CN117296510A - High-flux corn seed tester and method - Google Patents

High-flux corn seed tester and method Download PDF

Info

Publication number
CN117296510A
CN117296510A CN202311157148.1A CN202311157148A CN117296510A CN 117296510 A CN117296510 A CN 117296510A CN 202311157148 A CN202311157148 A CN 202311157148A CN 117296510 A CN117296510 A CN 117296510A
Authority
CN
China
Prior art keywords
ears
corn
data processing
image
ear
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
Application number
CN202311157148.1A
Other languages
Chinese (zh)
Inventor
王喜庆
张悦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Zhongnong University Frontier Technology Research Institute
Huarui Smart Shenzhen Agricultural Technology Co ltd
Original Assignee
Shenzhen Zhongnong University Frontier Technology Research Institute
Huarui Smart Shenzhen Agricultural Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Zhongnong University Frontier Technology Research Institute, Huarui Smart Shenzhen Agricultural Technology Co ltd filed Critical Shenzhen Zhongnong University Frontier Technology Research Institute
Priority to CN202311157148.1A priority Critical patent/CN117296510A/en
Publication of CN117296510A publication Critical patent/CN117296510A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01C—PLANTING; SOWING; FERTILISING
    • A01C1/00—Apparatus, or methods of use thereof, for testing or treating seed, roots, or the like, prior to sowing or planting
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0098—Plants or trees
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/56—Cameras or camera modules comprising electronic image sensors; Control thereof provided with illuminating means
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Signal Processing (AREA)
  • Wood Science & Technology (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Medicinal Chemistry (AREA)
  • Food Science & Technology (AREA)
  • Soil Sciences (AREA)
  • Environmental Sciences (AREA)
  • Botany (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention relates to a high-flux corn seed tester and a method, comprising the following steps: a case; the image acquisition unit is arranged at the top of the box body; the material drawer is arranged at the bottom of the box body and is used for accommodating the fruit cluster to be measured, and the fruit cluster is positioned right below the image acquisition unit; the data processing unit is arranged on the outer side wall of the box body, and the image acquisition unit transmits the acquired image information of the clusters to the data processing unit for image information data processing. Placing corn ears on a material drawer, photographing once through a camera and a light source, turning the ears 180 degrees through a carrier roller under the condition of no movement of the position, photographing once again, completing image information acquisition of the front surface and the back surface of the ears, and transmitting the image information to a data processing unit; the data processing unit performs image analysis to identify corn ears and performs image segmentation; and measuring the characteristics of the number of ears, the number of rows of grains, the width of ears, the length of ears and the length of bald tips of individual ears in the corn ear image, and completing seed examination.

Description

High-flux corn seed tester and method
Technical Field
The invention relates to the technical field of corn test, in particular to a high-throughput corn test instrument and method based on visual image machine learning.
Background
With the current increasingly severe environment and the increasing population, the grain supply pressure is increasing, and high-yield and high-quality corns need to be cultivated to meet the current grain demands. Breeding is an important factor influencing corn yield, and seed examination is one of important links in the corn breeding process and is an important guarantee for realizing yield increase. The corn test method mainly comprises the character measurement of the ear line number, the row grain number, the ear width, the ear length, the bald tip length and the like.
Traditional seed examination is mainly manual measurement, and the tool is crude, low in efficiency and precision and limited by time. With the continuous development of computer technology, more and more image processing technologies are applied to agriculture, and by means of the technology, a corn seed test system can acquire cell cluster data in batches in a short time and quickly and accurately acquire a large number of character parameters related to clusters.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a high-flux corn seed tester and a method based on visual image machine learning, which combine an optical technology with an image processing technology to realize high-flux corn seed testing.
In order to achieve the above purpose, the present invention adopts the following technical scheme: a high throughput corn tester, comprising: a case; the image acquisition unit is arranged at the top of the box body; the material drawer is arranged at the bottom of the box body and is used for accommodating the fruit cluster to be measured, and the fruit cluster is positioned right below the image acquisition unit; the data processing unit is arranged on the outer side wall of the box body, and the image acquisition unit transmits the acquired image information of the clusters to the data processing unit for image information data processing so as to test corn seeds.
Further, a light shielding plate is movably arranged on the box body and positioned at the front side of the image acquisition unit.
Further, the image acquisition unit comprises a mounting plate, a camera and a light source; the mounting plate is fixedly arranged at the top in the box body, and the cameras are arranged on the central line of the mounting plate and are at least two; the light sources are distributed on two sides of the camera by taking the camera as the center.
Further, the material drawer comprises a plurality of carrier rollers and a drawer plate; the drawing plate is movably arranged at the bottom of the box body, and a plurality of parallel arc grooves are arranged at the top of the drawing plate at intervals; each arc-shaped groove is internally provided with a carrier roller, and each carrier roller can rotate on the drawing plate;
the clusters are placed between the adjacent carrier rollers and are orderly placed along the vertical direction of the gaps of the adjacent carrier rollers.
Further, the front side of the box body is provided with a lifting plate.
Further, be provided with automatic code scanning device in middle part one side that is located the box, automatic code scanning device is located the top of material drawer for discern the bar code on the cluster that waits to survey, and with the information transmission to the data processing unit of discernment.
A high-throughput corn seed test method based on the high-throughput corn seed test instrument comprises the following steps: opening a lifting plate at the front side of the box body, placing corn ears on a material drawer, placing a shading plate, placing the corn ears, photographing the corn ears once through a camera and a light source, turning the corn ears 180 degrees through a carrier roller under the condition of no movement of the position, photographing the corn ears once again, completing image information acquisition of the front surface and the back surface of the corn ears, and transmitting the image information to a data processing unit; the data processing unit reads the image information in real time and performs data analysis, the image analysis identifies corn ears, and image segmentation is performed; and measuring the characteristics of the number of ears, the number of rows of grains, the width of ears, the length of ears and the length of bald tips of individual ears in the corn ear image, and completing seed examination.
Further, a machine learning training module is arranged in the data processing unit, can identify single clusters and give coordinates, and cut the single clusters according to the frame coordinates, and are ordered from left to right and from top to bottom according to the coordinates.
Further, the method for measuring the characteristics of the ear number, the row number, the ear width, the ear length and the bald tip length of the single ear in the corn ear image comprises the following steps:
widening the ear body map of the clusters according to a preset proportion, detecting the seeds, if the detection label is kernel, returning the central coordinate information of each seed, and counting the seed coordinates, thus obtaining the number of the seeds of each cluster;
according to the external rectangular frame of the ear body of the ear, determining the ear length and the ear width of the ear;
counting the starting points of each spike row, and if the number is 0, the length of the bald tip is 0; if the number is 3, taking the average of y coordinates of the starting points of 3 spike rows by the length of the bald tip; otherwise, the bald tip length takes the average of the y coordinates of the starting point;
according to the spike body map, spike length, spike width and seed coordinate set, setting a measuring area, finding all seeds in the area to be measured, sorting all points from top to bottom, determining the seeds belonging to the same column by comparing transverse coordinate values, taking the uppermost seed of the row as the starting point of the row, and sequentially and circularly starting to find the next column so as to determine the row number and spike number.
Further, the measurement region is set as: transverse direction 1/5*w-4/5*w and longitudinal direction 4/7*h-5/7*h.
Due to the adoption of the technical scheme, the invention has the following advantages:
the corn ear test device can conduct corn ear test in batches, and the test efficiency is improved. The invention uses a plurality of cameras to image, which can ensure the definition of the shot image. And by carrying an image recognition technology, various characters can be analyzed, and the condition of manual evaluation is avoided.
Drawings
FIG. 1 is a schematic diagram of a high throughput corn seed tester in an embodiment of the invention;
reference numerals:
1-box, 2-material drawer, 3-data processing unit, 4-light screen, 5-camera, 6-light source, 7-lifter plate, 8-automatic yard device of sweeping.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which are obtained by a person skilled in the art based on the described embodiments of the invention, fall within the scope of protection of the invention.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
The invention provides a high-throughput corn seed tester based on visual image machine learning and a method thereof, wherein the machine is provided with an automatic code scanning device for identifying bar codes, and can measure the ears of the whole community; opening a lifting plate, placing corn ears into a material drawer, putting down a shading plate, mounting a plurality of industrial cameras and light sources to collect images of the front and back surfaces of the ears, and uploading the images to a data processing unit 3; the image analysis system mounted on the data processing unit 3 reads the task state in the database in real time and analyzes the submitted analysis data, the data analysis is completed, the state is updated to the test analysis completion, and the user can select the data to be exported as an excel file by himself; the image analysis system identifies corn ears and cuts the corn ears; measuring the characteristics of the single ear, such as the number of lines, the number of rows, the width of ears, the length of bald tips and the like; the system can be managed by account, and the data are not interfered with each other. The invention establishes an intelligent, standardized and systematic seed test system, realizes high-efficiency seed test of mass materials, reduces operation difficulty, reduces manual investment, is not subject to manual subjective interference, and provides technical support for breeding research.
In one embodiment of the invention, a high throughput corn seed meter is provided. In this embodiment, as shown in fig. 1, the high-throughput corn seed tester includes:
a case 1;
the image acquisition unit is arranged at the top of the box body 1 and is used for shooting and illuminating the shooting box body 1;
the material drawer 2 is arranged at the bottom of the box body 1 and is used for accommodating the ears to be measured, and the ears are positioned right below the image acquisition unit;
the data processing unit 3 is arranged on the outer side wall of the box body 1, and the image acquisition unit transmits the acquired image information of the clusters to the data processing unit 3 for image information data processing, so that corn seed test is realized.
When the corn seed testing device is used, the to-be-tested clusters are placed into the material drawer 2, the image acquisition unit acquires the picture information of the clusters and transmits the picture information to the data processing unit 3, and the data processing unit 3 processes the cluster image information to finish corn seed testing.
In the above embodiment, the light shielding plate 4 is movably disposed on the case 1 and located at the front side of the image capturing unit, so as to ensure the image information capturing effect of the image capturing unit, so as to facilitate better imaging.
Specifically, the upper parts of two sides of the box body 1 are provided with first sliding rails for sliding the light shielding plates 4; two sides of the light cutting and shielding plate 4 are provided with sliding blocks matched with the first sliding rail.
In the above embodiment, the image pickup unit includes the mounting board, the camera 5, and the light source 6. The mounting plate is fixedly arranged at the top in the box body 1, the cameras 5 are arranged on the central line of the mounting plate, at least two cameras are arranged, and the light sources can be uniformly distributed on the clusters in the shooting process on the basis of preventing reflection; the light sources 6 are distributed on two sides of the camera 5 with the camera 5 as the center, and provide enough light sources for the camera 5 to shoot.
In this embodiment, the number of cameras 5 is preferably three, and 1080p high-definition cameras are adopted for each camera 5.
When the camera shooting device is used, the light sources can be uniformly distributed on the clusters in the shooting process on the basis of preventing reflection of light through the matching of the cameras 5 and the light sources 6, and the image cutting configuration can be adjusted in the camera setting so as to achieve the optimal shooting effect.
In the above embodiment, the material drawer 2 includes a plurality of idlers and a drawer plate. The drawing plate is movably arranged at the bottom of the box body 1, and a plurality of parallel arc grooves are arranged at the top of the drawing plate at intervals; each arc groove is internally provided with a carrier roller, and each carrier roller can rotate on the drawing plate. The clusters are placed between the adjacent carrier rollers and are orderly placed along the vertical direction of the gaps of the adjacent carrier rollers. In this embodiment, preferably, the clusters are orderly arranged in 9 columns in the longitudinal direction, and each camera 5 corresponds to 3 columns of clusters.
Specifically, the two sides of the box body 1 are provided with second sliding rails along the length direction of the drawing plate, and the second sliding rails are used for sliding the drawing plate.
In the above embodiment, the front side of the case 1 is further provided with the lifting plate 7, and the top of the case 1 is provided with the bar-shaped through hole, so that the lifting plate 7 moves upward when lifted, the two sides of the case 1 are provided with the third sliding rails, and the third sliding rails are located at the front side of the first sliding rails. The lifting plate 7 moves up and down in the case 1 along the third slide rail. When the lifting plate 7 moves downward, the box 1 is closed to form a closed space.
In the above embodiment, the automatic code scanning device 8 is disposed on one side of the middle of the case 1, and the automatic code scanning device 8 is disposed above the material drawer 2, and is used for identifying the bar code on the cluster to be measured, and transmitting the identified information to the data processing unit 3.
Specifically, each district cluster is provided with an independent bar code, the bar code is placed into an automatic code scanning device 8 for identification, 18 clusters can be placed in a material drawer at most, and the clusters in the whole district can be measured.
In the above embodiment, the data processing unit 3 is provided outside one side of the casing 1, which has a touch screen, and can display data in real time.
When the automatic scanning device is used, the power switch is turned on, the lifting plate 7 is lifted, the data processing unit 3 is turned on, the bar codes are scanned and read in by the automatic scanning device 8, a plurality of ears are put into the material drawer 2, the light shielding plate 4 is pulled down, a corn seed tester system carried by the data processing unit 3 is used for checking whether imaging is clear, otherwise, the camera 5 and the light source 6 are required to be adjusted, after a front image is shot, the light shielding plate 4 is turned on, the ears are rotated by 180 degrees, the light shielding plate is pulled down again for shooting, the bag is finished and synchronous analysis is clicked in a system, data are transmitted to a database, the system performs real-time analysis, and the inquiry state and the derived data can be performed in the system.
In one embodiment of the present invention, based on the high-throughput corn test instrument in the above embodiments, a high-throughput corn test method is further provided, which includes the following steps:
1) Opening a lifting plate 7 at the front side of the box body 1, placing corn ears on the material drawer 2, putting down a light shielding plate 4, placing the ears well, photographing the ears once through a camera 5 and a light source 6, turning the ears 180 degrees through a carrier roller under the condition of no movement of the position, photographing the ears once again, completing the image information acquisition of the front and back sides of the ears, and transmitting the image information to a data processing unit 3;
2) The data processing unit 3 reads the image information in real time and performs data analysis, the state is updated to be 'examination analysis completion', and a user can select data to be exported as an excel file by himself; the corn ears are identified through image analysis, and image segmentation is carried out;
3) And measuring the characteristics of the single ear in the corn ear image, such as the ear number, the row number, the ear width, the ear length, the bald tip length and the like, so as to finish seed examination.
In the step 2), the image to be analyzed includes a plurality of clusters, so the data processing unit 3 is internally provided with a machine learning training module, which can identify individual clusters and give coordinates, and can segment the individual clusters according to the frame coordinates, and the individual clusters are ordered from left to right and from top to bottom according to the coordinates.
In the above step 3), the various shape measurement includes the steps of:
3.1 Widening the ear body map of the clusters according to a preset proportion, detecting the seeds, if the detection label is kernel, indicating that the seeds are seeds, returning the central coordinate information of each seed, and counting the coordinates of the seeds, thus obtaining the number of the seeds of each cluster;
3.2 Determining the ear length and the ear width of the ears according to the external rectangular frame of the ear bodies of the ears;
3.3 Counting the starting points of each spike row, and if the number is 0, the length of the bald tip is 0; if the number is 3, taking the average of y coordinates of the starting points of 3 spike rows by the length of the bald tip; otherwise, the bald tip length takes the average of the y coordinates of the starting point;
3.4 According to the spike body map, spike length, spike width, and seed coordinate set, a measurement region is set (in this embodiment, it is preferable that: transverse 1/5*w-4/5*w and longitudinal 4/7*h-5/7*h), finding all grains existing in the area to be detected, sorting all dots from top to bottom, determining grains belonging to the same column by comparing transverse coordinate values, taking the uppermost grain of the row as the starting point of the row, and sequentially and circularly starting to find the next column, thereby determining the row grain number and the spike row number.
In the above embodiments, since each user uses the default account to be inconvenient to manage, and the own data is not wanted to be revealed, the user's own account can be established through the touch screen, and can independently manage, and the password can be modified and the account can be logged out at any time.
In the above embodiments, the data processing unit 3 may operate offline, without being connected to the internet, and three USB interfaces may be installed to transmit data.
In summary, when the invention is used, the automatic code scanning device 8 is used for identifying the bar codes, and 18 corn ears can be placed in the material drawer 2 at most, so that the ears in the whole community can be measured.
The lifting plate 7 is opened on the front face, the clusters are placed in the material drawer 2, the clusters are placed in order along the vertical direction of the gap of the carrier roller, the clusters are placed in order according to the longitudinal 9 rows, each imaging device corresponds to 3 rows, and the light shielding plate 4 is put down so as to facilitate better imaging.
The data processing unit 3 can perform activity and touch screen operation on one side of the box body 1, new data are uploaded to the database each time, the state is submitted and analyzed, a system carried by the data processing unit 3 can read the state of the database in real time, and when the submitted data are read, the submitted data are listed in an analysis queue for sequential analysis;
after the data analysis is finished, the states of the database and the system can be automatically updated to be 'test analysis finished', and the 'test analysis finished' data can be selected from the system and merged and exported into an excel file, so that the method is convenient for non-technicians to check.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A high throughput corn seed tester, comprising:
a case;
the image acquisition unit is arranged at the top of the box body;
the material drawer is arranged at the bottom of the box body and is used for accommodating the fruit cluster to be measured, and the fruit cluster is positioned right below the image acquisition unit;
the data processing unit is arranged on the outer side wall of the box body, and the image acquisition unit transmits the acquired image information of the clusters to the data processing unit for image information data processing so as to test corn seeds.
2. The high throughput corn tester of claim 1, wherein a light shielding plate is movably disposed on the housing and positioned on the front side of the image acquisition unit.
3. The high throughput corn tester of claim 1, wherein the image acquisition unit comprises a mounting plate, a camera, and a light source; the mounting plate is fixedly arranged at the top in the box body, and the cameras are arranged on the central line of the mounting plate and are at least two; the light sources are distributed on two sides of the camera by taking the camera as the center.
4. The high throughput corn test instrument of claim 1, wherein the material drawer comprises a plurality of idlers and a drawer plate; the drawing plate is movably arranged at the bottom of the box body, and a plurality of parallel arc grooves are arranged at the top of the drawing plate at intervals; each arc-shaped groove is internally provided with a carrier roller, and each carrier roller can rotate on the drawing plate;
the clusters are placed between the adjacent carrier rollers and are orderly placed along the vertical direction of the gaps of the adjacent carrier rollers.
5. The high throughput corn test instrument of claim 1, wherein the front side of the housing is provided with a lifter plate.
6. The high throughput corn seed tester of claim 1, wherein an automatic code scanning device is arranged on one side of the middle of the box body, and the automatic code scanning device is arranged above the material drawer and is used for identifying the bar code on the clusters to be measured and transmitting the identified information to the data processing unit.
7. A high throughput corn test method based on the high throughput corn test instrument of any one of claims 1 to 6, comprising:
opening a lifting plate at the front side of the box body, placing corn ears on a material drawer, placing a shading plate, placing the corn ears, photographing the corn ears once through a camera and a light source, turning the corn ears 180 degrees through a carrier roller under the condition of no movement of the position, photographing the corn ears once again, completing image information acquisition of the front surface and the back surface of the corn ears, and transmitting the image information to a data processing unit;
the data processing unit reads the image information in real time and performs data analysis, the image analysis identifies corn ears, and image segmentation is performed;
and measuring the characteristics of the number of ears, the number of rows of grains, the width of ears, the length of ears and the length of bald tips of individual ears in the corn ear image, and completing seed examination.
8. The method of claim 7, wherein a machine learning training module is disposed in the data processing unit, and is capable of identifying individual ears and giving coordinates, dividing the individual ears according to frame coordinates, and sorting the individual ears from left to right and from top to bottom according to the coordinates.
9. The method of high throughput corn test of claim 7, wherein determining the ear count, row count, ear width, ear length and bald tip length of individual ears in the image of corn ears comprises:
widening the ear body map of the clusters according to a preset proportion, detecting the seeds, if the detection label is kernel, returning the central coordinate information of each seed, and counting the seed coordinates, thus obtaining the number of the seeds of each cluster;
according to the external rectangular frame of the ear body of the ear, determining the ear length and the ear width of the ear;
counting the starting points of each spike row, and if the number is 0, the length of the bald tip is 0; if the number is 3, taking the average of y coordinates of the starting points of 3 spike rows by the length of the bald tip; otherwise, the bald tip length takes the average of the y coordinates of the starting point;
according to the spike body map, spike length, spike width and seed coordinate set, setting a measuring area, finding all seeds in the area to be measured, sorting all points from top to bottom, determining the seeds belonging to the same column by comparing transverse coordinate values, taking the uppermost seed of the row as the starting point of the row, and sequentially and circularly starting to find the next column so as to determine the row number and spike number.
10. The high throughput corn test method of claim 9, wherein the measuring area is set to: transverse direction 1/5*w-4/5*w and longitudinal direction 4/7*h-5/7*h.
CN202311157148.1A 2023-09-07 2023-09-07 High-flux corn seed tester and method Pending CN117296510A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311157148.1A CN117296510A (en) 2023-09-07 2023-09-07 High-flux corn seed tester and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311157148.1A CN117296510A (en) 2023-09-07 2023-09-07 High-flux corn seed tester and method

Publications (1)

Publication Number Publication Date
CN117296510A true CN117296510A (en) 2023-12-29

Family

ID=89285711

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311157148.1A Pending CN117296510A (en) 2023-09-07 2023-09-07 High-flux corn seed tester and method

Country Status (1)

Country Link
CN (1) CN117296510A (en)

Similar Documents

Publication Publication Date Title
US4975863A (en) System and process for grain examination
US11673166B2 (en) Seed imaging
EP2497823B1 (en) Device for harvesting bacterial colony and method therefor
US8791993B2 (en) Medicine management system and method using the same
CN107345789B (en) PCB hole position detection device and method
CN107185850B (en) Corn seed activity detection device based on hyperspectral imaging and electrical impedance
WO2017034776A1 (en) Multifunction livestock measurement station
CN106091926A (en) The detection apparatus and method of the miniature workpiece inside groove size of the asynchronous exposure of multi-point source
CN109784200B (en) Binocular vision-based cow behavior image acquisition and body condition intelligent monitoring system
CN108776138A (en) One kind is accelerated the ripening fruit library fruit quality on-Line Monitor Device
CN101929843B (en) Device and method for automatically measuring spike length of rice
DE112017004878T5 (en) Zell state measuring device
CN108549840A (en) A kind of method and device that analog instrument simultaneously and rapidly identifies
CA3093646C (en) Method and system for extraction of statistical sample of moving objects
US10873699B2 (en) Method and device for imaging a plant, and method for determining a characteristic of a plant
US20200167924A1 (en) Method, apparatus and system for cell detection
CN112304969A (en) Display module detection device, method, apparatus and system and storage medium
CN117296510A (en) High-flux corn seed tester and method
CN108733751A (en) Fat information monitoring system and method are surveyed in a kind of pig farm
CN112557394A (en) Full-automatic corn ear high-flux seed tester
CN117191788A (en) Multi-lens type wheat grain phenotype detection device and method
CN110865080A (en) Seed disk capable of collecting soybean hilum phenotype image data and collection method thereof
CN107389511B (en) Crop seed phenotype measuring method and portable device
CN109406506A (en) A kind of shared self-rated health terminal and test method
US11756214B2 (en) Method and apparatus for tracking nematode worms

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