CN109035209A - Sugarcane tillering stage automatic observation process - Google Patents
Sugarcane tillering stage automatic observation process Download PDFInfo
- Publication number
- CN109035209A CN109035209A CN201810719627.0A CN201810719627A CN109035209A CN 109035209 A CN109035209 A CN 109035209A CN 201810719627 A CN201810719627 A CN 201810719627A CN 109035209 A CN109035209 A CN 109035209A
- Authority
- CN
- China
- Prior art keywords
- sugarcane
- image
- plant
- sugarcane plant
- tillering stage
- 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
- G06T7/10—Segmentation; 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
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/30168—Image quality inspection
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses sugarcane tillering stage automatic observation process, comprising: obtains sugarcane image in real time；Sugarcane image is pre-processed；Extract sugarcane plant image；Calculate sugarcane plant green pixel coverage FVC；Calculate sugarcane plant number of vertex amount；Calculate sugarcane plant leaf and stem crosspoint quantity；If sugarcane plant green pixel coverage FVC >=coverage threshold value FVCg, sugarcane plant number of vertex amount >=sugarcane plant number of vertex amount threshold value, sugarcane plant leaf and stem crosspoint quantity >=sugarcane plant leaf and stem crosspoint amount threshold, then the sugarcane plant in sugarcane image enters sugarcane tillering stage.The present invention utilizes image recognition technology, sugarcane tillering stage automatic Observation is completed by calculating sugarcane plant green pixel coverage, sugarcane plant number of vertex amount, sugarcane plant leaf and stem crosspoint quantity,, timeliness higher than traditional artificial observation method objectivity and practical, and reduce labor intensity and production cost.
Description
Technical field
The present invention relates to cane planting technical fields.It is more particularly related to sugarcane tillering stage automatic Observation side
Method.
Background technique
Sugarcane is one of sugar cane crop mostly important in the world, accounts for sugar yield by the sucrose that sugarcane presses in China
90% or more.Developing precision agricultural is to realize the effective measures of Sugarcane Industry sustainable development, accurate in real time to obtain sugarcane
Puberty information is one of the key foundation that accurate Sugarcane Industry is implemented.By the speed and process of accurately observing sugarcane development
Etc. information, can such as be irrigated, be applied fertilizer and prevention and control of plant diseases, pest control production activity is to increase production with scientific guidance, can be applied to sugarcane production
Model improves the accuracy of sugarcane yield prediction, analyze to sugarcane production development condition and then for efficiently and accurately
Sugarcane Industry service.For a long time, sugarcane puberty information is observed mainly based on traditional artificial observation mode, Observation personnel
Field work amount and large labor intensity, low efficiency, subjectivity are strong and rest on to estimate or simple device survey, hand-kept, papery
Archive etc. falls behind level, and artificial observation is discontinuous and lacks quantification standard, has been unable to meet modern sugarcane production and management
It needs, there is an urgent need to change and promoted sugarcane breeding time observation method thus.Sugarcane tillering stage is to determine sugarcane number of productive tiller
Important period, and capture the critical period of sugarcane high-yield, this period of objective and accurate identification can scientifically and rationally plant
Strive for that effective tillering controls ineffective tillering in training, is of great significance to the fine-grained management of sugarcane production.2012 year clock Chu etc.
It delivers in " sugarcane physiological development time and development stage estimation " and sugarcane is sent out using plant physiology development time in " sugar section of China "
Sprouting stage, Seedling Stage and stem elongation phase are predicted that prediction of result relative error is respectively 7,3,6,15 days, and prediction effect is preferable,
There is certain practicability, but because breeding time is observed for two days 1 time manual patrol, causes certain error, and no pair
Sugarcane tillering stage is predicted.In computer vision field, it is not yet found that the open report of sugarcane tillering stage identification technology, existing
Some documents carry out cane planting identification, Sugarcane growth monitoring neck related to sugarcane yield estimation mainly around satellite remote sensing images
Domain research.Such as, long tinkling of pieces of jade of king in 2014 etc. delivers " the multidate HJ star image sugarcane knowledge of object-oriented in " Journal of Agricultural Engineering "
Other method " in utilize sugarcane locally consistent sex index GLCM derived from the spectrum image feature on different phase images
Homogeneity, the classifying rules collection for establishing decision tree logic extract cane -growing region, nicety of grading 91.3%.2015
Chen Yanli etc. delivers base in " the Guangxi sugarcane rudiment tillering stage arid hierarchic space distribution based on GIS " in " Jiangsu's agriculture science "
In GIS technology, carried out using sugarcane grade disaster frequency and geographical factors of the multiple regression analysis method to sugarcane rudiment tillering stage
Regression analysis establishes spatial distribution model and analyzes the Droughts hierarchic space distribution characteristics in two periods.Above-mentioned phase
The method that document does not provide real-time detection sugarcane tillering stage is closed, and satellite remote sensing images image-forming range is remote, resolution ratio is low, at
Image quality amount is influenced by weather, is unable to actively monitoring variation, the crop entirety growth conditions analysis being more suitable under large scale, uncomfortable
Selection for sugarcane tillering stage observation method.
Summary of the invention
The object of the present invention is to provide sugarcane tillering stage automatic observation process, sweet by calculating using image recognition technology
Sugarcane plant green pixel coverage, sugarcane plant number of vertex amount, Sugarcane Leaves and stem crosspoint quantity complete sugarcane tillering stage
Automatic Observation, timeliness higher than traditional artificial observation method objectivity and practical, and reduce labor intensity and production
Cost.
In order to realize these purposes and other advantages according to the present invention, sugarcane tillering stage automatic observation process is provided,
Include:
Step 1: obtaining sugarcane image in real time；
Step 2: being pre-processed to sugarcane image；
Step 3: being split to sugarcane image, sugarcane plant image is extracted；
Step 4: calculating sugarcane plant green pixel coverage FVC according to sugarcane plant image；
Step 5: calculating sugarcane plant number of vertex amount according to sugarcane plant image；
Step 6: calculating sugarcane plant leaf and stem crosspoint quantity according to sugarcane plant image；
Step 7: if sugarcane plant green pixel coverage FVC >=coverage threshold value FVCg, sugarcane plant number of vertex amount >=
Sugarcane plant number of vertex amount threshold value, sugarcane plant leaf and stem crosspoint quantity >=sugarcane plant leaf and stem crosspoint quantity threshold
Value, then the sugarcane plant in sugarcane image enters sugarcane tillering stage.
Preferably, in the sugarcane tillering stage automatic observation process, sugarcane production is obtained in real time in the step 1
After image, further include the steps that carrying out quality testing to sugarcane image.
Preferably, in the sugarcane tillering stage automatic observation process, the step 2 specifically: to sugarcane image into
Row noise removal process.
Preferably, in the sugarcane tillering stage automatic observation process, the step 3 specifically: use K-means
Clustering procedure is split sugarcane image, and weeds, soil and sugarcane plant is separated, extracts sugarcane plant colouring information and connects
Logical region；According to the geometry and contour feature of Sugarcane Leaves and limb, sugarcane plant image is extracted in connected region.
Preferably, in the sugarcane tillering stage automatic observation process, the step 4 specifically: utilize sugarcane plant
Image RGB color calculates sugarcane plant green pixel coverage FVC.
Preferably, in the sugarcane tillering stage automatic observation process, the step 5 specifically: calculated using Harris
The color image that method obtains after dividing in step 3 is converted into gray level image, extracts sugarcane plant number of vertex amount.
Preferably, in the sugarcane tillering stage automatic observation process, the step 6 specifically: by step 3 points
The color image binaryzation obtained after cutting, and refined using thinning algorithm, calculate sugarcane plant leaf and stem crosspoint quantity.
The present invention is include at least the following beneficial effects:
The present invention utilizes image recognition technology, by calculating plant green pixel coverage, sugarcane plant number of vertex amount, sweet
Sugarcane blade and stem crosspoint quantity complete sugarcane tillering stage automatic Observation, it is higher than traditional artificial observation method objectivity, when
Effect property and practical, and reduces labor intensity and production cost.
The present invention can be used for the sugarcane production and management of the cane plantings gardens such as sugarcane " double height " Demonstration Base, be precisely sweet
Sugarcane industry development provides the first-hand means of production of science, has and value is widely applied.
The present invention overcomes the deficiencies of traditional artificial observation sugarcane tillering stage method, can refer to existing artificial observation
On the basis of sugarcane tillering stage, the sugarcane production image acquired in real time using sugarcane field utilizes sugarcane color characteristic, several as object
What shape and contour feature is influenced for naturally strong light and weeds, is partitioned into sugarcane plant using K-means clustering methodology
Come, extract sugarcane plant image and calculates sugarcane plant image Green pixel coverage；Sugarcane plant apex feature is carried out
It analyzes and counts sugarcane plant number of vertex amount；Sugarcane Leaves and stem intersection feature are analyzed, color image is carried out two
Value simultaneously refines, and sugarcane plant leaf and stem crosspoint quantity is calculated, finally with sugarcane plant green pixel coverage, sugarcane planting
Strain vertex quantity, sugarcane plant leaf and stem crosspoint quantity condition achieved are secondary when 12 in synthesis 3 days as judgment basis
The judgment basis that image averaging reaches determines that sugarcane enters the time in tillering stage, to improve the objectivity and practicability of observation, subtracts
Few observed strength and reduction observation cost, provide good decision support for fining sugarcane production and management.
Further advantage, target and feature of the invention will be partially reflected by the following instructions, and part will also be by this
The research and practice of invention and be understood by the person skilled in the art.
Detailed description of the invention
Fig. 1 is the flow diagram of sugarcane tillering stage automatic Observation according to an embodiment of the invention；
Fig. 2 is the flow diagram according to an embodiment of the invention that quality testing is carried out to sugarcane image.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art referring to specification text
Word can be implemented accordingly.
It should be noted that in the description of the present invention, term " transverse direction ", " longitudinal direction ", "upper", "lower", "front", "rear",
The orientation or positional relationship of the instructions such as "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is based on attached drawing institute
The orientation or positional relationship shown, is merely for convenience of description of the present invention and simplification of the description, and is not the dress of indication or suggestion meaning
It sets or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as to limit of the invention
System.
Embodiment 1
As shown in Figure 1, the present invention provides sugarcane tillering stage automatic observation process, comprising:
Step 1: obtaining sugarcane image in real time；
Step 2: being pre-processed to sugarcane image；
Step 3: being split to sugarcane image, sugarcane plant image is extracted in connected region；
Step 4: calculating sugarcane plant green pixel coverage FVC according to sugarcane plant image；
Step 5: calculating sugarcane plant number of vertex amount according to sugarcane plant image；
Step 6: calculating sugarcane plant leaf and stem crosspoint quantity according to sugarcane plant image；
Step 7: according to sugarcane tillering stage history image, in conjunction with the characteristics of image of sugarcane tillering stage artificial observation element, structure
Sugarcane image feature base is built, sugarcane tillering stage sugarcane plant green pixel coverage FVC is countedg, sugarcane plant number of vertex
Amount and Sugarcane Leaves and stem crosspoint quantity.If sugarcane plant green pixel coverage FVC >=coverage threshold value FVCg, sugarcane planting
Strain vertex quantity >=sugarcane plant number of vertex amount threshold value, Sugarcane Leaves and stem crosspoint quantity >=sugarcane plant leaf and stem intersect
Point amount threshold, then the sugarcane plant in sugarcane image enters sugarcane tillering stage.
In the sugarcane tillering stage automatic observation process, after obtaining sugarcane production image in real time in the step 1, also
Include the steps that carrying out quality testing to sugarcane image, the flow diagram for carrying out quality testing to sugarcane image is as shown in Figure 2.
In the sugarcane tillering stage automatic observation process, the step 2 specifically: noise is carried out to sugarcane image and is gone
Except processing.
In the sugarcane tillering stage automatic observation process, the step 3 specifically: using K-means clustering procedure to sweet
Sugarcane image is split, and weeds, soil and sugarcane plant is separated, extracts sugarcane plant colouring information connected region；Root
According to the geometry and contour feature of Sugarcane Leaves and limb, sugarcane plant image is extracted in connected region.
In the sugarcane tillering stage automatic observation process, the step 4 specifically: utilize sugarcane plant image RGB face
The colour space calculates sugarcane plant green pixel coverage FVC.
In the sugarcane tillering stage automatic observation process, the step 5 specifically: utilize Harris algorithm by step
The color image obtained after dividing in three is converted into gray level image, extracts sugarcane plant number of vertex amount.
In the sugarcane tillering stage automatic observation process, the step 6 specifically: obtained after dividing in step 3
Color image binaryzation, and refined using thinning algorithm, calculate sugarcane plant leaf and stem crosspoint quantity.
In the above method, calculate sugarcane plant green pixel coverage FVC, sugarcane plant number of vertex amount, Sugarcane Leaves and
Stem crosspoint quantity, by the same day shoot a sugarcane image be calculated, in order to prevent accidentally survey, can by one day into
Row obtains after shooting several times to each time results are averaged, or is averaged after being shot by these last few days to several days results
Value obtains, or repeatedly by shooting daily, is averaged to obtain to each shooting result after shooting in several days.
Embodiment 2
As shown in Figure 1, the present invention provides sugarcane tillering stage automatic observation process, comprising:
Step 1: obtaining sugarcane image in real time；
Step 2: being pre-processed to sugarcane image；
Step 3: being split to sugarcane image, sugarcane plant image is extracted in connected region；
Step 4: calculating sugarcane plant green pixel coverage FVC according to sugarcane plant image；In order to improve sugarcane plant
The detection accuracy of green pixel coverage FVC obtains the sugarcane image at n ' a time point, n ' > 1 daily, and counts in n days
Captured all sugarcane images, n >=2 calculate separately the corresponding sugarcane plant green pixel coverage of every sugarcane image
FVC, and be averaged.
Step 5: calculating sugarcane plant number of vertex amount according to sugarcane plant image；In order to improve sugarcane plant number of vertex amount
Detection accuracy, statistics n days in captured by all sugarcane images after, also calculate separately the corresponding sugarcane of every sugarcane image
Plant vertex quantity, and be averaged.
Step 6: calculating sugarcane plant leaf and stem crosspoint quantity according to sugarcane plant image；In order to improve sugarcane top
The detection accuracy of piece and stem crosspoint quantity, statistics n days in captured by all sugarcane images after, also calculate separately every it is sweet
The corresponding Sugarcane Leaves of sugarcane image and stem crosspoint quantity, and be averaged.
Step 7: according to sugarcane tillering stage history image, in conjunction with the characteristics of image of sugarcane tillering stage artificial observation element, structure
Sugarcane image feature base is built, sugarcane tillering stage sugarcane plant green pixel coverage FVC is countedg, sugarcane plant number of vertex
Amount and Sugarcane Leaves and stem crosspoint quantity.The sugarcane plant green pixel coverage FVC >=coverage threshold value tested with the same day
FVCg, and average value >=coverage threshold value FVC of the sugarcane plant green pixel coverage FVC obtained in n daysg, it is set as condition 1；
Sugarcane plant number of vertex amount >=sugarcane plant number of vertex amount threshold value, sugarcane plant leaf and the stem crosspoint quantity tested with the same day
>=Sugarcane Leaves and stem crosspoint amount threshold, and average value >=sugarcane plant of the sugarcane plant number of vertex amount obtained in n days
Average value >=sugarcane the plant leaf and stem of vertex amount threshold, the sugarcane plant leaf obtained in n days and stem crosspoint quantity
Crosspoint amount threshold is set as condition 2, if condition 1 and condition 2 meet simultaneously, show it is last 1 time acquisition sugarcane image in
Sugarcane plant enter sugarcane tillering stage.
In the sugarcane tillering stage automatic observation process, after obtaining sugarcane production image in real time in the step 1, also
Include the steps that carrying out quality testing to sugarcane image, the flow diagram for carrying out quality testing to sugarcane image is as shown in Figure 2.
In the sugarcane tillering stage automatic observation process, the step 2 specifically: noise is carried out to sugarcane image and is gone
Except processing.
In the sugarcane tillering stage automatic observation process, the step 3 specifically: using K-means clustering procedure to sweet
Sugarcane image is split, and weeds, soil and sugarcane plant is separated, extracts sugarcane plant colouring information connected region；Root
According to the geometry and contour feature of Sugarcane Leaves and limb, sugarcane plant image is extracted in connected region.
In the sugarcane tillering stage automatic observation process, the step 4 specifically: utilize sugarcane plant image RGB face
The colour space calculates sugarcane plant green pixel coverage FVC.
In the sugarcane tillering stage automatic observation process, the step 5 specifically: utilize Harris algorithm by step
The color image obtained after dividing in three is converted into gray level image, extracts sugarcane plant number of vertex amount.
In the sugarcane tillering stage automatic observation process, the step 6 specifically: obtained after dividing in step 3
Color image binaryzation, and refined using thinning algorithm, calculate sugarcane plant leaf and stem crosspoint quantity.
