Germinated seed screening device and method based on machine vision

Abstract

The invention provides a germinated seed screening device and method based on machine vision, and the method comprises the steps: collecting a plurality of stage images of a seed disc, marking the position of a seed in each stage image, determining a plurality of key analysis positions in the seed disc, obtaining the image information of each key analysis position in different stage images, and obtaining the image information of each key analysis position; determining a seed growth trend corresponding to the key analysis position, further analyzing an estimated germination time period corresponding to each seed, obtaining seed state characteristics in the estimated germination time periods, and further determining a planting position corresponding to each germinated seed in the seed disc by using the seed state characteristics; the planting position is marked, a seed germination report is generated and transmitted to the designated terminal for display, the germinated seeds can be recognized from many seeds through the image recognition technology, the manual pressure is reduced, the manual workload is reduced, and the screening accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural industry, and in particular to a device and method for screening germinated seeds based on machine vision. Background Art

[0002] The means of identifying crop germination are mainly through observing seeds, soil and environmental changes, as well as using some tools and methods for detection. Germination is a critical stage in plant growth, and timely identification of germination is crucial for agricultural management and crop growth regulation. The following are several common means of identifying crop germination: 1. Visual inspection method Method: This is the most common and direct method, which is to judge whether germination has occurred by observing the surface conditions of seeds and soil. Seeds in soil or moist environment can be checked regularly for a period of time after sowing.

[0003] Identification mark: Seed coat rupture: After the seeds absorb water and swell, cracks appear in the outer shell.

[0004] Root growth: The seed roots begin to break through the seed coat and grow downward, appearing as white or transparent roots.

[0005] Protrusion of the germ: The germ breaks through the seed coat, usually as a small green bud or stem.

[0006] Soil surface observation: If you see small green sprouts or sprout tips emerging from the soil, it means that the seeds have germinated.

[0007] 2. Water immersion method (seed soaking method) Method: Soak the seeds in water and observe their swelling after absorbing water. Usually, the seeds will begin to swell after absorbing water, and cracks may appear on the seed coat. This is a physiological phenomenon before the seeds germinate.

[0008] Steps: Soak the seeds in clean water for 24 hours (the soaking time may vary for different types of seeds).

[0009] Watch the seeds for swelling and any cracks.

[0010] If some of the seeds begin to crack and reveal small roots or sprouts, it means the seeds have entered the germination process.

[0011] 3. Wet cloth method Method: Place the seeds in a damp cloth or paper towel to simulate a natural wet environment. Keep the cloth moist and at a suitable temperature, and check regularly to see if the seeds have begun to germinate.

[0012] Steps: Take an appropriate amount of seeds and place them on a damp paper towel or cloth.

[0013] Place the seeds and damp cloth in a warm environment (such as 25-30°C).

[0014] Check the seeds regularly to see if there is any sign of a germ or root protruding from them.

[0015] Once you see the root or shoot tip breaking through the seed coat, you can be sure the seeds have germinated.

[0016] 4. Temperature and humidity monitoring method Method: By monitoring the temperature and humidity of the soil or sowing environment, combined with the physiological characteristics of the seeds, the germination situation can be inferred. Different crops have different germination temperature and humidity requirements. By using the changes in these conditions, the germination situation can be indirectly judged.

[0017] Steps: Use a thermometer and hygrometer to monitor the temperature and humidity of the planting environment to ensure they are within the appropriate range for seed germination.

[0018] Under suitable conditions, check the sowing area regularly and judge the germination progress based on changes in temperature and humidity.

[0019] Look for signs of seeds protruding from the soil surface or in the seedling tray.

[0020] 5. Transillumination method Method: Use a light-transmitting device (such as a portable magnifier or microscope) to examine the internal structure of the seed to see if the embryo is beginning to extend.

[0021] Steps: Remove the seeds and gently unpack or use a clear container to view.

[0022] Look inside the seeds for signs of roots or sprouts extending.

[0023] If the embryo has broken through the seed coat, it can be confirmed that the seeds have begun to germinate.

[0024] 6. Soil detection method (probe method) Method: Use professional soil detection tools, such as soil probes or detectors, to check the status of seeds deep in the soil. This method is usually used for large areas of farmland.

[0025] Steps: Use a soil probe to gently probe the depth of the seed in the soil.

[0026] If the probe touches a root or a sprout that has broken through the soil, the seed has germinated.

[0027] At the same time, monitor the temperature and humidity of the soil to ensure that the seeds germinate in a suitable environment.

[0028] 7. Seed Vitality Test Method: Check the germination ability of seeds through professional seed vigor testing. Usually it needs to be carried out under laboratory conditions and adopts standardized germination test methods.

[0029] Steps: A batch of seeds was removed and processed according to standard testing procedures.

[0030] Under suitable temperature and humidity conditions, observe the germination of seeds.

[0031] The germination rate and germination time were recorded to determine the vigor of the seeds and their suitability for planting.

[0032] Although the above methods can identify germinated seeds among many seeds, they all require manual observation and screening. Since different seeds have different germination cycles and observation experiments also require professional personnel, identifying whether seeds have germinated has become a high-pressure and high-workload task.

[0033] Therefore, the present invention provides a device and method for screening germinated seeds based on machine vision. Summary of the invention

[0034] The present invention discloses a germinated seed screening device and method based on machine vision, which can identify germinated seeds among many seeds by using image recognition technology, thereby reducing manual pressure, reducing manual workload, and improving screening accuracy.

[0035] The present invention provides a germination seed screening device based on machine vision, comprising: A visual acquisition module is used to acquire several stage images of the seed tray, mark the seed position in each stage image, and determine several key analysis positions in the seed tray; A key analysis module, used to respectively obtain image information of each key analysis position in the images of different stages, and determine the seed growth trend corresponding to the key analysis position according to the image information; A germination supervision module is used to analyze the estimated germination time period corresponding to each seed according to the seed growth germination trend, and obtain the seed state characteristics within the estimated germination time period; The germination screening module is used to determine the planting position corresponding to each germinated seed in the seed tray according to the seed state characteristics, mark the planting position and generate a seed germination report to transmit to a designated terminal for display.

[0036] In one practicable manner, The visual acquisition module comprises: a cycle adjustment unit, used to obtain the seed attributes in the seed tray, search for the seed attributes in big data, determine the growth data of the corresponding seeds, simulate the growth of the seeds according to the growth data and the environmental data of the seed tray, determine the growth cycle of the seeds in the seed tray, and determine the image acquisition frequency; An acquisition execution unit, used for acquiring a plurality of stage images of the seed tray according to the image acquisition frequency, and encoding the corresponding stage image according to the acquisition time corresponding to each stage image, so as to generate a periodic image set of the seed tray; The key positioning unit is used to perform pixel segmentation on each of the stage images respectively, determine the seed distribution position corresponding to the stage image according to the segmentation result, obtain the distribution information corresponding to each of the stage images, fuse the distribution information in the periodic image set, and determine several key analysis positions of the seed disk.

[0037] In one practicable manner, The key analysis module includes: A preliminary processing unit is used to establish a planting matrix of the seed tray according to the distribution of the key analysis positions in the seed tray, mark the key analysis positions in each of the stage images, divide each of the stage images into a plurality of unit images, and obtain a unit image set corresponding to each of the key analysis positions; An information identification unit, used to respectively identify the image change features of each of the unit image sets, respectively map each of the image change features to the element positions corresponding to the planting matrix, obtain the planting change matrix of the seed tray, and analyze the corresponding influencing features between different adjacent key analysis positions according to the planting change matrix; An information processing unit, used to modify corresponding image change features according to a plurality of influencing features corresponding to each of the key analysis positions, generate image information corresponding to each of the key analysis positions, and draw a regional dynamic map corresponding to the key analysis positions according to the image information; A trend analysis unit is used to identify the seed fixed position corresponding to the key analysis position in the regional dynamic map, obtain the dynamic change characteristics corresponding to the seed fixed position, perform growth analysis on the dynamic change characteristics according to the growth data of the seed, and determine the seed growth trend corresponding to the key analysis position.

[0038] In one practicable manner, The germination supervision module comprises: A trend analysis unit, used to determine the current growth quality of the corresponding seeds according to the seed growth trend, classify the seeds with the same current growth quality into the same seed category, obtain the planting time corresponding to each seed respectively, and determine the growth time of the corresponding seeds according to the planting time; A deep analysis unit, for analyzing the nutrient supply speed corresponding to different seeds in each of the seed classes according to the growth time, analyzing the estimated germination time period of the corresponding seeds in combination with the corresponding current growth quality, and adding a category label and a time period label to each seed according to the estimated germination time period corresponding to different seeds in each of the seed classes; A state refinement unit, for determining the current growth state and remaining germination time of the corresponding seed according to the category label and time period label corresponding to each seed, drawing a growth concept chart of the corresponding seed, and identifying the seed growth information corresponding to each unit time in the growth concept chart according to the corresponding growth trend and nutrient supply speed; The overall analysis unit is used to respectively collect the real-time growth information corresponding to each of the seeds, determine the current growth deviation information corresponding to the seeds according to the unit time corresponding to the supervision collection time, adjust the estimated germination time period of the corresponding seeds according to the current growth deviation information, and obtain the precise germination time period corresponding to each of the seeds. When the supervision collection time coincides with the precise germination time period, the seed state characteristics corresponding to the seeds are obtained.

[0039] In one practicable manner, The process of adjusting the estimated germination time period of the corresponding seeds according to the current growth deviation information to obtain the precise germination time period corresponding to each of the seeds includes: When the current growth deviation information is positive, it is determined that the corresponding seed is currently in a positive stimulation state, and the current positive stimulation level of the seed is analyzed according to the deviation amount corresponding to the growth deviation information; According to the current positive stimulation level, the corresponding estimated germination time period is moved positively to obtain the temporary germination time period corresponding to the seeds; Obtaining updated growth deviation information corresponding to the seed at the next supervised collection moment, and when the updated growth deviation is positive, determining a stable stimulation level of the external environment to the seed according to an updated positive stimulation level corresponding to the updated growth deviation information and the current positive stimulation level; Analyzing the growth stimulation speed of the seeds by the external environment according to the stable stimulation level and the corresponding seed growth trend, adjusting the duration of the temporary germination period according to the growth stimulation speed, and obtaining the precise germination period of the seeds; When the current growth deviation information is negative, the estimated germination time period is regarded as the precise germination time period of the corresponding seed; When the current growth deviation information is positive and the corresponding updated growth deviation information is negative, the estimated germination time period is regarded as the precise germination time period of the corresponding seed.

[0040] In one practicable manner, The germination screening module comprises: A germination positioning unit, used to determine a number of germinated seeds showing germination characteristics in the seed tray according to the seed state, and obtain a planting position corresponding to each of the germinated seeds; A germination marking unit, used for selecting a corresponding wavelength of promoting light according to the seed attributes corresponding to the seed, using the promoting light to establish a marking cursor, and using the marking cursor to mark the planting position; The report generating unit is used to respectively obtain the appearance information corresponding to each of the germinated seeds, generate a seed germination report of the seed tray, and transmit it to a designated terminal for display.

[0041] In one practicable manner, The report generating unit comprises: The visual analysis subunit is used to respectively obtain the germination images corresponding to each of the germinating seeds, respectively perform image projection on each of the germination images to obtain the seed images contained in each of the germination images, and perform corner point recognition on each of the seed images using a peak detection method to obtain a plurality of corner point connection lines contained in each of the seed images; A germination classification subunit is used to map the corner point connection line in the corresponding germination image, obtain the seed crack information and seed water information corresponding to each germination image, regard the first germinated seed containing both the seed crack information and the seed water information as a Class I germinated seed, regard the second germinated seed containing the seed crack information as a Class II germinated seed, and regard the third germinated seed containing the seed water information as a Class III germinated seed; The report generating unit is used to calculate the germination rate of the seeds in the seed tray and the number of germinations corresponding to each type of germinating seeds, establish a seed germination report of the seed tray and transmit it to a designated terminal for display.

[0042] In one practicable manner, Also includes: The analysis and reminder module is used to collect the non-germination time corresponding to each of the key analysis positions, and when the non-germination time is longer than a preset time, determine the corresponding seed germination identification and generate reminder information.

[0043] The present invention provides a method for screening germinated seeds based on machine vision, comprising: Step 1: Collect several stage images of the seed tray, mark the seed position in each stage image, and determine several key analysis positions in the seed tray; Step 2: respectively obtaining image information of each of the key analysis positions in the images of different stages, and determining the seed growth trend corresponding to the key analysis position according to the image information; Step 3: Analyze the estimated germination time period corresponding to each seed according to the seed growth and germination trend, and obtain the seed state characteristics within the estimated germination time period; Step 4: Determine the planting position corresponding to each germinated seed in the seed tray according to the seed status characteristics, mark the planting position and generate a seed germination report and transmit it to the designated terminal for display. In one practicable manner, The step 3 comprises: Step 31: determining the current growth quality of the corresponding seeds according to the seed growth trend, classifying the seeds with the same current growth quality as the same seed category, obtaining the planting time corresponding to each seed respectively, and determining the growth time of the corresponding seeds according to the planting time; Step 32: Analyze the nutrient supply speed corresponding to different seeds in each seed class according to the growth time, analyze the estimated germination time period of the corresponding seeds in combination with the corresponding current growth quality, and add a category label and a time period label to each seed according to the estimated germination time period corresponding to different seeds in each seed class; Step 33: determining the current growth state and remaining germination time of the corresponding seed according to the category label and time period label corresponding to each seed, drawing a growth concept chart of the corresponding seed, and identifying the seed growth information corresponding to each unit time in the growth concept chart according to the corresponding growth trend and nutrient supply speed; Step 34: respectively collect the real-time growth information corresponding to each of the seeds, determine the current growth deviation information corresponding to the seeds according to the unit time corresponding to the supervised collection time, adjust the estimated germination time period of the corresponding seeds according to the current growth deviation information, and obtain the precise germination time period corresponding to each of the seeds. When the supervised collection time coincides with the precise germination time period, obtain the seed state characteristics corresponding to the seeds.

[0044] The achievable beneficial effects of the above technical solution are as follows: in order to reduce the work pressure of the staff and improve the efficiency of screening germinated seeds, several stage images of the seed tray are first collected, and the seed position is determined in the stage image, thereby determining several key analysis positions in the seed tray, and further image analysis is performed on the key analysis positions to determine the seed growth trend presented by the seeds in each key analysis position, thereby estimating the estimated germination time period of the seeds. When the time reaches the estimated germination time period, the seed state characteristics of the seeds during this period are collected, and the planting position of the germinated seeds in the seed tray is further determined based on the seed state characteristics, and corresponding reminders are given. Finally, a seed germination report is established based on the data of this germination, and transmitted to the designated terminal for display. The staff can quickly determine the position of the germinated seeds based on the report, thereby completing the purpose of rapid screening. Screening using image analysis can also improve the accuracy of screening, reduce the randomness of manual screening, and increase the speed of agricultural development.

[0045] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0046] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 Schematic diagram of the composition of a germinated seed screening device based on machine vision in an embodiment of the present invention; Figure 2 The figure is a schematic diagram of the workflow of a method for screening germinated seeds based on machine vision in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0049] Example 1 This embodiment provides a germination seed screening device based on machine vision, such as Figure 1 As shown, including: A visual acquisition module is used to acquire several stage images of the seed tray, mark the seed position in each stage image, and determine several key analysis positions in the seed tray; A key analysis module, used to respectively obtain image information of each key analysis position in the images of different stages, and determine the seed growth trend corresponding to the key analysis position according to the image information; A germination supervision module is used to analyze the estimated germination time period corresponding to each seed according to the seed growth germination trend, and obtain the seed state characteristics within the estimated germination time period; The germination screening module is used to determine the planting position corresponding to each germinated seed in the seed tray according to the seed state characteristics, mark the planting position and generate a seed germination report to transmit to a designated terminal for display.

[0050] In this example, the stage images represent images acquired at different moments; In this example, several seeds are planted in the seed tray, and the seeds may be planted at different times; In this example, the key analysis position indicates the position of the seed. One key analysis position contains one or more seeds. When the interval between seeds is greater than 2 cm, one key analysis position corresponds to one seed. When the interval between seeds is less than 2 cm, one key analysis position corresponds to multiple seeds. In this example, the image information includes information presented at the next key analysis position at different times; In this example, the seed growth trend indicates the growth of seeds planted at the focus analysis location; In this example, the estimated germination time period means that the seeds will germinate at any time within the time period.

[0051] The working principle and beneficial effects of the above technical solution are as follows: in order to reduce the work pressure of the staff and improve the efficiency of screening germinated seeds, several stage images of the seed tray are first collected, and the seed position is determined in the stage image, thereby determining several key analysis positions in the seed tray, and further image analysis is performed on the key analysis positions to determine the seed growth trend presented by the seeds in each key analysis position, thereby estimating the estimated germination time period of the seeds. When the time reaches the estimated germination time period, the seed state characteristics of the seeds during this period are collected, and the planting position of the germinated seeds in the seed tray is further determined based on the seed state characteristics, and corresponding reminders are given. Finally, a seed germination report is established based on the data of this germination and transmitted to the designated terminal for display. The staff can quickly determine the position of the germinated seeds based on the report, thereby completing the purpose of rapid screening. Screening using image analysis can also improve the accuracy of screening, reduce the randomness of manual screening, and increase the speed of agricultural development.

[0052] Example 2 On the basis of Example 1, the germinated seed screening device based on machine vision is characterized in that the visual acquisition module includes: a cycle adjustment unit, used to obtain the seed attributes in the seed tray, search for the seed attributes in big data, determine the growth data of the corresponding seeds, simulate the growth of the seeds according to the growth data and the environmental data of the seed tray, determine the growth cycle of the seeds in the seed tray, and determine the image acquisition frequency; An acquisition execution unit, used for acquiring a plurality of stage images of the seed tray according to the image acquisition frequency, and encoding the corresponding stage image according to the acquisition time corresponding to each stage image, so as to generate a periodic image set of the seed tray; The key positioning unit is used to perform pixel segmentation on each of the stage images respectively, determine the seed distribution position corresponding to the stage image according to the segmentation result, obtain the distribution information corresponding to each of the stage images, fuse the distribution information in the periodic image set, and determine several key analysis positions of the seed disk.

[0053] In this example, the seed attributes include the name of the seed and the seed source, which are used to identify the seed; In this example, the growth data represents the data generated when the seeds grow in the acclimated environment; In this example, the growth cycle refers to the period from planting to germination of seeds in the seed tray, which includes the water absorption stage (early germination stage), activation stage (enzyme activation stage), radicle breakthrough stage, embryo breakthrough stage, first true leaf expansion stage and root system development and nutrient absorption stage of the seeds; In this example, the image acquisition frequency indicates the frequency of taking images of the seed tray. The image acquisition frequency is related to the growth cycle of the seeds. Three images need to be taken at each stage of the growth cycle. In this example, the period image set represents the result of encoding and sorting the stage images in chronological order; In this example, the distribution information represents the distribution of seeds in a stage image; In this example, the purpose of the fusion process is to check the position of the seeds.

[0054] The working principle and beneficial effects of the above technical solution: In order to improve the screening efficiency of germinated seeds, it is necessary to determine the planting position of the seeds in the early stage of screening, so as to focus on the analysis of the planting position. First, the growth data of the seeds is found according to the seed attributes, and the growth cycle of the seeds in the seed tray is determined by simulation. The frequency of image acquisition is determined, and then the stage images of the seed tray are collected according to the frequency. The periodic image set of the seed tray is established by encoding and sorting the stage images, and the seed distribution information presented in each periodic image is fused, so that the position of the seeds is calibrated and checked many times, and several key analysis positions in the seed tray are determined. Then, when analyzing and screening, it is only necessary to focus on the key analysis positions to determine the position of the germinated seeds, which reduces a lot of unnecessary identification work and improves the efficiency of screening.

[0055] Example 3 On the basis of Example 1, the germinated seed screening device based on machine vision, the key analysis module includes: A preliminary processing unit is used to establish a planting matrix of the seed tray according to the distribution of the key analysis positions in the seed tray, mark the key analysis positions in each of the stage images, divide each of the stage images into a plurality of unit images, and obtain a unit image set corresponding to each of the key analysis positions; An information identification unit, used to respectively identify the image change features of each of the unit image sets, respectively map each of the image change features to the element positions corresponding to the planting matrix, obtain the planting change matrix of the seed tray, and analyze the corresponding influencing features between different adjacent key analysis positions according to the planting change matrix; An information processing unit, used to modify corresponding image change features according to a plurality of influencing features corresponding to each of the key analysis positions, generate image information corresponding to each of the key analysis positions, and draw a regional dynamic map corresponding to the key analysis positions according to the image information; A trend analysis unit is used to identify the seed fixed position corresponding to the key analysis position in the regional dynamic map, obtain the dynamic change characteristics corresponding to the seed fixed position, perform growth analysis on the dynamic change characteristics according to the growth data of the seed, and determine the seed growth trend corresponding to the key analysis position.

[0056] In this example, the planting matrix represents a blank matrix established based on the distribution of the key analysis locations; In this example, the unit image refers to an image used to represent a focus analysis position in a stage image; In this example, the unit image set refers to an image set generated by aggregating unit images with a focus analysis position in different phase images; In this example, the image change feature represents a feature about the seed change, which is composed of the difference between different unit images in a unit image set; In this example, a unit image set corresponds to an image change feature and also corresponds to an element position; In this example, the influence feature represents the seed growth influence between the focused analysis positions with adjacent relationships; In this example, the regional dynamic graph represents a dynamic image of changes occurring in the focused analysis area; In this example, the position of the seed in the focus analysis position is fixed.

[0057] The working principle and beneficial effects of the above technical solution are as follows: Since the environment has an impact on the germination of seeds, in order to better analyze the growth trend of seeds, a planting matrix of the seed tray is first established according to the distribution of key analysis positions in the seed tray, and each stage image is divided into a number of unit images to generate a unit image set corresponding to each key analysis position, and then the image change characteristics of the unit image set are mapped in the planting matrix, the influence characteristics between different adjacent key analysis positions are analyzed, and then the image change characteristics are corrected using the influence characteristics to determine the image information at the key analysis position, thereby drawing a regional dynamic map of the key analysis position, and focusing on the analysis of the fixed position of the seed in the regional dynamic map to obtain the dynamic change characteristics of the position, and combining the growth data of the seed to perform growth analysis to determine the seed growth trend of the key analysis position. In this way, all seeds in the seed tray can be uniformly analyzed at the same time to determine their seed growth trend, which is convenient for subsequent corresponding screening work.

[0058] Example 4 On the basis of Example 1, the germination seed screening device based on machine vision, the germination supervision module includes: A trend analysis unit, used to determine the current growth quality of the corresponding seeds according to the seed growth trend, classify the seeds with the same current growth quality into the same seed category, obtain the planting time corresponding to each seed respectively, and determine the growth time of the corresponding seeds according to the planting time; A deep analysis unit, for analyzing the nutrient supply speed corresponding to different seeds in each of the seed classes according to the growth time, analyzing the estimated germination time period of the corresponding seeds in combination with the corresponding current growth quality, and adding a category label and a time period label to each seed according to the estimated germination time period corresponding to different seeds in each of the seed classes; A state refinement unit, for determining the current growth state and remaining germination time of the corresponding seed according to the category label and time period label corresponding to each seed, drawing a growth concept chart of the corresponding seed, and identifying the seed growth information corresponding to each unit time in the growth concept chart according to the corresponding growth trend and nutrient supply speed; The overall analysis unit is used to respectively collect the real-time growth information corresponding to each of the seeds, determine the current growth deviation information corresponding to the seeds according to the unit time corresponding to the supervision collection time, adjust the estimated germination time period of the corresponding seeds according to the current growth deviation information, and obtain the precise germination time period corresponding to each of the seeds. When the supervision collection time coincides with the precise germination time period, the seed state characteristics corresponding to the seeds are obtained.

[0059] In this example, the current growth quality indicates the current growth stage of the seed and the degree of growth in this stage; In this example, the greater the nutrient supply rate, the closer the estimated germination time period of the seeds is to the current moment; In this example, the purpose of adding category labels and time period labels is to further classify seeds; In this example, the current growth state is related to the current growth quality, which is a synchronous relationship; In this example, the remaining germination time represents the time between the current moment and the last moment of the estimated germination time period; In this example, the current growth deviation information indicates the information corresponding to the case where the real-time growth information is inconsistent with the seed growth information at the corresponding unit time; In this example, the seed growth information means analyzing the growth of the seed at different time units by predicting; In this example, the supervision collection time corresponds one-to-one with the unit time; In this example, the precise germination time period refers to the result of determining the influence of the external environment on the seeds based on the real-time growth information of the seeds, thereby further refining and adjusting the estimated germination time period.

[0060] The working principle and beneficial effects of the above technical solution are as follows: first, the current growth quality of the seeds is analyzed according to their growth trend, and then the seeds are classified, and then the growth time of the seeds is determined in combination with the planting time of each seed, so as to analyze the nutrient supply speed of different seeds in the same seed class, determine the estimated germination time period of the seeds, and add corresponding category labels and time period labels to each seed, so as to facilitate the subsequent determination of the current growth state and remaining germination time of each seed, draw a growth concept chart of each seed, and analyze the nutrient supply speed of the seeds through the image, so as to determine the seed growth information corresponding to each unit time, and then monitor the seeds in real time to determine the current growth deviation information corresponding to different time periods, and finally use the current growth deviation information to further accurately analyze the estimated germination time period of the seeds, determine the precise germination time period of the seeds, and collect the state characteristics of the seeds within the time period, so that the situation of the seeds can be deeply supervised in the time period when the seeds are about to germinate, and the germination information of the seeds can be collected at the first time when the seeds germinate, thereby improving the working efficiency of the germinated seed screening device and reducing the error of manual screening.

[0061] Example 5 On the basis of Example 4, the device for screening germinating seeds based on machine vision adjusts the estimated germination time period of the corresponding seeds according to the current growth deviation information to obtain the precise germination time period corresponding to each of the seeds, including: When the current growth deviation information is positive, it is determined that the corresponding seed is currently in a positive stimulation state, and the current positive stimulation level of the seed is analyzed according to the deviation amount corresponding to the growth deviation information; According to the current positive stimulation level, the corresponding estimated germination time period is moved positively to obtain the temporary germination time period corresponding to the seeds; Obtaining updated growth deviation information corresponding to the seed at the next supervised collection moment, and when the updated growth deviation is positive, determining a stable stimulation level of the external environment to the seed according to an updated positive stimulation level corresponding to the updated growth deviation information and the current positive stimulation level; Analyzing the growth stimulation speed of the seeds by the external environment according to the stable stimulation level and the corresponding seed growth trend, adjusting the duration of the temporary germination period according to the growth stimulation speed, and obtaining the precise germination period of the seeds; When the current growth deviation information is negative, the estimated germination time period is regarded as the precise germination time period of the corresponding seed; When the current growth deviation information is positive and the corresponding updated growth deviation information is negative, the estimated germination time period is regarded as the precise germination time period of the corresponding seed.

[0062] In this example, the positive stimulus state means that the external environment promotes the growth of the seed; In this example, the current positive stimulation level is related to the external environment. When the current positive stimulation level increases by one level, it moves forward by one unit time, and the maximum possible movement is 4 unit time. The unit time is set in advance by the staff, and is generally 24 hours. In this example, the direction of positive movement is the direction at the current moment; In this example, the updated growth deviation information indicates the deviation between the real-time growth information and the seed growth information corresponding to the next supervision moment; In this example, the growth stimulation rate is related to the external environment, and the precise germination period can be obtained by multiplying the growth stimulation rate by the corresponding temporary germination period; In this example, when adjusting the estimated germination time period, the odd-numbered supervised collection moments and their adjacent even-numbered supervised collection moments are regarded as a deviation adjustment combination, the purpose of which is to determine the stable external stimulation of the seeds and reduce randomness.

[0063] The working principle and beneficial effects of the above technical solution: in the process of adjusting the estimated germination time period, the stimulation of the external environment on the seeds is taken into account, and a combined analysis is performed by analyzing the corresponding growth deviation information at different supervised collection times, responding to the positive stimulation of the external environment on the seeds, thereby scaling the estimated germination time period of the seeds, determining the precise germination time period, and improving the efficiency of screening germinated seeds.

[0064] Example 6 On the basis of Example 1, the germination seed screening device based on machine vision, the germination screening module includes: A germination positioning unit, used to determine a number of germinated seeds showing germination characteristics in the seed tray according to the seed state, and obtain a planting position corresponding to each of the germinated seeds; A germination marking unit, used for selecting a corresponding wavelength of promoting light according to the seed attributes corresponding to the seed, using the promoting light to establish a marking cursor, and using the marking cursor to mark the planting position; The report generating unit is used to respectively obtain the appearance information corresponding to each of the germinated seeds, generate a seed germination report of the seed tray, and transmit it to a designated terminal for display.

[0065] In this example, the promoting light refers to light that promotes the growth of seeds. The wavelength of the promoting light is determined by the properties of the seeds, and promoting light of different wavelengths promotes different seeds.

[0066] The working principle and beneficial effects of the above technical solution are as follows: the seeds in the seed tray that are in a germination state are determined by the seed status, and then the light marking method is used to remind relevant personnel of the location of the germinating seeds. At the same time, a seed germination report is generated for relevant personnel to review, so that the growth status of the seeds in the seed tray can be understood at any time.

[0067] Example 7 On the basis of Example 6, the germinated seed screening device based on machine vision, the report generating unit comprises: The visual analysis subunit is used to respectively obtain the germination images corresponding to each of the germinating seeds, respectively perform image projection on each of the germination images to obtain the seed images contained in each of the germination images, and perform corner point recognition on each of the seed images using a peak detection method to obtain a plurality of corner point connection lines contained in each of the seed images; A germination classification subunit is used to map the corner point connection line in the corresponding germination image, obtain the seed crack information and seed water information corresponding to each germination image, regard the first germinated seed containing both the seed crack information and the seed water information as a Class I germinated seed, regard the second germinated seed containing the seed crack information as a Class II germinated seed, and regard the third germinated seed containing the seed water information as a Class III germinated seed; The report generating unit is used to calculate the germination rate of the seeds in the seed tray and the number of germinations corresponding to each type of germinating seeds, establish a seed germination report of the seed tray and transmit it to a designated terminal for display.

[0068] In this example, the corner point connection line represents an irregular line segment composed of edges, edge intersections, and line corners contained in the seed image; In this example, the seed crack information indicates that the seeds are cracked; In this example, the seed water release information indicates that the seeds have sprouted and there is no water release on the sprouts; In this example, different kinds of germinated seeds refer to seeds at different stages of germination.

[0069] The working principle and beneficial effects of the above technical solution are as follows: by projecting the germination image of the germinated seeds to identify the corner points in the seed image, and then continuously mapping the corner points in the germination image, identifying the seed crack information and seed water information of the germinated seeds, and then classifying the germinated seeds according to these two information, and constructing a seed germination report in combination with the germination rate of the seeds in the seed tray for relevant personnel to view. Relevant personnel can use the report to understand the germination status of the seeds at any time, providing a reference for their next technical work.

[0070] Example 8 On the basis of Example 1, the germinated seed screening device based on machine vision further includes: The analysis and reminder module is used to collect the non-germination time corresponding to each of the key analysis positions, and when the non-germination time is longer than a preset time, determine the corresponding seed germination identification and generate reminder information.

[0071] The working principle and beneficial effects of the above technical solution: When seeds do not germinate for a long time, relevant personnel are reminded to check as soon as possible to find out the reasons.

[0072] Example 9 This embodiment provides a method for screening germinating seeds based on machine vision, such as Figure 2 As shown, including: Step 1: Collect several stage images of the seed tray, mark the seed position in each stage image, and determine several key analysis positions in the seed tray; Step 2: respectively obtaining image information of each of the key analysis positions in the images of different stages, and determining the seed growth trend corresponding to the key analysis position according to the image information; Step 3: Analyze the estimated germination time period corresponding to each seed according to the seed growth and germination trend, and obtain the seed state characteristics within the estimated germination time period; Step 4: Determine the planting position corresponding to each germinated seed in the seed tray according to the seed state characteristics, mark the planting position and generate a seed germination report which is transmitted to a designated terminal for display.

[0073] In this example, the stage images represent images acquired at different moments; In this example, several seeds are planted in the seed tray, and the seeds may be planted at different times; In this example, the key analysis position indicates the position of the seed. One key analysis position contains one or more seeds. When the interval between seeds is greater than 2 cm, one key analysis position corresponds to one seed. When the interval between seeds is less than 2 cm, one key analysis position corresponds to multiple seeds. In this example, the image information includes information presented at the next key analysis position at different times; In this example, the seed growth trend indicates the growth of seeds planted at the focus analysis location; In this example, the estimated germination time period means that the seeds will germinate at any time within the time period.

[0074] The working principle and beneficial effects of the above technical solution are as follows: in order to reduce the work pressure of the staff and improve the efficiency of screening germinated seeds, several stage images of the seed tray are first collected, and the seed position is determined in the stage image, thereby determining several key analysis positions in the seed tray, and further image analysis is performed on the key analysis positions to determine the seed growth trend presented by the seeds in each key analysis position, thereby estimating the estimated germination time period of the seeds. When the time reaches the estimated germination time period, the seed state characteristics of the seeds during this period are collected, and the planting position of the germinated seeds in the seed tray is further determined based on the seed state characteristics, and corresponding reminders are given. Finally, a seed germination report is established based on the data of this germination and transmitted to the designated terminal for display. The staff can quickly determine the position of the germinated seeds based on the report, thereby completing the purpose of rapid screening. Screening using image analysis can also improve the accuracy of screening, reduce the randomness of manual screening, and increase the speed of agricultural development.

[0075] Example 10 On the basis of Example 9, the method for screening germinated seeds based on machine vision, step 3, comprises: Step 31: determining the current growth quality of the corresponding seeds according to the seed growth trend, classifying the seeds with the same current growth quality as the same seed category, obtaining the planting time corresponding to each seed respectively, and determining the growth time of the corresponding seeds according to the planting time; Step 32: Analyze the nutrient supply speed corresponding to different seeds in each seed class according to the growth time, analyze the estimated germination time period of the corresponding seeds in combination with the corresponding current growth quality, and add a category label and a time period label to each seed according to the estimated germination time period corresponding to different seeds in each seed class; Step 33: determining the current growth state and remaining germination time of the corresponding seed according to the category label and time period label corresponding to each seed, drawing a growth concept chart of the corresponding seed, and identifying the seed growth information corresponding to each unit time in the growth concept chart according to the corresponding growth trend and nutrient supply speed; Step 34: respectively collect the real-time growth information corresponding to each of the seeds, determine the current growth deviation information corresponding to the seeds according to the unit time corresponding to the supervised collection time, adjust the estimated germination time period of the corresponding seeds according to the current growth deviation information, and obtain the precise germination time period corresponding to each of the seeds. When the supervised collection time coincides with the precise germination time period, obtain the seed state characteristics corresponding to the seeds.

[0076] In this example, the current growth quality indicates the current growth stage of the seed and the degree of growth in this stage; In this example, the greater the nutrient supply rate, the closer the estimated germination time period of the seeds is to the current moment; In this example, the purpose of adding category labels and time period labels is to further classify seeds; In this example, the current growth state is related to the current growth quality, which is a synchronous relationship; In this example, the remaining germination time represents the time between the current moment and the last moment of the estimated germination time period; In this example, the current growth deviation information indicates the information corresponding to the case where the real-time growth information is inconsistent with the seed growth information at the corresponding unit time; In this example, the seed growth information means analyzing the growth of the seed at different time units by predicting; In this example, the supervision collection time corresponds one-to-one with the unit time; In this example, the precise germination time period refers to the result of determining the influence of the external environment on the seeds based on the real-time growth information of the seeds, thereby further refining and adjusting the estimated germination time period.

[0077] The working principle and beneficial effects of the above technical solution are as follows: first, the current growth quality of the seeds is analyzed according to their growth trend, and then the seeds are classified, and then the growth time of the seeds is determined in combination with the planting time of each seed, so as to analyze the nutrient supply speed of different seeds in the same seed class, determine the estimated germination time period of the seeds, and add corresponding category labels and time period labels to each seed, so as to facilitate the subsequent determination of the current growth state and remaining germination time of each seed, draw a growth concept chart of each seed, and analyze the nutrient supply speed of the seeds through the image, so as to determine the seed growth information corresponding to each unit time, and then monitor the seeds in real time to determine the current growth deviation information corresponding to different time periods, and finally use the current growth deviation information to further accurately analyze the estimated germination time period of the seeds, determine the precise germination time period of the seeds, and collect the state characteristics of the seeds within the time period, so that the situation of the seeds can be deeply supervised in the time period when the seeds are about to germinate, and the germination information of the seeds can be collected at the first time when the seeds germinate, thereby improving the working efficiency of the germinated seed screening device and reducing the error of manual screening.

[0078] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A germinated seed screening device based on machine vision, characterized in that: include: A visual acquisition module is used to acquire several stage images of the seed tray, mark the seed position in each stage image, and determine several key analysis positions in the seed tray; A key analysis module, used to respectively obtain image information of each key analysis position in the images of different stages, and determine the seed growth trend corresponding to the key analysis position according to the image information; A germination supervision module is used to analyze the estimated germination time period corresponding to each seed according to the seed growth germination trend, and obtain the seed state characteristics within the estimated germination time period; The germination screening module is used to determine the planting position corresponding to each germinated seed in the seed tray according to the seed state characteristics, mark the planting position and generate a seed germination report to transmit to a designated terminal for display.

2. A germinated seed screening device based on machine vision as claimed in claim 1, characterized in that: The visual acquisition module comprises: a cycle adjustment unit, used to obtain the seed attributes in the seed tray, search for the seed attributes in big data, determine the growth data of the corresponding seeds, simulate the growth of the seeds according to the growth data and the environmental data of the seed tray, determine the growth cycle of the seeds in the seed tray, and determine the image acquisition frequency; An acquisition execution unit, used for acquiring a plurality of stage images of the seed tray according to the image acquisition frequency, and encoding the corresponding stage image according to the acquisition time corresponding to each stage image, so as to generate a periodic image set of the seed tray; The key positioning unit is used to perform pixel segmentation on each of the stage images respectively, determine the seed distribution position corresponding to the stage image according to the segmentation result, obtain the distribution information corresponding to each of the stage images, fuse the distribution information in the periodic image set, and determine several key analysis positions of the seed disk.

3. The device for screening germinated seeds based on machine vision as claimed in claim 1, characterized in that: The key analysis module includes: A preliminary processing unit is used to establish a planting matrix of the seed tray according to the distribution of the key analysis positions in the seed tray, mark the key analysis positions in each of the stage images, divide each of the stage images into a plurality of unit images, and obtain a unit image set corresponding to each of the key analysis positions; An information identification unit, used to respectively identify the image change features of each of the unit image sets, respectively map each of the image change features to the element positions corresponding to the planting matrix, obtain the planting change matrix of the seed tray, and analyze the corresponding influencing features between different adjacent key analysis positions according to the planting change matrix; An information processing unit, used to modify corresponding image change features according to a plurality of influencing features corresponding to each of the key analysis positions, generate image information corresponding to each of the key analysis positions, and draw a regional dynamic map corresponding to the key analysis positions according to the image information; A trend analysis unit is used to identify the seed fixed position corresponding to the key analysis position in the regional dynamic map, obtain the dynamic change characteristics corresponding to the seed fixed position, perform growth analysis on the dynamic change characteristics according to the growth data of the seed, and determine the seed growth trend corresponding to the key analysis position.

4. The device for screening germinated seeds based on machine vision as claimed in claim 1, characterized in that: The germination supervision module comprises: A trend analysis unit, used to determine the current growth quality of the corresponding seeds according to the seed growth trend, classify the seeds with the same current growth quality into the same seed category, obtain the planting time corresponding to each seed respectively, and determine the growth time of the corresponding seeds according to the planting time; A deep analysis unit, for analyzing the nutrient supply speed corresponding to different seeds in each of the seed classes according to the growth time, analyzing the estimated germination time period of the corresponding seeds in combination with the corresponding current growth quality, and adding a category label and a time period label to each seed according to the estimated germination time period corresponding to different seeds in each of the seed classes; A state refinement unit, for determining the current growth state and remaining germination time of the corresponding seed according to the category label and time period label corresponding to each seed, drawing a growth concept chart of the corresponding seed, and identifying the seed growth information corresponding to each unit time in the growth concept chart according to the corresponding growth trend and nutrient supply speed; The overall analysis unit is used to respectively collect the real-time growth information corresponding to each of the seeds, determine the current growth deviation information corresponding to the seeds according to the unit time corresponding to the supervision collection time, adjust the estimated germination time period of the corresponding seeds according to the current growth deviation information, and obtain the precise germination time period corresponding to each of the seeds. When the supervision collection time coincides with the precise germination time period, the seed state characteristics corresponding to the seeds are obtained.

5. The device for screening germinated seeds based on machine vision as claimed in claim 4, characterized in that: The process of adjusting the estimated germination time period of the corresponding seeds according to the current growth deviation information to obtain the precise germination time period corresponding to each of the seeds includes: When the current growth deviation information is positive, it is determined that the corresponding seed is currently in a positive stimulation state, and the current positive stimulation level of the seed is analyzed according to the deviation amount corresponding to the growth deviation information; According to the current positive stimulation level, the corresponding estimated germination time period is moved positively to obtain the temporary germination time period corresponding to the seeds; Obtaining updated growth deviation information corresponding to the seed at the next supervised collection moment, and when the updated growth deviation is positive, determining a stable stimulation level of the external environment to the seed according to an updated positive stimulation level corresponding to the updated growth deviation information and the current positive stimulation level; Analyzing the growth stimulation speed of the seeds by the external environment according to the stable stimulation level and the corresponding seed growth trend, adjusting the duration of the temporary germination period according to the growth stimulation speed, and obtaining the precise germination period of the seeds; When the current growth deviation information is negative, the estimated germination time period is regarded as the precise germination time period of the corresponding seed; When the current growth deviation information is positive and the corresponding updated growth deviation information is negative, the estimated germination time period is regarded as the precise germination time period of the corresponding seed.

6. The device for screening germinated seeds based on machine vision as claimed in claim 1, characterized in that: The germination screening module comprises: A germination positioning unit, used to determine a number of germinated seeds showing germination characteristics in the seed tray according to the seed state, and obtain a planting position corresponding to each of the germinated seeds; A germination marking unit, used for selecting a corresponding wavelength of promoting light according to the seed attributes corresponding to the seed, using the promoting light to establish a marking cursor, and using the marking cursor to mark the planting position; The report generating unit is used to respectively obtain the appearance information corresponding to each of the germinated seeds, generate a seed germination report of the seed tray, and transmit it to a designated terminal for display.

7. The device for screening germinated seeds based on machine vision as claimed in claim 6, characterized in that: The report generating unit comprises: The visual analysis subunit is used to respectively obtain the germination images corresponding to each of the germinating seeds, respectively perform image projection on each of the germination images to obtain the seed images contained in each of the germination images, and perform corner point recognition on each of the seed images using a peak detection method to obtain a plurality of corner point connection lines contained in each of the seed images; A germination classification subunit is used to map the corner point connection line in the corresponding germination image, obtain the seed crack information and seed water information corresponding to each germination image, regard the first germinated seed containing both the seed crack information and the seed water information as a Class I germinated seed, regard the second germinated seed containing the seed crack information as a Class II germinated seed, and regard the third germinated seed containing the seed water information as a Class III germinated seed; The report generating unit is used to calculate the germination rate of the seeds in the seed tray and the number of germinations corresponding to each type of germinating seeds, establish a seed germination report of the seed tray and transmit it to a designated terminal for display.

8. The device for screening germinated seeds based on machine vision as claimed in claim 1, characterized in that: Also includes: The analysis and reminder module is used to collect the non-germination time corresponding to each of the key analysis positions, and when the non-germination time is longer than a preset time, determine the corresponding seed germination identification and generate reminder information.

9. A method for screening germinated seeds based on machine vision, characterized in that: include: Step 1: Collect several stage images of the seed tray, mark the seed position in each stage image, and determine several key analysis positions in the seed tray; Step 2: respectively obtaining image information of each of the key analysis positions in the images of different stages, and determining the seed growth trend corresponding to the key analysis position according to the image information; Step 3: Analyze the estimated germination time period corresponding to each seed according to the seed growth and germination trend, and obtain the seed state characteristics within the estimated germination time period; Step 4: Determine the planting position corresponding to each germinated seed in the seed tray according to the seed state characteristics, mark the planting position and generate a seed germination report which is transmitted to a designated terminal for display.

10. A method for screening germinated seeds based on machine vision as claimed in claim 9, characterized in that: The step 3 comprises: Step 31: determining the current growth quality of the corresponding seeds according to the seed growth trend, classifying the seeds with the same current growth quality as the same seed category, obtaining the planting time corresponding to each seed respectively, and determining the growth time of the corresponding seeds according to the planting time; Step 32: Analyze the nutrient supply speed corresponding to different seeds in each seed class according to the growth time, analyze the estimated germination time period of the corresponding seeds in combination with the corresponding current growth quality, and add a category label and a time period label to each seed according to the estimated germination time period corresponding to different seeds in each seed class; Step 33: determining the current growth state and remaining germination time of the corresponding seed according to the category label and time period label corresponding to each seed, drawing a growth concept chart of the corresponding seed, and identifying the seed growth information corresponding to each unit time in the growth concept chart according to the corresponding growth trend and nutrient supply speed; Step 34: respectively collect the real-time growth information corresponding to each of the seeds, determine the current growth deviation information corresponding to the seeds according to the unit time corresponding to the supervised collection time, adjust the estimated germination time period of the corresponding seeds according to the current growth deviation information, and obtain the precise germination time period corresponding to each of the seeds. When the supervised collection time coincides with the precise germination time period, obtain the seed state characteristics corresponding to the seeds.

Images