KR20200111648A - Method, Apparatus and System for monitoring and growing of plant - Google Patents

Abstract

The present invention relates to an apparatus and a method for plant monitoring, and a plant cultivation system. The apparatus and the method for plant monitoring, and the plant cultivation system of the present invention obtain an image by sequentially irradiating visible light and near-infrared light to a plant, and measure a plant size by masking a plant portion from the image irradiated with the near-infrared light. Meanwhile, the apparatus and the method for plant monitoring, and the plant cultivation system derive a component value of the plant through RGB analysis after applying the masked image to the image irradiated with the visible light. According to the present invention, plant growth conditions are controlled using the plant size and the component value. The plant monitoring apparatus comprises a first light source, a second light source, an imaging means, and an image analyzer.

Description

Plant monitoring and cultivation method, apparatus and system {Method, Apparatus and System for monitoring and growing of plant}

The present invention relates to a plant monitoring and cultivation method, apparatus, and system that monitors the size and component values of plants at each stage of growth by image analysis using visible and near-infrared rays, and receives feedback from the monitored values to control plant growth conditions.

The space for planting is gradually decreasing due to environmental factors that are difficult for humans to control, such as climate change and desertification. In addition, extreme weather conditions such as torrential rains, typhoons, droughts, and global warming frequently disrupt the stable supply of crops. Therefore, various studies on facility cultivation techniques such as plant factories, green house cultivation, and container cultivation are being conducted in order to stably supply crops.

For example, a plant factory is an agricultural system that can mass-produce a variety of high value-added agricultural products indoors by combining cutting-edge high-efficiency energy technology. Plant factories plan and produce crops by artificially controlling the environment such as light, temperature, humidity, carbon dioxide concentration and culture medium. Plant factories enable a typical low-carbon green business using indoor plant cultivation systems mainly by LEDs and spraying devices.

Plant factories as well as facility cultivation methods such as green house cultivation and container cultivation are mainly developed in underground spaces, inside buildings, and inside containers, so they can be independent from environmental factors that cannot be controlled by humans. It can produce clean, fresh, uniform, high-quality plants in large quantities in a faster time than farms that rely solely on natural light, regardless of unexpected climate changes and seasons. In addition, since it is sealed with the outside, there is no damage from pests, so it can produce a safe product without anxiety caused by pesticides.

Facility cultivation techniques have been known to have a positive effect on environmental improvement. For example, as disclosed in Korean Registered Patent Publication No. 10-959994, it is possible to reduce greenhouse gas in cities by collecting carbon dioxide that is rapidly increasing in the urban atmosphere and supplying it to plant factories, and since LED is used as a light source, one year Plants can be cultivated continuously throughout the year, which not only ensures stable food, but also saves energy.

On the other hand, in order to manage plants that continuously grow inside the facility, it is necessary to perform a process of confirming plant growth information and giving feedback to the management system. In the method for monitoring plant growth disclosed in Korean Patent Application Publication No. 2013-0015278, when a photographing unit captures an image of a plant, the control unit controls the calculation unit to measure the size of the plant, and the measured data is stored in the data storage unit. It is a method of measuring the size of a plant, which is more efficient than the method of manually measuring the size of a plant. However, in order to calculate the size of a plant in a state in which the boundary between the plant and the background is not clearly distinguished in the photographed image, a complex and heavy algorithm and analysis equipment for advanced image processing are required.

Meanwhile, a method capable of directly measuring the growth and quality of plants by measuring functional components of plants using an instrument analysis device has been used. This method is a method of measuring functional components using a high pressure liquid chromatography (HPLC) system after drying the leaves of a plant, crushing, and extracting the leaves of the plant, and the cost of the equipment is high. There is a disadvantage that it takes a long time to measure.

Confirmation of growth information using an image can quickly confirm the result and give feedback, but securing a high-quality DB and accurate analysis of growth information is possible only when securing a precise image is prioritized. Therefore, the method of confirming growth information using an image should put the greatest emphasis on extracting a precise image.

Korean Patent Publication No. 2013-0015278 (2013. 02. 14)

The present invention has been proposed to solve the problems of the prior art as described above, and a plant monitoring and cultivation method capable of easily performing a growth state analysis by clearly distinguishing the boundary between a plant subject part and a background part in an image of a plant, It is to provide devices and systems.

The present invention for solving the above problem is an embodiment, a first light source for irradiating visible light; And, a second light source for irradiating near-infrared light; And, from the plant subject irradiated with visible light of the first light source. Imaging means for acquiring one image and acquiring a second image of the subject to which the near-infrared ray of the second light source is irradiated; And an image processing module that obtains a third image by masking a subject part from the second image, and an image analyzer including a calculation module that measures the size of the subject part from the third image. do.

The image processing module may further perform image processing to attenuate blue pixels in the second image before the masking process.

In the masking process, pixels are set to be divided into first pixels representing a subject and second pixels representing a background by comparing a value of each pixel constituting the second image with a predetermined threshold value. I can.

In another embodiment, the present invention includes the plant monitoring device; and, a main light source including at least one LED and providing a light spectrum for plant growth; And a controller that adjusts at least one of the light intensity and the light wavelength of the main light source based on the size of the subject provided by the plant monitoring device.

According to another embodiment of the present invention, a first light source that irradiates visible light; and a second light source that irradiates near-infrared light; and, obtaining a first image from a plant subject irradiated with visible light of the first light source, Imaging means for obtaining a second image of the subject irradiated with near-infrared rays of the second light source; And an image processing module that obtains a third image by masking a subject part from the second image, and obtains a fourth image by removing a part corresponding to the background part of the third image from the first image. 4 We propose a plant monitoring device including an image analyzer including a calculation module that derives the state of a plant component based on the analysis result of the image.

The image analyzer, by comparing the RGB value of the fourth image and a previously prepared RGB-component table to derive a plant component state, or by substituting the RGB value of the fourth image into a pre-prepared RGB-component relation, State can be derived.

The image processing module may further perform image processing to attenuate blue pixels in the second image before the masking process.

In the masking process, pixels are set to be divided into first pixels representing a subject and second pixels representing a background by comparing a value of each pixel constituting the second image with a predetermined threshold value. I can.

The present invention is another embodiment, the plant monitoring device of claim 5; And, a main light source including at least one LED and providing a light spectrum for plant growth; And it proposes a plant cultivation system comprising a controller for adjusting at least one of the light intensity and the light wavelength of the main light source based on the state of the component provided by the plant monitoring device.

In another embodiment, the present invention provides, in another embodiment, obtaining a first image of a subject irradiated with visible light; and obtaining a second image of the subject irradiated with near-infrared rays; and, in the second image, the subject is Acquiring a third image in which a portion is masked; and, measuring the size of a subject portion in the third image; and removing a portion corresponding to a background portion of the third image from the first image 4 acquiring an image; and deriving a state of a plant component based on the analysis result of the fourth image; And adjusting at least one of a light intensity and a light wavelength of a main light source for plant growth based on the measured size of the subject part and the derived state of the plant component.

Before the masking process, the step of processing the second image to weaken the blue-based pixel may be further included.

In the masking process, each pixel constituting the second image can be divided into pixels of a first color representing a subject and pixels of a second color representing a background by comparing a value with a predetermined threshold value. have.

In the step of deriving the component state of the plant, the component state of the plant may be derived by comparing the RGB value derived by analyzing the fourth image with a previously prepared RGB-component table.

The RGB-component table may be generated by periodically repeating the steps of storing the RGB values of the fourth image and the actually measured plant component values.

The wavelength region of the near-infrared ray may be defined in the range of 0.7 to 1.3 μm.

According to embodiments of the present invention, it is possible to easily monitor the growth state of plants without the need for complex and heavy image processing algorithms or equipment.

1 is a block diagram of a plant monitoring device according to an embodiment of the present invention.
2 is a detailed block diagram of the plant monitoring device of FIG. 1.
3 is a block diagram of a plant monitoring device according to another embodiment of the present invention.
4 is a detailed block diagram of the plant monitoring device of FIG. 3.
5 is a block diagram of a plant monitoring device according to another embodiment of the present invention.
6 is a detailed block diagram of the plant monitoring device of FIG. 5.
7 is a block diagram of a plant cultivation apparatus according to an embodiment of the present invention.
8 is a detailed block diagram of the plant cultivation apparatus of FIG. 7.
9 is a flowchart illustrating a pretreatment process of a plant monitoring method according to an embodiment of the present invention.
10 is a flow chart of a plant cultivation method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art may easily implement the present invention. However, this is not intended to limit the present invention to a specific embodiment, it is to be understood to include all changes, equivalents, or substitutes included in the spirit and scope of the present invention.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it is directly connected to or may be connected to the other component, but other components may exist in the middle. Should be.

On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The terms used in the present specification are only used to describe specific embodiments and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, processes, operations, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the possibility of addition or presence of elements or numbers, processes, operations, components, parts, or combinations thereof is not preliminarily excluded.

Unless otherwise defined, all terms including technical or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in this application. Does not.

The term “MODULE” described herein refers to a unit that processes a specific function or operation, and may mean hardware or software, or a combination of hardware and software.

The terms or words used in the present specification and claims are not limited to their usual or dictionary meanings and should not be interpreted, and the inventor may appropriately define the concept of terms in order to describe his own invention in the best way. Based on the principle that there is, it should be interpreted as a meaning and concept consistent with the technical idea of the present invention.

In addition, unless there are other definitions in the technical terms and scientific terms used, they have the meanings commonly understood by those of ordinary skill in the art to which this invention belongs, and the gist of the present invention in the following description and accompanying drawings Descriptions of known functions and configurations that may be unnecessarily obscure will be omitted.

The drawings introduced below are provided as examples in order to sufficiently convey the spirit of the present invention to those skilled in the art. Accordingly, the present invention is not limited to the drawings presented below and may be embodied in other forms. In addition, the same reference numbers throughout the specification indicate the same elements. It should be noted that the same elements in the drawings are indicated by the same reference numerals wherever possible.

Hereinafter, it will be described in detail with reference to the accompanying drawings in the present specification.

<Example 1>

1 is a configuration diagram of a plant monitoring device according to an embodiment of the present invention, and FIG. 2 is a block diagram showing the configuration of FIG. 1 in detail.

As shown in FIG. 1, the plant monitoring apparatus 100 according to an embodiment includes a first light source 110 for irradiating visible light, a second light source 120 for irradiating near-infrared rays, a digital imaging means 130, It comprises an image analyzer 140 for measuring the size of the subject.

In general, the leaves of plants absorb red and blue wavelengths in the visible light region, so the first light source 110 is irradiated and the photographed image is mainly green. In addition, since the cells inside the leaves of the plant show high reflectance to near infrared (NIR) in the region of 0.7 to 1.3 μm among infrared rays, the second light source 120 is preferably irradiated with near infrared rays among infrared rays. However, depending on the type and characteristics of plants, the infrared section with high reflectivity may be partially different, so the infrared ray in the 0.7 ~ 1.3 µm region is only an example, and the wavelength region emitted by the second light source 120 is within the infrared ray section. Can be adjusted accordingly.

In all embodiments of the present invention, the first light source 110 and the second light source 120 are separated to logically divide the light irradiation wavelength range of each light source 110 or 120, and must be physically divided into two types. It is not necessary to have a light source. Therefore, if two types of wavelength ranges can be provided by one light source, this can also be regarded as having the first light source 110 and the second light source 120 in the present invention.

As a more specific example, if visible light and infrared light can be separately provided through a single light source and a wavelength filtering means that transmits only a wavelength of a specific section, it should be considered to be included in the scope of the present invention. Examples of such wavelength filtering means include cellophane, a film coated with inorganic phosphors, a film coated with quantum dots, and a film coated with Perovskite.

Therefore, as the first light source 110, an artificial light source such as a light emitting diode (LED), a halogen lamp, a fluorescent lamp, and an incandescent lamp may be used, or a natural light source such as sunlight may be used, and the artificial light source and the natural light source as described above may be used together. May be.

The imaging means 130 is a digital device that acquires a first image from a plant subject irradiated with visible light from the first light source 110, and obtains a second image of the subject irradiated with infrared rays from the second light source 120. It's a camera. The image sensor of the imaging means 130 includes a charge-coupled device (CCD), a complementary metal-oxide semiconductor (CMOS), and a contact image sensor (CIS). It can be used, and any other type of image sensor is fine.

In the image captured by the imaging means 130, in order to more clearly distinguish the shape of the subject from the background, it is preferable that a background plate of a material or color having a smooth light absorption is installed on the rear surface of the subject as much as possible before photographing.

The image analyzer 140 includes an image processing module 14 that obtains a third image by masking a subject part from the second image, and a calculation module 15 that measures the size of the subject part masked from the third image. Includes.

Measuring the size of the subject part may refer to measuring the length of the subject part in the horizontal or vertical direction, or may refer to calculating the area occupied by the subject part.

Masking processing refers to an image processing process that separates the boundary between a subject and a background. The image processing module 14 compares the value of each pixel constituting the second image with a predetermined threshold value, and divides each pixel into first pixels representing a subject and second pixels representing a background. Set the pixels. For example, the image processing module 14 may set first pixels representing a subject to white and second pixels representing a background to black. However, the present invention is not necessarily limited thereto, and if the subject and the background can be clearly distinguished, it is possible to set the color to any two colors desired by the user.

Prior to the masking process, the image processing module 14 may further perform image processing to attenuate blue pixels in the second image. In other words, in the image of the projectile irradiated with infrared light, the color contrast between the subject and the background becomes more clear by weakening a few blue pixels from a plurality of red pixels. To this end, the following algorithm may be applied to subtract the blue range value from the red color range value among the pixel values with an appropriate weight.

NEW CHANNEL = RED-k * BLUE (k is a predetermined weight value)

Meanwhile, as an example, the image processing module 14 and the calculation module 15 may be implemented as software programs running on a general-purpose personal computer (PC). In this case, the image analyzer 140 is regarded as a desktop PC, a notebook PC, or a server computer executing a software program equipped with the image processing module 14 and the calculation module 15.

As another example, the image processing module 14 and the calculation module 15 may be implemented as software embedded in a nonvolatile memory such as ROM, PROM, EPROM, EEPROM, and flash memory in the form of firmware.

When the first light source 110, the second light source 120 and the imaging means 130 are mounted together and implemented as a single device 100 such as a digital camera or a closed circuit camera, the device 100 is A wired or wireless communication module 12 may be further provided to transmit image data to the image analyzer 140. In addition, the device 100 may further include a control module 11 for sequentially controlling the first light source 110, the second light source 120, and the imaging unit 130 according to a preset algorithm.

Although not shown in the drawings, an embodiment in which the first light source 110, the second light source 120, and the imaging unit 130 are implemented individually, rather than a single device, may be assumed. In this case, the first light source 110, the second light source 120 and the imaging means 130 must each have a communication module (not shown in the drawing) for communicating with each other or with the image analyzer 140, It may be operated according to a control signal transmitted by a control module (not shown in the drawing) of the image analyzer 140.

The image analyzer 140 is a communication module for receiving image data from the device 100 or the imaging means 130 or transmitting a control signal to the first light source 110, the second light source 120, and the imaging means 130. (13) may be further provided.

<Example 2>

3 is a configuration diagram of a plant monitoring device according to another embodiment of the present invention, and FIG. 4 is a block diagram showing the configuration of FIG. 3 in detail.

As shown in FIG. 3, the plant monitoring apparatus 200 according to an embodiment includes a first light source 210 for irradiating visible light, a second light source 220 for irradiating near-infrared rays, a digital imaging means 230, It comprises an image analyzer 240 and a spectrum-component table 250 for analyzing the components of the plant subject.

The first light source 210, the second light source 220 and the imaging means 230, and the control module 21 and communication modules 22 and 23 included in each component are the aforementioned first light source 110 and the second light source. Since the light source 120, the imaging means 130, and the components included in each component are the same, a duplicate description will be omitted.

The image analyzer 240 obtains a third image by masking a subject portion from the second image, and obtains a fourth image by removing a portion corresponding to the background portion of the third image from the first image. A module 24 and a calculation module 25 for deriving a plant component state by comparing the wavelength of the fourth image with the previously stored spectrum-component table 250 are included. Here, the masking process of the second image and the process of weakening the blue-based pixel may be applied in the same manner as the image processing module 14 described above.

Since the first image is a photographed image for visible light, the boundary between the plant subject portion and the background portion, that is, the color contrast of both portions may be relatively unclear compared to the third image. Therefore, in the present embodiment, rather than directly masking the background portion of the first image, the background portion of the third image is accurately masked by applying a third image whose background portion is clearly masked to the first image.

The more accurately the background area is masked, the more accurate the RGB spectrum analysis result of the plant subject becomes because the spectral crosstalk due to the ambiguity of the subject-background boundary area decreases.

The spectrum-component table 250 includes a predetermined specific wavelength or at least two or more specific wavelengths included in an image for a predetermined specific area (eg, leaf, flower, leaf and stem) for each plant type or specific plant. It is a data set obtained by matching the characteristic values of the combination of these and the corresponding component values. Here, the characteristic value may refer to the intensity of a wavelength or the brightness of light of a corresponding wavelength.

As an example, when an RGB camera is used as an imaging means, a spectral field of the spectrum-component table 250 is performed by inverting the logged R image after specifically logging the R image for the RGB spectrum of a leaf part of a specific plant. Is defined, and a numerical composition of a specific component or component(s) corresponding to a unitized numerical value of R log may be defined as a component field of the spectrum-component table 250. In this case, even though the spectrum-component table 250 is called the RGB-component table 250, both are interpreted in the same way. Furthermore, by analyzing the RGB-component pattern of the spectrum-component table 250, a normalized relational expression between the RGB-components may be derived.

As another example, when a monochrome camera is used as an imaging means, a spectral field of the spectrum-component table 250 is defined by logging an image of a characteristic specific wavelength within a wavelength range of 400-1000 nm, and A numerical composition of a specific component or a numerical composition of the component(s) corresponding to the unitized numerical value of the spectrum-component table 250 may be defined as a component field of the spectrum-component table 250. Further, by analyzing the specific wavelength(s)-component pattern of the spectrum-component table 250, a normalized relational expression between the specific wavelength(s)-components may be derived.

The spectrum-component table 250 may be newly constructed by periodically measuring and storing the wavelength distribution of the fourth image and the measured component value of the plant throughout the entire growth cycle of the plant. You can also use a database.

Hereinafter, embodiments using an RGB camera as an imaging means will be described for convenience of explanation, but as described above, it is not necessarily limited to an RGB camera, and any type of camera capable of distinguishing characteristics of a specific wavelength(s) may be used. have.

<Example 3>

Example 3 relates to a plant monitoring device that measures/analyzes the size of the target plant or the area of the leaf and the component value or the composition of the component value of the same target plant.

5 is a configuration diagram of the plant monitoring device of Example 3, and FIG. 6 is a detailed block diagram of the plant monitoring device of FIG. 5.

The first light source 310, the second light source 320 and the imaging means 330 of the third embodiment, the control module 31 and the communication module 32 included in each configuration are the aforementioned first light source 110, The second light source 120, the imaging means 130, and the configurations included in each configuration are the same, and the image processing module 34 of the image analyzer of the third embodiment is the same as the image processing module 24 described above. Description is omitted.

The calculation module 35 of the third embodiment is characterized in that it simultaneously performs the role of the calculation module 14 of the first embodiment and the analysis module 24 of the second embodiment. That is, the image processing module 34 measures the size of the subject part in the masked third image, while the RGB value of the fourth image generated by the image processing module 34 and the pre-stored spectrum-component table 350 Compared to derive the state of the composition of the plant.

<Example 4>

Example 4 relates to a plant cultivation system in which the plant size monitoring result of Example 1 and/or the plant component monitoring result of Example 2 are fed back to control the growth conditions of plants. Here, the term "plant growth conditions" means to include the intensity of light irradiated to the plant, the wavelength of light, ambient temperature, ambient humidity, and carbon dioxide concentration. For convenience of description, in this specification, an embodiment of adjusting the intensity or wavelength of an artificial light source will be described.

7 is a block diagram of a plant cultivation system according to an embodiment of the present invention, and FIG. 8 is a block diagram of the system of FIG. 7.

As shown in FIG. 7, the plant cultivation system of an embodiment includes at least one plant monitoring device 300, at least one LED, and includes a main light source 400 providing a light spectrum for plant growth, and a plant monitoring device ( The control server 500 and the growth database 550 are configured to adjust at least one of the light intensity and light wavelength of the main light source based on the plant size value and/or the plant component value provided by 300).

As described above, the plant monitoring device 100 of Example 1 measures the size of the target plant or the area of the leaf, and the plant monitoring device 200 of Example 2 determines the value of a specific component or the composition of the component value of the target plant. Analyze. The plant cultivation system of Example 4 may be implemented as an embodiment including one or more of the plant monitoring device 100 of Example 1, and one or more of the plant monitoring device 200 of Example 2 It may be implemented as an embodiment. In addition, it may be implemented as an embodiment including one or a plurality of the plant monitoring device 300 of the third embodiment. Here, an embodiment including a plurality of the plant monitoring device 300 of Example 3 will be described.

Assuming that a plurality of plant monitoring devices are provided in Example 4, the first light source 310, the second light source 320, the imaging means 330, the control module 31 and the communication module 32 are It is provided for each device to photograph a specific plant allocated to each plant monitoring device 300. In contrast, the image processing module 34, the calculation module 35, the image analyzer 340 including the analysis module 36, and the spectrum-component table 350 are jointly used for the plurality of plant monitoring devices 300. Since it can be utilized, only one may be installed in the control server 500 connected through a predetermined communication network. In this case, the image analyzer 340 may be designed to simultaneously perform multiple image processing-calculation-analysis processes in order to simultaneously and rapidly process image data sent by the plurality of monitoring devices 300.

Images of the first light source 310, the second light source 320, the imaging means 330, the control module 31, the communication modules 32 and 33, and the image analyzer 340 included in the plant monitoring device 300 The processing module 34, the calculation module 35, the analysis module 36, and the spectrum-component table 350 have the same configurations, functions, and roles in the first to third embodiments. Omit it.

The controller 50 compares the size or area value of the subject transmitted by the calculation module 31 of the image analyzer and the component value of the plant transmitted by the analysis module 32 with the growth database 550.

The growth database 550 stores standard leaf size and target component values for each growth unit set in advance for a specific plant A. For example, the standard leaf sizes of the 3rd, 7th, 15th, 20th, and 30th days of the Anabell strawberry variety are 1.1cm, 2.5cm, 4.3cm, and 5.8cm, respectively, and the target content of the garlic acid component is 0.012, respectively. It may be previously stored in the growth database 550 in mg, 0.034mg, 0.086mg, 0.126mg.

If the leaf size measured on the 3rd day is 0.8cm and the gallic acid content is 0.0008mg, there is a difference compared to the values of 1.1cm and 0.012mg previously stored in the growth database 550, so that the leaf size is further increased. At least one of the light intensity, wavelength, and light period temperature of the main light source 400 is adjusted to promote the generation of hazardous or gallic acid.

<Example 5>

9 and 10 are flowcharts sequentially showing a plant monitoring and plant cultivation method according to an embodiment.

9 shows a process of pre-building an RGB-component relational equation or a spectrum-component table as a preliminary step for deriving a component value of a plant.

The plant monitoring apparatus acquires a first image of a plant subject irradiated with visible light from the first light source (S101), and acquires a second image of the subject irradiated with infrared rays from the second light source on the same plant (S202). As for the infrared rays of the second light source, near infrared rays in the 0.7 ~ 1.3 ㎛ wavelength range may be used, but the wavelength range may be partially changed depending on factors such as the type of plant or the light environment of the cultivation facility, but is not limited thereto as described above. .

The plant monitoring device performs image processing to attenuate blue pixels in the second image (S103). In the image of the projectile irradiated with infrared light, the color contrast between the subject and the background becomes more clear by weakening a few blue pixels from a plurality of red pixels. Step S103 is a pre-processing step for more clearly distinguishing the boundary of the subject shape, and may be selectively performed as necessary.

The plant monitoring apparatus obtains a third image by masking a subject portion in the second image or the image in which the blue pixels are weakened in the second image (S104). In other words, the subject part and the background part are treated as white and black, respectively, based on the boundary between the subject part and the background part.

The plant monitoring device obtains a fourth image by removing a portion corresponding to the background portion of the third image from the first image (S105). When photographing a subject with visible light, it is desirable to install a background plate of a material or color that absorbs light in the background of the subject as much as possible so that the background is expressed as black as possible, but nevertheless, due to the limitation of light absorption of the background plate. Therefore, there is a limit to distinguishing the subject from the background. Therefore, it is easy to analyze the RGB values of the remaining pixels except the black pixels in the first image by processing the background part excluding the subject as black using the third image in which the background is treated as pure black for the same subject. I can do it.

The plant monitoring device analyzes the RGB value of the plant subject part in the fourth image and records it in the memory. Then, it is stored in the spectrum-component table along with the actual measured plant component values using a component measuring system or other known plant component measuring process (S106). Steps S101 to S106 are performed at a constant cycle over the entire cycle of the plant growth to complete one spectrum-component table. Furthermore, it is possible to derive an RGB-component relational expression by analyzing the relationship between the current RGB value for the growth period and the previously derived standard RGB value from the spectrum-component table.

FIG. 10 is a flowchart sequentially showing a method of monitoring plant growth and controlling plant growth using the spectrum-component table derived from FIG. 9.

In FIG. 10, since the steps of acquiring, pre-processing, masking and deleting the background portion of the plant subject (S201 to S204, S206) are the same as steps S101 to S104 and S105 of FIG. 9, a duplicate description will be omitted.

The plant monitoring device calculates the size or area of the subject part from the third image masking the subject part in the second image (S205), and the subject from the fourth image from which the background part has been removed (or color processed in black, etc.) The RGB value of the part is calculated (S207). In addition, the plant cultivation device compares the component value corresponding to the size of the subject and RGB provided from the plant monitoring device with the growth database, and when the size and/or component value of the plant is insufficient compared to the target value previously stored in the growth database, the main light source The growth environment of plants is controlled by varying the intensity and wavelength, varying the ambient temperature using an electric heater, controlling the humidity using a humidifier, or controlling the concentration of CO2 by controlling a ventilator or ventilation window (S208) .

It will be easily understood by those skilled in the art that the partial functions of the plant image analysis system described above may be provided by being included in a recording medium that can be read through a computer by tangibly implementing a program of instructions for implementing the same. The computer-readable recording medium may include a program command, a data file, a data structure, or the like alone or in combination. The program instructions recorded on the computer-readable recording medium may be specially designed and constructed for the present invention, or may be known and usable to those skilled in computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and floptical disks. Magneto-optical media and hardware devices specially configured to store and execute program instructions such as ROM, RAM, flash memory, USB memory, and the like. The computer-readable recording medium may be a transmission medium such as an optical or metal wire or a waveguide including a carrier wave for transmitting a signal specifying a program command or a data structure. Examples of program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

It goes without saying that the present invention is not limited to the above-described embodiments, and various modifications are possible without departing from the gist of the present invention as claimed in the claims, as well as a variety of application ranges.

100, 200, 300: plant monitoring device
110, 210, 310: first light source 120, 220, 320: second light source
130, 230, 330: imaging means 140, 240, 340: image analyzer
150, 250, 350: RGB-component table
400: main light source 500: control server
550: growth database

Claims (16)

A first light source for irradiating visible light;
A second light source irradiating near infrared rays;
An imaging means for acquiring a first image from a plant subject irradiated with visible light from the first light source and a second image of the subject irradiated with near infrared rays from the second light source; And
An image analyzer including an image processing module that obtains a third image by masking a subject part from the second image, and a calculation module that measures the size of the subject part from the third image
Plant monitoring device comprising a. The image processing module,
Prior to the masking process, the plant monitoring apparatus further performs image processing to attenuate blue pixels in the second image. The method of claim 1,
In the masking process, pixels are set to be divided into first pixels representing a subject and second pixels representing a background by comparing a value of each pixel constituting the second image with a predetermined threshold value. Plant monitoring device, characterized in that. The plant monitoring device of claim 1;
A main light source comprising at least one LED and providing a light spectrum for plant growth; And
Controller for adjusting at least one of light intensity and light wavelength of the main light source based on the size of the subject provided by the plant monitoring device
Plant cultivation system comprising a. A first light source for irradiating visible light;
A second light source irradiating near infrared rays;
An imaging means for acquiring a first image from a plant subject irradiated with visible light from the first light source and a second image of the subject irradiated with near infrared rays from the second light source; And
An image processing module that obtains a third image by masking a subject portion from the second image, and obtains a fourth image by removing a portion corresponding to a background portion of the third image from the first image; and the fourth An image analyzer that includes a calculation module that derives the state of plant components based on the analysis results of the image.
Plant monitoring device comprising a. The method of claim 5,
The image analyzer,
A plant monitoring device, characterized in that for deriving a plant component state by comparing the RGB value of the fourth image with a previously prepared RGB-component table. The method of claim 5,
The image analyzer,
The plant monitoring device, characterized in that to derive the component state of the plant by substituting the RGB value of the fourth image into a previously prepared RGB-component relational equation. The method of claim 5,
The image processing module,
Prior to the masking process, the plant monitoring apparatus further performs image processing to attenuate blue pixels in the second image. The method of claim 5,
In the masking process, pixels are set to be divided into first pixels representing a subject and second pixels representing a background by comparing a value of each pixel constituting the second image with a predetermined threshold value. Plant monitoring device, characterized in that . The plant monitoring device of claim 5;
A main light source comprising at least one LED and providing a light spectrum for plant growth; And
Controller for adjusting at least one of the light intensity and the light wavelength of the main light source based on the state of the component provided by the plant monitoring device
Plant cultivation system comprising a. Obtaining a first image of a subject irradiated with visible light;
Obtaining a second image of the subject irradiated with near infrared rays;
Obtaining a third image obtained by masking a subject part from the second image;
Measuring the size of the subject part in the third image;
Obtaining a fourth image by removing a portion corresponding to a background portion of the third image from the first image;
Deriving a component state of the plant based on the analysis result of the fourth image; And
Adjusting at least one of the light intensity and light wavelength of the main light source for plant growth based on the measured size of the subject part and the derived plant component state
Plant cultivation method comprising a. The method of claim 11,
Prior to the masking process, processing the second image to weaken blue pixels. The method of claim 11,
The masking process divides each pixel constituting the second image into pixels of a first color representing a subject and pixels of a second color representing a background by comparing a value with a predetermined threshold value. Plant cultivation method, characterized in that. The method of claim 11,
The step of deriving the component state of the plant,
And comparing the RGB values derived by analyzing the fourth image with a previously prepared RGB-component table to derive the component state of the plant. The method of claim 14,
The RGB-component table,
The plant cultivation method, characterized in that it is generated by periodically repeating the step of storing the RGB value of the fourth image and the actually measured plant component value. The method of claim 11,
The plant cultivation method, characterized in that the wavelength region of the near infrared is 0.7 ~ 1.3 ㎛.

Images