Plant lamp power supply control method and plant lamp

Abstract

The invention relates to a plant lamp power supply control method and a plant lamp, and the method comprises the steps: recognizing the type of a plant; acquiring a corresponding growth model according to the category of the plant; sending the obtained plant image into a growth model to obtain position information of the plant in a growth curve; controlling the power supply to work according to the mapping relation among the position information, the growth curve and the illumination information so as to adjust the illumination information of the plant lamp. According to the plant lamp, appropriate illumination information can be sent out according to different growth stages of different plants, and the compatibility of the plant lamp is improved.

Description

Technical Field

[0001] The present invention relates to the field of plant lamp control, and particularly to a method for controlling a plant lamp power supply and a plant lamp. Background Art

[0002] A plant lamp is a lamp used for plants. The plant lamp simulates the principle that plants need sunlight for photosynthesis, and provides supplementary light for plants or completely replaces sunlight. Irradiating plants with suitable plant light can promote plant growth.

[0003] However, different plant categories and different growth stages of the same plant require different lighting. Currently, it is generally judged manually to adjust the lighting information of the plant lamp.

[0004] With the development of image recognition technology, some technologies for controlling plant lamp lighting information based on image recognition have emerged. However, plant lamps generally do not have a processor with very powerful computing power and cannot execute very complex recognition models. Therefore, the current plant lamps with image recognition are generally designed for single plants and cannot be compatible with other plants. Summary of the Invention

[0005] The present invention aims at the problem of how to enable a plant lamp to automatically recognize images and adapt to multiple growth stages of multiple plants.

[0006] In a first aspect, the present application provides a method for controlling a plant lamp power supply, the method including:

[0007] Identifying the category of the plant;

[0008] Obtaining a corresponding growth model according to the category of the plant;

[0009] Feeding the obtained plant image into the growth model to obtain the position information of the plant in the growth curve;

[0010] Controlling the power supply to work according to the mapping relationship between the position information, the growth curve and the lighting information, so as to adjust the lighting information of the plant lamp.

[0011] In some embodiments, the growth model is a multi-classification model, and the classification result of the growth model is: multiple growth intervals in the growth curve; each growth interval corresponds to a set of lighting information;

[0012] The step of feeding the obtained plant image into the growth model to obtain the position information of the plant in the growth curve includes:

[0013] Feeding the plant image into the growth model, and the growth model outputs the growth interval where the plant is currently in the growth curve.

[0014] In some embodiments, the plant includes a flower, and the growth interval includes a growth stage and a flowering stage. The light information in the growth stage is light suitable for the growth of the flower, and the light information in the flowering stage is light that inhibits the growth of the flower.

[0015] In some embodiments, the number of classifications of the growth model corresponds one-to-one with the plant.

[0016] In some embodiments, the number of classifications of the growth models corresponding to different plants is different.

[0017] In some embodiments, feeding the obtained plant image into the growth model to obtain the position information of the plant in the growth curve includes:

[0018] Collecting plant images at a first time interval within a first time period to obtain a sequence of plant images, where the first time is greater than or equal to 8 hours and the first time interval is greater than or equal to 20 minutes;

[0019] Feeding the sequence of plant images into the growth model, and the growth model outputs the current position of the plant in the growth curve.

[0020] In some embodiments, feeding the sequence of plant images into the growth model specifically includes:

[0021] Feeding the image sequence into a convolutional neural network in sequence, and the convolution outputs a feature map;

[0022] After flattening the feature map, feeding it into a recurrent neural network, and the recurrent neural network outputs the growth interval.

[0023] In some embodiments, identifying the category of the plant includes: obtaining a group of plants, where the group of plants includes one or more plants, and each group of plants corresponds to a growth model;

[0024] Obtaining the corresponding growth model according to the category of the plant includes: confirming the growth model of the plant according to the corresponding relationship between the group of plants and the growth model.

[0025] In some embodiments, obtaining the group of plants includes:

[0026] Feeding the plant image into a classification model, and the classification model outputs the group of plants.

[0027] In some embodiments, the classification model is a convolutional neural network.

[0028] In a second aspect, the present application provides a plant lamp, which includes:

[0029] A power supply, connected to the lamp group, is used to output different power supplies to control the lamp group to emit different lights.

[0030] A memory stores a power control program for the plant lamp.

[0031] A processor is connected to the memory and the power supply. The processor is used to execute the power control program for the plant lamp to implement the power control method for the plant lamp as described above.

[0032] In this application, by obtaining the category of the plant, calling the corresponding growth model, then the growth model outputs the growth range according to the plant image, and then through the corresponding relationship between the growth range and the light information, the light information required by the plant is obtained. Finally, the power supply of the plant lamp is controlled to work to control the plant lamp to emit the corresponding light information to promote the growth of the plant. Description of the Drawings

[0033] Figure 1 It is a flowchart of an embodiment of the power control method for the plant lamp of this application.

[0034] Figure 2 It is a model diagram of the power control method for the plant lamp of this application.

[0035] Figure 3 It is a flowchart of another embodiment of the power control method for the plant lamp of this application. Detailed Embodiments

[0036] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0037] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined.

[0038] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without the use of these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0039] Example 1

[0040] In some embodiments, the plant lamp includes: a lamp group, which includes LED lamps of different wavelengths;

[0041] a power supply circuit for adjusting the duty cycle of the PWM signal through pulse width adjustment, and further adjusting the brightness of the lamp group; a processor for giving the power supply circuit illumination information, where the illumination information includes wavelength and brightness, and the power supply circuit controls the operation of the lamp group according to the illumination information to emit light that meets the requirements of the illumination information;

[0042] Among them, the illumination information includes: illumination duration, illumination brightness, illumination wavelength, illumination period, etc. Specifically, according to the actual test results, the most suitable illumination information for different stages of various plants can be obtained, and then stored corresponding to the plant category, growth interval, and illumination information. Furthermore, the illumination information can be indexed according to the plant category and growth interval.

[0043] Referring to Figure 1 , in one embodiment, the plant lamp power control method includes:

[0044] S100. Identify the category of the plant;

[0045] Exemplarily, the category of the plant can be obtained through an interactive interface to allow the user to set the category of the plant;

[0046] In the present application, image recognition technology is preferably used to identify the category of the plant. A camera can be arranged to collect an image of the plant, and then the plant image is sent to a recognition model for recognition. Optionally, in the present application, the recognition model can recognize mainstream plant categories.

[0047] S200. Obtain the corresponding growth model according to the category of the plant;

[0048] Referring to Figure 2, after the plant image enters the classification model, the classification model obtains a classification result, and the classification result can correspond to one of the first model, the second model, the third model, and the fourth model; and the plant image is sent to the selected growth model (the first model, the second model, the third model, the fourth model).

[0049] S300. Send the obtained plant image into the growth model to obtain the position information of the plant in the growth curve;

[0050] It should be noted that the characteristics of different plants at different growth stages are completely different. Therefore, if the same growth model is used for different plants, it will cause too many classification results that the model needs to output, and then lead to low accuracy of the model. For example, for four plants, each plant corresponds to 4 growth intervals, then the growth model has 4 * 16 = 64 classification results, which requires very high training requirements for the model, and the obtained model parameters are very large, and it is difficult to integrate into the processor of the plant lamp.

[0051] In this application, four plants correspond to four models respectively, and each model performs 4-class classification respectively, which is beneficial to the miniaturization of the model and can be well integrated into the processor of the plant lamp.

[0052] S400. Control the power supply to work according to the mapping relationship between the position information, the growth curve, and the light information to adjust the light information of the plant lamp.

[0053] Exemplarily, through experiments, the light information of different growth intervals of each plant can be obtained first, then the mapping relationship between the growth interval and the light information can be established. Only by knowing the position information (growth interval) of the plant in the growth interval can the light information be obtained. After obtaining the light information, controlling the power supply to work can control the plant lamp to emit the corresponding light to promote plant growth.

[0054] This application obtains the category of the plant, calls the corresponding growth model, then the growth model outputs the growth interval according to the plant image, and then through the corresponding relationship between the growth interval and the light information, obtains the light information required by the plant. Finally, control the power supply of the plant lamp to control the plant lamp to emit the corresponding light information to promote plant growth.

[0055] In some embodiments, the growth model is a multi-classification model, and the classification result of the growth model is: multiple growth intervals in the growth curve; each growth interval corresponds to a set of light information;

[0056] The step S300 of sending the obtained plant image into the growth model to obtain the position information of the plant in the growth curve includes: sending the plant image into the growth model, and the growth model outputs the growth interval where the plant is currently in the growth curve.

[0057] In actual verification, within a growth interval of a plant, the required light information basically does not change. Only after entering the next growth stage does the plant need new light information. To reduce the computational load and meet the growth requirements of the plant, in this embodiment, the change of the optimal light information corresponding to the growth interval of the plant is first experimentally verified, and then a growth interval with a relatively gentle change in light information is set as a growth interval, so that the growth interval can be divided into multiple growth intervals. In this way, the growth model does not need to regress the position of the plant on the growth curve currently, but only needs to classify the plant into each growth interval to obtain the light information. By replacing the regression model with a classification model, the computational load is reduced.

[0058] In some embodiments, the plant includes flowers, and the growth interval includes a growth stage and a flowering stage. The light information in the growth stage is the light suitable for the growth of the flowers; the light information in the flowering stage is the light that inhibits the growth of the flowers.

[0059] Exemplarily, through application tests, plant lights are very suitable for the growth, flowering, and fruiting of plants. For general indoor plant flowers, due to the lack of natural light, their growth will deteriorate over time. However, by irradiating with plant lights of the spectrum required by the plants, not only can their growth be promoted. In this application, the growth interval can be the growth stage, flowering stage, and fruiting stage of the plant. In this way, the features recognized by the growth model are relatively obvious, such as bud tips, flowers, fruits, etc.

[0060] In this embodiment, light suitable for growth can be irradiated during the growth stage of the flower, while during the flowering stage of the flower, no light is irradiated, light that cannot well promote the growth of the flower is irradiated, or light that delays growth is irradiated, and light suitable for the growth of the flower is irradiated again during the fruiting stage.

[0061] In other embodiments, the growth interval further includes different states of the flower, for example: the first stage is the flower bud, the second stage is the initial bloom, the third stage is the mature flower stage, and the fourth stage is the withering of the flower.

[0062] In this embodiment, light suitable for growth can be irradiated during the growth stage of the flower, while during the flowering stage of the flower, no light is irradiated or light that cannot well promote the growth of the flower is irradiated, no light is irradiated or light that delays growth is irradiated during the mature flower stage, and light suitable for growth is irradiated during withering to promote flower iteration.

[0063] In some embodiments, the number of classifications of the growth model corresponds to the plant one by one; and / or, the number of classifications of the growth model corresponding to different plants is different.

[0064] Benefiting from the present application that first selects a growth model according to the plant, the growth model can be designed for the plant. That is, the number of growth intervals for different plants is different. For those with more frequent changes in light information, more growth intervals can be divided, while for those with very small changes in light information, fewer growth intervals can be divided, so as to adapt to different plants. In this embodiment, by optimizing the classification number of the growth model, each growth model can meet the classification requirements of the growth intervals while reducing the calculation amount.

[0065] It should be noted that a method for further reducing the calculation amount is proposed later. By dividing the plants into multiple groups and selecting the corresponding growth model according to the group instead of according to the plant category. By dividing the plants with basically the same light requirements or the difference less than the threshold into one group, and then only identifying the group can confirm the growth model, reducing the calculation amount for confirming the growth model.

[0066] On this basis, in this embodiment, only "plant" needs to be replaced with "group".

[0067] Refer to Figure 3 , in some embodiments, the step of sending the obtained plant image into the growth model to obtain the position information of the plant in the growth curve includes:

[0068] Collecting plant images at a first time interval within a first time period to obtain a plant image sequence; wherein, the first time is greater than or equal to 8 hours, and the first time interval is greater than or equal to 20 minutes

[0069] Sending the plant image sequence into the growth model, and the growth model outputs the current position of the plant in the growth curve.

[0070] In this embodiment, the step of sending the plant image sequence into the growth model specifically includes:

[0071] S301. Sequentially sending the image sequence into a convolutional neural network, and the convolution outputs a feature map;

[0072] S302. After flattening the feature map, sending it into a recurrent neural network, and the recurrent neural network outputs the growth interval.

[0073] It should be noted that the state of the plant is different within a day. By only collecting images in a single time period, the identification of the growth interval may be inaccurate.

[0074] To address this issue, in this embodiment, plant images can be collected at a first time interval within a first time period (1 day, 12 hours, 8 hours) to obtain a sequence of plant images. Then, the image sequence is fed into a convolutional neural network to extract spatial features, and finally, the image sequence is fed into a recurrent neural network to extract temporal features. In this way, the model can determine the current growth interval of the plant based on the spatial and temporal features of the plant within the first time period, that is, the changes at different times.

[0075] Exemplarily, the recurrent neural network can be an LSTM. In other embodiments, it can also be a GRU model.

[0076] In some embodiments, identifying the category of the plant includes: obtaining a group of plants, where the group includes one or more plants, and each group corresponds to a growth model.

[0077] Obtaining the corresponding growth model according to the category of the plant includes: confirming the growth model of the plant based on the corresponding relationship between the group of plants and the growth model.

[0078] Further, obtaining the group of plants includes:

[0079] Feeding the plant image into a classification model, and the classification model outputs the group of plants. In this embodiment, the classification model is a convolutional neural network.

[0080] Example 2

[0081] This application provides a plant lamp, which includes: a power supply connected to a lamp group, and the power supply is used to output different power supplies to control the lamp group to emit different lights; a memory storing a power control program of the plant lamp; a processor connected to the memory and the power supply, and the processor is used to execute the power control program of the plant lamp to implement the following plant lamp power control method:

[0082] S100. Identify the category of the plant;

[0083] S200. Obtain the corresponding growth model according to the category of the plant;

[0084] S300. Feed the obtained plant image into the growth model to obtain the position information of the plant in the growth curve;

[0085] S400. Control the power supply to work according to the mapping relationship between the position information, the growth curve, and the light information to adjust the light information of the plant lamp.

[0086] In some embodiments, the growth model is a multi-classification model, and the classification result of the growth model is: multiple growth intervals in the growth curve; each growth interval corresponds to a set of light information.

[0087] The S300 sends the acquired plant image into the growth model to obtain the position information of the plant in the growth curve, including: sending the plant image into the growth model, and the growth model outputs the growth interval of the plant in the growth curve currently.

[0088] In some embodiments, the plant includes a flower, and the growth interval includes: a growth stage and a flowering stage. The light information in the growth stage is the light suitable for the growth of the flower; the light information in the flowering stage is the light that inhibits the growth of the flower.

[0089] In some embodiments, the number of classifications of the growth model corresponds to the plant one by one.

[0090] In some embodiments, the number of classifications of the growth models corresponding to different plants is different.

[0091] In some embodiments, the sending the acquired plant image into the growth model to obtain the position information of the plant in the growth curve includes:

[0092] Collecting plant images at a first time interval within a first time period to obtain a plant image sequence; wherein, the first time is greater than or equal to 8 hours, and the first time interval is greater than or equal to 20 minutes

[0093] Sending the plant image sequence into the growth model, and the growth model outputs the position of the plant in the growth curve currently.

[0094] Refer to Figure 3 , in some embodiments, the sending the plant image sequence into the growth model specifically includes:

[0095] S301: Sending the image sequence into a convolutional neural network in sequence, and the convolution outputs a feature map;

[0096] S302: After flattening the feature map, sending it into a recurrent neural network, and the recurrent neural network outputs the growth interval.

[0097] In some embodiments, the identifying the category of the plant includes: obtaining a plant group, the plant group includes one or more plants, and each plant group corresponds to a growth model;

[0098] The obtaining the corresponding growth model according to the category of the plant includes: confirming the growth model of the plant according to the corresponding relationship between the plant group and the growth model.

[0099] In some embodiments, the obtaining the plant group includes:

[0100] Sending the plant image into a classification model, and the classification model outputs the plant group.

[0101] In some embodiments, the classification model is a convolutional neural network.

[0102] It should be noted that in the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0103] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0105] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0107] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0108] 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 equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A plant lamp power control method, characterized in that: The method comprises: Identify plant species; Obtain the corresponding growth model according to the type of plant; The acquired plant image is sent to the growth model to obtain the position information of the plant in the growth curve; According to the mapping relationship among the position information, the growth curve and the illumination information, the power supply is controlled to adjust the illumination information of the plant lamp.

2. The power control method for a plant lamp according to claim 1, characterized in that: The growth model is a multi-classification model, and the classification result of the growth model is: multiple growth intervals in the growth curve; each growth interval corresponds to a set of illumination information; The step of sending the acquired plant image to the growth model to obtain the position information of the plant in the growth curve includes: The plant image is sent to a growth model, and the growth model outputs the current growth interval of the plant in the growth curve.

3. The power control method for a plant lamp according to claim 2, characterized in that: The plants include flowers, and the growth interval includes: a growth stage and a flowering stage. The light information in the growth stage is light suitable for flower growth; and the light information in the flowering stage is light that inhibits flower growth.

4. The power control method for a plant lamp according to claim 2, characterized in that: The number of classifications of the growth model corresponds one to one with the number of plants.

5. The power control method for a plant lamp according to claim 2, characterized in that: Different plants have different numbers of growth model classifications.

6. The power control method for a plant lamp according to claim 1, characterized in that: The step of sending the acquired plant image to the growth model to obtain the position information of the plant in the growth curve includes: Collect plant images at first time intervals within a first time period to obtain a plant image sequence; wherein the first time is greater than or equal to 8 hours, and the first time interval is greater than or equal to 20 minutes The plant image sequence is fed into a growth model, and the growth model outputs the current position of the plant in the growth curve.

7. The power control method for a plant lamp according to claim 6, characterized in that: The step of sending the plant image sequence into the growth model specifically comprises: The image sequence is sequentially fed into a convolutional neural network, and the convolution outputs a feature map; After the feature map is flattened, it is sent to a recurrent neural network, and the recurrent neural network outputs the growth interval.

8. The power control method for a plant lamp according to claim 1, characterized in that: The identifying of the plant category includes: obtaining plant groups, the group including one or more plants, each group corresponding to a growth model; The acquiring the corresponding growth model according to the plant category includes: confirming the plant growth model according to the corresponding relationship between the plant category group and the growth model.

9. The power supply control method for a plant lamp according to claim 7, characterized in that: The plant groups obtained include: The plant image is sent to a classification model, and the classification model outputs plant groups; the classification model is a convolutional neural network.

10. A plant lamp, characterized in that: include: A power supply connected to the light group, the power supply being used to output different power supplies to control the light group to emit different illuminations; A memory storing a power control program of the plant lamp; A processor is connected to the memory and the power supply, and the processor is used to execute the power control program of the plant lamp to implement the plant lamp power control method as described in any one of claims 1-9.

Images