CN108037123A - A kind of hybrid paddy rice disc type sows performance parameter accurate detecting method - Google Patents
A kind of hybrid paddy rice disc type sows performance parameter accurate detecting method Download PDFInfo
- Publication number
- CN108037123A CN108037123A CN201710942178.1A CN201710942178A CN108037123A CN 108037123 A CN108037123 A CN 108037123A CN 201710942178 A CN201710942178 A CN 201710942178A CN 108037123 A CN108037123 A CN 108037123A
- Authority
- CN
- China
- Prior art keywords
- image
- disc type
- seed
- seedling
- performance parameter
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Pretreatment Of Seeds And Plants (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of hybrid paddy rice disc type to sow performance parameter accurate detecting method, the method is used in the intelligent constant seeding detection system developed containing (SuSE) Linux OS and open-source cross-platform vision storehouse OPENCV, realize that disc type in hybrid paddy rice seedling planting, is sowed performance parameter to it and accurately detected.It includes：Seed pelleting pre-processes, seedling disk seeding operation, and the collection of seedling disk original image, drawing of seeds picture processing, the processing of disc type grid image, finally extracts characteristic parameter, establish Stochastic Decision-making forest algorithm, and sowing performance parameter is accurately detected.The method realizes the accurate detection to hybrid paddy rice disc type seedling planting performance parameter, and detection result is good, and speed is fast, and arithmetic accuracy is high, while has established Research foundation for the follow-up amount of broadcasting Optimum Regulation, constant sowing.
Description
Technical field
The invention belongs to agriculture intelligent measurement, is specially a kind of hybrid paddy rice disc type sowing performance parameter Precision measurement side
Method.
Background technology
China's hybrid paddy rice cultivated area accounts for the 50% of the Rice Cropping gross area, about 15,000,000 hectares.Hybrid paddy rice is because with super
Strong tillering ability, can increase number of productive ear, according to this growth characteristics of hybrid paddy rice, usually require that Low seeding rate, bunch planting is accurate
During seedling, it is ensured that 2-3/cave.Because being needed before seedling operation to being sowed after presprouting of seeds, seed bud length, seed during sowing
Inconsistent change can all occur for water content and seed sizes, influence to sow performance.Therefore, it is necessary to alms bowl in seeding process
The amount of broadcasting in the every cave of body disc is accurately detected, and finds the change of sowing state in time, is carried subsequently to regulate and control the amount of broadcasting or reseeding work
For foundation, to ensure that the seed number on seedling disk per cave is consistent substantially, reach intelligent constant precise sowing job requirements.
In American-European countries, the researchs such as many scholars are split and counted to the cereal of adhesion.Canadian ZHANG G etc.
The cereal of the method segmentation adhesion of people's ellipse fitting and counting.Above-mentioned segmentation and counting algorithm research to adhesion cereal only limits
In the low cereal of adhesion degree, when overlapping or adhesion degree complexity situation occurs in cereal, arithmetic accuracy is not high.Domestic neat dragon
Et al. using machine vision and virtual technology realize super rice seedlings circle or whirl in the air cave, simple grain, more than double grains 3 kinds of situations on-line checking；
Wang Chen magnitudes people detects the Seeding Quantity in seedling disk seedling cave in terms of image procossing using area-method and fractional spins,
It is higher to hole and single seed detection efficiency；Tan Sui is beautiful et al. to propose a kind of super hybridized rice connection based on pattern classifier
Region application rate method for identifying and classifying, to selecting different characteristic value combinations and structure BP neural network as seed rice connected region
Application rate mode discriminator, for traditional gray average, area-method or ellipse fitting method to there are overlapping, intersection, adhesion paddy
The granule number accuracy of detection of thing is low, and multi-feature extraction and feature Optimization Analysis are carried out to connected region, to connected region for crack rice/
Impurity, 1,2,3,6 kinds of situations of 4 and more than 5 classification is identified, realize the accurate of super hybridized rice application rate
Detection.Ma Xu et al. propose it is a kind of improve fractional spins and improve SUSAN operators realize adhesion hybrid paddy rice segmentation and
Automatic detection is counted, improved SUSAN operators are based on adaptive template radius of circle, can effectively detect super hybridized rice connected region
The angle point of domain profile.Dong Wen is great et al. to combine high-efficient automatic seedling production line actual condition, according to " closed loop feedback control "
Thought designs, and have developed a kind of seeding tray seeding raising intelligent constant precision seed metering device, real-time ensuring application rate reaches in constant range
To the purpose of intelligent constant precise sowing.
At present for seedling disk sowing performance detection technology mainly for seedling circle or whirl in the air cave and monoseeding amount detection result it is preferable,
But when adhesion, overlapping cases occurs in seed, detection result is poor, and detection seed amount species is simple, is examined when application rate increases
Precision is surveyed drastically to decline；Next detection device and method are chiefly used in blanket seedling disk and (are accurately examined for disc type sowing performance at present
There are problem, the gray value of bed soil and seed in disc type approaches, can not better extract when carrying out image processing and analyzing for survey
Go out the binary image of seed；And when carrying out Image Acquisition to the grid of disc type, there are serious reflective phenomenon, be not easy to from
Seedling flaking lattice are isolated in image), rarely have research in terms of research is accurately detected to the amount of broadcasting of bowl hole tray.
To sum up, to realize to the amount of the broadcasting Precision measurement on seedling planting production line during bowl plate seedling raising, now there is an urgent need for develop
The bowl hole tray accurate detecting method that a kind of arithmetic accuracy is high, detection result is good, for the follow-up amount of broadcasting control, optimization, constant is broadcast
Kind lays the foundation.
The content of the invention
In view of the shortcomings of the prior art, the object of the present invention is to provide a kind of hybrid paddy rice disc type sowing performance parameter is accurate
Detection method, this method realize the accurate detection to hybrid paddy rice disc type seedling planting performance parameter, and speed is fast, arithmetic accuracy
Height, detection result is good, while has established Research foundation for the follow-up amount of broadcasting Optimum Regulation, constant sowing.
The present invention relates to a kind of hybrid paddy rice disc type to sow performance parameter accurate detecting method, which is used to grasp containing Linux
Make system, among the intelligent constant seeding detection system that open-source cross-platform vision storehouse OPENCV is developed；Realize disc type miscellaneous
When handing over rice seedling planting, performance parameter is sowed to it and is accurately detected.Specifically include the pretreatment of (1) seed pelleting；(2) seedling disk
Seeding operation；(3) seedling disk original image gathers；(4) drawing of seeds picture is handled, and in particular to color of image space is changed, drawing of seeds
As gray scale, binaryzation, dilation erosion computing, obtains image connectivity region；
(5) disc type grid image is handled, and in particular to color of image space is changed, grid image gray scale, binaryzation, profit
With sciagraphy will often go on binary image, the pixel of each column is added, ranks pixel and peak point are calculated, draws transverse and longitudinal grid
Line, preferred orientation detection zone or seedling cave；(6) extract characteristic parameter, establish Stochastic Decision-making forest algorithm, finally to disc type
Sowing performance parameter is precisely detected.
The collection of the image of above-mentioned seedling disk and seed, analyzing and processing are that the automation of amount detection systems is being broadcast containing intelligent constant
Completed on seedling production line.After the detecting system is installed on seedling assembly line upper berth bed soil device and precision seed metering device
Side, wherein detecting system include the image capture module containing high-definition camera, image processing and analyzing module.During work, paving soil, broadcast
Seedling disk after kind broadcasts amount detection systems by intelligent constant, and high-definition camera carries out Image Acquisition operation, image processing and analyzing mould
Block handles the image collected.
Step (4) in the claims 1 is more particularly to drawing of seeds picture processing：S1 after) collecting germinative seed image,
Color space conversion is carried out to image.RGB image is converted to hsv color space, sets S, V component threshold value, original to collecting
Image carries out data analysis filtering, and the image of seed is isolated from original image；S2) upper step is isolated the image of seed into
Row gray scale, binaryzation, dilation erosion shape filtering calculation process, filter the noise spot on non-seed image, finally obtain seed
Binary image；S3 boundary scan) is carried out to seed binary image, obtains seed connected region.
Step (5) in the claims 1 is more particularly to the processing of disc type grid image：S1 it is) former to seedling in earthen bowl grid
Beginning image carries out color space conversion.The RGB image collected is converted into Lab color spaces, threshold is set only for b components
Value, carries out data analysis filtering to original image, isolates the grid image in disc type kind cave；S2) the alms bowl for extracting upper step
Body seedling grid image carries out gray scale, binaryzation, and dilation erosion shape filtering calculation process, filters the noise spot of non-grid image,
Finally obtain grid binary image；S3) each row and column pixel on binary image is added using sciagraphy, calculates row, column
Pixel and peak point, draw transverse and longitudinal grid lines, preferred orientation detection zone and seedling cave.
Step (6) in the claims 1 is more particularly to extracting characteristic parameter, establishing Stochastic Decision-making forest algorithm, most
Sowing effect is precisely tested and analyzed eventually.S1 detection and localization region and seedling are preferably gone out described in (S3)) according to claim 4
Cave, you can be syncopated as the connected region image of seed；S2 the feature of the connected region in the sectioning image after each cutting) is obtained
Parameter；The random forest tree established when S3) according to sample learning is predicted characteristic parameter, draws in each sectioning image
Seed amount；S4) can statistical separate out seed amount in each section, the seed total amount and its hole rate of all sections.
(S3) in the claims 5 is more particularly to area, not girth, the bending moment to the seed connected region got
Feature extraction is carried out etc. parameter.Wherein bending moment does not characterize the geometric properties of image-region mainly, has rotation, translation, scale
Consistency.The feature that bending moment can be unimportant as one is based on face to represent object using the moment ratio of border sequence
Long-pending square can obtain the misclassification of low probability, reduce calculation amount.
(S3) in the claims 4 is specifically related to sciagraphy, preferably goes out detection and localization region and seedling cave.It is wherein described
Sciagraphy be：Disc type grid binary image edge is both horizontally and vertically projected respectively, vertical direction and level side
To having a series of wave crest and trough, corresponding row and column disc type grid pixel quantity is each represented.
For the amount of the broadcasting precision detecting system on supporting automation seedling production line during bowl plate seedling raising, the hybrid rice seed
It need to carry out seed pelleting pretreatment.Sticker or film forming agent are specially utilized, by fungicide, insecticide, micro- fertilizer, plant growth tune
The components such as section agent are wrapped in outside seed.
The present invention has following beneficial effect compared with prior art：
(1) after collecting germinative seed image, color space conversion is carried out to image.RGB image is converted to hsv color sky
Between, S, V component threshold value are set, data analysis filtering is carried out to collecting original image, is preferably isolated from original image
The image of seed；
(2) color space conversion is carried out to seedling in earthen bowl grid original image.The RGB image collected is converted into Lab face
The colour space, threshold value is set only for b components, is carried out data analysis filtering to original image, is preferably isolated disc type kind cave
Grid image；
(3) using sciagraphy will often go on the binary image of disc type grid, the pixel of each column is added, row, column is obtained
Pixel and peak point, draw transverse and longitudinal grid lines, preferred orientation detection zone and seedling cave.The detection method can be realized to seedling planting
The amount of broadcasting Precision measurement on production line during bowl plate seedling raising, its arithmetic accuracy is high, detection result is good, for the follow-up amount of broadcasting control,
Optimization, constant sowing lay the foundation.
Brief description of the drawings
Fig. 1 sows performance parameter accurate detecting method fundamental diagram for a kind of hybrid paddy rice disc type.
Fig. 2 is sample learning process principle figure after the drawing of seeds picture of the present invention gathers.
Fig. 3 is the disc type original image containing seed that the present invention gathers.
Fig. 4 is the drawing of seeds picture of the invention through color space conversion.
Fig. 5 is seed binary image of the present invention.
Fig. 6 is that seed binary image of the present invention carries out dilation erosion computing.
Fig. 7 is the disc type grid image of the invention through color space conversion.
Fig. 8 is disc type grid binary image of the present invention.
Row peak value figure after the often row pixel summation of Fig. 9 disc type grid binary images of the present invention.
Row peak value figure after Figure 10 disc type grid binary image each column pixel summations of the present invention.
The seed connected region image of Figure 11 present invention is according to grid lines cutting schematic diagram.
The small table images of seed connected region after the cutting of Figure 12 present invention.
Embodiment
It is clear in order to be more clearly understood that the object of the invention, technical solution and advantage, with reference to the accompanying drawings and embodiments to this
Invention is described in further details.It should be appreciated that instantiation described herein is only used for explaining the present invention, rather than limit
The fixed present invention.
The collection of the image of seedling disk and seed, analyzing and processing are that the automation seedling of amount detection systems is being broadcast containing intelligent constant
Completed on production line.The detecting system is installed on the rear of seedling assembly line upper berth bed soil device and precision seed metering device, its
Middle detecting system includes the image capture module containing high-definition camera, image processing and analyzing module.During work, paving soil, after planting
Seedling disk broadcast amount detection systems by intelligent constant, high-definition camera carries out Image Acquisition operation, image processing and analyzing module pair
The image collected is handled.The preferred Agriculture In South China of precision seed metering device of amount detection systems is broadcast in the present invention containing intelligent constant
The 2SJB-500 type raising rice seedlings precision seeding system of university's Development and design carries out operation, and seedling disk is using current most common length
× wide × a height of 585mm × 285mm × 22mm, cavities number (mould seedling for the soft modeling seedling disk of pot-grown rice seedling in 406 caves containing embedded software
Disk composite pallet).
Before Image Acquisition, adjust the height of high-definition camera, adjust 500 disks of the operating rate/h, i.e. 7.2s/ of production line
Disk, adjusts seedling disk both sides limiting plate on production line, when detection seedling disk reaches shooting area, computer control camera is shot per 3s
Image, each seedling disk gather 2 width images, overlapping shooting area are not present between image.In addition, also need the sky of adjustment detecting system
Between uniform intensity degree, select uniform color hybrid paddy rice be conducive to extract overall shape connected region, improve Detection accuracy.
Preferably, it is the amount of the broadcasting precision detecting system on supporting automation seedling production line during bowl plate seedling raising, it is described
Hybrid rice seed need to carry out seed pelleting pretreatment.Sticker or film forming agent are specially utilized, by fungicide, insecticide, micro- fertilizer, plant
The components such as thing growth regulator are wrapped in outside seed.After causing seed pelleting to handle, it is obvious poor to exist with bed soil background color
Different, this specific embodiment is handled seed using red seed coat agent.
With reference to shown in Fig. 1 and 2, which is used to contain (SuSE) Linux OS, and open-source cross-platform vision storehouse OPENCV is developed
Among intelligent constant seeding detection system；Disc type is realized in seedling planting, performance parameter is sowed to it and is accurately detected.
Specifically include the pretreatment of (1) seed pelleting；(2) seedling disk seeding operation；(3) seedling disk original image gathers；(4) at drawing of seeds picture
Reason, and in particular to color of image space is changed, drawing of seeds picture gray scale, binaryzation, dilation erosion computing, obtains image connectivity area
Domain；(5) disc type grid image is handled, and in particular to color of image space is changed, and grid image gray scale, binaryzation, utilize throwing
Shadow method will often go on binary image, the pixel of each column is added, and is calculated ranks pixel and peak point, is drawn transverse and longitudinal grid lines, excellent
Selected position detection zone or seedling cave；(6) extract characteristic parameter, establish Stochastic Decision-making forest algorithm, finally to the sowing of disc type
Performance parameter is precisely detected.
With reference to shown in Fig. 2-6, drawing of seeds picture processing procedure.S1 after) collecting germinative seed image, color is carried out to image
Change in space.RGB image is converted to hsv color space, sets S, V component threshold value, and data point are carried out to collecting original image
Analysis filtering, isolates the image of seed from original image；S2) image that upper step is isolated to seed carries out gray scale, binaryzation,
Dilation erosion shape filtering calculation process, filters the noise spot on non-seed image, finally obtains the binary image of seed；
S3 boundary scan) is carried out to seed binary image, obtains seed connected region.
With reference to shown in Fig. 7-10, the processing of disc type grid image.S1 color space) is carried out to seedling in earthen bowl grid original image
Conversion.The RGB image collected is converted into Lab color spaces, threshold value is set only for b components, to original image into line number
Filtered according to analysis, isolate the grid image in disc type kind cave；S2) the seedling in earthen bowl grid image for extracting upper step carries out ash
Degree, binaryzation, dilation erosion shape filtering calculation process, filters the noise spot of non-grid image, finally obtains grid binaryzation
Image；S3) each row and column pixel on binary image is added using sciagraphy, row, column pixel and peak point is calculated, draws horizontal stroke
Vertical grid lines, preferred orientation detection zone and seedling cave.
Preferably, it is detection zone that the present embodiment, which chooses the cave of 9 caves × 13 in shooting area,.The wherein described sciagraphy is pair
Disc type grid binary image both vertically and horizontally has a series of along both horizontally and vertically projecting respectively
Wave crest and trough, each represent corresponding row and column disc type grid pixel quantity.
With reference to shown in Figure 11,12, extraction characteristic parameter, establish Stochastic Decision-making forest algorithm, finally accurate to sowing effect
The process of detection and analysis.S1) detection and localization region or seedling cave are preferably gone out according to upper step, you can be syncopated as the connection of seed
Area image；Preferably, the drawing of seeds picture of complete meshing is retained, the imperfect meshing in edge is given up, do not handled.S2)
Obtain the characteristic parameter of the connected region in the sectioning image after each cutting；Preferably, and in particular to the seed got
The area of connected region, girth, the parameter such as bending moment progress feature extraction.Wherein bending moment does not characterize the several of image-region mainly
What feature, has rotation, translation, the consistency of scale.Feature that bending moment can be unimportant as one represents object, and
The misclassification of low probability can be obtained using square of the moment ratio based on area of border sequence, reduces calculation amount.The present invention's is constant
Square data can be the view data after original image, diminution half, horizontal inversion, 45 ° of rotation.Built when S3) according to sample learning
Vertical random forest tree is predicted characteristic parameter, draws the seed amount in each sectioning image；S4) specifically can statistical
Separate out the seed amount in each section, the seed total amount of all sections and its hole rate etc. and sow performance parameter；By to more
Drawing of seeds picture in a disc type after planting is analyzed, and can get overall sowing performance parameter.
It is above-mentioned for the preferable embodiment of the present invention, but embodiments of the present invention and from the limitation of the above, its
His any Spirit Essence without departing from the present invention with made under principle change, modification, replacement, combine, simplification, should be
The substitute mode of effect, is included within protection scope of the present invention.
Claims (8)
1. a kind of hybrid paddy rice disc type sows performance parameter accurate detecting method, this method is used for containing (SuSE) Linux OS and opens
In the intelligent constant seeding detection system that the cross-platform vision storehouse OPENCV in source is developed, realize disc type in hybrid paddy rice seedling planting
When, performance parameter is sowed to it and is precisely detected.It is characterized in that, it the described method comprises the following steps：
(1) seed pelleting pre-processes；
(2) seedling disk seeding operation；
(3) seedling disk original image gathers, including drawing of seeds picture collection and the collection of disc type grid image；
(4) drawing of seeds picture gathered is handled, and in particular to the conversion of color of image space, drawing of seeds picture gray scale and two-value
Change, dilation erosion computing and acquisition image connectivity region；
(5) the disc type grid image gathered is handled, and in particular to the conversion of color of image space, grid image gray scale
And binaryzation, using sciagraphy will on binary image often the pixel of row and each column be added, calculate ranks pixel and peak point,
Go out transverse and longitudinal grid lines and preferred orientation detection zone or seedling cave；
(6) extract and characteristic parameter and establish Stochastic Decision-making forest algorithm, finally the sowing performance parameter to hybrid paddy rice disc type into
Row precisely detection.
A kind of 2. hybrid paddy rice disc type sowing performance parameter accurate detecting method according to claim 1, it is characterised in that：
The collection of the image of above-mentioned seedling disk and seed and analyzing and processing are that the automation seedling of amount detection systems is being broadcast containing intelligent constant
Completed on production line, which is installed on the rear of seedling assembly line upper berth bed soil device and precision seed metering device, its
Middle detecting system includes image capture module and image processing and analyzing module containing high-definition camera, pawnshop soil and after planting
When seedling disk broadcasts amount detection systems by intelligent constant, Image Acquisition operation is carried out by high-definition camera and sends image procossing point to
Analysis module handles the image collected.
3. a kind of hybrid paddy rice disc type sowing performance parameter accurate detecting method according to claim 1 and 2, its feature exist
In：Step (4) in the claims 1 is more particularly to drawing of seeds picture processing：
S1 after) collecting germinative seed image, color space conversion is carried out to image.RGB image is converted to hsv color space,
S, V component threshold value are set, data analysis filtering is carried out to collecting original image, the figure of seed is isolated from original image
Picture；
S2) image that upper step is isolated to seed carries out gray scale, binaryzation, and dilation erosion shape filtering calculation process, filters non-
Noise spot in drawing of seeds picture, finally obtains the binary image of seed；
S3 boundary scan) is carried out to seed binary image, obtains seed connected region.
4. a kind of hybrid paddy rice disc type sowing performance parameter accurate detecting method according to claim 1 or 2, its feature exist
In：Step (5) in the claims 1 is more particularly to the processing of disc type grid image：
S1 color space conversion) is carried out to seedling in earthen bowl grid original image, the RGB image collected is converted into Lab colors sky
Between, threshold value is set only for b components, data analysis filtering is carried out to original image, isolates the grid image in disc type kind cave；
S2) the seedling in earthen bowl grid image for extracting upper step carries out gray scale and binaryzation, then carries out dilation erosion form filter
Ripple calculation process, filters the noise spot of non-grid image, finally obtains grid binary image；
S3) each row and column pixel on binary image is added using sciagraphy, row and row pixel and peak point is calculated, draws
Transverse and longitudinal grid lines, preferred orientation detection zone and seedling cave.
A kind of 5. hybrid paddy rice disc type sowing performance parameter accurate detecting method according to claim 4, it is characterised in that：
Characteristic parameter is extracted in step (6) in the claims 1, establishes Stochastic Decision-making forest algorithm, finally to sowing effect essence
Quasi- detection and analysis specifically include：
S1) according to the detection and localization region preferably gone out and seedling cave, it is syncopated as the connected region image of seed；
S2 the characteristic parameter of the connected region in the sectioning image after each cutting) is obtained；
The random forest tree established when S3) according to sample learning is predicted characteristic parameter, draws in each sectioning image
Seed amount；
S4) can statistical separate out seed amount in each section, the seed total amount and its hole rate of all sections.
6. a kind of hybrid paddy rice disc type sowing performance parameter accurate detecting method according to claim 5, it is special
Sign is：The acquisition seed connected region specifically includes the area to connected region, girth, the parameter such as bending moment does not carry out feature
Extraction, the not bending moment are used for the geometric properties for characterizing image-region, have rotation, translation, the consistency of scale, bending moment can not
To represent object as an important feature, and using border sequence square of the moment ratio based on area can obtain it is relatively low general
The misclassification of rate, reduces calculation amount.
7. a kind of hybrid paddy rice disc type sowing performance parameter accurate detecting method according to claim 4, it is special
Sign is：The sciagraphy is that disc type grid binary image edge is both horizontally and vertically projected respectively, Vertical Square
To having a series of wave crest and trough with horizontal direction, corresponding row and column disc type grid pixel quantity is each represented.
A kind of 8. hybrid paddy rice disc type sowing performance parameter accurate detecting method according to claim 1, it is characterised in that：
For the amount of the broadcasting precision detecting system on supporting automation seedling production line during bowl plate seedling raising, the hybrid rice seed need to be planted
Attached bag clothing pre-processes.Specially utilize sticker or film forming agent, by fungicide, insecticide, micro- fertilizer, plant growth regulator etc. into
Subpackage is rolled in outside seed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710942178.1A CN108037123B (en) | 2017-10-11 | 2017-10-11 | Precision detection method for sowing performance parameters of hybrid rice bowl body tray |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710942178.1A CN108037123B (en) | 2017-10-11 | 2017-10-11 | Precision detection method for sowing performance parameters of hybrid rice bowl body tray |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108037123A true CN108037123A (en) | 2018-05-15 |
| CN108037123B CN108037123B (en) | 2020-06-19 |
Family
ID=62093335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710942178.1A Active CN108037123B (en) | 2017-10-11 | 2017-10-11 | Precision detection method for sowing performance parameters of hybrid rice bowl body tray |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108037123B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110495355A (en) * | 2019-09-24 | 2019-11-26 | 安徽省农业科学院作物研究所 | A kind of Xinjiang region sesame under-film drip irrigation water-fertilizer integral cultural method |
| CN111932551A (en) * | 2020-07-10 | 2020-11-13 | 华南农业大学 | Missing transplanting rate detection method of rice transplanter |
| CN112907516A (en) * | 2021-01-27 | 2021-06-04 | 山东省计算中心（国家超级计算济南中心） | Sweet corn seed identification method and device for plug seedling |
| CN114818883A (en) * | 2022-04-07 | 2022-07-29 | 中国民用航空飞行学院 | CART decision tree fire image identification method based on optimal combination of color features |
| CN116267326A (en) * | 2023-02-22 | 2023-06-23 | 华南农业大学 | Intelligent seedling tray seeding rate regulating and controlling device and method for rice seedling raising production line |
-
2017
- 2017-10-11 CN CN201710942178.1A patent/CN108037123B/en active Active
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110495355A (en) * | 2019-09-24 | 2019-11-26 | 安徽省农业科学院作物研究所 | A kind of Xinjiang region sesame under-film drip irrigation water-fertilizer integral cultural method |
| CN111932551A (en) * | 2020-07-10 | 2020-11-13 | 华南农业大学 | Missing transplanting rate detection method of rice transplanter |
| CN111932551B (en) * | 2020-07-10 | 2023-06-23 | 华南农业大学 | Missing transplanting rate detection method of rice transplanter |
| CN112907516A (en) * | 2021-01-27 | 2021-06-04 | 山东省计算中心（国家超级计算济南中心） | Sweet corn seed identification method and device for plug seedling |
| CN112907516B (en) * | 2021-01-27 | 2022-08-02 | 山东省计算中心（国家超级计算济南中心） | Sweet corn seed identification method and device for plug seedling |
| CN114818883A (en) * | 2022-04-07 | 2022-07-29 | 中国民用航空飞行学院 | CART decision tree fire image identification method based on optimal combination of color features |
| CN116267326A (en) * | 2023-02-22 | 2023-06-23 | 华南农业大学 | Intelligent seedling tray seeding rate regulating and controlling device and method for rice seedling raising production line |
| CN116267326B (en) * | 2023-02-22 | 2024-05-28 | 华南农业大学 | Intelligent seedling tray seeding rate regulating and controlling device and method for rice seedling raising production line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108037123B (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037123A (en) | A kind of hybrid paddy rice disc type sows performance parameter accurate detecting method | |
| CN108985260B (en) | Remote sensing and meteorological integrated rice yield estimation method | |
| CN100416590C (en) | Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic | |
| Sun et al. | Image processing algorithms for infield single cotton boll counting and yield prediction | |
| CN105740759B (en) | Semilate rice information decision tree classification approach based on feature extraction in multi-temporal data | |
| CN110163138B (en) | Method for measuring and calculating wheat tillering density based on multispectral remote sensing image of unmanned aerial vehicle | |
| CN106355143A (en) | Seed maize field identification method and system based on multi-source and multi-temporal high resolution remote sensing data | |
| Li et al. | Prediction of plant transpiration from environmental parameters and relative leaf area index using the random forest regression algorithm | |
| CN102524024A (en) | Crop irrigation system based on computer vision | |
| CN114818909B (en) | Weed detection method and device based on crop growth characteristics | |
| CN102663397B (en) | Automatic detection method of wheat seedling emergence | |
| CN107316116A (en) | A kind of leafy vegetable production prediction method | |
| Ma et al. | Automatic detection of crop root rows in paddy fields based on straight-line clustering algorithm and supervised learning method | |
| Chang et al. | Quantifying muskmelon fruit attributes with A-TEP-based model and machine vision measurement | |
| CN105844632A (en) | Rice plant identification and positioning method based on machine visual sense | |
| CN108323389A (en) | The detection method and device of the rice transplanting rice shoot spacing in the rows and cave rice shoot number of rice transplanter | |
| CN106846334A (en) | Field corn plant recognition methods based on Support Vector data description | |
| CN114694047A (en) | Corn sowing quality evaluation method and device | |
| CN102663396B (en) | Method for automatically detecting rice milky ripe stage | |
| CN113221806A (en) | Cloud platform fusion multi-source satellite image and tea tree phenological period based automatic tea garden identification method | |
| CN102339378A (en) | Method and device for automatically extracting cotton seeds | |
| CN102592118A (en) | Automatic detection method for time emergence of seedling of corns | |
| CN102360428B (en) | Automatic detection methods for trefoil stage and seven-leaf stage of corn | |
| CN110598514A (en) | Method for monitoring plot scale crop seeding area of land reclamation project area | |
| Zhang et al. | Application of computer vision technology in agricultural field |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |