CN107527066A - One kind is based on Embedded hybrid paddy rice sowing performance detecting system and detection method - Google Patents
One kind is based on Embedded hybrid paddy rice sowing performance detecting system and detection method Download PDFInfo
- Publication number
- CN107527066A CN107527066A CN201710617095.5A CN201710617095A CN107527066A CN 107527066 A CN107527066 A CN 107527066A CN 201710617095 A CN201710617095 A CN 201710617095A CN 107527066 A CN107527066 A CN 107527066A
- Authority
- CN
- China
- Prior art keywords
- control module
- module
- image
- sowing
- micro
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- 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
- 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
- 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
Abstract
The present invention discloses a kind of based on Embedded hybrid paddy rice sowing performance detecting system, including image capture module, micro-system kernel control module, sowing performance regulation and control module, input module and display module.Invention additionally discloses a kind of detection method of use based on Embedded hybrid paddy rice sowing performance detecting system, this method carries out IMAQ by image capture module to sowing seedling disk, after performance data carries out gray scale, binaryzation, dilation erosion calculation process by micro-system kernel control module, get connected region in image and extract the characteristic parameter in region, eventually through Stochastic Decision-making forest algorithm to even kind of efficacy parameter precisely detect and analyze for kind of amount in seedling disk, and it is sent to sowing performance regulation and control module and is handled.Compared with prior art, technical solution of the present invention can dynamic detection sowing performance parameter, according to the performance change and specifying information detected, form corresponding application rate regulation and control feedback signal, constant control application rate.
Description
Technical field
The present invention relates to agricultural production detection technique field, and in particular to one kind is based on Embedded hybrid paddy rice sowing performance
Detecting system and detection method.
Background technology
China's hybrid paddy rice cultivated area accounts for Monitoring of Paddy Rice Plant Area 55%, about 15,000,000 hectares.In the prior art, rice
Seedling planting equipment is primarily adapted for use in the big amount of the broadcasting bunch planting of conventional Rice and broadcasted sowing, and is not suitable for hybrid paddy rice.Hybrid paddy rice has superpower
Tillering ability, number of productive ear can be increased, according to this growth characteristics of hybrid paddy rice, usually require that low application rate, accurate seedling, simultaneously
Ensure 2-3 grains/cave.Because rice paddy seed is sowed after wanting vernalization, seed bud length, seed moisture content and kind during sowing
Sub- size, which changes, can all influence to sow performance.And seeding technique and means are difficult to reach above-mentioned requirements at present, therefore have very much
Necessity is precisely detected in seeding process to the application rate in the cave in each seedling disk, with the change of timely discovery sowing state
Change, foundation is provided subsequently to regulate and control application rate or reseeding work, it is real to ensure that the seed number of the single cave on seedling disk is consistent
Now intelligent constant precise sowing operation.
In the prior art, the hybrid paddy rice sowing seedling performance intelligent checking system based on machine vision, which has been developed, designs
Come, but this type system is because system volume itself is larger, power consumption is high, executing efficiency is low, it is impossible to meet efficiently automatic
Change the requirement of rice industrial sowing seedling production line on-line checking performance, such system can not be integrated in sowing and educate in addition
On seedling production line, a subsystem is become, to cooperate with rice industrial sowing seedling production line work.
Therefore, a kind of small volume of exploitation is now needed badly, low in energy consumption, executing efficiency is high, is easily integrated in rice factory
Change the sowing performance detection regulating system on sowing seedling production line, to realize that the seeding quality to production line carries out on-line checking
And sowing mechanism is controlled according to testing result, sowing performance is optimized and constant precise sowing.
The content of the invention
The main object of the present invention is to propose one kind based on Embedded hybrid paddy rice sowing performance detecting system, and the present invention is also
It is proposed a kind of detection method of use based on Embedded hybrid paddy rice sowing performance detecting system, it is intended to which sowing performance detection is adjusted
Section system optimizes design, and constant precise sowing is carried out to sow performance detection regulating system.
To achieve the above object, the present invention proposes a kind of based on Embedded hybrid paddy rice sowing performance detecting system, described
Detecting system includes being used to gather the image capture module of view data, the micro-system core for analyzing and processing view data
Control module, the sowing performance for kind of amount and even kind of Properties Control to after planting seedling disk regulate and control module, the sowing performance
Regulate and control the input module of module input setup parameter and show the display module of result;Described image acquisition module with it is described micro-
System core control module is connected, and the micro-system kernel control module is connected with the sowing performance regulation and control module, described to broadcast
Kind of performance regulation and control module also be connected with the input module and the display module respectively, the detecting system for based on
(SuSE) Linux OS carries out the embedded system of open-source cross-platform computer vision storehouse Opencv technological development design.
Preferably, described image acquisition module is high-definition camera, and the micro-system kernel control module includes being integrated in
Embedded microprocessor MCU on circuit board, with the embedded microprocessor MCU data being connected and program storage device
Flash and running memory SDRAM, the sowing performance regulation and control module is STM32F10X circuit boards, and the input module is key
Disk, the display module are LED digital display screens;The high-definition camera passes through USB interface and the embedded microprocessor
MCU is connected, and the embedded microprocessor MCU is connected by DB9 serial line interfaces with STM32F10X circuit boards, described
STM32F10X circuit boards are connected by I/O interfaces with the keyboard and the LED digital display screens.
Preferably, the parameter of the input module input includes the change of average grain weight, the qualification rate in cave, hole rate, cave
Different coefficient.
The present invention also proposes the detection method based on Embedded hybrid paddy rice sowing performance detecting system described in a kind of use,
Comprise the following steps:
S1:Activation system, system is learnt and trained according to the image sample data gathered in advance, then in system
Portion establishes Stochastic Decision-making forest algorithm;
S2:Start image capture module, image capture module is to the seedling disk on the automatic seedling streamline of batch production after planting
Image data acquiring is carried out, the view data collected is sent to the micro-system core and controls mould by described image acquisition module
Block;
S3:The micro-system kernel control module carries out gray scale, binaryzation, dilation erosion processing to view data, obtains
The bianry image of drawing of seeds picture in current seedling disk;
S4:The micro-system kernel control module carries out boundary scan to the bianry image, obtains seed connected region
Image;
S5:The micro-system kernel control module filters to the small area connected region in connected region, by going
Except small area connected region, to remove the non-seed impurity little particle region in image, the connected region image of seed is obtained;
S6:The micro-system kernel control module is according to Stochastic Decision-making forest algorithm to the hybrid paddy rice in seedling disk for kind of an amount
With even kind of efficacy parameter precisely detect and analyze, and analysis result is sent to the sowing performance regulation and control module;
S7:The sowing performance regulation and control module shows sowing performance parameter by the display module, and is realized to be follow-up
Intelligentized regulating and controlling application rate is prepared.
Preferably, comprise the following steps in the step S6 for kind of an amount detection:
S611:The micro-system kernel control module predicts each individually connected region pair according to Stochastic Decision-making forest algorithm
The seed amount answered;
S612:By obtain each individually corresponding seed amount is added to obtain the total of seed in image in connected region
Number;
S613:Finally obtain in seedling disk for kind of an amount parameter, for kind of an amount parameter include average grain weight, the qualification rate in cave,
Hole rate, the coefficient of variation in cave;
Preferably, even kind of effect detection in the step S6 comprises the following steps:
S621:After obtaining seed connected region image, according to the size of seedling disk single cave area correspondence image pixel, to image
The mesh segmentation processing of 15 rows 20 row is carried out, obtains the small image of 300 single caves;
S622:The each grid image obtained for above-mentioned middle segmentation, utilizes random forests algorithm to predict each small trrellis diagram
Seed number as in, if seed number is 0, judge this cave for hole;
S623:The small lattice number that seed amount is 0 is added, obtains total hole number;Then with total hole number divided by always
Cave number, draw hole rate;
S624:Even kind of efficacy parameter specifically includes the contrast ratio of seedling disk both sides cave qualification rate, the coefficient of variation in cave.
Technical solution of the present invention propose one kind be based on Embedded hybrid paddy rice sowing performance detecting system have small volume,
Low in energy consumption, the advantages that program implementation rate is high, the sowing performance inspection being easily integrated on rice industrial sowing seedling production line
Examining system.A kind of use that technical solution of the present invention also proposes simultaneously is based on Embedded hybrid paddy rice sowing performance detecting system
Detection method, can dynamic on-line monitoring continuous conveying sowing seedling disk, realize the Precision measurement to application rate in each seedling disk.Inspection
After surveying imaging, system can count sowing performance parameter, according to the change of the sowing performance detected and specifying information, be formed corresponding
Application rate regulation and control feedback signal, constant control application rate.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described.It should be evident that drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Structure according to these accompanying drawings obtains other accompanying drawings.
Fig. 1 is the structural representation that the present invention sows performance detecting system based on Embedded hybrid paddy rice;
Fig. 2 is the overhaul flow chart that the present invention sows performance detecting system based on Embedded hybrid paddy rice;
Fig. 3 is the binary picture of seedling disk image of the present invention;
Fig. 4 is that the present invention supplies kind of an amount detection image processing procedure based on Embedded hybrid paddy rice sowing performance detecting system
Figure;
Fig. 5 is the hole rate detection image processing procedure that the present invention sows performance detecting system based on Embedded hybrid paddy rice
Figure.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only the part of the embodiment of the present invention, rather than whole embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art obtained under the premise of creative work is not made it is all its
His embodiment, belongs to the scope of protection of the invention.
The present invention proposes a kind of based on Embedded hybrid paddy rice sowing performance detecting system.
Refer to Fig. 1, in embodiments of the present invention, based on Embedded hybrid paddy rice sowing performance detecting system be based on
The embedded system of (SuSE) Linux OS, and designed for the Opencv technological development of open-source cross-platform computer vision storehouse.Based on embedding
Enter the hybrid paddy rice sowing performance detecting system of formula including being used to gather the image capture module of view data, view data being carried out
The micro-system kernel control module of analyzing and processing, the sowing performance for kind of amount and even kind of Properties Control to after planting seedling disk are adjusted
Module is controlled, the input module of setup parameter is inputted to sowing performance regulation and control module and shows the display module of result;Image is adopted
Collection module is connected with micro-system kernel control module, and micro-system kernel control module is connected with sowing performance regulation and control module, is sowed
Performance regulation and control module is also connected with input module and display module respectively.
Specifically, in the embodiment of the present invention, image capture module is high-definition camera, and micro-system kernel control module includes
Be integrated in circuit upper plate embedded microprocessor MCU, with the embedded microprocessor MCU data being connected and program storage device
Flash and running memory SDRAM, sowing performance regulation and control module is STM32F10X circuit boards, and input module is keyboard, display
Module is LED digital display screens;High-definition camera is connected by USB interface with embedded microprocessor MCU, embedded microprocessor
Device MCU is connected by DB9 serial line interfaces with STM32F10X circuit boards, STM32F10X circuit boards by I/O interfaces and keyboard with
And LED digital display screens are connected.
In the embodiment of the present invention, the parameter of input module input includes average grain weight, the qualification rate in cave, hole rate, cave
The coefficient of variation.
Refer to Fig. 2, operation principle of the embodiment of the present invention based on Embedded hybrid paddy rice sowing performance detecting system:
During work, seedling disk after planting is by the embodiment of the present invention based on Embedded hybrid paddy rice sowing performance detection system
System, micro-system kernel control module control high-definition camera to carry out IMAQ, subsequent micro-system kernel control module to seedling disk
Gray scale, binaryzation, dilation erosion calculation process are carried out to the image collected, to obtain connected region and the company of extracting in image
Characteristic parameter in logical region, after getting corresponding characteristic parameter, according to Stochastic Decision-making forest algorithm to supplying kind in seedling disk
Amount with even kind of efficacy parameter precisely detect, analyzed, and obtains currently sowing performance data eventually through display on a display screen,
Sowing performance data is sent to sowing performance regulation and control module again, subsequently to realize that the Intelligentized regulating and controlling amount of broadcasting is prepared.
The present invention also proposes a kind of detection method of use based on Embedded hybrid paddy rice sowing performance detecting system, specifically
Comprise the following steps:
S1:Activation system, system is learnt and trained according to the image sample data gathered in advance, then in system
Portion establishes Stochastic Decision-making forest algorithm;
S2:Start image capture module, image capture module is to the seedling disk on the automatic seedling streamline of batch production after planting
Image data acquiring is carried out, image capture module sends the view data collected to micro-system kernel control module;
S3:Micro-system kernel control module carries out gray scale, binaryzation, dilation erosion processing to view data, obtains current
The bianry image of drawing of seeds picture in seedling disk;
S4:Micro-system kernel control module carries out boundary scan to bianry image, obtains seed connected region image;
S5:Micro-system kernel control module filters to the small area connected region in connected region, small by removing
Area connected region, to remove the non-seed impurity little particle region in image, obtain the connected region image of seed;
S6:Micro-system kernel control module is according to Stochastic Decision-making forest algorithm to hybrid paddy rice in seedling disk for kind of amount and even
Kind efficacy parameter precisely detect and analyze, and analysis result is sent to sowing performance and regulates and controls module;
S7:Sow performance regulation and control module and sowing performance parameter is shown by display module, and intelligent adjust is realized to be follow-up
Control application rate is prepared.
Comprise the following steps in wherein above-mentioned steps S6 for kind of an amount detection:
S611:Micro-system kernel control module is according to corresponding to each individually connected region of Stochastic Decision-making forest algorithm prediction
Seed amount;
S612:By obtain each individually corresponding seed amount is added to obtain the total of seed in image in connected region
Number;
S613:Finally obtain in seedling disk for kind of an amount parameter, for kind of an amount parameter include average grain weight, the qualification rate in cave,
Hole rate, the coefficient of variation in cave;
Even kind of effect detection in other above-mentioned steps S6 comprises the following steps:
S621:After obtaining seed connected region image, according to the size of seedling disk single cave area correspondence image pixel, to image
The mesh segmentation processing of 15 rows 20 row is carried out, obtains the small image of 300 single caves;
S622:The each grid image obtained for above-mentioned middle segmentation, each small lattice are predicted using random forests algorithm
Seed number in image, if seed number is 0, judge this cave for hole;
S623:The small lattice number that seed amount is 0 is added, obtains total hole number;Then with total hole number divided by always
Cave number, draw hole rate;
S624:Even kind of efficacy parameter specifically includes the contrast ratio of seedling disk both sides cave qualification rate, the coefficient of variation in cave.
Refer to Fig. 1 to Fig. 5, the detection based on Embedded hybrid paddy rice sowing performance detecting system of the embodiment of the present invention
The specific control process of method is:
After the sowing performance detecting system start of Embedded hybrid paddy rice, corresponding sowing performance requirement parameter is set,
The parameter of input includes average grain weight, the qualification rate in cave, hole rate, the coefficient of variation in cave, and start sowing performance detection and
Control, so as to establish Stochastic Decision-making forest in internal system.Micro-system kernel control module controls the high definition of image capture module
The seedling disk image of camera collection after planting, if the image collected is effective image, micro-system kernel control module will have
The image of effect carries out gradation conversion as after gray level image, micro-system kernel control module continues to handle gray level image and be converted to
Bianry image, bianry image is finally made the processing of dilation erosion shape filtering by micro-system kernel control module, to obtain in image
Connected region.
Micro-system kernel control module continues to extract the image features in connected region, to the facet in connected region
Product connected region is filtered, and by removing small area connected region, removes the non-seed impurity little particle region in image,
To obtain the connected region image of seed, corresponding seed amount in each connected region is then predicted according to decision forest, in advance
Seed amount corresponding to each connected region that prediction obtains then is added up after survey to obtain seed total amount in seedling disk.Pass through above-mentioned mistake
Journey, it can obtain in current seedling disk and measure a parameter for kind, average grain weight, cave qualification rate, hole rate are specifically included for kind of an amount parameter
And the coefficient of variation in cave.If be more than setting for kind of the deviation measured between preset value, need to adjust by sowing performance
Control module then continues follow-up work to being adjusted for kind of an amount after adjustment.
If be not more than setting for kind of the deviation measured between preset value, the connected region image of seed is subjected to net
Lattice are split, and according to the size of seedling disk single cave area correspondence image pixel, the mesh segmentation that 15 rows 20 row are carried out to image is handled, obtained
To the small image of 300 single caves, for splitting obtained each grid image, grid after decision forest algorithm prediction segmentation is utilized
Interior seed amount, if seed amount is 0, the cave is judged for hole, and the grid number that seed amount is 0 in cumulative grid
Amount, obtains total hole number, then using total hole number divided by total cave number, so that hole rate is calculated.Pass through above-mentioned stream
Journey, can obtain even kind of efficacy parameter in current seedling disk, and even kind of efficacy parameter specifically includes the contrast of seedling disk both sides cave qualification rate
Rate and the coefficient of variation in cave.If the deviation between hole rate and preset value is more than setting, by sowing performance
Module is adjusted to even kind amount, continues follow-up work after adjustment, if the deviation between hole rate and preset value is little
When setting, then judge whether to need halt system, the halt system if judged result is affirmative;If judged result is negative
Then continue through high-definition camera and image is gathered to seedling disk after planting.
Technical solution of the present invention propose one kind be based on Embedded hybrid paddy rice sowing performance detecting system have small volume,
Low in energy consumption, the advantages that program implementation rate is high, the sowing performance inspection being easily integrated on rice industrial sowing seedling production line
Examining system.A kind of and inspection of the use that technical solution of the present invention also proposes based on Embedded hybrid paddy rice sowing performance detecting system
Survey method, can dynamic on-line monitoring continuous conveying sowing seedling disk, realize the Precision measurement to application rate in each seedling disk.Detection
After imaging, system can count sowing performance parameter, according to the change of the sowing performance detected and specifying information, be formed corresponding
Application rate regulates and controls feedback signal, constant control application rate.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the scope of the invention, it is every at this
Under the design of invention, the equivalent structure transformation made using description of the invention and accompanying drawing content, or directly/it is used in indirectly
He is included in the scope of patent protection of the present invention related technical field.
Claims (6)
1. one kind is based on Embedded hybrid paddy rice sowing performance detecting system, it is characterised in that the detecting system includes being used for
Gather view data image capture module, view data is analyzed and processed micro-system kernel control module, to sowing
The sowing performance for kind of amount and even kind of Properties Control of seedling disk regulates and controls module, the sowing performance regulation and control module input setting afterwards
The input module of parameter and the display module for showing result;Described image acquisition module and the micro-system kernel control module
Connection, the micro-system kernel control module are connected with the sowing performance regulation and control module, and the sowing performance regulation and control module is also
It is connected respectively with the input module and the display module, the detecting system is to be opened based on (SuSE) Linux OS
The embedded system of source cross-platform computer vision library Opencv technological development design.
2. as claimed in claim 1 based on Embedded hybrid paddy rice sowing performance detecting system, it is characterised in that described image
Acquisition module is high-definition camera, and the micro-system kernel control module includes the embedded microprocessor being integrated on circuit board
MCU, with the embedded microprocessor MCU data being connected and program storage device Flash and running memory SDRAM, institute
It is STM32F10X circuit boards to state sowing performance regulation and control module, and the input module is keyboard, and the display module is LED digital
Display screen;The high-definition camera is connected by USB interface with the embedded microprocessor MCU, the embedded microprocessor
Device MCU is connected by DB9 serial line interfaces with STM32F10X circuit boards, and the STM32F10X circuit boards pass through I/O interfaces and institute
State keyboard and the LED digital display screens are connected.
3. as claimed in claim 1 based on Embedded hybrid paddy rice sowing performance detecting system, it is characterised in that the input
The parameter of module input includes average grain weight, the qualification rate in cave, hole rate, the coefficient of variation in cave.
4. a kind of detection method using as claimed in claim 1 based on Embedded hybrid paddy rice sowing performance detecting system, its
It is characterised by, comprises the following steps:
S1:Activation system, system are learnt and trained according to the image sample data gathered in advance, then built in internal system
Vertical Stochastic Decision-making forest algorithm;
S2:Start image capture module, image capture module is carried out to the seedling disk on the automatic seedling streamline of batch production after planting
Image data acquiring, described image acquisition module send the view data collected to the micro-system kernel control module;
S3:The micro-system kernel control module carries out gray scale, binaryzation, dilation erosion processing to view data, obtains current
The bianry image of drawing of seeds picture in seedling disk;
S4:The micro-system kernel control module carries out boundary scan to the bianry image, obtains seed connected region image;
S5:The micro-system kernel control module filters to the small area connected region in connected region, small by removing
Area connected region, to remove the non-seed impurity little particle region in image, obtain the connected region image of seed;
S6:The micro-system kernel control module is according to Stochastic Decision-making forest algorithm to the hybrid paddy rice in seedling disk for kind of amount and even
Kind efficacy parameter precisely detect and analyze, and analysis result is sent to the sowing performance and regulates and controls module;
S7:The sowing performance regulation and control module shows sowing performance parameter by the display module, and realizes intelligence to be follow-up
Change regulation and control application rate to prepare.
5. detection method as claimed in claim 4, it is characterised in that include following step for kind of an amount detection in the step S6
Suddenly:
S611:The micro-system kernel control module is according to corresponding to each individually connected region of Stochastic Decision-making forest algorithm prediction
Seed amount;
S612:Corresponding seed amount in obtained each independent connected region is added to obtain the sum of seed in image;
S613:Finally obtain in seedling disk and measure a parameter for kind, include average grain weight, the qualification rate in cave, hole for kind of an amount parameter
Rate, the coefficient of variation in cave.
6. detection method as claimed in claim 4, it is characterised in that even kind of effect detection in the step S6 includes as follows
Step:
S621:After obtaining seed connected region image, according to the size of seedling disk single cave area correspondence image pixel, image is carried out
The mesh segmentation processing of 15 rows 20 row, obtains the small image of 300 single caves;
S622:The each grid image obtained for above-mentioned middle segmentation, is predicted in each small table images using random forests algorithm
Seed number, if seed number be 0, judge this cave for hole;
S623:The small lattice number that seed amount is 0 is added, obtains total hole number;Then with total hole number divided by total cave
Number, draws hole rate;
S624:Even kind of efficacy parameter specifically includes the contrast ratio of seedling disk both sides cave qualification rate, the coefficient of variation in cave.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710617095.5A CN107527066A (en) | 2017-07-26 | 2017-07-26 | One kind is based on Embedded hybrid paddy rice sowing performance detecting system and detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710617095.5A CN107527066A (en) | 2017-07-26 | 2017-07-26 | One kind is based on Embedded hybrid paddy rice sowing performance detecting system and detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107527066A true CN107527066A (en) | 2017-12-29 |
Family
ID=60680271
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710617095.5A Pending CN107527066A (en) | 2017-07-26 | 2017-07-26 | One kind is based on Embedded hybrid paddy rice sowing performance detecting system and detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107527066A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108323389A (en) * | 2018-01-18 | 2018-07-27 | 华南农业大学 | The detection method and device of the rice transplanting rice shoot spacing in the rows and cave rice shoot number of rice transplanter |
CN108982136A (en) * | 2018-05-23 | 2018-12-11 | 安徽农业大学 | A kind of system and method for seed sowing device performance detection |
CN112102258A (en) * | 2020-08-28 | 2020-12-18 | 无锡卡尔曼导航技术有限公司 | Air-suction type seeder seeding detection method based on machine vision |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101358905A (en) * | 2008-09-08 | 2009-02-04 | 南京农业大学 | System for detecting sowing quality of rice seedling raising disk and application thereof for detecting |
US20130294656A1 (en) * | 2011-07-19 | 2013-11-07 | Ball Horticultural Company | Seed holding device and seed classification system with seed holding device |
CN104392430A (en) * | 2014-10-22 | 2015-03-04 | 华南农业大学 | Machine vision-based super hybrid rice bunch seeding quantity detection method and device |
-
2017
- 2017-07-26 CN CN201710617095.5A patent/CN107527066A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101358905A (en) * | 2008-09-08 | 2009-02-04 | 南京农业大学 | System for detecting sowing quality of rice seedling raising disk and application thereof for detecting |
US20130294656A1 (en) * | 2011-07-19 | 2013-11-07 | Ball Horticultural Company | Seed holding device and seed classification system with seed holding device |
CN104392430A (en) * | 2014-10-22 | 2015-03-04 | 华南农业大学 | Machine vision-based super hybrid rice bunch seeding quantity detection method and device |
Non-Patent Citations (1)
Title |
---|
谭穗妍等: "《基于嵌入式机器视觉的水稻秧盘育秧图像无线传输系统》", 《农业机械学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108323389A (en) * | 2018-01-18 | 2018-07-27 | 华南农业大学 | The detection method and device of the rice transplanting rice shoot spacing in the rows and cave rice shoot number of rice transplanter |
CN108982136A (en) * | 2018-05-23 | 2018-12-11 | 安徽农业大学 | A kind of system and method for seed sowing device performance detection |
CN112102258A (en) * | 2020-08-28 | 2020-12-18 | 无锡卡尔曼导航技术有限公司 | Air-suction type seeder seeding detection method based on machine vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10747999B2 (en) | Methods and systems for pattern characteristic detection | |
CN107316116B (en) | Leaf vegetable yield prediction method | |
CN107527066A (en) | One kind is based on Embedded hybrid paddy rice sowing performance detecting system and detection method | |
CN108739052A (en) | A kind of system and method for edible fungi growth parameter optimization | |
CN109063815A (en) | A kind of pest identification statistic device, system and method | |
CN114694047A (en) | Corn sowing quality evaluation method and device | |
TW201906038A (en) | Semiconductor wafer analyzing system and method thereof | |
CN107202784B (en) | Method for detecting process nodes in rice seed soaking and germination accelerating process | |
CN108037123B (en) | Precision detection method for sowing performance parameters of hybrid rice bowl body tray | |
CN108537164B (en) | Method and device for monitoring germination rate of dibbling and sowing based on unmanned aerial vehicle remote sensing | |
Zhao et al. | Transient multi-indicator detection for seedling sorting in high-speed transplanting based on a lightweight model | |
WO2022104867A1 (en) | Feature detection method and device for target object | |
CN101911877B (en) | Seed vitality authentication device and method based on laser light diffuse reflection image technology | |
US20230309464A1 (en) | Method and apparatus for automated crop recipe optimization | |
CN115774391A (en) | System and method for optimizing growth parameters of edible fungi | |
Chauhan et al. | Classification of Nutritional Deficiencies in Cabbage Leave Using Random Forest | |
CN106919740A (en) | Detect method, device and the electronic equipment of plant nitrogen content | |
TWM550465U (en) | Semiconductor wafer analyzing system | |
CN113516635B (en) | Fish and vegetable symbiotic system and vegetable nitrogen element demand estimation method based on fish behaviors | |
CN112889612B (en) | Low-phosphorus-resistant screening device and screening method for soybeans | |
Dumont et al. | Screening root morphology in grafted grapevine using 2D digital images from rhizotrons | |
Zhang et al. | Online Recognition of Small Vegetable Seed Sowing Based on Machine Vision | |
CN114170673A (en) | Method for identifying pig feeding behavior in video based on convolutional neural network | |
CN111932551A (en) | Missing transplanting rate detection method of rice transplanter | |
CN112034912A (en) | Greenhouse crop disease control method based on real-time feedback |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171229 |