
Battle array U；If gathering honey bee and follow bee quantity be SN, S is randomly generatedNThe position of/2 gathering honey bees is as cluster centre；
S33：The fitness of all food sources is calculated by formula (1), and sets current iteration number as C=1, is started the cycle over；
Wherein λ is fitness dynamic factor；
S34：Gathering honey bee is cooked neighborhood search according to formula (2) and obtains New food source position Vi, its new adaptation is calculated with formula (1)
Degree；
Vi=Xi+ψi(Xi-Xk) (2)
In formula, k ∈ { 1,2 ..., SN, and k ≠ i is generated at random, ψiRandom number between [- 1,1].
S35：Using greedy algorithm to new and old position preferentially, if ViFitness be greater than the optimal value in memory, then Xi=
Vi, otherwise, XiIt is constant；
S36：It is calculated according to formula (3) and follows bee i probability P relevant to food sourcei, follow bee according to PiSelect food source；
Wherein, SNFor food source number；
S37：It follows bee to carry out neighborhood search and generates new explanation Vi, its fitness is calculated, if ViFitness be greater than memory in
Adaptive optimal control degree, then Xi=Vi, otherwise, XiIt is constant；
S38：After L circulation, if fitness does not change, the food source is abandoned, search bee is according to formula at this time
(4) it generates a new explanation and replaces current Xi；
X in formulamin--- the minimum value of food source value range
Xmax--- the maximum value of food source value range
R --- the random number between [0,1]
Xi(n) --- n-th of feasible solution
S39：Remember the maximum food source position of current fitness and stop iteration if the number of iterations reaches M, finds most
Excellent cluster centre；Otherwise step S34, C=C+1 are gone to；
S310：Each sample is solved for the degree of membership of Optimal cluster centers, according to maximum membership grade principle to image into
Row segmentation, then target image is obtained by Morphological scale-space.
The beneficial effects of the present invention are：The method that the method for the invention uses image procossing carries out fruit tree image
Maximum stable extremal region and layering edge analysis algorithm obtain illumination patterns figure and are calculated using artificial bee colony fuzzy clustering is improved
Method is split fruit, and judges its size；To carry out light filling and fruit thinning to fruit tree.
Image processing application in agricultural production, can be helped agricultural producer to complete in farm extensive kind by the present invention
The monitoring of plant judges the growth of Tree Fruit, is illuminated by the light situation situation, and agricultural producer is assisted to be managed and repair fruit tree
It cuts, fruit tree is made to generate higher economic value.
Detailed description of the invention
In order to keep the purpose of the present invention, technical scheme and beneficial effects clearer, the present invention provides following attached drawing and carries out
Explanation：
Fig. 1 is the overall flow figure of the method for the invention；
Fig. 2 is maximum stable extremal region and layering edge analysis algorithm flow chart in the embodiment of the present invention；
Fig. 3 is that artificial bee colony fuzzy clustering algorithm flow chart is improved in the embodiment of the present invention.
Specific embodiment
Below in conjunction with attached drawing, a preferred embodiment of the present invention will be described in detail.
Fig. 1 be the method for the invention overall flow figure, Fig. 2 be the embodiment of the present invention in maximum stable extremal region and
It is layered edge analysis algorithm flow chart, Fig. 3 is that artificial bee colony fuzzy clustering algorithm flow chart is improved in the embodiment of the present invention.
As shown in Figure 1, the embodiment of the present invention provides a kind of light filling based on artificial bee colony fuzzy clustering algorithm and fruit thinning
Method includes the following steps：S1：Image is acquired, is adopted by module transfers such as wireless device or Bluetooth transmissions to image
In truck either image receiver module；S2：Illumination point is obtained using maximum stable extremal region and layering edge analysis algorithm
Butut；S3：Fruit is split using artificial bee colony fuzzy clustering algorithm is improved, and judges its size；S4：Fruit tree is carried out
Light filling and fruit thinning.
Fig. 2 is maximum stable extremal region and layering edge analysis algorithm flow chart in the embodiment of the present invention, such as Fig. 2 institute
Show, step S2 specifically comprises the following steps in the present embodiment：
S21：The acquisition of image RGB component, obtains green component：Color image is divided into the image of tri- components of RGB, point
Not Biao Shi Red Green Blue component image, each component is 256 grades.Obtain R, after the image of tri- kinds of components of G, B,
Retain green component.
S22：Gradation conversion：True color image is converted into gray level image using rgb2gray function.
S23：Wiener filtering：Wiener filtering is carried out using 3 × 3 filter window and filters out the Gaussian noise in image.
S24：Maximum stable extremal region algorithm detects area-of-interest：For piece image, the threshold value pair of alternation is utilized
Image carries out binarization segmentation, and threshold value t takes 0~255 totally 256 numerical value, thus obtains 256 width bianry images.In threshold value t by 0
Constantly increase or by 255 it is ever-reduced during, have some connected regions in larger range threshold value shape keep stablize, this
A little regions are maximum stable extremal region.
S25：Region shape analysis carries out preliminary screening：Oval mesh is carried out for each maximum stable extremal region profile
Mark fitting carries out shape analysis to area results are extracted, and preliminary screening provides the maximum stable extremal area of suitable shape feature
Domain.
P maximum stable extremal region is extracted using maximum stable extremal region algorithm, wherein i-th of extremal region
Fit the ellipse target E comeiParameter is
Ei={ xi,yi,ai,bi,θi},i∈[1,P]
(x in formulai,yi) it is center coordinate, ai、biRespectively long axis and minor axis length, θiFor transverse inclination angle.According to this
Oval eccentricity eiRemoval is invalid oval
T in formula4For eccentricity threshold value.
S26：It is layered edge analysis：The distinctive illumination patterns call by pattern of fruit surface is detected with layering method for profile analysis
To by center outer layers LM,LM-1,LM-23 grades of contour lines.
S27：Hough transformation circle fitting：For the outer profile of three-level contour, it is utilized respectively round Hough transformation and is justified
Detection.Every grade of contour line of each fruit target fits a circle, thus fits multiple approximate concentric circles,
The as layering contour feature of fruit target.Finally, nested analysis is carried out to multistage contour line according to following formula to obtain
Final target circle.
Wherein RiWith RjRespectively indicate round CiWith circle CjRadius, dijIndicate the distance in two centers of circle.When two round centers of circle
When distance is close enough, then it is assumed that circle CiBelong to round CjA part, therefore only retain circle Cj.The last one finally remained
Circle target uniquely corresponds to a fruit.
S28：It obtains a result.
Fig. 3 is that artificial bee colony fuzzy clustering algorithm flow chart is improved in the embodiment of the present invention, as shown in figure 3, in this implementation
Step S3 specifically comprises the following steps in example：
S31：Original image is read in, the H-I color model statistic histogram of image is generated.
S32：Initialization of population inputs threshold value L, maximum cycle M, fuzzy membership exponent m.Initialize degree of membership square
Battle array U.If gathering honey bee and follow bee quantity be SN, S is randomly generatedNThe position of/2 gathering honey bees is as cluster centre.
S33：The fitness of all food sources is calculated by formula (1), and sets current iteration number as C=1, is started the cycle over；
λ is fitness dynamic factor.
S34：Gathering honey bee is cooked neighborhood search according to formula (2) and obtains New food source position Vi, its new adaptation is calculated with formula (1)
Degree；
Vi=Xi+ψi(Xi-Xk) (2)
In formula, k ∈ { 1,2 ..., SN, and k ≠ i is generated at random, ψiRandom number between [- 1,1].
S35：Using greedy algorithm to new and old position preferentially, if ViFitness be greater than the optimal value in memory, then Xi=
Vi, otherwise, XiIt is constant；
S36：It is calculated according to formula (3) and follows bee i probability P relevant to food sourcei, follow bee according to PiSelect food source；
SNFor food source number.
S37：It follows bee to carry out neighborhood search and generates new explanation Vi, its fitness is calculated, if ViFitness be greater than memory in
Adaptive optimal control degree, then Xi=Vi, otherwise, XiIt is constant；
S38：After L circulation, if fitness does not change, the food source is abandoned, search bee is according to formula at this time
(4) it generates a new explanation and replaces current Xi；
X in formulamin--- the minimum value of food source value range
Xmax--- the maximum value of food source value range
R --- the random number between [0,1]
Xi(n) --- n-th of feasible solution
S39：Remember the maximum food source position of current fitness and stop iteration if the number of iterations reaches M, finds most
Excellent cluster centre；Otherwise step S34, C=C+1 are gone to；
S310：Each sample is solved for the degree of membership of Optimal cluster centers, according to maximum membership grade principle to image into
Row segmentation, then target image is obtained by Morphological scale-space.
Finally, it is stated that preferred embodiment above is only used to illustrate the technical scheme of the present invention and not to limit it, although logical
It crosses above preferred embodiment the present invention is described in detail, however, those skilled in the art should understand that, can be
Various changes are made to it in form and in details, without departing from claims of the present invention limited range.
Claims (3)
1. a kind of fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm, it is characterised in that：Including following step
Suddenly：
S1：Image is acquired, by wireless device or Bluetooth communication modules by image and transmission of video to image pick-up card
Either in image receiver module；
S2：Illumination patterns figure is obtained using maximum stable extremal region and layering edge analysis algorithm；
S3：Fruit is split using artificial bee colony fuzzy clustering algorithm is improved, and judges its size；
S4：Light filling and fruit thinning are carried out to fruit tree.
2. the fruit tree light filling and fruit thinning method according to claim 1 based on artificial bee colony fuzzy clustering algorithm, feature
It is：In step s 2, the maximum stable extremal region and layering edge analysis algorithm include the following steps：
S21：The acquisition of image RGB component, obtains green component：Color image is divided into the image of tri- components of RGB, respectively table
Showing the component image of Red Green Blue, each component is 256 grades, after obtaining the image of three kinds of components of red, green, blue,
Retain green component；
S22：Gradation conversion：True color image is converted into gray level image using rgb2gray function；
S23：Wiener filtering：Wiener filtering is carried out using 3 × 3 filter window and filters out the Gaussian noise in image；
S24：Maximum stable extremal region algorithm detects area-of-interest：For piece image, using the threshold value of alternation to image
Binarization segmentation is carried out, threshold value t takes 0~255 totally 256 numerical value, thus obtains 256 width bianry images；It is continuous by 0 in threshold value t
Increase or by 255 it is ever-reduced during, have some connected regions in larger range threshold value shape keep stablize, these areas
Domain is maximum stable extremal region；
S25：Region shape analysis carries out preliminary screening：It is quasi- that ellipse target is carried out for each maximum stable extremal region profile
It closes, carries out shape analysis to area results are extracted, preliminary screening provides the maximum stable extremal region of suitable shape feature；
P maximum stable extremal region is extracted using maximum stable extremal region algorithm, wherein i-th of extremal region fits
The ellipse target E comeiParameter is
Ei={ xi,yi,ai,bi,θi},i∈[1,P]
(x in formulai,yi) it is center coordinate, ai、biRespectively long axis and minor axis length, θiFor transverse inclination angle；According to the ellipse
Eccentricity eiRemoval is invalid oval：
T in formula4For eccentricity threshold value；
S26：It is layered edge analysis：The distinctive illumination patterns mode of fruit surface is detected with layering method for profile analysis, is obtained
By center outer layers LM,LM-1,LM-23 grades of contour lines；
S27：Hough transformation circle fitting：For the outer profile of three-level contour, it is utilized respectively round Hough transformation and carries out loop truss；
Every grade of contour line of each fruit target fits a circle, thus fits multiple approximate concentric circles, as fruit mesh
Target is layered contour feature；Finally, nested analysis is carried out to multistage contour line according to following formula and obtains final target circle：
Wherein RiWith RjRespectively indicate round CiWith circle CjRadius, dijIndicate the distance in two centers of circle；When two round circle center distances
When close enough, then it is assumed that circle CiBelong to round CjA part, therefore only retain circle Cj；The last one the circle mesh finally remained
Mark uniquely corresponds to a fruit；
S28：It obtains a result.
3. the fruit tree light filling and fruit thinning method according to claim 2 based on artificial bee colony fuzzy clustering algorithm, feature
It is：In step s3, the improvement artificial bee colony fuzzy clustering algorithm includes：
S31：Original image is read in, the H-I color model statistic histogram of image is generated；
S32：Initialization of population inputs threshold value L, maximum cycle M, fuzzy membership exponent m；Initialize subordinated-degree matrix U；
If gathering honey bee and follow bee quantity be SN, S is randomly generatedNThe position of/2 gathering honey bees is as cluster centre；
S33：The fitness of all food sources is calculated by formula (1), and sets current iteration number as C=1, is started the cycle over；
Wherein, λ is fitness dynamic factor；
S34：Gathering honey bee is cooked neighborhood search according to formula (2) and obtains New food source position Vi, its new fitness is calculated with formula (1)；
Vi=Xi+ψi(Xi-Xk) (2)
In formula, k ∈ { 1,2 ..., SN, and k ≠ i is generated at random, ψiRandom number between [- 1,1]；
S35：Using greedy algorithm to new and old position preferentially, if ViFitness be greater than the optimal value in memory, then Xi=Vi, no
Then, XiIt is constant；
S36：It is calculated according to formula (3) and follows bee i probability P relevant to food sourcei, follow bee according to PiSelect food source；
Wherein SNIndicate food source number；
S37：It follows bee to carry out neighborhood search and generates new explanation Vi, its fitness is calculated, if ViFitness be greater than memory in it is optimal
Fitness, then Xi=Vi, otherwise, XiIt is constant；
S38：After L circulation, if fitness does not change, the food source is abandoned, search bee produces according to formula (4) at this time
A raw new explanation replaces current Xi；
X in formulaminIndicate the minimum value of food source value range, XmaxThe maximum value of expression food source value range, r expression [0,
1] random number between, Xi(n) n-th of feasible solution is indicated；
S39：Remember the maximum food source position of current fitness and stop iteration if the number of iterations reaches M, finds optimal poly-
Class center；Otherwise step S34, C=C+1 are gone to；
S310：Each sample is solved for the degree of membership of Optimal cluster centers, image is divided according to maximum membership grade principle
It cuts, then target image is obtained by Morphological scale-space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810689327.2A CN108901540A (en) | 2018-06-28 | 2018-06-28 | Fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810689327.2A CN108901540A (en) | 2018-06-28 | 2018-06-28 | Fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108901540A true CN108901540A (en) | 2018-11-30 |
Family
ID=64421764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810689327.2A Pending CN108901540A (en) | 2018-06-28 | 2018-06-28 | Fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108901540A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112021016A (en) * | 2020-09-07 | 2020-12-04 | 江苏农林职业技术学院 | Flower and fruit thinning system for strawberries |
| CN113075709A (en) * | 2021-03-24 | 2021-07-06 | 刘成 | Vehicle-mounted satellite navigation method and device, storage medium and processor |
| CN114330839A (en) * | 2021-12-13 | 2022-04-12 | 重庆邮电大学 | Landslide displacement prediction method based on WOA-LSTM model |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034440A (en) * | 2007-01-12 | 2007-09-12 | 浙江工业大学 | Identification method for spherical fruit and vegetables |
| CN101356877A (en) * | 2008-09-19 | 2009-02-04 | 中国农业大学 | Cucumber picking robot system and picking method in greenhouse |
| CN102622755A (en) * | 2012-02-28 | 2012-08-01 | 中国农业大学 | Plant limb identification method |
| CN102726270A (en) * | 2012-05-30 | 2012-10-17 | 溧阳市天目湖大紫王葡萄专业合作社 | Grape planting method |
| CN103081730A (en) * | 2013-02-05 | 2013-05-08 | 青岛农业大学 | Hydraulic transmission type fruit tree flower thinning machine based on machine vision and flower thinning method |
| CN103279762A (en) * | 2013-05-21 | 2013-09-04 | 常州大学 | Judging method for common growth form of fruit under natural environment |
| CN103295030A (en) * | 2013-06-21 | 2013-09-11 | 中国科学院对地观测与数字地球科学中心 | Classification method and device based on hyperspectral remote sensing images |
| CN103529855A (en) * | 2013-10-11 | 2014-01-22 | 华南农业大学 | Rotary adjustable binocular vision target recognition and positioning device and application thereof in agricultural fruit harvesting machinery |
| CN106780501A (en) * | 2016-12-16 | 2017-05-31 | 中国人民解放军装甲兵工程学院 | Based on the image partition method for improving artificial bee colony algorithm |
| CN108090910A (en) * | 2018-01-04 | 2018-05-29 | 中国计量大学 | It is a kind of that tomato plant image segmentation algorithm outside the night room of PCNN models is simplified based on comentropy gradient |
| CN108133471A (en) * | 2016-11-30 | 2018-06-08 | 天津职业技术师范大学 | Agriculture Mobile Robot guidance path extracting method and device based on artificial bee colony algorithm under the conditions of a kind of natural lighting |
-
2018
- 2018-06-28 CN CN201810689327.2A patent/CN108901540A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034440A (en) * | 2007-01-12 | 2007-09-12 | 浙江工业大学 | Identification method for spherical fruit and vegetables |
| CN101356877A (en) * | 2008-09-19 | 2009-02-04 | 中国农业大学 | Cucumber picking robot system and picking method in greenhouse |
| CN102622755A (en) * | 2012-02-28 | 2012-08-01 | 中国农业大学 | Plant limb identification method |
| CN102726270A (en) * | 2012-05-30 | 2012-10-17 | 溧阳市天目湖大紫王葡萄专业合作社 | Grape planting method |
| CN103081730A (en) * | 2013-02-05 | 2013-05-08 | 青岛农业大学 | Hydraulic transmission type fruit tree flower thinning machine based on machine vision and flower thinning method |
| CN103279762A (en) * | 2013-05-21 | 2013-09-04 | 常州大学 | Judging method for common growth form of fruit under natural environment |
| CN103295030A (en) * | 2013-06-21 | 2013-09-11 | 中国科学院对地观测与数字地球科学中心 | Classification method and device based on hyperspectral remote sensing images |
| CN103529855A (en) * | 2013-10-11 | 2014-01-22 | 华南农业大学 | Rotary adjustable binocular vision target recognition and positioning device and application thereof in agricultural fruit harvesting machinery |
| CN108133471A (en) * | 2016-11-30 | 2018-06-08 | 天津职业技术师范大学 | Agriculture Mobile Robot guidance path extracting method and device based on artificial bee colony algorithm under the conditions of a kind of natural lighting |
| CN106780501A (en) * | 2016-12-16 | 2017-05-31 | 中国人民解放军装甲兵工程学院 | Based on the image partition method for improving artificial bee colony algorithm |
| CN108090910A (en) * | 2018-01-04 | 2018-05-29 | 中国计量大学 | It is a kind of that tomato plant image segmentation algorithm outside the night room of PCNN models is simplified based on comentropy gradient |
Non-Patent Citations (5)
| Title |
|---|
| 卢军等: "弱光复杂背景下基于MSER和HCA的树上绿色柑橘检测", 《农业工程学报》 * |
| 夏雪等: "自然环境下果实作业机器人幼果期苹果侦测方法 ", 《中国农业科技导报》 * |
| 罗晓丽: "柑橘果实信息智能识别及定位方法研究", 《菏泽学院学报》 * |
| 罗陆锋等: "基于改进人工蜂群模糊聚类的葡萄图像快速分割方法", 《农业机械学报》 * |
| 雷世俊等: "《科技惠农一号工程 果树设施栽培》", 31 December 2015, 山东科学技术出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112021016A (en) * | 2020-09-07 | 2020-12-04 | 江苏农林职业技术学院 | Flower and fruit thinning system for strawberries |
| CN113075709A (en) * | 2021-03-24 | 2021-07-06 | 刘成 | Vehicle-mounted satellite navigation method and device, storage medium and processor |
| CN114330839A (en) * | 2021-12-13 | 2022-04-12 | 重庆邮电大学 | Landslide displacement prediction method based on WOA-LSTM model |
| CN114330839B (en) * | 2021-12-13 | 2024-05-28 | 重庆邮电大学 | Landslide displacement prediction method based on WOA-LSTM model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009542B (en) | Weed image segmentation method in rape field environment | |
| CN108901540A (en) | Fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm | |
| CN102214306B (en) | Leaf disease spot identification method and device | |
| CN109740721B (en) | Wheat ear counting method and device | |
| CN107622236B (en) | Crop disease diagnosis and early warning method based on swarm and gradient lifting decision tree algorithm | |
| CN107563389A (en) | A kind of corps diseases recognition methods based on deep learning | |
| Xu et al. | Recognition method for apple fruit based on SUSAN and PCNN | |
| CN109684906A (en) | The method of detection red turpentine beetle based on deep learning | |
| CN111798470B (en) | Crop image entity segmentation method and system applied to intelligent agriculture | |
| Gutte et al. | A survey on recognition of plant disease with help of algorithm | |
| CN112257702A (en) | Crop disease identification method based on incremental learning | |
| CN108764347A (en) | Tellurion National Imagery recognition methods based on convolutional neural networks | |
| Umar et al. | Precision Agriculture Through Deep Learning: Tomato Plant Multiple Diseases Recognition with CNN and Improved YOLOv7 | |
| CN116934787A (en) | Image processing method based on edge detection | |
| CN107578414A (en) | A kind of processing method of pavement crack image | |
| CN111612797B (en) | Rice image information processing system | |
| CN106067175B (en) | A kind of solar activity object detection method based on square net structure | |
| CN112085032A (en) | Grapefruit disease and insect pest dynamic monitoring model based on combination of Internet of things image processing and SVM (support vector machine) | |
| CN115601690B (en) | Edible fungus environment detection method based on intelligent agriculture | |
| CN111160180A (en) | Night green apple identification method of apple picking robot | |
| CN114581470B (en) | Image edge detection method based on plant community behaviors | |
| Kumar et al. | The Different Techniques for Detection of Plant Leaves Diseases | |
| CN114202687B (en) | Automatic tobacco plant extraction and counting method and system based on unmanned aerial vehicle images | |
| CN116863403A (en) | Crop big data environment monitoring method and device and electronic equipment | |
| CN109241865A (en) | A kind of vehicle detection partitioning algorithm under weak contrast's traffic scene |
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: 20181130 |
|
| RJ01 | Rejection of invention patent application after publication |