Embodiment 3
As shown in Figure 1, the present invention provides sugarcane tillering stage automatic observation process, comprising:
Step 1: obtaining sugarcane image in real time；
Step 2: being pre-processed to sugarcane image；
Step 3: being split to sugarcane image, sugarcane plant image is extracted in connected region；
Step 4: calculating sugarcane plant green pixel coverage FVC according to sugarcane plant image；In order to improve sugarcane plant
The detection accuracy of green pixel coverage FVC, the daily sugarcane image for obtaining 4 time points, such as daily 8:00,10:00,
14:00,16:00 shoot sugarcane image, and sugarcane image when counting captured in 3 days 12 time, calculate separately every it is sweet
The corresponding sugarcane plant green pixel coverage FVC of sugarcane image, and be averaged.
Step 5: calculating sugarcane plant number of vertex amount according to sugarcane plant image；In order to improve sugarcane plant number of vertex amount
Detection accuracy, after the sugarcane image in statistics 3 days at captured 12 time, it is corresponding also to calculate separately every sugarcane image
Sugarcane plant number of vertex amount, and be averaged.
Step 6: calculating sugarcane plant leaf and stem crosspoint quantity according to sugarcane plant image；In order to improve sugarcane planting
The detection accuracy of strain blade and stem crosspoint quantity is also distinguished in statistics 3 days after sugarcane image secondary at captured 12
The corresponding sugarcane plant leaf of every sugarcane image and stem crosspoint quantity are calculated, and is averaged.
Step 7: according to sugarcane tillering stage history image, in conjunction with the characteristics of image of sugarcane tillering stage artificial observation element, structure
Sugarcane image feature base is built, sugarcane tillering stage sugarcane plant green pixel coverage FVC is countedg, sugarcane plant number of vertex
Amount and Sugarcane Leaves and stem crosspoint quantity.The sugarcane plant green pixel coverage FVC >=coverage threshold value tested with the same day
FVCg, and average value >=coverage threshold value FVC of the sugarcane plant green pixel coverage FVC obtained in 3 daysg, it is set as condition 1；
Sugarcane plant number of vertex amount >=sugarcane plant number of vertex amount threshold value, sugarcane plant leaf and the stem crosspoint quantity tested with the same day
>=sugarcane plant leaf and stem crosspoint amount threshold, and average value >=sugarcane of the sugarcane plant number of vertex amount obtained in 3 days
The average value of plant vertex amount threshold, the sugarcane plant leaf obtained in 3 days and stem crosspoint quantity >=sugarcane plant leaf
With stem crosspoint amount threshold, it is set as condition 2, if condition 1 and condition 2 meet simultaneously, shows the sugarcane figure of last 1 acquisition
Sugarcane plant as in enters sugarcane tillering stage.
In the sugarcane tillering stage automatic observation process, after obtaining sugarcane production image in real time in the step 1, also
Include the steps that carrying out quality testing to sugarcane image, the flow diagram for carrying out quality testing to sugarcane image is as shown in Figure 2.
In the sugarcane tillering stage automatic observation process, the step 2 specifically: noise is carried out to sugarcane image and is gone
Except processing.
In the sugarcane tillering stage automatic observation process, the step 3 specifically: using K-means clustering procedure to sweet
Sugarcane image is split, and weeds, soil and sugarcane plant is separated, extracts sugarcane plant colouring information connected region；Root
According to the geometry and contour feature of Sugarcane Leaves and limb, sugarcane plant image is extracted in connected region.
In the sugarcane tillering stage automatic observation process, the step 4 specifically: utilize sugarcane plant image RGB face
The colour space calculates sugarcane plant green pixel coverage FVC.
In the sugarcane tillering stage automatic observation process, the step 5 specifically: utilize Harris algorithm by step
The color image obtained after dividing in three is converted into gray level image, extracts sugarcane plant number of vertex amount.
In the sugarcane tillering stage automatic observation process, the step 6 specifically: obtained after dividing in step 3
Color image binaryzation, and refined using thinning algorithm, calculate sugarcane plant leaf and stem crosspoint quantity.
Using the method for embodiment 3, tested in multiple sample fields, it is detecting automatically the results show that of the invention judged
The sugarcane time in tillering stage and artificial observation time consistency, accuracy rate of testing result is high, observed strength and at low cost.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily
Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited
In specific details and legend shown and described herein.
Claims (7)
1. sugarcane tillering stage automatic observation process characterized by comprising
Step 1: obtaining sugarcane image in real time；
Step 2: being pre-processed to sugarcane image；
Step 3: being split to sugarcane image, sugarcane plant image is extracted；
Step 4: calculating sugarcane plant green pixel coverage FVC according to sugarcane plant image；
Step 5: calculating sugarcane plant number of vertex amount according to sugarcane plant image；
Step 6: calculating sugarcane plant leaf and stem crosspoint quantity according to sugarcane plant image；
Step 7: if sugarcane plant green pixel coverage FVC >=coverage threshold value FVCg, sugarcane plant number of vertex amount >=sugarcane
Plant vertex amount threshold, sugarcane plant leaf and stem crosspoint quantity >=sugarcane plant leaf and stem crosspoint amount threshold,
Then the sugarcane plant in sugarcane image enters sugarcane tillering stage.
2. sugarcane tillering stage automatic observation process as described in claim 1, which is characterized in that obtained in real time in the step 1
After sugarcane production image, further include the steps that carrying out quality testing to sugarcane image.
3. sugarcane tillering stage automatic observation process as described in claim 1, which is characterized in that the step 2 specifically: right
Sugarcane image carries out noise removal process.
4. sugarcane tillering stage automatic observation process as described in claim 1, which is characterized in that the step 3 specifically: adopt
Sugarcane image is split with K-means clustering procedure, weeds, soil and sugarcane plant is separated, extract sugarcane plant
Colouring information connected region；According to the geometry and contour feature of Sugarcane Leaves and limb, sugarcane planting is extracted in connected region
Strain image.
5. sugarcane tillering stage automatic observation process as described in claim 1, which is characterized in that the step 4 specifically: benefit
Sugarcane plant green pixel coverage FVC is calculated with sugarcane plant image RGB color.
6. sugarcane tillering stage automatic observation process as described in claim 1, which is characterized in that the step 5 specifically: benefit
The color image obtained after being divided in step 3 with Harris algorithm is converted into gray level image, extracts sugarcane plant number of vertex
Amount.
7. sugarcane tillering stage automatic observation process as described in claim 1, which is characterized in that the step 6 specifically: will
The color image binaryzation obtained after dividing in step 3, and refined using thinning algorithm, it calculates sugarcane plant leaf and stem is handed over
Crunode quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810719627.0A CN109035209A (en) | 2018-07-03 | 2018-07-03 | Sugarcane tillering stage automatic observation process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810719627.0A CN109035209A (en) | 2018-07-03 | 2018-07-03 | Sugarcane tillering stage automatic observation process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109035209A true CN109035209A (en) | 2018-12-18 |
Family
ID=65521586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810719627.0A Pending CN109035209A (en) | 2018-07-03 | 2018-07-03 | Sugarcane tillering stage automatic observation process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109035209A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680114A (en) * | 2017-09-22 | 2018-02-09 | 交通运输部天津水运工程科学研究所 | A kind of meadow cover degree measuring method based on Computer Image Processing |
| CN112270708A (en) * | 2020-10-26 | 2021-01-26 | 中国计量大学 | Vegetable and fruit plant side branch point identification method based on different edge type intersection points |
| CN112715077A (en) * | 2020-12-31 | 2021-04-30 | 广西壮族自治区农业科学院 | Sugarcane tillering and thinning and planting management machine |
| US20220312684A1 (en) * | 2020-01-16 | 2022-10-06 | Canon Kabushiki Kaisha | Imaging diagnosis apparatus, imaging diagnosis system, imaging diagnosis method, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102102988A (en) * | 2009-12-22 | 2011-06-22 | 中国农业科学院农业环境与可持续发展研究所 | Method, system and device for measuring crop yield information in real time |
| CN102278979A (en) * | 2011-04-28 | 2011-12-14 | 华中科技大学 | Automatic detection method of transplanting and tillering of paddy rice |
| CN106845366A (en) * | 2016-12-29 | 2017-06-13 | 江苏省无线电科学研究所有限公司 | Sugarcane coverage automatic testing method based on image |
| CN106954385A (en) * | 2015-01-09 | 2017-07-14 | 日立麦克赛尔株式会社 | Plant information obtains system, plant information acquisition device, plant information adquisitiones, crop management system and crop management method |
-
2018
- 2018-07-03 CN CN201810719627.0A patent/CN109035209A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102102988A (en) * | 2009-12-22 | 2011-06-22 | 中国农业科学院农业环境与可持续发展研究所 | Method, system and device for measuring crop yield information in real time |
| CN102278979A (en) * | 2011-04-28 | 2011-12-14 | 华中科技大学 | Automatic detection method of transplanting and tillering of paddy rice |
| CN106954385A (en) * | 2015-01-09 | 2017-07-14 | 日立麦克赛尔株式会社 | Plant information obtains system, plant information acquisition device, plant information adquisitiones, crop management system and crop management method |
| CN106845366A (en) * | 2016-12-29 | 2017-06-13 | 江苏省无线电科学研究所有限公司 | Sugarcane coverage automatic testing method based on image |
Non-Patent Citations (1)
| Title |
|---|
| 李焕章: "冬小麦农大183分蘖、叶片发生规律与穗部关系的初步研究", 《作物学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680114A (en) * | 2017-09-22 | 2018-02-09 | 交通运输部天津水运工程科学研究所 | A kind of meadow cover degree measuring method based on Computer Image Processing |
| US20220312684A1 (en) * | 2020-01-16 | 2022-10-06 | Canon Kabushiki Kaisha | Imaging diagnosis apparatus, imaging diagnosis system, imaging diagnosis method, and storage medium |
| CN112270708A (en) * | 2020-10-26 | 2021-01-26 | 中国计量大学 | Vegetable and fruit plant side branch point identification method based on different edge type intersection points |
| CN112270708B (en) * | 2020-10-26 | 2024-02-02 | 中国计量大学 | Vegetable and fruit plant lateral branch point identification method based on intersection points of different edge types |
| CN112715077A (en) * | 2020-12-31 | 2021-04-30 | 广西壮族自治区农业科学院 | Sugarcane tillering and thinning and planting management machine |
| CN112715077B (en) * | 2020-12-31 | 2022-03-25 | 广西壮族自治区农业科学院 | Sugarcane tillering and thinning and planting management machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Martinez-Casasnovas et al. | Analysis of vineyard differential management zones and relation to vine development, grape maturity and quality | |
| CN112418188B (en) | Crop growth whole-course digital evaluation method based on unmanned aerial vehicle vision | |
| WO2021098471A1 (en) | Wide-range crop phenology extraction method based on morphological modeling method | |
| CN109035209A (en) | Sugarcane tillering stage automatic observation process | |
| CN105740759B (en) | Semilate rice information decision tree classification approach based on feature extraction in multi-temporal data | |
| CN111709379A (en) | Remote sensing image-based hilly area citrus planting land plot monitoring method and system | |
| CN110472184A (en) | A kind of cloudy misty rain area rice recognition methods based on Landsat remotely-sensed data | |
| Ma et al. | Automatic detection of crop root rows in paddy fields based on straight-line clustering algorithm and supervised learning method | |
| CN105989601A (en) | Machine vision-based method for extracting inter-corn-row navigation reference line of agricultural AGV (Automated Guided Vehicle) | |
| Ramesh et al. | Comparison and analysis of Rice Blast disease identification in Greenhouse Controlled Environment and Field Environment using ML Algorithms | |
| CN102663396B (en) | Method for automatically detecting rice milky ripe stage | |
| CN113920106B (en) | Corn growth vigor three-dimensional reconstruction and stem thickness measurement method based on RGB-D camera | |
| Zhou et al. | Wheat phenology detection with the methodology of classification based on the time-series UAV images | |
| CN110969654A (en) | Corn high-throughput phenotype measurement method and device based on harvester and harvester | |
| CN107680098A (en) | A kind of recognition methods of sugarcane sugarcane section feature | |
| CN102542560B (en) | Method for automatically detecting density of rice after transplantation | |
| Han et al. | Rice yield estimation using a CNN-based image-driven data assimilation framework | |
| CN102855485B (en) | The automatic testing method of one grow wheat heading | |
| CN112580671A (en) | Automatic detection method and system for multiple development stages of rice ears based on deep learning | |
| CN111967441A (en) | Crop disease analysis method based on deep learning | |
| CN112116206A (en) | Intelligent agricultural system based on big data | |
| CN116129260A (en) | Forage grass image recognition method based on deep learning | |
| CN116300608A (en) | Intelligent agriculture remote monitoring system based on big data | |
| CN106845366B (en) | Sugarcane coverage automatic detection method based on image | |
| CN102592118B (en) | Automatic detection method for time emergence of seedling of corns |
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: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |