CN117405607B

CN117405607B - Seed phenotype measurement system, method and related equipment

Info

Publication number: CN117405607B
Application number: CN202311726460.8A
Authority: CN
Inventors: 韩志国; 张佳菲; 金林; 赵前哲; 李皓
Original assignee: Phenotrait Beijing Technology Co ltd; Huinuo Yunpu Hainan Technology Co ltd
Current assignee: Phenotrait Beijing Technology Co ltd; Huinuo Yunpu Hainan Technology Co ltd
Priority date: 2023-12-15
Filing date: 2023-12-15
Publication date: 2024-02-23
Anticipated expiration: 2043-12-15
Also published as: CN117405607A

Abstract

The application designs a seed type measurement system, a seed type measurement method and related equipment. The method comprises the following steps: collecting original hyperspectral information data of seeds in a seed-separating movable disk in a linear array push-broom mode by utilizing a measuring mechanism; acquiring white board hyperspectral data corresponding to a preset white board arranged on a seed separation movable disk, and performing reflectivity conversion on original hyperspectral information data according to dark current hyperspectral data and white board hyperspectral data acquired in advance to obtain hyperspectral information data; hyperspectral information data comprising: a single band image under a plurality of bands; according to a pre-acquired transformation matrix, performing error shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data; seed characteristic data is extracted according to the three-dimensional hyperspectral data, and seed phenotype data is determined according to the seed characteristic data. The method and the device can accurately acquire the phenotype data of the seeds, avoid waste and loss, and improve detection efficiency.

Description

Seed phenotype measurement system, method and related equipment

Technical Field

The application relates to the technical field of plant phenotypes, in particular to a seed type measuring system, a seed type measuring method and related equipment.

Background

Seeds are agricultural chips. The breeding is the design process of the seed chip, and the seed production is the production and processing process of the seed chip. In the variety breeding and production processing processes, seed quality and seed phenotype are important evaluation factors, and high-throughput and fine measurement analysis is required.

In the related art, the manual detection mode is time-consuming and labor-consuming, waste of seeds and uneven quality of the seeds are easy to cause, and relative errors are caused by individual cognition differences in different people during detection. In addition, in the prior art, measurement is carried out on tens or hundreds of seeds, and high-throughput automatic measurement on single seeds cannot be realized. Therefore, the related art has the problems of low detection efficiency, poor detection accuracy, resource waste and the like.

Disclosure of Invention

In view of the foregoing, it is an object of the present application to provide a seed type measurement system, method and related apparatus.

In accordance with the above objects, in a first aspect, the present application provides a seed type measurement system comprising:

the device comprises a seed separating mechanism, a transmission mechanism and a measuring mechanism;

the seed separation mechanism comprises: the device comprises a first bracket, a second bracket, a seed separation rotary table, a seed separation rod, a seed separation baffle plate and a seed separation pipe;

The seed separation carousel includes: the seed separation rotary table is arranged on the first bracket, and the rotary shaft is arranged at the center of the first bracket and can drive the rotary table to rotate by taking the rotary shaft as a rotary shaft;

the seed separating rod is arranged on the second bracket opposite to the first bracket and extends along one surface of the turntable far away from the first bracket;

the seed separation baffle is arranged on the second bracket, surrounds the turntable, and is provided with a through hole at one end close to the turntable;

the seed separating pipe is arranged on the first bracket, and an opening at one end of the seed separating pipe corresponds to the through hole;

under the rotation of the rotary table, the seed separating rod sweeps seeds on the rotary table along one surface of the rotary table far away from the first bracket so that the seeds enter an opening at one end of the seed separating pipe corresponding to the seed separating baffle through the through hole;

the transmission mechanism set up in divide kind of mechanism's one side, transmission mechanism includes: the seed separating movable disc is arranged at the position, facing the opening at the other end of the seed separating pipe, of the seed separating movable disc and the transmission assembly connected with the seed separating movable disc, and can move along a plane parallel to the opening at the other end of the seed separating pipe under the driving of the transmission assembly so as to collect seeds passing through the seed separating pipe;

The measuring mechanism is arranged on one side surface of the seed separating movable disk, which is close to the seed separating pipe, and is used for collecting phenotype data of the seeds when the seed separating movable disk moves to a target position corresponding to the measuring mechanism under the drive of the transmission assembly; the measuring mechanism includes: a measurement assembly, the measurement assembly comprising: one or more of a visible near infrared hyperspectral camera and a short wave infrared hyperspectral camera.

In one possible implementation manner, the seed separating mechanism further includes: a seed separation plate which is arranged on the seed separation baffle along the through hole and can slide along the seed separation baffle; the seed separation sheet can slide along the seed separation baffle to block or expose the through hole.

In one possible implementation, the transmission assembly includes: the device comprises a transmission motor, a first guide rail arranged along a first direction and a second guide rail arranged along a second direction perpendicular to the first direction; under the drive of the transmission motor, the seed separating movable plate can move along a plane parallel to the opening at the other end of the seed separating pipe through the first guide rail and/or the second guide rail so as to collect seeds passing through the seed separating pipe.

In one possible implementation manner, a mesh plate is arranged on one surface of the seed separation movable plate, which is close to the seed separation pipe, and a plurality of collecting holes for accommodating seeds are formed in the mesh plate.

In one possible implementation, the transmission mechanism further includes: a conveyor belt coupled to the drive assembly; the conveyor belt is used for moving the seed separating movable plate from the opening towards the position of the other end of the seed separating pipe to the target position.

In one possible implementation, a recovery telescopic assembly is connected to one end of the conveyor belt away from the seed separation tube; the retrieve flexible subassembly includes: the telescopic ejector rod and the accommodating box are arranged on one side, close to the ground, of the conveyor belt, and the accommodating box is used for accommodating the seed separation movable disc; the conveying belt conveys the seed separation movable disc to a position corresponding to the accommodating box so that the seed separation movable disc is accommodated in the accommodating box, and the telescopic ejector rod moves a target distance along one side far away from the conveying belt; and the target distance is determined according to the height of the seed separation movable plate.

In one possible implementation, the measuring mechanism includes: an illumination assembly disposed on one side of the measurement assembly; the intersection center of the illumination assembly and the measurement assembly is the target location.

In a first aspect, the present application provides a seed phenotyping method using the seed phenotyping system of the first aspect, the method comprising:

collecting original hyperspectral information data of seeds in a seed-separating movable disk in a linear array push-broom mode by utilizing a measuring mechanism;

acquiring whiteboard hyperspectral data corresponding to a preset whiteboard arranged on the seed separation movable plate, and performing reflectivity conversion on the original hyperspectral information data according to the pre-acquired dark current hyperspectral data and the whiteboard hyperspectral data to obtain hyperspectral information data; the hyperspectral information data includes: a single band image under a plurality of bands;

according to a pre-acquired transformation matrix, performing error shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data;

and extracting seed characteristic data according to the three-dimensional hyperspectral data, and determining seed phenotype data according to the seed characteristic data.

In one possible implementation, the transmission mechanism further includes: a conveyor belt coupled to the drive assembly;

the original hyperspectral information data of seeds in the seed-separating movable disk are collected by using a measuring mechanism in a linear array push-broom mode, and the method comprises the following steps:

Placing a mesh plate in a seed separating movable plate for placing seeds on the conveyor belt;

and responding to the seed separating movable disk to run to a target position corresponding to the measuring assembly, and acquiring original hyperspectral information data of seeds under a target area in the seed separating movable disk in a linear array push-broom mode.

In one possible implementation, the raw hyperspectral information data includes: original visible near infrared hyperspectral data, and/or original shortwave infrared hyperspectral data;

the method for acquiring the original hyperspectral information data of seeds under a target area in a seed separation movable disk in a linear array push-broom mode comprises the following steps:

and acquiring original visible near infrared hyperspectral data and/or original short wave infrared hyperspectral data of the same group of seeds in the seed separation movable disk by utilizing the measuring mechanism in a linear array push-broom mode at a preset moment.

In one possible implementation manner, the seed separation movable plate is provided with a mesh plate; the transmission mechanism further includes: a conveyor belt coupled to the drive assembly;

the obtaining the white board hyperspectral data corresponding to the preset white board arranged on the seed separation movable disk, and performing reflectivity conversion on the original hyperspectral information data according to the pre-obtained dark current hyperspectral data and the white board hyperspectral data to obtain hyperspectral information data, comprising:

Placing a preset white board with the same size as the mesh board in the seed separation movable disc on the conveyor belt, and executing shutter opening operation on the measuring mechanism to acquire white board hyperspectral data with the same spatial resolution and the same spectral resolution as the original hyperspectral information data;

performing reflectivity calibration on each pixel point in the original hyperspectral information data according to a preset reflectivity formula by using whiteboard hyperspectral data and dark current hyperspectral data to obtain hyperspectral information data;

wherein the preset reflectivity formula is expressed as

；

Wherein,digital quantization value representing white board hyperspectral data, < >>Digital quantized values representing dark current hyperspectral data, < >>Digital quantized value of original hyperspectral information data representing seed,/->Indicating the reflectivity of the preset whiteboard.

In one possible implementation manner, the seed separation movable plate is provided with a mesh plate;

according to the pre-acquired transformation matrix, performing a shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data, including:

extracting a single-band image in each band in hyperspectral information data, performing binarization operation on the single-band image in each band based on a predetermined threshold value to extract and obtain a mesh plate contour line, and determining a first included angle between the upper bottom edge and the lower bottom edge of the mesh plate and a preset horizontal datum line;

Acquiring standard mesh plate images corresponding to the mesh plates, and miscut the original pixel positions in each single-band image into the first included angles along the target direction to obtain target pixel positions in a standard coordinate system corresponding to the standard mesh plate images;

and determining the transformation matrix according to the original pixel position and the target pixel position, and performing a shear-shift operation on each pixel position in the single-band image under each band according to the transformation matrix to obtain three-dimensional hyperspectral reflectivity data.

In one possible implementation, the three-dimensional hyperspectral data includes: visible near infrared hyperspectral data, and/or short wave infrared hyperspectral data; the seed separation movable plate is provided with a mesh plate;

the method comprises the steps of respectively performing shear-shift on the single-band images under each band according to a pre-acquired transformation matrix to obtain three-dimensional hyperspectral data, and further comprises the following steps:

determining whether the three-dimensional hyperspectral data comprise visible near infrared hyperspectral data and shortwave infrared hyperspectral data;

in response to the three-dimensional hyperspectral data including visible near-infrared hyperspectral data and shortwave infrared hyperspectral data, removing redundant pixel data at two ends of a first dimension of a three-dimensional array from the visible near-infrared hyperspectral data with the spatial resolution of 1024 so that the spatial resolution of the visible near-infrared hyperspectral data is the same as that of the shortwave infrared hyperspectral data;

Taking a single-band binary image extracted according to the visible near infrared hyperspectral data as a reference image, taking the single-band binary image extracted according to the short-wave infrared hyperspectral data as a target image, selecting a mesh plate in a seed-dividing movable disk as a characteristic region, and determining an affine transformation coefficient based on a scale invariant feature transformation algorithm;

performing affine transformation on the target image according to the affine transformation coefficient to obtain affine transformed target coordinates corresponding to the characteristic region in the target image;

and mapping the reflectivity of a first band spectrum corresponding to the original coordinate before transformation in the target image to the target coordinate, and splicing the first band spectrum with a second band spectrum of the reference image to obtain full-band three-dimensional hyperspectral data.

In one possible implementation, the seed phenotype data comprises: a major axis and a minor axis of the seed;

after the full-band three-dimensional hyperspectral data are obtained, the method further comprises the following steps:

extracting spliced visible near infrared hyperspectral data corresponding to the second band spectrum according to the full-band three-dimensional hyperspectral data, and extracting RGB band images for the spliced visible near infrared hyperspectral data;

Graying the RGB wave band image to obtain a grayed RGB wave band image;

according to a segmentation threshold value determined based on a local Ojin self-adaptive threshold algorithm, carrying out binarization threshold segmentation on the gray RGB wave band image to obtain a candidate RGB wave band image, and determining a single seed region according to the candidate RGB wave band image;

extracting single seed contours according to the single seed regions, and determining contour count, perimeter and projection area of single seeds according to the single seed contours;

determining a contour two-dimensional coordinate vector of the single seed according to the single seed contour, performing a card-Luo transformation on the contour two-dimensional coordinate vector to obtain transformed coordinates, and calculating a minimum circumscribed rectangle of the single seed according to the transformed coordinates;

and determining the length and the width of the minimum bounding rectangle, and respectively representing the long axis and the short axis of the seed by the length and the width of the minimum bounding rectangle.

In one possible implementation, the phenotype data further comprises: seed coat color;

after the single seed contour is extracted according to the single seed region, the method further comprises the following steps:

and determining RBG components corresponding to the single seed outline, and representing seed coat colors by the RBG components.

In one possible implementation, the phenotype data further comprises: seed coat gloss;

after the grayscale is performed on the RGB band image to obtain a grayscale RGB band image, the method further includes:

calculating a co-occurrence matrix of the gray RGB wave band image, and determining an angular second moment and entropy of the co-occurrence matrix according to the co-occurrence matrix;

determining the sum of the angular second moment given to the first preset weight and the entropy given to the second preset weight, and representing the seed coat glossiness by the sum.

In one possible implementation, the phenotype data further comprises: a seed protein component and a seed oil component;

after the spliced visible near infrared hyperspectral data corresponding to the second band spectrum is extracted according to the full band three-dimensional hyperspectral data, the method further comprises the following steps:

extracting spliced short-wave infrared hyperspectral data corresponding to the first band spectrum according to the full-band three-dimensional hyperspectral data;

determining each single-band data in the spliced short-wave infrared hyperspectral data, establishing partial least square regression between each single-band data and seed protein component data, determining first target single-band data with highest correlation degree with the seed protein component data, and representing the seed protein component data by using the first target single-band data;

And establishing partial least square regression between each single-band data and the seed oil data to determine second target single-band data with highest correlation degree with the seed oil data, and representing the seed oil data by using the second target single-band data.

after determining each single-band data in the spliced short-wave infrared hyperspectral data, the method further comprises the following steps:

sequentially establishing partial least square regression between the ratio of any two single-band data and seed protein component data to determine third target single-band data with highest correlation degree with the seed protein component data, and representing the seed protein component data by using the third target single-band data;

and sequentially establishing partial least square regression between the ratio of any two single-band data and the seed oil content data to determine fourth target single-band data with highest correlation degree between the seed oil content data, and representing the seed oil content data by the fourth target single-band data.

sequentially establishing partial least square regression between the normalized ratio of any two single-band data and seed protein component data to determine fifth target single-band data with highest correlation degree with the seed protein component data, and representing the seed protein component data by using the fifth target single-band data;

and sequentially establishing partial least square regression between the normalized ratio of any two single-band data and the seed oil content data to determine sixth target single-band data with highest correlation degree between the seed oil content data, and representing the seed oil content data by the sixth target single-band data.

after determining whether the three-dimensional hyperspectral data comprise visible near-infrared hyperspectral data and short-wave infrared hyperspectral data, the method further comprises the following steps:

responding to the three-dimensional hyperspectral data comprising visible near infrared hyperspectral data or short-wave infrared hyperspectral data, and extracting RGB band images from the visible near infrared hyperspectral data or the short-wave infrared hyperspectral data;

Graying the RGB wave band image to obtain a grayed RGB wave band image;

after the response to the three-dimensional hyperspectral data comprises visible near infrared hyperspectral data or short wave infrared hyperspectral data, the method further comprises the following steps:

determining each single-band data in the visible near infrared hyperspectral data or the short wave infrared hyperspectral data, establishing partial least square regression between each single-band data and seed protein component data, determining first target single-band data with highest correlation degree with the seed protein component data, and representing the seed protein component data by the first target single-band data;

after determining each single-band data in the visible near infrared hyperspectral data or the shortwave infrared hyperspectral data, the method further comprises the following steps:

In a third aspect, the present application provides a seed type measurement device comprising:

the acquisition module is configured to acquire original hyperspectral information data of seeds in the seed-dividing movable disk in a linear array push-broom mode by utilizing the measurement mechanism;

The reflectivity conversion module is configured to acquire white board hyperspectral data corresponding to a preset white board arranged on the seed separation movable disk, and execute reflectivity conversion on the original hyperspectral information data according to the dark current hyperspectral data acquired in advance and the white board hyperspectral data so as to obtain hyperspectral information data; the hyperspectral information data includes: a single band image under a plurality of bands;

the shear-shift module is configured to respectively perform shear shift on the single-band images under each band according to a pre-acquired transformation matrix so as to obtain three-dimensional hyperspectral data;

a measurement module configured to extract seed characteristic data from the three-dimensional hyperspectral data and determine seed phenotype data from the seed characteristic data.

In a fourth aspect, the present application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the seed phenotype measurement method according to the second aspect when executing the program.

In a fifth aspect, the present application provides a computer readable storage medium storing computer instructions for causing a computer to perform the seed phenotype measurement method of the second aspect.

In a sixth aspect, the present application provides a computer program product comprising computer program instructions which, when run on a computer, cause the computer to perform the seed phenotype measurement method according to the second aspect.

From the above, it can be seen that the system, the method and the related equipment for measuring seed types provided by the application collect original hyperspectral information data of seeds in a seed-separating movable disk in a linear array push-broom mode by using a measuring mechanism; acquiring whiteboard hyperspectral data corresponding to a preset whiteboard arranged on the seed separation movable plate, and performing reflectivity conversion on the original hyperspectral information data according to the pre-acquired dark current hyperspectral data and the whiteboard hyperspectral data to obtain hyperspectral information data; the hyperspectral information data includes: a single band image under a plurality of bands; according to a pre-acquired transformation matrix, performing error shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data; and extracting seed characteristic data according to the three-dimensional hyperspectral data, and determining seed phenotype data according to the seed characteristic data. By utilizing the measuring mechanism, automatic measurement is realized, high-flux and fine measurement analysis is performed, the quality and nutrition balance of each seed can be ensured through the detection of the sensor and the operation of the controller, the workload of manual operation is reduced, the cost of crop planting is reduced, the phenotype data of the seeds can be accurately acquired based on a spectrum and image recognition algorithm, the internal state is avoided from wasting and losing, the detection efficiency and the detection accuracy are further improved, the constant and unique error range is ensured, and the relative errors caused by different sampling individuals are eliminated.

Drawings

In order to more clearly illustrate the technical solutions of the present application or related art, the drawings that are required to be used in the description of the embodiments or related art will be briefly described below, and it is apparent that the drawings in the following description are only embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.

FIG. 1 illustrates a front view of a seed type measurement system provided in an embodiment of the present application.

FIG. 2 illustrates a top view of a seed type measurement system provided in an embodiment of the present application.

Fig. 3 shows a partial schematic view of a sorting baffle according to an embodiment of the present application.

Fig. 4 shows an exemplary application scenario of a seed type measurement method according to an embodiment of the present application.

FIG. 5 is a flow chart illustrating an exemplary method for seed type measurement according to an embodiment of the present application.

Fig. 6 shows a schematic diagram of a visual data determination flow according to an embodiment of the present application.

FIG. 7 is a schematic diagram of an exemplary structure of a seed type measurement device according to an embodiment of the present application.

Fig. 8 shows an exemplary structural schematic diagram of an electronic device according to an embodiment of the present application.

Reference numerals illustrate:

1-seed separating mechanism, 101-first bracket, 102-second bracket, 103-seed separating rotary disc, 1031-rotary disc, 1032-rotary shaft, 104-seed separating rod, 105-seed separating baffle, 1051-through hole, 106-seed separating tube, 107-seed separating sheet, 2-transmission mechanism, 201-seed separating movable disc, 202-transmission assembly, 203-conveyor belt, 3-measuring mechanism, 301-measuring assembly, 302-lighting assembly, 4-recovery telescopic assembly, 401-telescopic ejector rod and 402-containing box.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings.

It should be noted that unless otherwise defined, technical or scientific terms used in the embodiments of the present application should be given the ordinary meaning as understood by one of ordinary skill in the art to which the present application belongs. The terms "first," "second," and the like, as used in embodiments of the present application, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.

As described in the background section, seeds are agricultural chips. The breeding is the design process of the seed chip, and the seed production is the production and processing process of the seed chip. In the variety breeding and production processing processes, seed quality and seed phenotype are important evaluation factors, and high-throughput and fine measurement analysis is required.

As such, the present application provides a seed table type measurement system, method and related equipment, which uses a measurement mechanism to collect original hyperspectral information data of seeds in a seed-separating movable disk in a linear array push-broom manner; acquiring whiteboard hyperspectral data corresponding to a preset whiteboard arranged on the seed separation movable plate, and performing reflectivity conversion on the original hyperspectral information data according to the pre-acquired dark current hyperspectral data and the whiteboard hyperspectral data to obtain hyperspectral information data; the hyperspectral information data includes: a single band image under a plurality of bands; according to a pre-acquired transformation matrix, performing error shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data; and extracting seed characteristic data according to the three-dimensional hyperspectral data, and determining seed phenotype data according to the seed characteristic data. By utilizing the measuring mechanism, automatic measurement is realized, high-flux and fine measurement analysis is performed, the quality and nutrition balance of each seed can be ensured through the detection of the sensor and the operation of the controller, the workload of manual operation is reduced, the cost of crop planting is reduced, the phenotype data of the seeds can be accurately acquired based on a spectrum and image recognition algorithm, the internal state is avoided from wasting and losing, the detection efficiency and the detection accuracy are further improved, the constant and unique error range is ensured, and the relative errors caused by different sampling individuals are eliminated.

Referring to fig. 1, a seed phenotype measurement system may include a seed separation mechanism 1, a transport mechanism 2, and a measurement mechanism 3. Wherein, seed separation mechanism 1 includes: a first bracket 101, a second bracket 102, a seed separating rotary disk 103, a seed separating rod 104, a seed separating baffle 105 and a seed separating pipe 106. A sorting carousel 103 comprising: the rotary table 1031 and the rotating shaft 1032, the seed separating rotary table 103 is disposed on the first bracket 101, the rotating shaft 1032 is disposed at the center of the first bracket 101, and the rotary table 1031 can rotate with the rotating shaft 1032 as a rotating shaft under the driving of the driving motor.

The transmission mechanism 2 is arranged at one side of the seed separating mechanism 1, and the transmission mechanism 2 comprises: the seed separating moving plate 201 is arranged at the position where the opening at the other end of the seed separating pipe 106 faces, and the transmission assembly 202 is connected with the seed separating moving plate 201, and the seed separating moving plate 201 can move along a plane parallel to the opening at the other end of the seed separating pipe 106 under the driving of the transmission assembly 202 so as to collect seeds passing through the seed separating pipe 106.

The measuring mechanism 3 is arranged on one side surface of the seed separating movable disk 201, which is close to the seed separating pipe 106, when the seed separating movable disk 201 moves to a target position corresponding to the measuring mechanism 3 under the drive of the transmission assembly 202, the measuring mechanism 3 can collect phenotype data of seeds.

Referring to fig. 2, a seed separating lever 104 is disposed on a second bracket 102 opposite to the first bracket 101 and extends along a surface of the turntable 1031 remote from the first bracket 101, and a seed separating baffle 105 is disposed on the second bracket and surrounds the turntable 1031. That is, the seed separating plate 105 and the turntable 1031 together enclose a containing cavity, and the seed separating plate 105 does not rotate along with the rotation of the turntable 1031, when the turntable 1031 rotates, seeds on the turntable 1031 can be placed to splash out, so that resource waste is caused.

It should be noted that, a third bracket crossing the turntable 1031 may be further disposed on the first bracket 101, the seed separating plate 105 may be disposed on the third bracket, and the seed separating rod 104 may be disposed on the third bracket, where when the turntable 1031 rotates, neither the seed separating plate 105 nor the seed separating rod 104 rotates along with the turntable 1031, so that the seeds on the turntable 1031 can slide along the seed separating rod 104 toward the seed separating plate 105, and the seed separating rod 104 plays a guiding role.

Fig. 3 shows a partial schematic view of the sorting baffle 105 according to an embodiment of the present application.

Referring to fig. 3, a through hole 1051 is provided at one end of the seed separating plate 105 near the turntable 1031, a seed separating tube 106 is provided at the first bracket 101, and an opening of one end of the seed separating tube 106 corresponds to the seed separating plate 105. Under the rotation of the turntable, the seed separating lever 104 sweeps the seeds on the turntable 1031 along the side of the turntable 1031 away from the first bracket 101, so that the seeds enter the seed separating tube 106 through the through hole 1051 and the end corresponding to the seed separating baffle 105 is opened.

Specifically, a motor may be provided on the first support 101, for driving the turntable 1031 to rotate with the rotating shaft 1032 as a rotating shaft, and the seed separating rod 104 may move the seeds on the turntable 1031 along the orientation when the turntable 1031 rotates, referring to fig. 2, the seed separating rod 104 may be fixedly provided, and when the turntable 1031 rotates, the seed separating rod 104 may be fixed, and the seed separating rod 104 and the turntable 1031 may move relatively, so as to sweep the seeds on the turntable 1031. Also, the seed-dividing bar 104 may be directed toward the through-hole 1051 such that the seeds can slide toward the through-hole 1051 under the guide of the seed-dividing bar 104 such that the seeds slide into the seed-dividing tube 106 through the through-hole 1051.

In some embodiments, the seed separation mechanism 1 further comprises: a seed separation plate 107 provided along the through hole 1051 in the seed separation plate 105 and slidable along the seed separation plate 105. The seed separating plate 107 can slide along the seed separating plate 105 to block or expose the through hole 1051, for example, when the seed separating plate 107 slides in a direction away from the through hole 1051, the through hole 1051 on the seed separating plate 105 can be exposed, and at this time, seeds on the turntable 1031 can be scanned to the through hole 1051 by the seed separating rod 104, so that the seeds can fall into the seed separating tube 106 along the through hole 1051.

Of course, when the seed separating piece 107 slides in a direction approaching to the through hole 1051, the through hole 1051 on the seed separating plate 105 can be blocked, and at this time, when the seed on the turntable 1031 is swept by the seed separating rod 104, the seeds cannot pass through the through hole, so that the number of seeds falling into the seed separating tube 106 can be controlled by adjusting the area of the through hole 1051 blocked by the seed separating piece 107. In addition, since the sizes of the different seeds are different, for example, when seeds with smaller sizes are collected, in order to ensure that the seeds do not pass through the through holes in a large amount, the seeds are blocked or unevenly collected during collection, the seed separation sheet 107 can slide in a direction close to the through holes 1051, so that the openings of the through holes 1051 are smaller. Similarly, in order to ensure that seeds can pass through the through-hole when seeds of a larger size are collected, the seed separation sheet 107 may be slid in a direction away from the through-hole 1051 so that the opening of the through-hole 1051 is larger.

For the seed separation movable plate 201 in the transmission assembly 202, a mesh plate is arranged on one surface of the seed separation movable plate 201, which is close to the seed separation pipe 106, and a plurality of collecting holes for accommodating seeds are formed in the mesh plate, so that the seeds can be collected by the collecting holes in the mesh plate when the seeds fall into the seed separation movable plate 201 from the seed separation pipe 106, and the seeds can be distributed in the mesh plate, so that subsequent measurement work is facilitated.

In some embodiments, the transmission assembly 202 includes: the device comprises a transmission motor, a first guide rail arranged along a first direction and a second guide rail arranged along a second direction perpendicular to the first direction, wherein the first direction can be an X-axis direction in a space coordinate system, and the second direction can be a Y-axis direction in the space coordinate system. Driven by the driving motor, the seed separating moving plate 201 can move along a plane parallel to the opening at the other end of the seed separating tube 106 through the first guide rail and/or the second guide rail to collect seeds passing through the seed separating tube 106. That is, the seed separating movable tray 201 can be moved in a horizontal plane by the first guide rail and the second guide rail, so that the seeds that come out from the seed separating tube 106 can be collected by the mesh plate in the seed separating movable tray 201 and collected uniformly. For example, the size of the collection hole in the mesh plate can accommodate single seeds, and when the seed separating moving plate 201 is moved in the horizontal plane, the collection hole can uniformly accommodate each single seed, thereby realizing the collection of seeds.

It should be noted that, other means than the guide rail, for example, a screw, an electric cylinder driving, or the like may be used, so that the seed dividing movable plate 201 may be moved in the X-axis and Y-axis directions in the space coordinate system, that is, in the horizontal plane, so that when the seed dividing movable plate 201 is moved in the horizontal plane, each single seed may be uniformly accommodated in the collection hole, and collection of the seeds may be achieved.

In some embodiments, the transport mechanism 2 further comprises: and a conveyor belt 203 connected to the transmission assembly 202, the conveyor belt 203 being used for moving the seed separating movable disk 201 from the other end opening direction position of the seed separating pipe 106 to a target position. The end of the conveyor belt 203 remote from the seed tube 106 is connected to the recovery telescoping assembly 4. Retrieve telescopic assembly 4, include: a telescopic ejector 401 provided on a side of the conveyor 203 close to the ground, and a housing box 402, the housing box 402 being for housing the seed-separating movable tray 201. The conveyor 203 conveys the seed-separating movable tray 201 to a position corresponding to the housing box 402, so that the seed-separating movable tray 201 is housed in the housing box 402, and the telescopic ejector 401 moves a target distance along a side away from the conveyor 203. Wherein the target distance is determined according to the height of the seed separating movable plate 201.

The conveyor 203 can move the seed-separating movable disk 201 from an initial position, which may be a position when the seed-separating movable disk 201 is located below the seed-separating tube 106 to collect seeds, to a target position, which may be a position when the measuring mechanism 3 measures seeds in the seed-separating movable disk 201, for example, directly below the measuring mechanism 3.

At the other end of the conveyor belt 203, a recovery telescopic assembly 4 is provided, wherein after the measurement work is completed, seeds in the seed-separating movable trays 201 can be moved to a position corresponding to the accommodating box 402 through the conveyor belt 203, the seed-separating movable trays 201 are recovered into the accommodating box 402, the accommodating box 402 can at least completely accommodate a plurality of seed-separating movable trays 201, after one seed-separating movable tray 201 is collected, the accommodating box 402 can be contracted towards a direction far away from the conveyor belt 203 through the telescopic ejector rod 401, so that the conveyor belt 203 can continuously convey other seed-separating movable trays 201 without collision with the accommodating box 402 or the previous seed-separating movable tray 201. By analogy, until more seed-separating movable disks 201 cannot be accommodated in the accommodating box 402, the seed-separating movable disks 201 in the accommodating box 402 can be transferred to the recycling bin, or the accommodating box 402 can be directly transferred to the recycling bin together, and a new accommodating box 402 is replaced, so that the seed-separating movable disks 201 can be continuously recycled. For example, if the height of the seed separating moving disc 201 is 10cm, after one seed separating moving disc 201 is recovered, the telescopic ejector rod 401 can be contracted by at least 10cm, so that the work of the conveyor belt 203 is not affected.

In some embodiments, the measuring mechanism 3 comprises: a measuring assembly 301, and an illumination assembly 302 disposed on one side of the measuring assembly 301. The center of intersection of the illumination assembly 302 and the measurement assembly 301 is the target location. A measurement assembly 301 comprising: one or more of a visible near infrared hyperspectral camera and a short wave infrared hyperspectral camera. The illumination assembly 302 may be a light supplement lamp disposed at one side of the measurement assembly 301, and an intersection point of the light beams emitted by the illumination assembly 302 and the measurement assembly 301 is a center of intersection, that is, a target position, where the phenotype data of the seeds are measured more accurately.

Referring to fig. 4, in this application scenario, a local terminal device 1001 and a server 1002 are included. The local terminal device 1001 and the server 1002 may be connected through a wired or wireless communication network, so as to implement data interaction.

The local terminal device 1001 may be an electronic device with data transmission and multimedia input/output functions near the user side, such as a desktop computer, a mobile phone, a mobile computer, a tablet computer, a media player, a car-mounted computer, an intelligent wearable device, a personal digital assistant (personal digital assistant, PDA), or other electronic devices capable of implementing the above functions, etc. The electronic device may include a processor for presenting a graphical user interface that may display a user operation interface, and a display screen having a touch input function for processing corresponding data, generating the graphical user interface, and controlling the display of the graphical user interface on the display screen.

The server 1002 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligence platforms, and the like.

In some exemplary embodiments, the seed phenotype measurement method may run on the local terminal device 1001 or the server 1002.

When the seed phenotype measuring method is run on the server 1002, the server 1002 is configured to provide a seed phenotype measuring service to a user of a terminal device in which a client in communication with the server 1002 is installed, and the user can specify a target program through the client. The server 1002 collects original hyperspectral information data of seeds in the seed-dividing movable disk in a linear array push-broom mode by using a measuring mechanism; acquiring whiteboard hyperspectral data corresponding to a preset whiteboard arranged on the seed separation movable plate, and performing reflectivity conversion on the original hyperspectral information data according to the pre-acquired dark current hyperspectral data and the whiteboard hyperspectral data to obtain hyperspectral information data; the hyperspectral information data includes: a single band image under a plurality of bands; according to a pre-acquired transformation matrix, performing error shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data; and extracting seed characteristic data according to the three-dimensional hyperspectral data, and determining seed phenotype data according to the seed characteristic data. Server 1002 may also send seed phenotype data to a client that presents the seed phenotype data to the user. Wherein the terminal device may be the aforementioned local terminal device 1001.

When the seed phenotyping method is run on the server 1002, the method may be implemented and executed based on a cloud interaction system.

The cloud interaction system comprises client equipment and a cloud server.

In some example embodiments, various cloud applications may be run under the cloud interaction system, such as: and (5) cloud game. Taking cloud game as an example, cloud game refers to a game mode based on cloud computing. In the running mode of the cloud game, the running main body of the game program and the game picture presentation main body are separated, the storage and running of the control method of the moving state in the game are completed on the cloud game server, and the client device is used for receiving and sending data and presenting the game picture, for example, the client device can be a display device with a data transmission function close to a user side, such as a mobile terminal, a television, a computer, a palm computer and the like; but the cloud game server which performs information processing is a cloud. When playing the game, the player operates the client device to send an operation instruction to the cloud game server, the cloud game server runs the game according to the operation instruction, codes and compresses data such as game pictures and the like, returns the data to the client device through a network, and finally decodes the data through the client device and outputs the game pictures.

In the above embodiments, the seed phenotype measuring method is described as being run on the server 1002 as an example, however the present disclosure is not limited thereto, and in some exemplary embodiments, the seed phenotype measuring method may also be run on the local terminal apparatus 1001.

The local terminal device 1001 may include a display screen and a processor. A client is installed in the local terminal device 1001, and a user can specify a target program through the client. The processor collects original hyperspectral information data of seeds in the seed-dividing movable disk in a linear array push-broom mode by utilizing the measuring mechanism; acquiring whiteboard hyperspectral data corresponding to a preset whiteboard arranged on the seed separation movable plate, and performing reflectivity conversion on the original hyperspectral information data according to the pre-acquired dark current hyperspectral data and the whiteboard hyperspectral data to obtain hyperspectral information data; the hyperspectral information data includes: a single band image under a plurality of bands; according to a pre-acquired transformation matrix, performing error shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data; and extracting seed characteristic data according to the three-dimensional hyperspectral data, and determining seed phenotype data according to the seed characteristic data. The processor may also send the seed phenotype data to a client that presents the seed phenotype data to a user via a display screen.

For example, the local terminal device 1001 may include a display screen for presenting a graphical user interface including an operation screen, and a processor for running the electronic system, generating a graphical user interface, and controlling the display of the graphical user interface on the display screen.

In some exemplary embodiments, the embodiments of the present disclosure provide a seed type measurement method, where a graphical user interface is provided by a terminal device, where the terminal device may be the aforementioned local terminal device 1001, or may be a client device in the aforementioned cloud interaction system.

A seed phenotype measurement method according to an exemplary embodiment of the present disclosure is described below in connection with the application scenario of fig. 4. It should be noted that the above application scenario is only shown for the convenience of understanding the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in any way in this respect. Rather, embodiments of the present disclosure may be applied to any scenario where applicable.

Referring to fig. 5, the method for measuring seed types provided in the embodiments of the present application specifically includes the following steps:

S502: and acquiring original hyperspectral information data of seeds in the seed-separating movable disk in a linear array push-broom mode by utilizing a measuring mechanism.

S504: acquiring whiteboard hyperspectral data corresponding to a preset whiteboard arranged on the seed separation movable plate, and performing reflectivity conversion on the original hyperspectral information data according to the pre-acquired dark current hyperspectral data and the whiteboard hyperspectral data to obtain hyperspectral information data; the hyperspectral information data includes: single band images at multiple bands.

S506: and respectively performing shear-shift on the single-band images under each band according to the pre-acquired transformation matrix to obtain three-dimensional hyperspectral data.

S508: and extracting seed characteristic data according to the three-dimensional hyperspectral data, and determining seed phenotype data according to the seed characteristic data.

In some embodiments, the mesh plate in the seed-separating movable disk for placing the seeds can be placed on the conveyor belt, and in response to the seed-separating movable disk running to a target position corresponding to the measuring component, the original hyperspectral information data of the seeds under the target area in the seed-separating movable disk are acquired in a linear array push-broom mode.

Wherein, the original hyperspectral information data may include: primary visible near infrared hyperspectral data and/or primary shortwave infrared hyperspectral data. Specifically, the original visible near infrared hyperspectral data and/or the original short wave infrared hyperspectral data of the same group of seeds in the seed-dividing movable disk can be collected by utilizing a linear array push-broom mode of the measuring mechanism at a preset moment. When the original visible near infrared hyperspectral data and the original shortwave infrared hyperspectral data are acquired, the two data can be acquired at the same time, and the two data can be acquired at different times.

Further, a preset whiteboard of the same size as the mesh plate in the seed tray may be placed on the conveyor belt, for example, the preset whiteboard may be a standard polytetrafluoroethylene whiteboard. Further, a shutter-open operation may be performed on the measurement mechanism to collect whiteboard hyperspectral data having the same spatial resolution and the same spectral resolution as the original hyperspectral information data. Still further, reflectivity calibration can be performed on each pixel point in the original hyperspectral information data according to a preset reflectivity formula by using the whiteboard hyperspectral data and the dark current hyperspectral data to obtain hyperspectral information data.

Wherein the preset reflectivity formula can be expressed as

；

Wherein,digital quantization value representing white board hyperspectral data, < >>Digital quantized values representing dark current hyperspectral data, < >>A digital quantization value representing the original hyperspectral information data of the seed,indicating the reflectivity of the preset whiteboard.

Still further, the seed spectral reflectance in the original hyperspectral information data can be smoothed by using a Savitzky-Golay filter, and the smoothing formula of the spectrum is as follows:

；

wherein,representing spectral reflectance before smoothing, +.>Representing the smoothed spectral reflectance, +. >Representing the smooth coefficients obtained by least squares fitting the polynomial, +.>Representing the weight factors in moving window smoothing.

In some embodiments, the correction of the image at each band may be performed because the friction of the conveyor belt may cause vertical deformation of the image of the original hyperspectral information data. Specifically, a single-band image in each band of the hyperspectral information data may be extracted, a binarization operation is performed on the single-band image in each band based on a predetermined threshold value, so as to extract and obtain an outline of the mesh plate, and a first included angle between the upper and lower bottom edges of the mesh plate and a predetermined horizontal reference line is determined, for example. Because noise exists in the background of the mesh plate, a threshold value can be taken, binarization operation can be carried out on the single-band image, and the outline of the outermost layer corresponding to the position of the mesh plate in the image is extracted and used as the outline of the mesh plate.

Further, standard mesh plate images corresponding to the mesh plates can be obtained, and original pixel positions in each single-band image are staggered at a first included angle along the target direction, so that target pixel positions in a standard coordinate system corresponding to the standard mesh plate images are obtained. That is, the actually photographed mesh plate image is miscut-transformed into the coordinate system in which the standard mesh plate image is located, and correction is performed for each pixel point in the image.

Specifically, the pixel position in the actually photographed mesh plate image, that is, the single-band image is transformed into the target image, that is, the position in the standard mesh plate image, and the coordinate system where the standard mesh plate image is located is taken as the operation coordinate system, so that the actually photographed mesh plate image is transformed into the coordinate system where the standard mesh plate image is located. Setting any point of the mesh plate image obtained by actual shootingStaggered in Y direction->After angulation a new position is obtained>Wherein

；

The coordinate change matrix formula before and after the miscut is obtained is as follows:

。

after the transformation matrix is determined according to the original pixel position and the target pixel position, the error shear transformation operation can be performed on each pixel position in the single-band image under each band according to the transformation matrix, so as to obtain three-dimensional hyperspectral reflectivity data.

Because the obtained original hyperspectral data may include any one or two of the original visible near-infrared hyperspectral data and the original short-wave infrared hyperspectral data, when the original hyperspectral data includes the original visible near-infrared hyperspectral data and the original short-wave infrared hyperspectral data at the same time, the obtained three-dimensional hyperspectral data also necessarily includes the visible near-infrared hyperspectral data and the short-wave infrared hyperspectral data at the same time, and for the accuracy of the result, image registration and spectrum band splicing can be performed on the obtained three-dimensional hyperspectral data.

Specifically, whether the three-dimensional hyperspectral data comprise visible near-infrared hyperspectral data and short-wave infrared hyperspectral data is determined, if the two data are contained at the same time, redundant pixel data at two ends of the first dimension of the three-dimensional array can be removed from the visible near-infrared hyperspectral data with the spatial resolution of 1024, so that the spatial resolution of the visible near-infrared hyperspectral data is the same as that of the short-wave infrared hyperspectral data, wherein the spatial resolution of the short-wave infrared hyperspectral data is 640, and therefore, the spatial resolution of the visible near-infrared hyperspectral data is finally reduced from 1024 to 640.

Further, a single-band binary image extracted according to visible and near infrared hyperspectral data is taken as a reference image, a single-band binary image extracted according to short-wave infrared hyperspectral data is taken as a target image, a mesh plate in a seed-dividing movable plate is selected as a characteristic region, and affine transformation coefficients are determined based on a Scale-invariant feature transformation (namely Scale-invariant feature transform) algorithm. The method comprises the steps of determining the angular points of the mesh plate in the reference image and the target image, and transforming the angular points.

Specifically, affine transformation can be performed on the target image according to affine transformation coefficients to obtain affine transformed target coordinates corresponding to the feature regions in the target image, then reflectivity of a first band spectrum corresponding to original coordinates before transformation in the target image is mapped to the target coordinates, and the first band spectrum and a second band spectrum of the reference image are spliced to obtain full-band three-dimensional hyperspectral data.

Wherein the mathematical expression of affine transformation is:

。

for example, the spectral reflectivity of the 900-1700nm band corresponding to the coordinate before the transformation of the target image can be mapped to the transformed coordinate, spliced with the 400-900nm band spectrum of the reference image, and reconstructed into the 400-1700nm full-band three-dimensional hyperspectral data.

In some embodiments, the seed phenotype data may include: the major and minor axes of the seed, the seed coat color, the glossiness of the seed coat, and the biochemical components. Extraction of seed phenotype features including quantitative features (number of seeds), morphological features (length and width of seeds, minimum circumcircle, outline perimeter, projected area), color texture features (seed coat color, glossiness), biochemical components (seed vigor, protein content, oil content).

Specifically, after the full-band three-dimensional hyperspectral data is obtained, since the correlation degree between the visible near-infrared hyperspectral data and the morphological characteristics and the color and text characteristics of the seeds is higher, spliced visible near-infrared hyperspectral data corresponding to the second band spectrum can be extracted according to the full-band three-dimensional hyperspectral data, the RGB band image can be extracted from the spliced visible near-infrared hyperspectral data, and the RGB band image can be further subjected to graying to obtain a gray-scale RGB band image.

And according to the segmentation threshold value determined based on the local Ojin self-adaptive threshold algorithm, carrying out binarization threshold value segmentation on the gray RGB band image to obtain a candidate RGB band image. At this time, there may be a problem of adhesion of multiple seeds, so that a foreground region and a background region in the candidate RGB band image may be obtained, and further, a fuzzy region representing adhesion of the seeds may be determined according to a difference between a corresponding parameter of the foreground region and a corresponding parameter of the background region, and an initial contour line of each seed in the candidate RGB band image may be obtained through image processing of corrosion and expansion. Further, an initial gray value of the candidate RGB band image is determined, and the gray value is adjusted within a predetermined gray value threshold range according to the range, so that a threshold centerline for distinguishing contour lines of mutually stuck seeds is determined according to a watershed algorithm. And determining the central coordinates of adjacent seeds according to a distance algorithm, and adjusting the gray value in the gray value threshold range until the example between the central point of the adjacent seeds and the central line of the threshold reaches the maximum value, so that the single seed region can be determined. And the contour count, perimeter and projection area of the single seeds can be determined according to the single seed contour.

Further, a contour two-dimensional coordinate vector of the single seed can be determined according to the contour of the single seed, a Karhunen-Loeve Transform (namely, a Karhunen-Loeve Transform) is performed on the contour two-dimensional coordinate vector to obtain transformed coordinates, and a minimum bounding rectangle of the single seed is calculated according to the transformed coordinates. And determining the length and the width of the minimum circumscribed rectangle, and respectively representing the long axis and the short axis of the seed by the length and the width of the minimum circumscribed rectangle.

Still further, an RBG component corresponding to a single seed contour may be determined and used to characterize seed coat color.

For the gray RGB band image obtained after gray scale, the co-occurrence matrix of the gray scale RGB band image can be calculated, and the angular second moment and entropy of the co-occurrence matrix can be determined according to the co-occurrence matrix, wherein the angular second moment can be expressed as

；

Entropy can be expressed as

。

The seed coat gloss may then be characterized by both, e.g., a sum of an angular second moment given a first preset weight, e.g., the first preset weight may be 0.3, and an entropy given a second preset weight, e.g., the second preset weight may be 0.7, and the sum of both may be used to characterize the seed coat gloss.

In some embodiments, the biochemical components in the seed phenotype data may include a seed protein component and a seed oil component, which are more correlated with the short-wave infrared hyperspectral data, so that the spliced short-wave infrared hyperspectral data corresponding to the first band spectrum may be extracted from the full-wave three-dimensional hyperspectral data, and each single-wave band data in the spliced short-wave infrared hyperspectral data may be determined.

The relationship between each single band of data in the spliced short wave infrared hyperspectral data and the protein component or oil component can be established in different ways, including but not limited to partial least squares regression (PLSR, partial least square regression), deep learning networks, machine learning algorithms, and the like.

For example, a partial least squares regression between each of the single band data and the seed protein component data may be established to determine a first target single band data having a highest correlation with the seed protein component data and characterize the seed protein component data with the first target single band data. And establishing partial least square regression between each single-band data and the seed oil data to determine second target single-band data with highest correlation degree between the second target single-band data and the seed oil data, and representing the seed oil data by the second target single-band data.

And a partial least square regression between the ratio of any two single-band data and the seed protein component data can be sequentially established to determine third target single-band data with highest relativity with the seed protein component data, and the seed protein component data is represented by the third target single-band data. And sequentially establishing partial least square regression between the ratio of any two single-band data and the seed oil content data to determine fourth target single-band data with highest correlation degree with the seed oil content data, and representing the seed oil content data by the fourth target single-band data.

And a partial least square regression between the normalized ratio of any two single-band data and the seed protein component data can be sequentially established to determine fifth target single-band data with highest correlation degree with the seed protein component data, and the fifth target single-band data is used for representing the seed protein component data. And sequentially establishing partial least square regression between the normalized ratio of any two single-band data and the seed oil content data to determine sixth target single-band data with highest correlation degree with the seed oil content data, and representing the seed oil content data by the sixth target single-band data.

It should be noted that, the seed protein component data may be further represented according to the data obtained by integrating the first target single-band data, the third target single-band data, and the fifth target single-band data, and the seed oil component data may be represented according to the data obtained by integrating the second target single-band data, the fourth target single-band data, and the sixth target single-band data.

Then, if the original hyperspectral information data only contains visible near infrared hyperspectral data or short wave infrared hyperspectral data, the three-dimensional hyperspectral data also contains visible near infrared hyperspectral data or short wave infrared hyperspectral data.

In some embodiments, the problem of low correlation between the visible near infrared hyperspectral data and the seed biochemical components may be ignored, so that the RGB band image may be extracted from the visible near infrared hyperspectral data or the short-wave infrared hyperspectral data, and the RGB band image may be further grayed to obtain a grayed RGB band image.

；

Entropy can be expressed as

。

In some embodiments, the biochemical components in the seed phenotype data, which may include seed protein components and seed oil components, may determine each single band of data in the visible near infrared hyperspectral data or the short wave infrared hyperspectral data.

The relationship between each single band of data and the protein component or oil component in the visible near infrared hyperspectral data or the short wave infrared hyperspectral data can be established in different ways, including but not limited to partial least squares regression (PLSR, partial least square regression), deep learning networks, machine learning algorithms, and the like.

Of course, if the problem of low correlation between the visible near infrared hyperspectral data and the seed biochemical components is considered, when the visible near infrared hyperspectral data is not acquired, the relationship between each single band data in the short wave infrared hyperspectral data and the protein component or the oil component can be established in different ways, including but not limited to the ways of partial least squares regression (PLSR, partial least square regression), a deep learning network, a machine learning algorithm and the like. And further determining characteristic data for characterizing the seed protein component and the seed oil component.

And when the short-wave infrared hyperspectral data is not acquired, the relation between each single-band data in the short-wave infrared hyperspectral data and the protein component or the oil component is not established, and the characteristic data for characterizing the seed protein component and the seed oil component is not determined.

Referring to fig. 6, the measured data may be stored in a database and analyzed to determine, for example, seed quality (grade a), seed percentage (90%) and seed vigor (89), and provide a detection report so that a user can automatically detect the corresponding phenotype data of the batch of seeds, provide real-time data support and decision analysis for the user, and assist the user in formulating a scientific planting strategy.

It should be noted that, the method of the embodiments of the present application may be performed by a single device, for example, a computer or a server. The method of the embodiment can also be applied to a distributed scene, and is completed by mutually matching a plurality of devices. In the case of such a distributed scenario, one of the devices may perform only one or more steps of the methods of embodiments of the present application, and the devices may interact with each other to complete the methods.

It should be noted that some embodiments of the present application are described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Based on the same inventive concept, the application also provides a seed table type measuring device corresponding to the method of any embodiment.

Referring to fig. 7, the seed phenotype measuring apparatus includes: the device comprises an acquisition module, a reflectivity conversion module, a shear conversion module and a measurement module; wherein,

the acquisition module is further configured to:

the reflectivity conversion module is further configured to:

wherein the preset reflectivity formula is expressed as

；

the shear-shift module is further configured to:

the device further comprises: splicing modules;

the splice module is configured to:

the measurement module is further configured to:

Graying the RGB wave band image to obtain a grayed RGB wave band image;

the measurement module is further configured to:

The measurement module is further configured to:

the measurement module is further configured to:

graying the RGB wave band image to obtain a grayed RGB wave band image;

the measurement module is further configured to:

The measurement module is further configured to:

the measurement module is further configured to:

For convenience of description, the above devices are described as being functionally divided into various modules, respectively. Of course, the functions of each module may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.

The device of the foregoing embodiment is used to implement the corresponding seed phenotype measurement method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.

Based on the same inventive concept, the application also provides an electronic device corresponding to the method of any embodiment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the seed phenotype measuring method of any embodiment when executing the program. Fig. 8 shows a more specific hardware architecture of an electronic device according to this embodiment, where the device may include: processor 810, memory 820, input/output interface 830, communication interface 840 and bus 850. Wherein processor 810, memory 820, input/output interface 830, and communication interface 840 enable communication connections among each other within the device via bus 850.

The processor 810 may be implemented by a general-purpose CPU (Central Processing Unit ), microprocessor, application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc. for executing relevant programs to implement the technical solutions provided in the embodiments of the present disclosure.

The Memory 820 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage device, dynamic storage device, or the like. Memory 820 may store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present specification are implemented in software or firmware, relevant program codes are stored in memory 820 and invoked by processor 810 for execution.

The input/output interface 830 is used for connecting with an input/output module to realize information input and output. The input/output module may be configured as a component in a device (not shown in the figure) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.

The communication interface 840 is used to connect a communication module (not shown in the figure) to enable communication interaction between the device and other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).

Bus 850 includes a path to transfer information between components of the device (e.g., processor 810, memory 820, input/output interface 830, and communication interface 840).

It should be noted that although the above-described device only shows processor 810, memory 820, input/output interface 830, communication interface 840, and bus 850, in an implementation, the device may include other components necessary to achieve proper operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.

The electronic device of the foregoing embodiment is configured to implement the corresponding seed phenotype measurement method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.

Based on the same inventive concept, corresponding to any of the above embodiments of the method, the present application also provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the seed phenotype measuring method as described in any of the above embodiments.

The computer readable media of the present embodiments, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.

The storage medium of the above embodiment stores computer instructions for causing the computer to perform the seed phenotype measuring method according to any of the above embodiments, and has the advantages of the corresponding method embodiments, which are not described herein.

Based on the same inventive concept, the present disclosure also provides a computer program product, corresponding to the seed phenotype measuring method described in any of the above embodiments, comprising computer program instructions. In some embodiments, the computer program instructions may be executable by one or more processors of a computer to cause the computer and/or the processor to perform the seed phenotype measurement method. Corresponding to the execution subject corresponding to each step in each embodiment of the seed phenotype measuring method, the processor for executing the corresponding step may belong to the corresponding execution subject.

The computer program product of the above embodiment is configured to enable the computer and/or the processor to perform the seed phenotype measuring method according to any one of the above embodiments, and has the advantages of the corresponding method embodiments, which are not described in detail herein.

Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the application (including the claims) is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the present application, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of brevity.

Additionally, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures, in order to simplify the illustration and discussion, and so as not to obscure the embodiments of the present application. Furthermore, the devices may be shown in block diagram form in order to avoid obscuring the embodiments of the present application, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform on which the embodiments of the present application are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative in nature and not as restrictive.

While the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of those embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalents, improvements and/or the like which are within the spirit and principles of the embodiments are intended to be included within the scope of the present application.

Claims

1. A method of seed phenotype measurement using a seed phenotype measurement system, the seed phenotype measurement system comprising:

the transmission mechanism set up in divide kind of mechanism's one side, transmission mechanism includes: the seed separating movable disc is arranged at the position, facing the opening at the other end of the seed separating pipe, of the seed separating movable disc and the transmission assembly connected with the seed separating movable disc, and can move along a plane parallel to the opening at the other end of the seed separating pipe under the driving of the transmission assembly so as to collect seeds passing through the seed separating pipe; a mesh plate is arranged on one surface of the seed separation movable plate, which is close to the seed separation pipe, and a plurality of collecting holes for accommodating seeds are formed in the mesh plate; the transmission mechanism further includes: a conveyor belt coupled to the drive assembly; the conveyor belt is used for moving the seed separation movable plate from the opening of the other end of the seed separation pipe to a target position;

The measuring mechanism is arranged on one side surface of the seed separating movable disk, which is close to the seed separating pipe, and is used for collecting phenotype data of the seeds when the seed separating movable disk moves to a target position corresponding to the measuring mechanism under the drive of the transmission assembly; the measuring mechanism includes: a measurement assembly, the measurement assembly comprising: one or more of a visible near infrared hyperspectral camera and a short wave infrared hyperspectral camera;

the method comprises the following steps:

acquiring whiteboard hyperspectral data corresponding to a preset whiteboard arranged on the seed separation movable plate, and performing reflectivity conversion on the original hyperspectral information data according to the pre-acquired dark current hyperspectral data and the whiteboard hyperspectral data to obtain hyperspectral information data; the hyperspectral information data includes: a single band image in a plurality of bands, the bands comprising: a visible near infrared hyperspectral band and a shortwave infrared hyperspectral band;

according to a pre-acquired transformation matrix, performing error shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data; according to the pre-acquired transformation matrix, performing a shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data, including:

determining the transformation matrix according to the original pixel position and the target pixel position, and performing a shear-shift operation on each pixel position in the single-band image under each band according to the transformation matrix to obtain three-dimensional hyperspectral reflectivity data;

2. The method of claim 1, wherein the seed separation mechanism further comprises: a seed separation plate which is arranged on the seed separation baffle along the through hole and can slide along the seed separation baffle; the seed separation sheet can slide along the seed separation baffle to block or expose the through hole.

3. The method of claim 1, wherein the transmission assembly comprises: the device comprises a transmission motor, a first guide rail arranged along a first direction and a second guide rail arranged along a second direction perpendicular to the first direction; under the drive of the transmission motor, the seed separating movable plate can move along a plane parallel to the opening at the other end of the seed separating pipe through the first guide rail and/or the second guide rail so as to collect seeds passing through the seed separating pipe.

4. The method of claim 1, wherein a recovery telescoping assembly is connected to an end of the conveyor belt remote from the seed tube; the retrieve flexible subassembly includes: the telescopic ejector rod and the accommodating box are arranged on one side, close to the ground, of the conveyor belt, and the accommodating box is used for accommodating the seed separation movable disc; the conveying belt conveys the seed separation movable disc to a position corresponding to the accommodating box so that the seed separation movable disc is accommodated in the accommodating box, and the telescopic ejector rod moves a target distance along one side far away from the conveying belt; and the target distance is determined according to the height of the seed separation movable plate.

5. The method of claim 1, wherein the measurement mechanism comprises: an illumination assembly disposed on one side of the measurement assembly; the intersection center of the illumination assembly and the measurement assembly is the target location.

6. The method of claim 1, wherein the acquiring raw hyperspectral information data of the seeds in the seed metering rotor by using the measuring mechanism in a linear array push-broom mode comprises:

7. The method of claim 6, wherein the raw hyperspectral information data comprises: original visible near infrared hyperspectral data, and/or original shortwave infrared hyperspectral data;

8. The method according to claim 1, wherein the acquiring the whiteboard hyperspectral data corresponding to the preset whiteboard provided on the seed tray, and performing reflectivity conversion on the original hyperspectral information data according to the previously acquired dark current hyperspectral data and the whiteboard hyperspectral data to obtain hyperspectral information data, comprises:

wherein the preset reflectivity formula is expressed as

；

9. The method of claim 1, wherein the three-dimensional hyperspectral data comprises: visible near infrared hyperspectral data, and/or short wave infrared hyperspectral data; the method comprises the steps of respectively performing shear-shift on the single-band images under each band according to a pre-acquired transformation matrix to obtain three-dimensional hyperspectral data, and further comprises the following steps:

10. The method of claim 9, wherein the seed phenotype data comprises: a major axis and a minor axis of the seed;

graying the RGB wave band image to obtain a grayed RGB wave band image;

11. The method of claim 10, wherein the phenotype data further comprises: seed coat color;

12. The method of claim 10, wherein the phenotype data further comprises: seed coat gloss;

13. The method of claim 10, wherein the phenotype data further comprises: a seed protein component and a seed oil component;

14. The method of claim 13, wherein the phenotype data further comprises: a seed protein component and a seed oil component;

15. The method of claim 13, wherein the phenotype data further comprises: a seed protein component and a seed oil component;

16. The method of claim 9, wherein the seed phenotype data comprises: a major axis and a minor axis of the seed;

graying the RGB wave band image to obtain a grayed RGB wave band image;

17. The method of claim 16, wherein the phenotype data further comprises: seed coat color;

18. The method of claim 16, wherein the phenotype data further comprises: seed coat gloss;

19. The method of claim 16, wherein the phenotype data further comprises: a seed protein component and a seed oil component;

20. The method of claim 19, wherein the phenotype data further comprises: a seed protein component and a seed oil component;

21. The method of claim 19, wherein the phenotype data further comprises: a seed protein component and a seed oil component;

22. Seed phenotype measuring apparatus for performing a seed phenotype measuring method employing a seed phenotype measuring system according to any of claims 1 to 21, the apparatus comprising:

the reflectivity conversion module is configured to acquire white board hyperspectral data corresponding to a preset white board arranged on the seed separation movable disk, and execute reflectivity conversion on the original hyperspectral information data according to the dark current hyperspectral data acquired in advance and the white board hyperspectral data so as to obtain hyperspectral information data; the hyperspectral information data includes: a single band image in a plurality of bands, the bands comprising: a visible near infrared hyperspectral band and a shortwave infrared hyperspectral band;

the shear-shift module is configured to respectively perform shear shift on the single-band images under each band according to a pre-acquired transformation matrix so as to obtain three-dimensional hyperspectral data; according to the pre-acquired transformation matrix, performing a shear transformation on the single-band image under each band to obtain three-dimensional hyperspectral data, including:

23. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-21 when the program is executed by the processor.

24. A computer readable storage medium storing computer instructions for causing the computer to implement the method of any one of claims 1-21.

25. A computer program product comprising computer program instructions which, when run on a computer, cause the computer to perform the method of any of claims 1-21.