CN108335298B - Grain particle counting device - Google Patents
Grain particle counting device Download PDFInfo
- Publication number
- CN108335298B CN108335298B CN201810229527.XA CN201810229527A CN108335298B CN 108335298 B CN108335298 B CN 108335298B CN 201810229527 A CN201810229527 A CN 201810229527A CN 108335298 B CN108335298 B CN 108335298B
- Authority
- CN
- China
- Prior art keywords
- guide rail
- control module
- grains
- pulley
- bracket
- 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.)
- Active
Links
Images
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention discloses a grain counting device, which comprises a mechanical device and a control module, wherein the mechanical device is connected with the control module; the mechanical device comprises a guide rail, a mechanical arm, a longitudinal pulley, an infrared camera, a transverse pulley, a deflector rod, a camera bracket connected with the deflector rod, a motor, a motion mechanism and a bracket; the guide rail is arranged on the bracket; the moving mechanism is connected with the guide rail through a longitudinal pulley and a transverse pulley which are arranged on the side surface of the moving mechanism, and the initial position of the moving mechanism is adjacent to the manipulator; the deflector rod is arranged at the upper end of the motion mechanism and moves along the guide rail together with the motion mechanism; the motor is arranged below the movement mechanism; and the control module comprises an image processing module and a motion control module. Compared with the prior art, the grain counting method has the advantages that the artificial intelligence algorithm is applied to grain counting, automatic grain counting is achieved, grain counting speed is improved, and labor and time costs are reduced.
Description
Technical Field
The invention relates to an intelligent agricultural device, in particular to a grain particle counting device.
Background
With the rapid development of economy and scientific technology, food supply and sanitary safety attract more and more extensive attention, so that the establishment of a precise and automatic modern intelligent agricultural management system has great significance.
In the development of intelligent agriculture, a serious problem that has to be paid attention to is that the grain counting work related to crop yield is still in a manual counting stage at present, and automation is not realized. On one hand, manual counting consumes a large amount of manpower and material resources, and on the other hand, the accuracy and speed of manual counting are far from those of a machine, and the counting device has the defects of low counting speed and low efficiency.
With the development of artificial intelligence in recent years, the accuracy and speed of image recognition are greatly improved compared with the conventional techniques, and therefore, it is a problem to be solved to apply the image recognition technology to a counting device for automatically counting the number of full grains and flat grains of grains such as rice ears and wheat ears.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a grain counting device to solve the problems of low manual counting speed and low accuracy of grain particles at present.
The technical scheme is as follows: a grain particle counting apparatus comprising:
the mechanical device comprises a guide rail, a mechanical arm, a longitudinal pulley, a shifting rod, an infrared camera arranged on the shifting rod, a transverse pulley, a motor, a motion mechanism and a bracket; the guide rail is arranged on the bracket; the moving mechanism is connected with the guide rail through a longitudinal pulley and a transverse pulley which are arranged on the side surface of the moving mechanism, and the initial position of the moving mechanism is adjacent to the manipulator; the deflector rod is arranged at the upper end of the motion mechanism and moves along the guide rail together with the motion mechanism; the motor is arranged below the movement mechanism;
and the control module comprises an image processing module and a motion control module, the image processing module is used for classifying and counting real grains and flat grains of the grains on the collected image, and the motion control module is used for controlling the motor to rotate.
The manipulator and the bracket are fixed on the same plane.
The infrared camera collects images of the falling grains.
The number of the infrared cameras is multiple.
The motor and the motion mechanism move synchronously.
The working principle is as follows: the invention applies an artificial intelligence algorithm to grain particle counting, and is particularly divided into a mechanical device and a control module, wherein the mechanical device fixes straws to be counted and disperses dense rice ears and wheat ear branches one by one, thereby realizing accurate particle counting; the control module comprises an image processing module and a motion control module, wherein the image processing module filters different images acquired by the infrared camera and then carries out contour extraction, and compares and removes the weight of the images, because the water content of real grains and the water content of flat grains are different, the temperature of the real grains and the flat grains is different along with the change of the environment, and the images under the infrared camera after thermal imaging are obviously different, so that the infrared images presented by the camera have different color depths and are classified into the real grains and the flat grains, and therefore, by utilizing an extreme learning algorithm ELM, a convolutional neural network algorithm CNN and a support vector machine SVM, grains on the acquired rice ear images can be counted, the real grains and the flat grains are classified, and the number of the rice ears on the rice straw branches is obtained through calculation; the motion control module controls the motor 6 to control the mechanical device to move along a preset track.
Has the advantages that: compared with the prior art, the automatic counting device has the advantages that the artificial intelligence algorithm is applied to grain particle counting, and the automatic counting of the grains such as the wheat ears and the rice ears can be realized by combining the mechanical device with the control module, so that the grain particle counting speed is increased, and the labor and time costs are reduced.
Drawings
FIG. 1 is a schematic mechanical diagram of the present invention;
FIG. 2 is a control flow diagram of the control module of the present invention.
Detailed Description
The counting machine comprises a mechanical device and a control module, wherein the mechanical device fixes straws to be counted and disperses dense rice ears and wheat ear branches one by one, so that accurate particle counting is realized; the control module is used for identifying and calculating the number of the grains which are full and flat and controlling the mechanical device to move along a preset track.
As shown in fig. 1, the mechanical device comprises a guide rail 1, a manipulator 2, a longitudinal pulley 3, an infrared camera 4, a shift lever 5, a motor 6, a motion mechanism 7, a camera support 8, a transverse pulley 9 and a support 10; the initial position of the movement mechanism 7 is adjacent to the manipulator 2, and the movement mechanism 7 is connected with the guide rail 1 through the longitudinal pulley 3 and the transverse pulley 9, so that the lateral positioning is realized, and the movement can be stable; the deflector rod 5 is arranged at the top end of the motion mechanism 7 and moves along the direction of the guide rail along with the motion mechanism 7; the manipulator 2 and the bracket 10 are respectively fixed on the same horizontal plane of the ground or the desktop through adjusting the distance; the guide rail 1 is arranged on the bracket 10, and the installation direction is the same as the movement direction of the movement mechanism 7; the longitudinal pulley 3 and the transverse pulley 9 are arranged on the side surface of the movement mechanism 7, are respectively attached to the upper surface and the side surface of the guide rail 1, are used for assisting the movement of the movement mechanism 7, respectively realize the longitudinal and transverse positioning of the movement mechanism, and limit the movement freedom degree of the movement mechanism 7, so that the movement mechanism runs stably; the motor 6 is arranged under the moving mechanism 7 and is used for driving the moving mechanism 7 to move on the guide rail 1; the number of the infrared cameras 4 is three, one of the infrared cameras is arranged right above the support 10, the other two infrared cameras are respectively arranged on the side surfaces of the camera support 8, and the infrared cameras and the camera support 8 can jointly move along the direction of the guide rail 1 along with the movement mechanism 7; the deflector rod 5 is connected with the camera bracket 8 and is used for supporting the front end of the ear of grain and simultaneously moves along with the movement mechanism 7, thereby continuously releasing the ear of grain.
As shown in fig. 2, the control module includes an image processing module and a motion control module, wherein the image processing module filters different images collected by the infrared camera 4, performs contour extraction, and compares and removes the weight of the images, and the infrared images presented by the camera have different color depths and are classified into real grains and flat grains due to different water contents of the real grains and the flat grains and different speeds of the temperature changing with the environment, so that the grains on the collected rice ear images can be counted and classified into the real grains and the flat grains by using a limit learning algorithm ELM, a convolutional neural network algorithm CNN and a support vector machine, and the quantity of the real grains and the flat grains on the rice stem branches can be obtained by calculation. The motion control module controls the motor 6 to control the mechanical device to move along a preset track.
Taking a rice straw as an example, the rice straw is initially placed at a designated position, then the mechanical arm 2 grabs the rice straw one by one, and the ear end of the rice straw is placed on the deflector rod 5;
after the counting is started, the control module controls the motor 6 to rotate. When the motor 6 rotates, the roller at the bottom of the motion mechanism 7 rolls along the guide rail 1, so that the motion mechanism 7 is driven to move in a direction far away from the manipulator 2;
when the movement mechanism 7 moves, the distance between the deflector rod 5 and the root of the rice ear is continuously increased, meanwhile, the infrared camera 4 starts to detect whether the rice ear branches fall off from the deflector rod 5, when the falling is detected, the motor 6 stops rotating, the movement mechanism 7 is static, and the infrared camera 4 collects images at the moment;
the image processing module classifies the collected different images into solid grains and flat grains, and calculates the quantity of the solid grains and the flat grains of the rice ears on the rice straw branches;
and after the identification of the single spike is finished, the motor 6 is controlled by the motion control module to continue to move towards the manipulator 2, and the residual spike stalks are continuously released.
And repeating the process until the counting is finished, so that the full grains and the shrunken grains of the whole rice ears can be counted.
Claims (3)
1. A grain counting device, characterized in that: the device comprises a mechanical device and a control module:
the mechanical device comprises a guide rail (1), a mechanical arm (2), a longitudinal pulley (3), a shifting lever (5), an infrared camera (4) arranged on the shifting lever (5), a transverse pulley (9), a motor (6), a motion mechanism (7) and a bracket (10); the initial position of the movement mechanism is adjacent to the manipulator, and the guide rail (1) is arranged on the bracket (10); the moving mechanism (7) is connected with the guide rail (1) through a longitudinal pulley (3) and a transverse pulley (9), and the initial position of the moving mechanism (7) is adjacent to the manipulator (2); the longitudinal pulley and the transverse pulley are arranged on the side surface of the movement mechanism and are attached to the guide rail; the shifting rod (5) is arranged at the upper end of the moving mechanism (7) and moves along the guide rail (1) along with the moving mechanism (7); the motor (6) is arranged below the movement mechanism (7) and drives the movement mechanism to move on the guide rail; the manipulator and the bracket are fixed on the same horizontal plane; the driving lever is connected with the camera bracket and moves along with the movement mechanism;
the control module comprises an image processing module and a motion control module; the image processing module filters different images acquired by the infrared camera, then carries out contour extraction, compares the images for removing weight, counts grains on the acquired rice ear images through different color depths of the infrared images presented by the camera, and utilizes an extreme learning algorithm ELM, a convolutional neural network algorithm CNN and a support vector machine SVM to classify the real grains and the shriveled grains, and obtains the quantity of the real grains and the shriveled grains of the rice ears on the rice straw branches through calculation; the motion control module controls the mechanical device to move along a preset track by controlling the motor; the manipulator grabs the rice ears one by one and places the ends of the rice ears on the deflector rods; the control module controls the motor to rotate, and then drives the movement mechanism to move on the guide rail along the direction far away from the manipulator.
2. The grain counting apparatus according to claim 1, wherein: the infrared camera (4) collects images of the falling grains.
3. The grain counting device according to claim 1 or 2, characterized in that: the number of the infrared cameras (4) is multiple.
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 CN108335298A (en) | 2018-07-27 |
| CN108335298B true 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) |
Families Citing this family (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 |
| 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 |
Citations (6)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8011133B2 (en) * | 2007-06-27 | 2011-09-06 | Pioneer Hi-Bred International, Inc. | Method and apparatus of high-throughput pollen extraction, counting, and use of counted pollen for characterizing a plant |
-
2018
- 2018-03-20 CN CN201810229527.XA patent/CN108335298B/en active Active
Patent Citations (6)
| 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 |
| 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 |
|---|
| 《利用ImageJ图像处理软件进行小麦籽粒计数的方法研究》;张世刚;《信息技术》;20171231(第258期);第65-69页； * |
| 《基于图像处理的小麦穗长和小穗数同步测量》;路文超 等；;《中国农机化学报》;20160630;第37卷(第6期);第742－751页； * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108335298A (en) | 2018-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108335298B (en) | Grain particle counting device | |
| US9462749B1 (en) | Selectively harvesting fruits | |
| CN105900610B (en) | The lossless harvesting hierarchical intelligence all-in-one of Table Grape and its control method | |
| CN102974552B (en) | Automatic arraying and intelligent sorting equipment for factory raising of grain seeds | |
| CN107094429A (en) | A kind of multiaxis fruit picking robot | |
| CN104737707A (en) | Combine harvester cleaning impurity rate self-adaptive control device and self-adaptive control cleaning method | |
| RU2588451C1 (en) | Method for artificial pollination of anemophilous plants and device therefor | |
| CN203775715U (en) | Fruit picking device | |
| CN116686545B (en) | Litchi picking robot shade removing method based on machine vision control | |
| CN109955265A (en) | A kind of indoor range complex intelligence shell case cleaning robot | |
| CN113396650B (en) | Intelligent vegetable inter-plant weeding device and control method | |
| CN113330915B (en) | Self-adaptive cotton harvesting method based on binocular vision recognition and intelligent mechanical harvesting device | |
| Hu et al. | Simplified 4-DOF manipulator for rapid robotic apple harvesting | |
| CN104704969A (en) | Self-propelled type transplanting machine with bad seedling removing function and transplanting method | |
| CN109570051A (en) | Chinese chestnut small holes caused by worms detection device based on machine vision, laser and acoustics | |
| CN101940096B (en) | System for sorting corn seed haploid | |
| CN206435159U (en) | A kind of disc balling machine green-ball size monitoring system based on image procossing | |
| CN107464232A (en) | A kind of unmanned rice transplanter plants the image detecting method of quality | |
| CN113714149A (en) | Parallel arm intelligent silkworm cocoon sorting robot and silkworm cocoon sorting method | |
| CN106233937A (en) | A kind of array extension type mechanical arm kiwifruit fruit picking robot | |
| CN209314338U (en) | Pick the robot of day lily | |
| CN201789739U (en) | Haploid corn seed sorting system | |
| CN112455665B (en) | Paddy field balance take-off and landing unmanned aerial vehicle and fixed-point weeding recovery operation method | |
| CN207147533U (en) | A kind of Miniature digital rice species test machine | |
| CN215011703U (en) | Rose picking robot |
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 |