CN107413674A - A kind of crop seed on-line sorting method and system - Google Patents
A kind of crop seed on-line sorting method and system Download PDFInfo
- Publication number
- CN107413674A CN107413674A CN201710428262.1A CN201710428262A CN107413674A CN 107413674 A CN107413674 A CN 107413674A CN 201710428262 A CN201710428262 A CN 201710428262A CN 107413674 A CN107413674 A CN 107413674A
- Authority
- CN
- China
- Prior art keywords
- seed
- image
- measured
- leptoprosopy
- crop
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
Landscapes
- Sorting Of Articles (AREA)
Abstract
The present invention provides a kind of crop seed on-line sorting method and system.Methods described includes:Wide the face image and leptoprosopy image of seed to be measured are obtained, the wide face image and the leptoprosopy image are spatially orthogonal;The threedimensional model of the seed to be measured is generated according to the wide face image and the leptoprosopy image;The phenotypic parameter of the threedimensional model is obtained, the seed to be measured is classified according to the phenotypic parameter.Crop seed on-line sorting method and system provided by the invention, are classified by the phenotypic parameter of the threedimensional model of crop seed to crop seed, the correct whole synthesis information for reflecting crop seed, improve the accuracy of crop seed sorting.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of crop seed on-line sorting method and system.
Background technology
Crop seed is valuable source in agri-scientific research and production, in molecular breeding, New Crop Varieties test, kind mirror
In the work such as fixed, quality estimating, realize crop seed phenotypic character quickly measure, sort it is most important.At present, high-volume crop
The screening and classification of seed, it is still desirable to manual operation, bothersome effort and subjective.
In order to solve the problems, such as that manual operation workload is big, mistake point rate is higher, have crop seed sorting system at present, from
The dynamic process for completing the screening of crop seed and sorting.Crop seed sorting system is obtained by gathering the direct picture of crop seed
Species seed phenotypic characteristic is taken as, screening sorting is carried out to crop seed according to phenotypic characteristic.
However, existing crop seed sorting system can only gather crop seed direct picture, crop seed is thus obtained
Phenotypic characteristic, it is impossible to the whole synthesis information of correct reflection crop seed, easily cause information erroneous judgement, cause sorting system mistake
Rate is high.
The content of the invention
For in the prior art the defects of, the embodiments of the invention provide a kind of crop seed on-line sorting method and be
System.
On the one hand, the embodiment of the present invention provides a kind of crop seed on-line sorting method, including:
Obtain wide the face image and leptoprosopy image of seed to be measured, the wide face image and the leptoprosopy image are spatially just
Hand over;
The threedimensional model of the seed to be measured is generated according to the wide face image and the leptoprosopy image;
The phenotypic parameter of the threedimensional model is obtained, the seed to be measured is classified according to the phenotypic parameter.
On the other hand, the embodiment of the present invention provides a kind of crop seed on-line sorting system, including:
Workbench, conveyer belt, imaging support, top side camera, side cameras, computer, spray valve and collection kind device;
The workbench is used to fix the conveyer belt, imaging support, spray valve and collection kind device;
The conveyer belt is arranged on the upper surface of the workbench, for automatically delivering seed to be measured;
The imaging support is arranged on the both sides of the workbench, is taken the photograph for fixing the top side camera and the side
Camera;
The top side camera is arranged on the top of the imaging support, and the side cameras is arranged on the imaging branch
The side of frame, the optical axis of the top side camera is orthogonal with the optical axis of the side cameras, the top side camera and described
Side cameras is used for the image for obtaining the seed to be measured;
The computer is connected with the top side camera and the side cameras, exists for performing above-mentioned crop seed
Line method for sorting, and control the switch of the spray valve;
The spray valve, installed in the side of the workbench, it is connected with the computer, for the seed to be measured to be divided
Pick in corresponding collection kind device;
The collection kind device, installed in the end of the workbench, the seed to be measured is collected for category.
Crop seed on-line sorting method and system provided in an embodiment of the present invention, pass through the threedimensional model of crop seed
Phenotypic parameter is classified to crop seed, the correct whole synthesis information for reflecting crop seed, improves the sorting of crop seed
Accuracy.
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 apparent that, drawings in the following description are this hairs
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is crop seed on-line sorting method flow schematic diagram provided in an embodiment of the present invention;
Fig. 2 is crop seed on-line sorting system structure diagram provided in an embodiment of the present invention;
Fig. 3 is the crop seed on-line sorting system structure diagram that further embodiment of this invention provides;
Description of reference numerals:
01-workbench;02-transmission belt;03-imaging support;
04-top side camera;05-side cameras;06-computer;
07-valve;08-collection kind device;09-colorimetric card;
10-light source;11-feed mechanism for seed;12-guidance panel;
13-transmission stepper motor.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is crop seed on-line sorting method flow schematic diagram provided in an embodiment of the present invention, as shown in figure 1, described
Method includes:
Step S11, wide the face image and leptoprosopy image of seed to be measured are obtained, the wide face image and the leptoprosopy image exist
It is spatially orthogonal;
Step S12, the threedimensional model of the seed to be measured is generated according to the wide face image and the leptoprosopy image;
Step S13, the phenotypic parameter of the threedimensional model is obtained, the seed to be measured is carried out according to the phenotypic parameter
Classification.
Specifically, seed to be measured is the crop seeds such as corn, wheat, and the sorting of crop seed is included in similar crop seed
The crop seed for meeting different condition is picked out, such as superior corn seed and inferior maize seed are sorted out in corn seed
Seed.The sorting of crop seed also includes being classified inhomogeneous crop seed category, for example, including corn seed, small
In the various crop seed such as wheat seeds seed and soybean seed, corn seed, wheat seed, soybean seed etc. are sorted out.
When needing to sort one of crop seed, wide the face image and leptoprosopy figure of seed to be measured are obtained first
Picture, wide the face image and leptoprosopy image are spatially orthogonal.Such as wide face image can be image corresponding to crop seed front,
Leptoprosopy image can be image corresponding to crop seed side.Because the structure of crop seed is relatively easy, single, it is therefore assumed that
Crop seed is symmetrical structure, and the threedimensional model of seed to be measured is generated according to mutually orthogonal wide face image and leptoprosopy image.So
The phenotypic parameter of threedimensional model is obtained afterwards, and the phenotypic parameter represents the phenotypic parameter of seed to be measured, according to phenotypic parameter to institute
Seed to be measured is stated to be classified.Specifically, according to the phenotypic parameter of acquisition and the phenotypic parameter threshold value of setting, seed to be measured is entered
Row classification.
For example, being sorted to a pile corn seed, then loose the face image and leptoprosopy figure of each corn seed are obtained first
Picture, herein, each corn seed is referred to as seed to be measured.Then generated according to wide the face image and leptoprosopy image of seed to be measured
The threedimensional model of seed to be measured, the phenotypic parameter of threedimensional model is obtained, the phenotypic parameter got and corn seed phenotype are joined
Number threshold value is contrasted, and corn seed is assigned in corresponding classification.
If being sorted to different classes of crop seed, using each crop seed as seed to be measured, obtain to be measured
Wide the face image and leptoprosopy image of seed, then generate the three of seed to be measured according to wide the face image and leptoprosopy image of seed to be measured
Dimension module;The phenotypic parameter of the threedimensional model is obtained, by the phenotypic parameter got and the different types of Crop Species of setting
The phenotypic parameter threshold value of seed is compared, if meeting the phenotypic parameter of A class crop seeds, seed to be measured is assigned into A class crops
In seed.
Crop seed on-line sorting method provided in an embodiment of the present invention, joined by the phenotype of the threedimensional model of crop seed
It is several that crop seed is classified, the correct whole synthesis information for reflecting crop seed, improve the correct of crop seed sorting
Rate.
On the basis of above-described embodiment, further, wide face image and leptoprosopy the image bag for obtaining seed to be measured
Include:
The first original image and the second original image of the seed to be measured are gathered simultaneously;
First object image is obtained according to first original image, the second target is obtained according to second original image
Image;
The first object image is divided into the first embryo and first endosperm two parts, if the first embryo area accounts for described
The ratio of one target image area is more than wide face experimental threshold values, then the wide face figure using the first object image as seed to be measured
Picture;
Second target image is divided into the second embryo and second endosperm two parts, if the second embryo area accounts for described
The ratio of two target image areas is more than leptoprosopy experimental threshold values, then using second target image as the narrow of the seed to be measured
Face image.
Specifically, the first original image and the second original image of seed to be measured are gathered using two groups of video cameras simultaneously, two
The optical axis of group video camera is orthogonal.Then the first original image collected is handled, obtains first object image, this first
Target image only includes the image of seed to be measured.For example, what is pre-saved is subtracted to the first original image using background subtraction
Background image, interesting target image is obtained as first object image.Then first object image is divided into the first embryo and
One endosperm two parts, such as with k means clustering algorithms by first object image clustering be the first embryo and first endosperm two parts, it
Calculate afterwards the first embryo area account for first object image area ratio, if the ratio is more than wide face experimental threshold values, by
Wide face image of one target image as seed to be measured.
Similarly, the second original image collected is handled, obtains the second target image, second target image is only
Include the image of seed to be measured.For example, subtracting the background image pre-saved to the second original image using background subtraction, obtain
Interesting target image is obtained as the second target image.In actual applications, the second original image may include multiple kinds to be measured
Seed, the second original image is divided into multiple images region first with dividing ridge method, it is then true according to the position of seed to be measured
The effective coverage of fixed seed to be measured, the second target image then is obtained to the imagery exploitation background subtraction in the region.Then will
Second target image is divided into the second embryo and second endosperm two parts, such as is clustered the second target image with k means clustering algorithms
For the second embryo and second endosperm two parts, calculate afterwards the second embryo area account for the second target image area ratio, if should
Ratio is more than leptoprosopy experimental threshold values, then the leptoprosopy image using the second target image as seed to be measured.
For example, gathering the first original image and the second original image of corn seed simultaneously, obtained using background subtraction
First object image, first object image is then divided into by the first embryo and first endosperm two parts according to k means clustering methods, counted
Calculate the first embryo area account for first object image area ratio, more than wide face experimental threshold values, then first object image is made
For the loose face image of the corn seed.The second original image is split according to watershed algorithm, had to the corn seed
Imitate region and obtain the second target image using background subtraction, be then divided into the second target image according to k means clustering methods
Second embryo and second endosperm two parts, the area of the second embryo of calculating accounts for the ratio of the area of the second target image, real more than leptoprosopy
Threshold value is tested, then the leptoprosopy image using the second target image as the corn seed.
Crop seed on-line sorting method provided in an embodiment of the present invention, seed to be measured is obtained by the first original image
Wide face image, the leptoprosopy image of seed to be measured is obtained by the second original image, make wide the face image and leptoprosopy figure of seed to be measured
Image as correctly reflecting crop seed, so that shape of the threedimensional model with closer actual crop seed, so as to improve
The accuracy of crop seed phenotypic parameter, and then improve the accuracy of crop seed sorting.
On the basis of the various embodiments described above, further, the first original image of the collection seed to be measured and
Also include before second original image:
Obtain colorimetric card graphic;
The colorimetric card graphic is parsed, obtains color correction parameters and dimension correction parameter;
Correspondingly, it is described that first object image is obtained according to first original image, according to second original image
Also include after obtaining the second target image:
Color correction is carried out to the first object image and second target image according to the color correction parameters;
Dimension correction is carried out to the first object image and second target image according to the dimension correction parameter.
Specifically, a colorimetric card is placed in seed same position to be measured first, then gathers the image of colorimetric card, according to
The actual color of each color lump obtains color correction parameters in the color of each color lump and colorimetric card in the image of acquisition, according to acquisition
The size of colorimetric card and the actual size of colorimetric card obtain dimension correction parameter in image.Then gather seed to be measured first is former
Beginning image and the second original image, first object image is obtained according to the first original image, and the is obtained according to the second original image
Two target images, color correction is carried out to first object image and the second target image according to color correction parameters, according to size
Correction parameter carries out dimension correction to first object image and the second target image.First object image is divided into the first embryo and
One endosperm two parts, if the ratio that the first embryo area accounts for first object image area is more than wide face experimental threshold values, by the first mesh
Wide face image of the logo image as seed to be measured;Second target image is divided into the second embryo and second endosperm two parts, if second
The ratio that embryo area accounts for the second target image area is more than leptoprosopy experimental threshold values, then using the second target image as seed to be measured
Leptoprosopy image.
Crop seed on-line sorting method provided in an embodiment of the present invention, the image of seed to be measured is carried out color correction and
Dimension correction, the image of seed to be measured is set more correctly to reflect the phenotypic characteristic of seed to be measured, so that threedimensional model is closer
Actual crop seed, so as to improve the accuracy of crop seed phenotypic parameter, and then improve the sorting of crop seed just
True rate.
It is further, described to be given birth to according to the wide face image and the leptoprosopy image on the basis of the various embodiments described above
Into the threedimensional model of the seed to be measured, it is specially;
The pixel profile of the wide face image and the pixel profile of the leptoprosopy image are calculated, according to the wide face image
The pixel profile of pixel profile and the leptoprosopy image generates the spatial surrounding box of the seed to be measured, to the seed to be measured
Spatial surrounding box registration, generate the threedimensional model of the seed to be measured.
Specifically, the pixel profile of wide face image is calculated according to the wide face image of seed to be measured, using B-spline curves to this
Pixel profile is fitted, and obtains the wide face parametrization profile of seed to be measured, leptoprosopy is calculated according to the leptoprosopy image of seed to be measured
The pixel profile of image, the pixel profile is fitted using B-spline curves, obtains the leptoprosopy parametrization wheel of seed to be measured
Exterior feature, the wide face parametrization profile of seed to be measured and the leptoprosopy parametrization profile of seed to be measured are spatially orthogonal.Joined according to wide face
Numberization profile and leptoprosopy parametrization profile generate the spatial surrounding box of seed to be measured, and profile and leptoprosopy parameter are parameterized according to wide face
Change spatial surrounding box registration of the profile to seed to be measured, because the structure of crop seed is relatively easy, single, it is therefore assumed that crop
Seed is symmetrical structure, and the threedimensional model of seed to be measured is generated according to spatial surrounding box.
Crop seed on-line sorting method provided in an embodiment of the present invention, the three of seed to be measured are generated according to spatial surrounding box
Dimension module, make the closer actual crop seed of threedimensional model, so as to improve the accuracy of crop seed phenotypic parameter, and then
Improve the accuracy of crop seed sorting.
On the basis of the various embodiments described above, further, the phenotypic parameter includes but is not limited to the threedimensional model
Colouring information, volume, surface area and embryo area.
Specifically, obtain the phenotypic parameter of threedimensional model, for example, obtain the colouring information of threedimensional model, volume, surface area,
Embryo area isophenous parameter, enters according to parameter threshold corresponding to the phenotypic parameter of threedimensional model and each phenotypic parameter to seed to be measured
Row classification.
Crop seed on-line sorting method provided in an embodiment of the present invention, by the phenotypic parameter of threedimensional model to kind to be measured
Seed is classified, the correct whole synthesis information for reflecting crop seed, improves the accuracy of crop seed sorting.
For example, classifying to corn seed, two classes are classified as, one kind is superior corn seed, and one kind is inferior jade
Rice seed.Colorimetric card graphic is gathered first, is obtained color correction parameters and dimension correction parameter, is then gathered corn seed to be measured
The first original image and the second original image, utilize dividing ridge method and background subtraction to obtain the loose face of corn seed to be measured
Image and leptoprosopy image, color correction and dimension correction then are carried out to wide face image and leptoprosopy image, make wide face image and narrow
Face image can correctly reflect the phenotypic characteristic of corn seed to be measured.Loose face is calculated according to the loose face image of corn seed to be measured afterwards
The pixel profile of image, the pixel profile is fitted using B-spline curves, obtains the loose face parametrization of corn seed to be measured
Profile, the pixel profile of leptoprosopy image is calculated according to the leptoprosopy image of corn seed to be measured, using B-spline curves to the pixel wheel
Exterior feature is fitted, and obtains the leptoprosopy parametrization profile of corn seed to be measured, and the loose face of corn seed to be measured parameterizes profile with treating
The leptoprosopy parametrization profile for surveying corn seed is spatially orthogonal.Profile and leptoprosopy parametrization profile generation are parameterized according to wide face
The spatial surrounding box of corn seed to be measured, profile is parameterized according to wide face and leptoprosopy parameterizes sky of the profile to maize seed seed to be measured
Between bounding box registration, generate the threedimensional model of corn seed to be measured.Then the colouring information of acquisition threedimensional model, volume, surface
Product, embryo area isophenous parameter, superior corn seed and the corresponding phenotypic parameter threshold value of inferior corn seed are contrasted, if jade to be measured
The phenotypic parameter of rice seed meets superior corn seed, then corn seed to be measured is divided into superior corn seed, if jade to be measured
The phenotypic parameter of rice seed meets inferior corn seed, then corn seed to be measured is divided into inferior corn seed.
Fig. 2 is crop seed on-line sorting system structure diagram provided in an embodiment of the present invention, as shown in Fig. 2 this is
System includes:Workbench 01, conveyer belt 02, imaging support 03, top side camera 04, side cameras 05, computer 06, spray valve 07
A device 08 is planted with collection, wherein:
Workbench 01 is used to fix the conveyer belt, imaging support, spray valve and collects kind of a device, and conveyer belt 02 is arranged on workbench
01 upper surface, for automatically delivering seed to be measured, the both sides of the installment work platform 01 of support 03 are imaged, are imaged for fixed top
Machine 04 and side cameras 05, top side camera 04 are arranged on the top of imaging support 03, and side cameras 05 is arranged on imaging
The side of support 03, the optical axis of top side camera 04 is perpendicular to conveyer belt, and the optical axis of side cameras 05 is parallel to conveyer belt, top
The optical axis of portion's video camera 04 is orthogonal with the optical axis of side cameras 05, and top side camera 04 and side cameras 05 are treated for acquisition
The image of seed is surveyed, computer 06 is connected with top side camera 04 and side cameras 05, existed for performing above-mentioned crop seed
Line method for sorting is classified to seed to be measured, and controls the switch of spray valve 07, and spray valve 07 is arranged on the side of the workbench,
It is connected with computer 06, for seed to be measured to be sorted in corresponding collection kind device 08, collection kind device 08 is installed in workbench 01
End, seed to be measured is collected for category.
Specifically, first according to the height of the big minor adjustment top side camera 04 of seed to be measured, and conveyer belt 02 is obtained
Speed.For example, top side camera 04 works under real-time monitoring pattern, a crop seed is placed in the entrance of conveyer belt 02,
Top side camera 04 detects that crop seed enters and leaves the time of camera field of view, then connects the above-mentioned time by USB
Mouth sends to computer 06, computer 06 and calculates line speed according to camera field of view region full-size(d).Transmit afterwards
Band 02 transmits seed to be measured, and top side camera 04 works under real-time monitoring pattern, when detecting that seed to be measured enters imaging area
During central area, the signal of collection image is sent to side cameras 05, top side camera 04 and side cameras 05 are adopted simultaneously
Collect the image of seed to be measured, then the image collected is sent by USB interface and performs above-mentioned to computer 06, computer 06
Crop seed on-line sorting method, obtains classification corresponding to seed to be measured, its process refers to above method embodiment, herein no longer
Repeat.Then computer 06 calculates seed to be measured according to the speed of conveyer belt and reaches the specified time for spraying valve 07, passes through electric-controlled
System starts spray valve when seed to be measured reaches and specifies spray valve 07, is carried with the compressor (not shown) that spray valve 07 is connected to spray valve
Seed to be measured is sprayed onto on corresponding track by supply pressure, spray valve 07, and then seed to be measured enters collection kind device along corresponding track
In 08, crop seed on-line sorting process is completed.
In actual applications, multiple spray valves can be set according to the classification of seed to be measured, for example, seed to be measured is two classes,
One spray valve can be then set, and two tracks are set on a moving belt, two collection kind devices are set.If seed to be measured is n classes, can
To set n-1 spray valve, accordingly, on a moving belt set n bar tracks, for spray valve start after transmit it is categorized not
Same crop seed, and a n collection kind device is set, collect crop seed for category.
In actual applications, side cameras can also be arranged on the side of imaging frame, and its optical axis is vertical with conveyer belt, top
Portion's video camera and the optical axis of side cameras are still orthogonal, can equally realize above-mentioned crop seed online classification method, herein
Repeat no more.
Crop seed on-line sorting system provided in an embodiment of the present invention, obtained by two groups of orthogonal video cameras of optical axis
Crop seed image carries out three-dimensional modeling to crop seed, and the threedimensional model correctly reflects the whole synthesis information of crop seed,
Improve the accuracy of crop seed sorting system.
On the basis of above-described embodiment, further, Fig. 3 is that the crop seed that further embodiment of this invention provides is online
Sorting system structural representation, as shown in figure 3, the system includes:Workbench 01, conveyer belt 02, imaging support 03, top are taken the photograph
Camera 04, side cameras 05, computer 06, spray valve 07, collection kind device 08, colorimetric card 09 and light source 10.Wherein workbench 01, biography
Band 02, imaging support 03, top side camera 04, side cameras 05, computer 06, spray valve 07 and collection kind device 08 is sent to refer to above-mentioned
Crop seed on-line sorting system, here is omitted.
Colorimetric card 09 is placed on the underface of top side camera 04, so that top side camera 04 obtains colorimetric card graphic, and
Colorimetric card graphic is sent to computer 06, so that computer 06 obtains color correction parameters and dimension correcting according to colorimetric card graphic
Positive parameter, light source 10 are used for the light filling when top side camera 04 and side cameras 05 are shot.
Specifically, before the image of seed to be measured is gathered, top side camera 04 gathers the image of colorimetric card 09 first, and
Colorimetric card graphic is sent to computer 06, computer 06 is according to assorted in the color of each color lump in colorimetric card graphic and colorimetric card
The actual color of block obtains color correction parameters, is obtained according to the size that the size of colorimetric card in colorimetric card graphic and colorimetric card are actual
Take dimension correction parameter, then according to color correction parameters and dimension correction parameter before three-dimensional modeling to the image of seed to be measured
Color correction and dimension correction are carried out, seed to be measured is divided according to the phenotypic parameter of the threedimensional model of seed to be measured afterwards
Class.Light source 10 is used for the light filling when top side camera 04 and side cameras 05 are shot, to reduce influence during natural light deficiency.
Crop seed on-line sorting system provided in an embodiment of the present invention, the image of seed to be measured is carried out color correction and
Dimension correction, the image of seed to be measured is set more correctly to reflect the phenotypic characteristic of seed to be measured, so that threedimensional model is closer
Actual crop seed, so as to improve the accuracy of crop seed phenotypic parameter, and then improve the sorting of crop seed just
True rate.
On the basis of the various embodiments described above, further, as shown in figure 3, the system includes:Workbench 01, transmission
Band 02, imaging support 03, top side camera 04, side cameras 05, computer 06, spray valve 07, collection kind of a device 08, colorimetric card 09,
Light source 10 and feed mechanism for seed 11, wherein workbench 01, conveyer belt 02, imaging support 03, top side camera 04, side cameras 05,
Computer 06, spray valve 07, collection kind device 08, colorimetric card 09 and light source 10 refer to above-mentioned crop seed on-line sorting system, herein not
Repeat again.Feed mechanism for seed 11 is arranged on the front end of workbench 01, at least one seed to be measured to be placed sequentially in into conveyer belt 02
On.
Crop seed on-line sorting system provided in an embodiment of the present invention, seed to be measured is sequentially placed on a moving belt,
Make the IMAQ operation of the completion crop seed of crop seed on-line sorting system order, improve crop seed on-line sorting
The efficiency of system.
On the basis of the various embodiments described above, further, as shown in figure 3, the system includes:Workbench 01, transmission
Band 02, imaging support 03, top side camera 04, side cameras 05, computer 06, spray valve 07, collection kind of a device 08, colorimetric card 09,
Light source 10, feed mechanism for seed 11, guidance panel 12 and transmission stepper motor 13, wherein workbench 01, conveyer belt 02, imaging support 03,
Top side camera 04, side cameras 05, computer 06, spray valve 07, collection kind device 08, colorimetric card 09, light source 10 and feed mechanism for seed 11
Above-mentioned crop seed on-line sorting system is referred to, here is omitted.Guidance panel 12 is arranged on the side of workbench 01, is used for
Receive the speed configuration information of conveyer belt;The front end that stepper motor 13 is arranged on conveyer belt 02 is transmitted, for controlling conveyer belt
Transfer rate.
Specifically, the speed of conveyer belt is set according to actual conditions on guidance panel 12, is then transported on stepper motor 13
According to the speed of the speed control conveyer belt of setting, the seed to be measured on conveyer belt is set to be passed on a moving belt according to the speed of setting
Send.
Crop seed on-line sorting system provided in an embodiment of the present invention, pass through guidance panel and transmission step motor control
The speed of conveyer belt, crop seed is transmitted according to the speed of setting, improve the efficiency of crop seed on-line sorting system.
On the basis of the various embodiments described above, further, the feed mechanism for seed includes:Seeding stepper motor, seeds box, row
Kind wheel, hole and discharging tube;The seeding stepper motor is connected with the seed wheel, for controlling the rotation speed of the seed wheel
Degree;The seeds box, installed in the front end of the workbench, for collecting at least one seed to be measured;The seed wheel,
In the seeds box, the hole, installed in the outside of the seeds box, the discharging tube is connected with the hole,
The seed wheel, the hole and the discharging tube are used to the seed to be measured in the seeds box being placed sequentially in the transmission
Take.
Specifically, multiple crop seeds to be sorted are have collected in seeds box, seeding step motor control seed wheel rotates,
The crop seed in seeds box is set to enter by hole in discharging tube, seed is sequentially placed on a moving belt by discharging tube.
Crop seed on-line sorting system provided in an embodiment of the present invention, seed to be measured is sequentially placed on a moving belt,
Make the IMAQ operation of the completion crop seed of crop seed on-line sorting system order, improve crop seed on-line sorting
The efficiency of system.
For example, being sorted to a pile corn seed, then the height of top side camera is adjusted first, makes corn seed to be measured
Image be exactly in the central area of image acquisition areas, then top side camera obtains the image of colorimetric card, and by colorimetric card
Image sends to computer, computer and obtains color correction parameters and dimension correction parameter.Then top side camera enters real-time
Monitoring pattern, the speed of conveyer belt is set on the control panel, starts conveyer belt by transmitting stepper motor, one is treated
Corn seed to be surveyed to be placed on conveyer belt, top side camera obtains the time that the corn seed enters and leaves camera field of view, and
It will send time to computer, computer and the speed of conveyer belt is calculated according to the actual size of camera field of view.
Corn seed to be sorted is put into seeds box afterwards, seeding step motor control seed wheel rotates, by seeds box
In corn seed be sequentially placed on a moving belt by hole and discharging tube.Before corn seed on conveyer belt is with conveyer belt
OK, when top side camera detects that corn seed enters imaging area central area, top side camera and side cameras are started
Shoot simultaneously, and the image photographed is sent to computer.The image and side that computer is shot according to top side camera are taken the photograph
The image of camera shooting obtains loose the face image and leptoprosopy image of corn seed, and carries out color to wide face image and leptoprosopy image
Correction and dimension correction, the threedimensional model of corn seed is then obtained according to wide the face image and leptoprosopy image after correction, calculated
The phenotypic parameter of threedimensional model, the threshold comparison with setting, obtain the classification of corn seed.Then computer is according to conveyer belt
Speed, calculate corn seed and reach the time for specifying spray valve, start in the time and specify spray valve, corn seed is entered classification
In corresponding track, subsequently into collection kind device, crop seed on-line sorting process is completed.
Device and system embodiment described above is only schematical, wherein described be used as separating component explanation
Unit can be or may not be physically separate, can be as the part that unit is shown or may not be
Physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can be according to the actual needs
Some or all of module therein is selected to realize the purpose of this embodiment scheme.Those of ordinary skill in the art are not paying
In the case of performing creative labour, you can to understand and implement.
Claims (10)
- A kind of 1. crop seed on-line sorting method, it is characterised in that including:Wide the face image and leptoprosopy image of seed to be measured are obtained, the wide face image and the leptoprosopy image are spatially orthogonal;The threedimensional model of the seed to be measured is generated according to the wide face image and the leptoprosopy image;The phenotypic parameter of the threedimensional model is obtained, the seed to be measured is classified according to the phenotypic parameter.
- 2. according to the method for claim 1, it is characterised in that wide the face image and leptoprosopy image for obtaining seed to be measured Including:The first original image and the second original image of the seed to be measured are gathered simultaneously;First object image is obtained according to first original image, the second target figure is obtained according to second original image Picture;The first object image is divided into the first embryo and first endosperm two parts, if the first embryo area accounts for first mesh The ratio of logo image area is more than wide face experimental threshold values, then the wide face image using the first object image as seed to be measured;Second target image is divided into the second embryo and second endosperm two parts, if the second embryo area accounts for second mesh The ratio of logo image area is more than leptoprosopy experimental threshold values, then the leptoprosopy figure using second target image as the seed to be measured Picture.
- 3. according to the method for claim 2, it is characterised in that the first original image of the collection seed to be measured and Also include before second original image:Obtain colorimetric card graphic;The colorimetric card graphic is parsed, obtains color correction parameters and dimension correction parameter;Correspondingly, it is described that first object image is obtained according to first original image, obtained according to second original image Also include after second target image:Color correction is carried out to the first object image and second target image according to the color correction parameters;Dimension correction is carried out to the first object image and second target image according to the dimension correction parameter.
- 4. according to the method for claim 1, it is characterised in that described to be given birth to according to the wide face image and the leptoprosopy image Into the threedimensional model of the seed to be measured, it is specially;The pixel profile of the wide face image and the pixel profile of the leptoprosopy image are calculated, according to the pixel of the wide face image The pixel profile of profile and the leptoprosopy image generates the spatial surrounding box of the seed to be measured, to the space of the seed to be measured Bounding box registration, generate the threedimensional model of the seed to be measured.
- 5. according to the method for claim 1, it is characterised in that the phenotypic parameter includes but is not limited to the threedimensional model Colouring information, volume, surface area and embryo area.
- A kind of 6. crop seed on-line sorting system, it is characterised in that including:Workbench, conveyer belt, imaging support, top side camera, side cameras, computer, spray valve and collection kind device;The workbench is used to fix the conveyer belt, imaging support, spray valve and collection kind device;The conveyer belt is arranged on the upper surface of the workbench, for automatically delivering seed to be measured;The imaging support is arranged on the both sides of the workbench, for fixing the top side camera and side shooting Machine;The top side camera is arranged on the top of the imaging support, and the side cameras is arranged on the imaging support Side, the optical axis of the top side camera is orthogonal with the optical axis of the side cameras, the top side camera and the side Video camera is used for the image for obtaining the seed to be measured;The computer is connected with the top side camera and the side cameras, for performing as claim 1-5 is any Method described in one claim, and control the switch of the spray valve;The spray valve, installed in the side of the workbench, it is connected with the computer, for the seed to be measured to be sorted to In corresponding collection kind device;The collection kind device, installed in the end of the workbench, the seed to be measured is collected for category.
- 7. system according to claim 6, it is characterised in that also include:Colorimetric card and light source, the colorimetric card are placed on the underface of the top side camera, so that the top side camera obtains Colorimetric card graphic is taken, and the colorimetric card graphic is sent to computer, so that the computer is according to the colorimetric card graphic Obtain color correction parameters and dimension correction parameter;The light source is used to clap in the top side camera and the side cameras Light filling when taking the photograph.
- 8. system according to claim 6, it is characterised in that also include:Feed mechanism for seed, installed in the front end of the workbench, at least one seed to be measured to be placed sequentially in into the biography Send and take.
- 9. system according to claim 6, it is characterised in that also include:Guidance panel and transmission stepper motor, the guidance panel is arranged on the side of the workbench, for receiving the biography Send the speed configuration information of band;The transmission stepper motor, installed in the front end of the conveyer belt, for controlling the conveyer belt Transfer rate.
- 10. system according to claim 8, it is characterised in that the feed mechanism for seed includes:Seeding stepper motor, seeds box, seed wheel, hole and discharging tube;The seeding stepper motor is connected with the seed wheel, for controlling the velocity of rotation of the seed wheel;The seeds box, installed in the front end of the workbench, for collecting at least one seed to be measured;The seed wheel, in the seeds box, the hole, installed in the outside of the seeds box, the discharging tube Be connected with the hole, the seed wheel, the hole and the discharging tube be used for by the seed to be measured in the seeds box according to It is secondary to be placed on the conveyer belt.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710428262.1A CN107413674B (en) | 2017-06-08 | 2017-06-08 | A kind of crop seed on-line sorting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710428262.1A CN107413674B (en) | 2017-06-08 | 2017-06-08 | A kind of crop seed on-line sorting method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107413674A true CN107413674A (en) | 2017-12-01 |
CN107413674B CN107413674B (en) | 2019-09-10 |
Family
ID=60429707
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710428262.1A Active CN107413674B (en) | 2017-06-08 | 2017-06-08 | A kind of crop seed on-line sorting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107413674B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108607819A (en) * | 2018-04-25 | 2018-10-02 | 重庆邮电大学 | Material sorting system and method |
CN110619297A (en) * | 2019-09-10 | 2019-12-27 | 中国科学院东北地理与农业生态研究所 | Bean seed image batch acquisition and identification method and device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4187545A (en) * | 1978-02-28 | 1980-02-05 | Frank Hamachek Machine Company | Article orientation determining apparatus |
RU2073571C1 (en) * | 1992-05-15 | 1997-02-20 | Шахматов Сергей Николаевич | Seed grader |
CN1603013A (en) * | 2004-11-02 | 2005-04-06 | 江苏大学 | On-line fruit quality detection and classification apparatus and method based on three camera chains |
CN101234381A (en) * | 2008-03-07 | 2008-08-06 | 天津市华核科技有限公司 | Granular material sorting classifying method based on visual sense recognition |
CN101395466A (en) * | 2006-03-02 | 2009-03-25 | 福斯分析有限公司 | Device and method for optical measurement of small particles such as grains from cereals and like crops |
CN102284428A (en) * | 2011-05-12 | 2011-12-21 | 浙江大学 | Corn real-time detection and grading machine vision system |
CN103841726A (en) * | 2014-03-06 | 2014-06-04 | 河南科技大学 | Luminance real-time adjusting device of light source in pole piece surface defect detection and adjusting method thereof |
CN105865335A (en) * | 2016-04-21 | 2016-08-17 | 四川大学 | Stator bar sectional dimension detection system based on machine vision |
CN106607344A (en) * | 2017-02-17 | 2017-05-03 | 河南省现代富博智能装备科技有限公司 | Corn seed dynamic image fine selection device and method used for oriented sowing |
-
2017
- 2017-06-08 CN CN201710428262.1A patent/CN107413674B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4187545A (en) * | 1978-02-28 | 1980-02-05 | Frank Hamachek Machine Company | Article orientation determining apparatus |
RU2073571C1 (en) * | 1992-05-15 | 1997-02-20 | Шахматов Сергей Николаевич | Seed grader |
CN1603013A (en) * | 2004-11-02 | 2005-04-06 | 江苏大学 | On-line fruit quality detection and classification apparatus and method based on three camera chains |
CN101395466A (en) * | 2006-03-02 | 2009-03-25 | 福斯分析有限公司 | Device and method for optical measurement of small particles such as grains from cereals and like crops |
CN101234381A (en) * | 2008-03-07 | 2008-08-06 | 天津市华核科技有限公司 | Granular material sorting classifying method based on visual sense recognition |
CN102284428A (en) * | 2011-05-12 | 2011-12-21 | 浙江大学 | Corn real-time detection and grading machine vision system |
CN103841726A (en) * | 2014-03-06 | 2014-06-04 | 河南科技大学 | Luminance real-time adjusting device of light source in pole piece surface defect detection and adjusting method thereof |
CN105865335A (en) * | 2016-04-21 | 2016-08-17 | 四川大学 | Stator bar sectional dimension detection system based on machine vision |
CN106607344A (en) * | 2017-02-17 | 2017-05-03 | 河南省现代富博智能装备科技有限公司 | Corn seed dynamic image fine selection device and method used for oriented sowing |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108607819A (en) * | 2018-04-25 | 2018-10-02 | 重庆邮电大学 | Material sorting system and method |
CN110619297A (en) * | 2019-09-10 | 2019-12-27 | 中国科学院东北地理与农业生态研究所 | Bean seed image batch acquisition and identification method and device |
CN110619297B (en) * | 2019-09-10 | 2024-05-14 | 中国科学院东北地理与农业生态研究所 | Bean fruiting body image batch acquisition and recognition method and device |
Also Published As
Publication number | Publication date |
---|---|
CN107413674B (en) | 2019-09-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5917927A (en) | Grain inspection and analysis apparatus and method | |
CN101905215B (en) | Digitalized paddy rice seed testing machine | |
CN104198324B (en) | Computer vision-based method for measuring proportion of cut leaves in cut tobacco | |
CN110473178A (en) | A kind of open defect detection method and system based on multiple light courcess fusion | |
BR102015032436B1 (en) | GRAIN QUALITY MONITORING METHOD AND NON-TRANSIENT COMPUTER READABLE MEDIA | |
CN109794437A (en) | Intelligent sorting system based on computer vision | |
CN112544242B (en) | AI cloud computing-based full-automatic rice threshing and yield analysis system | |
CN105549486A (en) | Tobacco topping sprouting inhibition detection control system based on machine vision | |
CN105806751A (en) | On-line monitoring system and method for crushing of cereals in grain tank of combine harvester | |
CN104256882A (en) | Method for measuring proportion of reconstituted tobacco in cut tobacco on basis of computer vision | |
CN113820325B (en) | Corn grain direct-harvest impurity-containing rate and breakage rate online detection system and method | |
CN113920106B (en) | Corn growth vigor three-dimensional reconstruction and stem thickness measurement method based on RGB-D camera | |
CN107413674A (en) | A kind of crop seed on-line sorting method and system | |
CN107121436A (en) | The Intelligent detecting method and identification device of a kind of silicon material quality | |
CN110188609A (en) | A kind of detection method of weed seed | |
CN109030504A (en) | The panorama potato defect detecting device and method combined based on actual situation imaging | |
CN205484102U (en) | Fruit quality control surveys system based on computer vision | |
CN104949916A (en) | Fall type corn ear property measuring apparatus and measuring method thereof | |
CN110314361A (en) | A kind of basketball goal score judgment method and system based on convolutional neural networks | |
CN104488405A (en) | Machine vision based corn ear high-throughput pipelining measurement device and method | |
CN112907516B (en) | Sweet corn seed identification method and device for plug seedling | |
CN114441444A (en) | Fusion sorting method based on multiband multiplexing | |
CN207366475U (en) | A kind of relief pattern Online Video detection device | |
CN112730417A (en) | Online detection device for wheat appearance quality | |
CN104574398A (en) | Boxed cigarette filter stick counting system based on line scanning camera |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |