CN116820147A - Automatic light-tracking control cultivation method and system based on artificial intelligence - Google Patents
Automatic light-tracking control cultivation method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN116820147A CN116820147A CN202310821382.3A CN202310821382A CN116820147A CN 116820147 A CN116820147 A CN 116820147A CN 202310821382 A CN202310821382 A CN 202310821382A CN 116820147 A CN116820147 A CN 116820147A
- Authority
- CN
- China
- Prior art keywords
- cultivation frame
- cultivation
- frame image
- sunlight
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 19
- 238000012364 cultivation method Methods 0.000 title claims abstract description 12
- 238000009826 distribution Methods 0.000 claims abstract description 49
- 238000013145 classification model Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000005286 illumination Methods 0.000 claims description 28
- 239000013598 vector Substances 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 12
- 230000012010 growth Effects 0.000 abstract description 11
- 241000196324 Embryophyta Species 0.000 description 47
- 239000003086 colorant Substances 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 244000068988 Glycine max Species 0.000 description 6
- 235000010469 Glycine max Nutrition 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 241000227653 Lycopersicon Species 0.000 description 5
- 235000007688 Lycopersicon esculentum Nutrition 0.000 description 5
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000002372 labelling Methods 0.000 description 4
- 230000008635 plant growth Effects 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000029553 photosynthesis Effects 0.000 description 3
- 238000010672 photosynthesis Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 235000015097 nutrients Nutrition 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 235000007516 Chrysanthemum Nutrition 0.000 description 1
- 244000189548 Chrysanthemum x morifolium Species 0.000 description 1
- 240000005979 Hordeum vulgare Species 0.000 description 1
- 235000007340 Hordeum vulgare Nutrition 0.000 description 1
- 244000178870 Lavandula angustifolia Species 0.000 description 1
- 235000010663 Lavandula angustifolia Nutrition 0.000 description 1
- 244000061458 Solanum melongena Species 0.000 description 1
- 235000002597 Solanum melongena Nutrition 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 244000098338 Triticum aestivum Species 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000001102 lavandula vera Substances 0.000 description 1
- 235000018219 lavender Nutrition 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000005070 ripening Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Cultivation Of Plants (AREA)
Abstract
The invention provides an automatic light tracking control cultivation method and system based on artificial intelligence, comprising the steps of acquiring a cultivation frame image through an image acquisition device; acquiring a first cultivation frame image according to the cultivation frame image; acquiring color distribution of the first cultivation frame image according to the first cultivation frame image; inputting the color distribution of the first cultivation frame image into a first classification model; the first classification model outputs the type classification and the current growing period classification of the plants on the first cultivation frame; classifying the sunlight quantity required by the classification of the type of the plant and the current growing period; and adjusting the light following angle of the first cultivation frame according to the required sunlight quantity. By the method and the system, the light following can be adjusted according to the type and the current growth of crops.
Description
Technical Field
The invention relates to the field of cultivation, in particular to an automatic light-tracking control cultivation method and system based on artificial intelligence.
Background
The light-following cultivation is a modern agricultural technology aiming at plant growth, and mainly aims to optimize illumination conditions to the maximum extent, and is mainly applied to greenhouse planting and indoor agriculture so as to increase the growth speed of plants, increase the yield and improve the quality.
Photosynthesis is a key process in plant growth, where light energy is converted into energy and nutrients required by plants. The light-following cultivation ensures that the light energy is maximally irradiated to the surface of the plant leaves by adjusting the position and the intensity of the light source, and provides enough photosynthesis energy, thereby promoting the growth of plants.
The light-following cultivation system can help to realize uniform illumination distribution in the whole growth process of plants. By adjusting the position and the angle of the light source, the shadow area can be reduced, the illumination uniformity of plants is improved, the influence of insufficient illumination on certain parts is avoided, and the consistency of the whole growth of the plants is promoted.
The light-following cultivation can save energy and reduce production cost by reasonably utilizing illumination resources. Through automatic control system, the use of light source can be adjusted according to actual demand, avoids excessive illumination or extravagant light energy. In addition, the light-following cultivation can realize higher yield of plants in a limited space, and the land utilization efficiency is improved.
In the prior art, the following spot cultivation is to maximize illumination, and the plants are controlled to be directly irradiated by sunlight through the sensor. However, the illumination required by different plants, the same plant, at different stages may all be different. For example, chrysanthemum, soybean, lavender, etc., the flowering process of plants can only be initiated when the time of day is reduced. Wheat, barley, etc., the flowering process of plants can only be initiated when the sun tends to be intense. In general, young plants have a high demand for light, they produce their own energy by photosynthesis, and they rely on the directionality of light to determine the direction of growth, and strong and uniform illumination can promote healthy growth of young plants. Some plants may be more dependent on other factors such as temperature, humidity and nutrient supply during the fruiting and ripening period, and only require proper illumination to maintain physiological function of the plant, at which time sunlight may be supplied more to other plants that are more in need of sunlight.
In addition, as land resources grow tightly, vertical agriculture, also called vertical farm, is a modern agriculture mode for crop planting in a vertical direction, in which crops are planted in layers up and down, the problem of uneven sunlight distribution is inevitable, and in the existing vertical agriculture, dynamic distribution cannot be achieved by manual adjustment and average distribution.
The prior art can not automatically carry out light-following distribution adjustment on different kinds of plants and plants in different growth periods, and needs further improvement.
Disclosure of Invention
The invention provides an artificial intelligence-based automatic light tracking control cultivation method and system, which aim to solve the technical problem that the technology in the prior art can not automatically perform light tracking distribution adjustment on different types of plants and plants in different growth periods.
In one aspect of the invention, an artificial intelligence based automatic light tracking control cultivation method is characterized by comprising the following steps: acquiring a cultivation frame image through an image acquisition device; acquiring a first cultivation frame image according to the cultivation frame image; according to the first cultivation frame image, acquiring color distribution of the first cultivation frame image, wherein the acquiring of the color distribution of the first cultivation frame image specifically comprises: dividing the first cultivation frame image according to a first grid, counting the different color value duty ratios in each grid to obtain color vectors of each grid, and combining the color vectors of all the grids into the color distribution; inputting the color distribution of the first cultivation frame image into a first classification model; the first classification model outputs the type classification and the current growing period classification of the plants on the first cultivation frame; classifying the sunlight quantity required by the classification of the type of the plant and the current growing period; and adjusting the light following angle of the first cultivation frame according to the required sunlight quantity.
Further, scaling is carried out on the first cultivation frame image, so that the first cultivation frame image reaches a preset size.
Further, the first cultivation frame image is divided according to the first grid, specifically, the first cultivation frame image is divided into grids of 16 x 16.
Further, according to historical experience, the optimal illumination of each crop in each growing period is manually arranged into a database, and the optimal sunlight quantity of each type of plant in the current growing period is inquired through the database.
Further, the system sensor records illumination time of the first cultivation frame, if the illumination time reaches required sunlight quantity, the light following angle of the first cultivation frame is adjusted to a back-to-back position, and other cultivation frames which do not reach the required sunlight quantity are adjusted to the optimal light following angle.
On the other hand, the invention also provides an artificial intelligence-based automatic light tracking control cultivation system, which is characterized by comprising the following modules: the image acquisition module is used for acquiring the cultivation frame image through the image acquisition device; the first processing module is used for acquiring a first cultivation frame image according to the cultivation frame image; the second processing module is configured to obtain a color distribution of the first cultivation frame image according to the first cultivation frame image, where the obtaining the color distribution of the first cultivation frame image specifically includes: dividing the first cultivation frame image according to a first grid, counting the different color value duty ratios in each grid to obtain color vectors of each grid, and combining the color vectors of all the grids into the color distribution; the classification module is used for inputting the color distribution of the first cultivation frame image into a first classification model; the output module is used for outputting the type classification and the current growing period classification of the plants on the first cultivation frame by the first classification model; the acquisition module is used for classifying the sunlight quantity required by the current growing period according to the type of the plant; and the adjusting module is used for adjusting the light following angle of the first cultivation frame according to the required sunlight quantity. Further, scaling is carried out on the first cultivation frame image, so that the first cultivation frame image reaches a preset size.
Further, the first cultivation frame image is divided according to the first grid, specifically, the first cultivation frame image is divided into grids of 16 x 16.
Further, according to historical experience, the optimal illumination of each crop in each growing period is manually arranged into a database, and the optimal sunlight quantity of each type of plant in the current growing period is inquired through the database.
Further, the system sensor records illumination time of the first cultivation frame, if the illumination time reaches required sunlight quantity, the light following angle of the first cultivation frame is adjusted to a back-to-back position, and other cultivation frames which do not reach the required sunlight quantity are adjusted to the optimal light following angle.
According to the technical scheme, the classification and growing period of crops added in cultivation are determined by acquiring the cultivation frame image, the classification and growing period of the crops added in cultivation are determined, the model training and identifying efficiency is improved, and furthermore, the current sunlight quantity required by the crops is determined through the classification and growing period of the crops, so that the current cultivation frame is automatically and pertinently subjected to light-following adjustment, and the technical effects of optimizing the overall light-following efficiency and adapting to the optimal light quantity are achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the method of the present invention.
Detailed Description
The invention will be described with reference to the drawings and detailed description.
The present embodiment solves the above problem by:
in one embodiment, referring to fig. 1, the present invention provides an artificial intelligence based automatic light tracking control cultivation method, the method comprising the steps of:
and acquiring the cultivation frame image through an image acquisition device.
A planter is a structure or device for supporting and growing plants. It provides the support and space required for plant growth, helps the plants to keep growing vertically, and facilitates management and harvesting. The cultivation shelves may be simple frame structures, typically vertically aligned support structures along which plants grow to maximize space utilization. The cultivation frame can be in the form of vertical columns, horizontal cross bars, grids or rope nets, etc., and plants can vertically grow by means of their supports.
In this embodiment, in order to enable the light following effect, the cultivation frame may be adjusted in multiple directions, and the illumination effect may be adjusted arbitrarily by adjusting the direction machine of the cultivation frame. The specific shape of the cultivation frame and the specific manner of adjustment are not within the scope of the invention and can be achieved in any manner in the prior art.
The image acquisition device can be any device capable of capturing images in the prior art, such as a webcam, an automatic camera and the like; the acquired image may be transmitted to a background server by wire, wireless or any other means, and the image is processed by the background server for subsequent steps.
Preferably, the focal length and angle of the image capturing apparatus can also be adjusted as needed to ensure the sharpness of the planter image and proper viewing angle.
Preferably, different images can be acquired from a plurality of angles or positions for the same object, and the images of the same object at different angles or positions are identified, so that the identification accuracy is improved.
And acquiring a first cultivation frame image according to the cultivation frame image.
The cultivation frame image may include a plurality of cultivation frames, each cultivation frame is used for planting only one plant, and different cultivation frames may be used for planting different plants, and by separating the single cultivation frame, the single cultivation frame can be identified and adjusted for light tracking independently; the cultivation frame can only be layered vertical agriculture, and each layer can be freely adjusted; the first cultivation frame is only for convenience of description, and the first cultivation frame may be any one of a plurality of cultivation frames in an image, and the processing manner of any single cultivation frame is the same in this embodiment.
In order to obtain the range of the first cultivation frame, preferably, special marks such as red punctuation are set at preset positions of the cultivation frames, after the cultivation frame images are obtained, the images are cut according to the red punctuation in the images, only the images in the punctuation areas are reserved, and the images of a plurality of cultivation frames can be obtained after the cutting according to the punctuation.
Further, in order to facilitate the processing in the subsequent machine learning process, the images of the cultivation frame are scaled, so that each image has the same size, the implementation priority size is 256x256, the data processing process can be simplified, all the images have the same input size, and the corresponding color parameters can be conveniently extracted according to the pixel positions of the images.
Further, the first cultivation frame may be subjected to image filtering, such as mean filtering, median filtering or gaussian filtering, so as to reduce noise in the image. The stability and the accuracy of a subsequent processing algorithm are improved.
Further, image enhancement techniques may also be used to improve the quality and visual effect of the image. For example, methods such as contrast enhancement or color correction may be applied to improve brightness, contrast, and color saturation of the image. It should be noted that the subsequent classification model in this embodiment is based on color, and therefore, the same image enhancement parameters need to be used to uniformly enhance all the images including the sample, so as to prevent the information contained in the image from being changed due to image enhancement.
And acquiring the color distribution of the first cultivation frame image.
In this embodiment, the color distribution refers to a distribution of the frequency or number of occurrences of different colors in an image. It describes the relative probability of occurrence of various colors in an image and can be used to analyze and describe the color characteristics of an image.
The colors on the cultivation frame are different due to different plants and different growth periods. For example, in the seedling stage of the plant, the main tone of the cultivation frame image is the background of the cultivation field, and the ornamental portion is green in the cultivation soil, at this time, although the specific types of the plants are not easily distinguished, the sunlight required in the seedling stage of all the current economic operations is large, and at this time, the light following parameters can be adjusted to acquire more illumination as much as possible. When plants grow, the color distribution of different plants becomes obvious, for example, vines occupy a larger area of green in an image, non-vines can show denser leaf colors in partial image areas, and the leaf shapes of different plants and the like cause different color distribution in the image; the flowering and fruiting period can generate more different color characteristics due to the flower color and fruit color, and can be easily distinguished according to the color distribution, for example, soybean flowers are white, and fruits are yellow or yellow brown; whereas the flowers of tomatoes are generally yellow and the fruits green to red.
Since the types of crops are limited, and the specific outline of the crops is not concerned, the embodiment can be simply distinguished from color distribution, such as small-area dark green in an image is mainly, and soybeans with white ornamental parts are used as flowering period; the large area of the image is light green, and red tomatoes are interspersed in the image, wherein the tomatoes are in the mature period. In this embodiment, only the common crops need to be identified, and the existing crops have various characteristics and are not usually illegible.
Further, the color distribution is realized by the following method: dividing the first cultivation frame image according to a first grid; preferably, the first cultivation frame image is divided into grids of 16×16, and the main distribution area of the colors can be identified without concern of the outline of the image object through grid division, for example, the vines will display green in the whole 16×16, but the non-vines may only display green in half of the grids, and the actual grids display background colors; and counting the probability distribution of the color values in each grid to obtain the color vector of each grid, and combining the color vectors of all the grids into the color distribution of the image. Further, the length of the color vector is determined according to the selected color data, for example, red, green and blue are selected as color classifications, and then the length of each color vector is 3, for example, a certain grid of color vectors is (0.2,0.3,0.5) to indicate that red, green and blue respectively occupy 0.2,0.3,0.5; note that red, green, and blue illustrated here each represent a color interval, for example, the red interval may be (R (200,255); G (0,60); B (0,60)); at this time, the color distribution result is a multi-dimensional vector of 16×16×3; the three colors are only examples, and more colors can be used for interval division, obviously, the finer the interval division is, the more detailed the color distribution can represent the characteristics, and the higher the identification accuracy is.
And inputting the color distribution of the first cultivation frame image into a first classification model.
The first classification model is a model which is trained in advance and can classify crops according to color distribution. Specifically, the first classification model in the present embodiment is trained by the following steps:
data preparation, namely collecting and arranging data containing the cultivation frame images, carrying out the processing of the steps on all the images, namely acquiring the color distribution of the cultivation frame images, and labeling each cultivation frame image. Here, a manual labeling manner may be adopted, for example, specifically labeling the image as: flowering soybean, fruiting tomato, growing eggplant, etc., ensuring that each type of annotation includes the type of crop and the growing period.
The data set is divided into a training set and a validation set. The training set is used for training the model, and the verification set is used for evaluating the performance of the model and adjusting the super parameters. Model training is performed using a training set, and the present embodiment selects a Convolutional Neural Network (CNN) as the classification model. The color distribution is used as an input characteristic, the corresponding label is used as a target variable, and parameters of the model are adjusted through an optimization algorithm (such as gradient descent) so that the input sample can be correctly classified. The trained model performance is evaluated using the validation set. Optional metrics include evaluation metrics including accuracy, precision, recall, F1 value, and the like. According to the performance of the model on the verification set, the super parameters of the model, such as learning rate, regularization parameters, network structure and the like, are adjusted to improve the performance and generalization capability of the model.
In this embodiment, since only the color distribution of the image is concerned, the image is simplified into a color vector, and compared with the conventional image recognition technology, the recognition feature is far smaller than that of the conventional image recognition technology, and the method of this embodiment can greatly improve the training and recognition speed.
The first classification model outputs the type classification and the current growing period classification of the plants on the first cultivation frame;
because the labeling information of the data simultaneously comprises the classification of crops and the classification of growing periods when the model is trained, the output of the first classification model is directly the classification of the types of plants on the cultivation frame and the classification of the current growing period. After inputting a color distribution into the first classification model, the model gives a classification of tomatoes in maturity.
The amount of sunlight required is determined according to the type classification of the plants and the current growing period.
The amount of sunlight required for the growth period of different plants is different, and the optimal illumination of each growth period of each crop can be manually arranged into a database according to historical experience, or can be obtained through other databases, and the embodiment is not limited further. Illustratively, the amount of sunlight may be as shown in the following table.
In the foregoing steps, the type classification of plants and the current growing period classification are obtained, so that the optimal amount of sunlight for each type of plants can be queried through the database.
Illustratively, in the foregoing step, after the color distribution is obtained by processing the image of the first cultivating frame, the color distribution is input into the trained first classification model, and the model output result is that the soybean in the pod stage has the highest daily illumination of 6 hours.
And adjusting the light following angle of the first cultivation frame according to the required sunlight quantity.
The system sensor records illumination time of the first cultivation frame, if the illumination time reaches required sunlight quantity, the light-following angle of the first cultivation frame is adjusted to a back-to-back position, and other cultivation frames which do not reach the required sunlight quantity are adjusted to the optimal light-following angle.
When the identification result of the first cultivation frame is soybean in the pod stage, the most-valued sunlight can be found from the database for 6 hours, and then the system automatically adjusts the light-following angle of the first cultivation frame.
In another implementation manner, the embodiment of the invention provides an automatic light tracking control cultivation system based on artificial intelligence, which is characterized by comprising the following modules:
the image acquisition module is used for acquiring the cultivation frame image through the image acquisition device;
the first processing module is used for acquiring a first cultivation frame image according to the cultivation frame image;
the second processing module is configured to obtain a color distribution of the first cultivation frame image according to the first cultivation frame image, where the obtaining the color distribution of the first cultivation frame image specifically includes: dividing the first cultivation frame image according to a first grid, counting the different color value duty ratios in each grid to obtain color vectors of each grid, and combining the color vectors of all the grids into the color distribution;
the classification module is used for inputting the color distribution of the first cultivation frame image into a first classification model;
the output module is used for outputting the type classification and the current growing period classification of the plants on the first cultivation frame by the first classification model;
the acquisition module is used for classifying the sunlight quantity required by the current growing period according to the type of the plant;
and the adjusting module is used for adjusting the light following angle of the first cultivation frame according to the required sunlight quantity. The above modules perform the methods described in the previous examples.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
The present invention is not limited to the specific partial module structure described in the prior art. The prior art to which this invention refers in the preceding background section as well as in the detailed description section can be used as part of the invention for understanding the meaning of some technical features or parameters. The protection scope of the present invention is subject to what is actually described in the claims.
Claims (10)
1. An automatic light-tracking control cultivation method based on artificial intelligence is characterized by comprising the following steps:
acquiring a cultivation frame image through an image acquisition device;
acquiring a first cultivation frame image according to the cultivation frame image;
according to the first cultivation frame image, acquiring color distribution of the first cultivation frame image, wherein the acquiring of the color distribution of the first cultivation frame image specifically comprises: dividing the first cultivation frame image according to a first grid, counting the different color value duty ratios in each grid to obtain color vectors of each grid, and combining the color vectors of all the grids into the color distribution;
inputting the color distribution of the first cultivation frame image into a first classification model;
the first classification model outputs the type classification and the current growing period classification of the plants on the first cultivation frame;
classifying the sunlight quantity required by the classification of the type of the plant and the current growing period;
and adjusting the light following angle of the first cultivation frame according to the required sunlight quantity.
2. The automatic light-following control cultivation method based on artificial intelligence according to claim 1, wherein the method comprises the following steps: and scaling the first cultivation frame image to enable the first cultivation frame image to reach a preset size.
3. The automatic light-following control cultivation method based on artificial intelligence according to claim 1, wherein the method comprises the following steps: the first cultivation frame image is divided according to a first grid, and specifically the first cultivation frame image is divided into grids of 16 x 16.
4. An artificial intelligence based automatic light tracking control cultivation method according to claim 1, wherein said classifying according to the type of said plants and the amount of sunlight required for the current growing period classification comprises: according to historical experience, the optimal illumination of each crop in each growing period is manually arranged into a database, and the optimal sunlight quantity of each plant in the current growing period is inquired through the database.
5. An artificial intelligence based automatic light tracking control cultivation method according to claim 1, wherein adjusting the light tracking angle of the first cultivation frame according to the required amount of sunlight comprises: and recording the illumination time of the first cultivation frame by a system sensor, and if the illumination time reaches the required sunlight amount, adjusting the light following angle of the first cultivation frame to a back-to-back position, and adjusting other cultivation frames which do not reach the required sunlight amount to an optimal light following angle.
6. An automatic light-tracking control cultivation system based on artificial intelligence is characterized by comprising the following modules:
the image acquisition module is used for acquiring the cultivation frame image through the image acquisition device;
the first processing module is used for acquiring a first cultivation frame image according to the cultivation frame image;
the second processing module is configured to obtain a color distribution of the first cultivation frame image according to the first cultivation frame image, where the obtaining the color distribution of the first cultivation frame image specifically includes: dividing the first cultivation frame image according to a first grid, counting the different color value duty ratios in each grid to obtain color vectors of each grid, and combining the color vectors of all the grids into the color distribution;
the classification module is used for inputting the color distribution of the first cultivation frame image into a first classification model;
the output module is used for outputting the type classification and the current growing period classification of the plants on the first cultivation frame by the first classification model;
the acquisition module is used for classifying the sunlight quantity required by the current growing period according to the type of the plant;
and the adjusting module is used for adjusting the light following angle of the first cultivation frame according to the required sunlight quantity.
7. An artificial intelligence based automatic light tracking control cultivation system according to claim 6, wherein: and scaling the first cultivation frame image to enable the first cultivation frame image to reach a preset size.
8. An artificial intelligence based automatic light tracking control cultivation system according to claim 6, wherein: the first cultivation frame image is divided according to a first grid, and specifically the first cultivation frame image is divided into grids of 16 x 16.
9. An artificial intelligence based automatic light tracking control cultivation system according to claim 6, wherein said classifying according to the type of said plants and classifying the amount of sunlight required for the current growing period comprises: according to historical experience, the optimal illumination of each crop in each growing period is manually arranged into a database, and the optimal sunlight quantity of each plant in the current growing period is inquired through the database.
10. An artificial intelligence based automatic light tracking control cultivation system according to claim 6, wherein adjusting the light tracking angle of said first cultivation shelf according to said amount of sunlight required comprises: and recording the illumination time of the first cultivation frame by a system sensor, and if the illumination time reaches the required sunlight amount, adjusting the light following angle of the first cultivation frame to a back-to-back position, and adjusting other cultivation frames which do not reach the required sunlight amount to an optimal light following angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310821382.3A CN116820147A (en) | 2023-07-05 | 2023-07-05 | Automatic light-tracking control cultivation method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310821382.3A CN116820147A (en) | 2023-07-05 | 2023-07-05 | Automatic light-tracking control cultivation method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116820147A true CN116820147A (en) | 2023-09-29 |
Family
ID=88112480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310821382.3A Pending CN116820147A (en) | 2023-07-05 | 2023-07-05 | Automatic light-tracking control cultivation method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116820147A (en) |
-
2023
- 2023-07-05 CN CN202310821382.3A patent/CN116820147A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4009441B2 (en) | Crop cultivation evaluation system | |
| CN112197819A (en) | Plant growth accurate control method based on production base | |
| WO2018133353A1 (en) | Nutrient solution control method and control device | |
| CN105700593B (en) | A kind of planting monitoring system and its method | |
| CN114740930B (en) | Intelligent management and control platform system for greenhouse and management and control processing method | |
| CN106651844A (en) | Apple growing period recognition method based on image analysis | |
| CN114004458A (en) | Polymorphic potential perception fusion plant growth management system | |
| CN108243678B (en) | Intelligent machine sowing system and control method and device thereof | |
| CN110119901A (en) | A kind of planting asparagus comprehensive management platform and its management method | |
| CN109116897A (en) | A kind of agricultural planting ambient intelligence adjusting method based on big data | |
| Debersaques et al. | Challenges faced by commercial kiwiberry (actinidia argute planch.) Production | |
| CN110521481A (en) | A kind of Chinese rose of cut flower spray breeding method of high-yield quick | |
| CN116797601B (en) | Image recognition-based Huashansong growth dynamic monitoring method and system | |
| Wang et al. | Evaluating the effect of light intensity on flower development uniformity in strawberry (Fragaria× ananassa) under early induction conditions in forcing culture | |
| CN105340675B (en) | A kind of vinegrowing fruiting management method | |
| CN205656488U (en) | Plant species plants monitored control system | |
| CN112400627A (en) | Single-vine-double-layer-six-melon light pruning cultivation method for crisp melons | |
| CN116820147A (en) | Automatic light-tracking control cultivation method and system based on artificial intelligence | |
| CN116755485A (en) | Greenhouse regulation and control method, device, system, equipment and storage medium | |
| CN111296209A (en) | Planting research method for improving yield of rhizoma curculiginis | |
| Perez-Vidal et al. | Computer based production of Saffron (Crocus sativus L.): From mechanical design to electronic control | |
| CN112602489B (en) | Double-peak blue light for promoting plant growth | |
| CN114882365A (en) | Intelligent monitoring system for peony grafting | |
| Schneider et al. | Detection of Growth Stages of Chilli Plants in a Hydroponic Grower Using Machine Vision and YOLOv8 Deep Learning Algorithms | |
| CN110135403A (en) | Houseplant cultural method, device, system, equipment and readable storage medium storing program for executing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |