CN108335298A - Cereal-granules counting device - Google Patents
Cereal-granules counting device Download PDFInfo
- Publication number
- CN108335298A CN108335298A CN201810229527.XA CN201810229527A CN108335298A CN 108335298 A CN108335298 A CN 108335298A CN 201810229527 A CN201810229527 A CN 201810229527A CN 108335298 A CN108335298 A CN 108335298A
- Authority
- CN
- China
- Prior art keywords
- motion
- cereal
- granules
- guide rail
- grain
- 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Abstract
The invention discloses a kind of cereal-granules counting devices, including mechanical device and control module;Mechanical device includes guide rail, manipulator, longitudinal pulley, infrared camera, lateral pulley, driving lever, the camera support being connected with driving lever, motor, motion and holder;Guide rail is rack-mount;Motion is connected by longitudinal pulley mounted on its side and lateral pulley with guide rail, and motion initial position and manipulator are adjacent;Driving lever is mounted on motion upper end, and is moved along guide rail with motion;Motor is installed below motion;Control module, including image processing module and motion-control module.Compared with prior art, intelligent algorithm is applied to cereal-granules and counted by the present invention, is realized the automatic counting of cereal, and then improve cereal-granules Statistical Speed, is reduced manpower and time cost.
Description
Technical field
The present invention relates to reading intelligent agriculture device more particularly to cereal-granules counting devices.
Background technology
With economic and science and technology fast development, the supply of food causes more and more extensive pass with safe and healthy
Note, thus establish precision, automation modern reading intelligent agriculture management system tool have very important significance.
And in the development of reading intelligent agriculture, it has to which a severe problem for making us paying attention to is ceased with crop yield
It ceases relevant cereal-granules Counts and is still in the artificial counting stage at present, and automation is not implemented.One side of artificial counting
A large amount of manpower and materials are expended in face, and on the other hand, the accuracy and speed manually counted differs greatly with machine, has and counts speed
The disadvantage that degree is slow, efficiency is low.
It being continued to develop recently as artificial intelligence, the accuracy of image recognition is compared with speed to be greatly improved in the past, because
This by image recognition technology apply to the cereal such as spike of rice, the wheat head carry out real grain, empty grain quantity programming count counting device at
For urgent problem to be solved.
Invention content
Goal of the invention:The object of the present invention is to provide a kind of cereal-granules counting devices, to solve current cereal-granules people
The problem that work counting rate is slow, accuracy rate is low.
Technical solution:Cereal-granules counting device, including:
Mechanical device, including guide rail, manipulator, longitudinal pulley, driving lever, the infrared camera being arranged on driving lever, transverse direction are sliding
Wheel, motor, motion and holder;Guide rail is rack-mount;Motion by longitudinal pulley mounted on its side and
Lateral pulley is connected with guide rail, and motion initial position and manipulator are adjacent;Driving lever be mounted on motion upper end, and with fortune
Motivation structure is moved along guide rail;Motor is installed below motion;
Control module, including image processing module and motion-control module, image processing module is in the image collected
Grain carry out real grain, empty grain classify and is counted, moving control module for controlling motor rotates.
Manipulator is fixed in the same plane with holder.
Infrared camera acquires the grain image fallen.
Infrared camera quantity is multiple.
Motor is moved synchronously with motion.
Operation principle:The present invention by intelligent algorithm be applied to cereal-granules count on, be specifically divided into mechanical device and
Control module two parts, the stalk that mechanical device will count are fixed and carry out intensive spike of rice, wheat head bifurcated one by one
Dispersion, to realize accurate grain count;Control module includes image processing module and motion-control module, wherein at image
Reason module carries out contours extract after filtering the different images that infrared camera acquires, and image is carried out comparison duplicate removal, due to reality
Grain is different with empty grain water content, and temperature is different with the speed of environmental change, and the image after thermal imaging under infrared camera has aobvious
Difference is write, therefore different by the presented infrared image color depth of camera, real grain and empty grain classification is carried out, to limit of utilization
Learning algorithm ELM, convolutional neural networks algorithm CNN, support vector machines, can be to the grain on collected spike of rice image
It is counted, and carries out real grain and empty grain classification, calculate the spike of rice reality grain and empty grain quantity on rice straw branch;Movement control
Molding block control machinery device by controlling motor 6 is moved along desired trajectory.
Advantageous effect:Compared with prior art, intelligent algorithm is applied to cereal-granules and counted by the present invention, is passed through
Mechanical device and control module are combined, and can realize the automatic counting of the cereal such as the wheat head and spike of rice, and then improve cereal
Grain Statistical Speed, reduces manpower and time cost.
Description of the drawings
Fig. 1 is mechanical structure schematic diagram of the present invention;
Fig. 2 is control module control flow chart of the present invention.
Specific implementation mode
The present invention includes mechanical device and control module, and the stalk that mechanical device will count is fixed and will be intensive
Spike of rice, wheat head bifurcated are disperseed one by one, to realize accurate grain count;Control module for identification and calculate cereal reality
Grain and empty grain quantity and control machinery device are moved along desired trajectory.
As shown in Figure 1, mechanical device include guide rail 1, manipulator 2, longitudinal pulley 3, infrared camera 4, driving lever 5, motor 6,
Motion 7, camera support 8, lateral pulley 9 and holder 10;The wherein initial position of motion 7 and manipulator 2 is adjacent, fortune
Motivation structure 7 is connected by longitudinal pulley 3 and lateral pulley 9 with guide rail 1, to realize lateral register so that movement can be steady;
Driving lever 5 is mounted on the top of motion 7, and motion 7 is followed to be moved along guide rail direction;Manipulator 2 passes through tune with holder 10
Whole distance is individually fixed in the same level of ground or desktop;Guide rail 1 is installed over the mount 10, installation direction and fitness machine
The direction of motion of structure 7 is identical;Longitudinal pulley 3, lateral pulley 9 are mounted on 7 side of motion, respectively above and side with guide rail 1
Face paste is closed, and is moved for synkinesia mechanism 7, realizes the vertical and horizontal positioning of motion respectively, limitation motion 7
Freedom of motion so that motion operates steadily;Motor 6 is installed on immediately below motion 7, for driving motion
7 movement on guide rail 1;4 quantity of infrared camera is three, one of them is mounted on right over holder 10, other two difference
It is installed on the side of camera support 8, motion 7 can be followed to be moved in 1 direction of guide rail jointly with camera support 8;Driving lever 5 with
Camera support 8 is connected, and is used to support grain ear front end, while motion 7 being followed to be moved, to constantly discharge grain ear.
As shown in Fig. 2, control module includes image processing module and motion-control module, wherein image processing module will be red
Contours extract is carried out after the different images filtering that outer camera 4 acquires, and image is subjected to comparison duplicate removal, since real grain and empty grain contain
Water is different, and temperature is different with the speed of environmental change, and there were significant differences for the image after thermal imaging under infrared camera, therefore
It is different by the presented infrared image color depth of camera, real grain and empty grain classification are carried out, to limit of utilization learning algorithm
ELM, convolutional neural networks algorithm CNN, support vector machines can count the grain on collected spike of rice image,
And real grain and empty grain classification are carried out, calculate the spike of rice reality grain and empty grain quantity on rice straw branch.Motion-control module is logical
It crosses control motor 6 and then control machinery device is moved along desired trajectory.
By taking rice straw as an example, rice straw is placed on designated position when initial, subsequent manipulator 2 captures rice straw one by one, and by its
Spike of rice end is positioned on driving lever 5;
After counting starts, control module controls motor 6 and rotates.When motor 6 rotates, the idler wheel edge of 7 bottom of motion is led
Rail 1 is rolled, to drive motion 7 to be moved to the direction far from manipulator 2;
When motion 7 moves, the distance between driving lever 5 and spike of rice root are continuously increased, while infrared camera 4 starts
Detected whether that spike of rice branch is fallen from driving lever 5, when detect fall when, motor 6 pause rotation, motion 7 is static, infrared
The image of the acquisition of camera 4 at this time;
The different images of acquisition are carried out real grain to image processing module and empty grain is classified, and calculates on rice straw branch
Spike of rice reality grain and empty grain quantity;
After the completion of Dan Zhisui identifications, continue to move to 2 direction of manipulator by moving control module for controlling motor 6,
Continue to discharge remaining fringe bar.
Repeat the above process, until count finish, so as to prune spike of rice real grain and empty grain count.
Claims (5)
1. a kind of cereal-granules counting device, it is characterised in that:Including:
Mechanical device, including guide rail (1), manipulator (2), longitudinal pulley (3), driving lever (5), setting are infrared on driving lever (5)
Camera (4), lateral pulley (9), motor (6), motion (7) and holder (10);The guide rail (1) is mounted on holder (10)
On;The motion (7) is connected by longitudinal pulley (3) mounted on its side and lateral pulley (9) with guide rail (1), institute
It states motion (7) initial position and manipulator (2) is adjacent;The driving lever (5) be mounted on motion (7) upper end, and with fortune
Motivation structure (7) is mobile along guide rail (1);The motor (6) is installed below motion (7);
Control module, including image processing module and motion-control module, described image processing module is in the image collected
Grain carry out real grain, empty grain classify and is counted, the moving control module for controlling motor (6) rotates.
2. cereal-granules counting device according to claim 1, it is characterised in that:The manipulator (2) and holder (10)
It fixes in the same plane.
3. cereal-granules counting device according to claim 2, it is characterised in that:Infrared camera (4) acquisition is fallen
Grain image.
4. cereal-granules counting device according to claim 3, it is characterised in that:Infrared camera (4) quantity is more
It is a.
5. cereal-granules counting device according to claim 1, it is characterised in that:The motor (6) and motion (7)
It moves synchronously.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810229527.XA CN108335298B (en) | 2018-03-20 | 2018-03-20 | Grain particle counting device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810229527.XA CN108335298B (en) | 2018-03-20 | 2018-03-20 | Grain particle counting device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108335298A true CN108335298A (en) | 2018-07-27 |
CN108335298B CN108335298B (en) | 2020-06-16 |
Family
ID=62932159
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810229527.XA Active CN108335298B (en) | 2018-03-20 | 2018-03-20 | Grain particle counting device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108335298B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109781732A (en) * | 2019-03-08 | 2019-05-21 | 江西憶源多媒体科技有限公司 | A kind of small analyte detection and the method for differential counting |
CN110378873A (en) * | 2019-06-11 | 2019-10-25 | 上海交通大学 | Rice Panicle strain grain based on deep learning lossless method of counting in situ |
CN113496240A (en) * | 2020-04-02 | 2021-10-12 | 山西农业大学 | Method for detecting millet under microscope based on YoLov3 network |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1163935A (en) * | 1997-08-25 | 1999-03-05 | Tokimec Inc | Grain diameter measuring equipment |
CN2407568Y (en) * | 1997-04-01 | 2000-11-29 | 陈兴芳 | Primary threshing rice and wheat harvester |
US20090000188A1 (en) * | 2007-06-27 | 2009-01-01 | Pioneer Hi-Bred International, Inc. | Method and apparatus of high-throughput pollen extraction, counting, and use of counted pollen for characterizing a plant |
CN101339118A (en) * | 2008-08-08 | 2009-01-07 | 华中科技大学 | Grain parameter automatic measuring equipment and method |
WO2011006844A1 (en) * | 2009-07-14 | 2011-01-20 | Roberto Magnaterra | Agricultural/industrial machine provided with pressurized gas cleaning system. |
CN103348815A (en) * | 2013-06-27 | 2013-10-16 | 山东泉林纸业有限责任公司 | Machine for harvesting corn, peeling corn husks and separating straws, and working method of machine |
CN105427275A (en) * | 2015-10-29 | 2016-03-23 | 中国农业大学 | Filed environment wheat head counting method and device |
-
2018
- 2018-03-20 CN CN201810229527.XA patent/CN108335298B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2407568Y (en) * | 1997-04-01 | 2000-11-29 | 陈兴芳 | Primary threshing rice and wheat harvester |
JPH1163935A (en) * | 1997-08-25 | 1999-03-05 | Tokimec Inc | Grain diameter measuring equipment |
US20090000188A1 (en) * | 2007-06-27 | 2009-01-01 | Pioneer Hi-Bred International, Inc. | Method and apparatus of high-throughput pollen extraction, counting, and use of counted pollen for characterizing a plant |
CN101339118A (en) * | 2008-08-08 | 2009-01-07 | 华中科技大学 | Grain parameter automatic measuring equipment and method |
WO2011006844A1 (en) * | 2009-07-14 | 2011-01-20 | Roberto Magnaterra | Agricultural/industrial machine provided with pressurized gas cleaning system. |
CN103348815A (en) * | 2013-06-27 | 2013-10-16 | 山东泉林纸业有限责任公司 | Machine for harvesting corn, peeling corn husks and separating straws, and working method of machine |
CN105427275A (en) * | 2015-10-29 | 2016-03-23 | 中国农业大学 | Filed environment wheat head counting method and device |
Non-Patent Citations (2)
Title |
---|
张世刚: "《利用ImageJ图像处理软件进行小麦籽粒计数的方法研究》", 《信息技术》 * |
路文超 等;: "《基于图像处理的小麦穗长和小穗数同步测量》", 《中国农机化学报》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109781732A (en) * | 2019-03-08 | 2019-05-21 | 江西憶源多媒体科技有限公司 | A kind of small analyte detection and the method for differential counting |
CN110378873A (en) * | 2019-06-11 | 2019-10-25 | 上海交通大学 | Rice Panicle strain grain based on deep learning lossless method of counting in situ |
CN110378873B (en) * | 2019-06-11 | 2021-04-13 | 上海交通大学 | In-situ lossless counting method for rice ear plants and grains based on deep learning |
CN113496240A (en) * | 2020-04-02 | 2021-10-12 | 山西农业大学 | Method for detecting millet under microscope based on YoLov3 network |
Also Published As
Publication number | Publication date |
---|---|
CN108335298B (en) | 2020-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109389161B (en) | Garbage identification evolutionary learning method, device, system and medium based on deep learning | |
CN108335298A (en) | Cereal-granules counting device | |
CN106362957B (en) | A kind of gangue piece-rate system and separation method | |
CN105900610B (en) | The lossless harvesting hierarchical intelligence all-in-one of Table Grape and its control method | |
CN104084379B (en) | A kind of corn seed image selecting device and its application method | |
CN206810710U (en) | A kind of quick-fried pearl filter stick detection means of cigarette based on machine vision | |
CN103752531B (en) | A kind of Nicotiana tabacum L. sorter based on machine vision | |
CN101614524B (en) | Automatic refined globular tooth diameter and height detection device | |
CN103056111B (en) | Prawns quality detecting and classifying device based on machine vision technology | |
CN105225225B (en) | A kind of leather system for automatic marker making method and apparatus based on machine vision | |
CN102217559A (en) | On-line automatic detection and sorting equipment and method for incubated egg quality | |
CN209935300U (en) | Intelligent sorting system based on computer vision | |
KR101879087B1 (en) | Apparatus for measuring size of transferred raw material | |
CN102615053A (en) | Flexible printing machine added with quality inspection substandard-product rejecting device | |
CN107891012B (en) | Pearl size and circularity sorting device based on equivalent algorithm | |
CN207222383U (en) | Plank sorting system | |
CN207408272U (en) | Rice grain shape parameter measuring apparatus based on linear array camera and X-ray Double-mode imaging | |
CN208449603U (en) | A kind of cleaning table automatic detecting executive device based on manipulator | |
CN207336378U (en) | A kind of device of automatic detection rice phenotypic parameter | |
CN105195438A (en) | Embedded type automatic pearl sorting device and method based on image recognition | |
CN104984920A (en) | Full-automatic bionic vision appearance detection equipment and method | |
CN108163526A (en) | A kind of grape shaping, vision positioning grasping mechanism and method | |
US11878328B2 (en) | Color sorting method for small-grain agricultural products combining area scanning photoelectric characteristic and line scanning photoelectric characteristic | |
CN205629665U (en) | Differential branch covers bull laser bottle lid flying laser marker device | |
CN208513101U (en) | A kind of two-sided vision-based detection mango grading plant |
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 |