Growth Management System

Abstract

To provide a growth management system that recognizes key parts of cultivated plants and determines their growth status. [Solution] A growth management system for managing the growth status of cultivated plants Q. The system includes an imaging device for capturing images of cultivated plants Q, a recognition unit for recognizing the main stem 51, branch and leaf parts 52 differentiated from the main stem 51, and flower cluster parts 53 differentiated from the main stem 51 of cultivated plants Q as captured in the images obtained by the imaging device, and a growth determination unit for determining the growth status based on the state of the main stem 51 and flower cluster parts 53.

Description

Technical Field

[0001] The present invention relates to a growth management system for cultivated plants.

Background Art

[0002] For example, as shown in the growth management system (referred to as "plant cultivation equipment" in the literature) disclosed in Patent Document 1, a system for determining the growth balance of cultivated plants (referred to as "plants" in the literature) has been conventionally disclosed. In the case of the system disclosed in Patent Document 1, the growth status of cultivated plants is determined by measuring the photosynthesis of the cultivated plants.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, in the configuration of Patent Document 1, the growth status is determined based on the measurement of photosynthesis. However, in order to grasp the growth status of cultivated plants, it is desirable to recognize the main part of the cultivated plants. As the main part of cultivated plants, the main stem is particularly useful, and in order to construct a useful growth management system, it is useful to recognize the main stem.

[0005] An object of the present invention is to provide a growth management system that determines the growth status after recognizing the main part of cultivated plants.

Means for Solving the Problems

[0006] The present invention relates to a growth management system for managing the growth status of cultivated plants, characterized in that it comprises: an imaging device for imaging the cultivated plants; a recognition unit for recognizing the main stem, branch and leaf portions differentiated from the main stem, and flower cluster portions differentiated from the main stem of the cultivated plants as captured in the images obtained by the imaging device; and a growth determination unit for determining the growth status based on the state of the main stem and the flower cluster portions.

[0007] According to the present invention, the recognition unit recognizes the main stem, the branches and leaves differentiated from the main stem, and the flower cluster differentiated from the main stem. The main stem, branches and leaves, and flower cluster are the main parts that serve as criteria for determining the growth status of cultivated plants. The recognition unit can recognize the relative positions of these main parts, namely the main stem, branches and leaves, and flower cluster. The growth determination unit then determines the growth status based on the respective states of the main stem and flower cluster. As a result, the growth determination unit can accurately grasp the growth status of the cultivated plant. Thus, with the present invention, a growth management system is realized that recognizes the essential parts of a cultivated plant and then determines its growth status.

[0008] In the present invention, it is preferable that the recognition unit is configured to recognize the fruit clusters that develop from the flower clusters, and that the growth determination unit is configured to represent the growth status with a first discriminant value that indicates the bias between vegetative growth, in which the main stem and branches and leaves grow, and reproductive growth, in which the fruit clusters grow.

[0009] This configuration makes it possible to obtain information on whether the growth of cultivated plants is biased towards vegetative growth or reproductive growth. This facilitates the construction of a growth management system that adjusts the growth balance of cultivated plants.

[0010] In the present invention, it is preferable that the growth determination unit is configured to express the growth status using a second discriminant value that indicates the rate of growth of the main stem and the branches and leaves.

[0011] This configuration allows for the acquisition of information regarding whether the growth rate of cultivated plants is too fast or too slow. This makes it easier to construct a growth management system that adjusts the growth balance of cultivated plants.

[0012] In the present invention, it is preferable that the growth determination unit is configured to represent the growth status with a third discriminant value that indicates which of a plurality of regions on a plane with the first discriminant value and the second discriminant value as axes the growth status belongs to.

[0013] This configuration allows for a multifaceted analysis based on information regarding whether the growth of cultivated plants is biased towards vegetative or reproductive growth, and whether the growth rate of the cultivated plants is too fast or too slow. This makes it easier to construct a growth management system that accurately adjusts the growth balance of cultivated plants.

[0014] In the present invention, it is preferable that the growth determination unit is configured to determine the future growth status based on the stem diameter of the main stem.

[0015] In this configuration, the growth determination unit determines the future growth status based on the stem diameter. Therefore, compared to configurations that acquire a large amount of environmental information using numerous sensors, the system's implementation cost is reduced, and it is expected to become a useful management system.

[0016] In the present invention, it is preferable that the growth determination unit is configured to determine the future growth status based on the main stem length, which indicates the length of the main stem between the upper end of the main stem and the flower cluster in a bloomed state.

[0017] In this configuration, the growth determination unit determines the future growth status based on the main stem length. Therefore, compared to configurations that acquire a large amount of environmental information using numerous sensors, the system's implementation cost is reduced, and it is expected to become a more useful management system. Furthermore, the growth determination unit can determine, based on the main stem length, whether the cultivated plants are prone to nutrient deficiency or tend to exhibit excessive vine growth.

[0018] In the present invention, it is preferable that a flowering state determination unit is provided that determines the flowering state of the inflorescence part at a plurality of stages, and the growth determination unit is configured to determine the growth state by performing weight conversion according to the stage of the flowering state.

[0019] Even when the inflorescence part is in bloom, the cultivated plant continues to grow. With this configuration, the growth determination unit performs weight conversion of information regarding the growth state according to the stage of the flowering state. As a result, the growth determination unit can determine the growth state based on a predetermined criterion in the flowering state of the inflorescence, and the determination accuracy of the growth state is improved.

[0020] In the present invention, it is preferable that the growth determination unit is configured to determine the growth state based on the stem diameter of the main stem.

[0021] With this configuration, it becomes easy to determine the growth state of the cultivated plant based on the stem diameter.

[0022] In the present invention, it is preferable that the growth determination unit is configured to determine the growth state based on the main stem length indicating the length of the main stem between the upper end of the main stem and the inflorescence part in the flowering state.

[0023] With this configuration, the growth determination unit can determine whether the cultivated plant tends to be nutrient-deficient or tends to have vine lodging or the like based on the length of the main stem between the upper end of the main stem and the foliage part in the state where the inflorescence has bloomed.

[0024] In the present invention, it is preferable that a watering control unit is provided that performs watering control based on the growth state.

[0025] With this configuration, the watering control is adjusted so that the cultivated plant grows in a balanced manner.

[0026] In the present invention, it is preferable that a solar radiation amount control unit for controlling the solar radiation amount based on the growth status is provided.

[0027] With this configuration, the solar radiation amount is adjusted so that the cultivated plants grow well in balance.

[0028] In the present invention, it is preferable that a carbon dioxide amount control unit for controlling the carbon dioxide amount based on the growth status is provided.

[0029] With this configuration, the carbon dioxide amount is adjusted so that the cultivated plants grow well in balance.

Brief Description of Drawings

[0030] [Figure 1] It is a plan view showing the entire interior of the horticultural facility. [Figure 2] It is a side view showing the entire interior of the horticultural facility. [Figure 3] It is a block diagram showing the configuration of the growth management system. [Figure 4] It is a diagram showing an example of a method for calculating the stem diameter of a cultivated plant. [Figure 5] It is a diagram showing an example of a method for calculating the stem diameter of a cultivated plant. [Figure 6] It is a diagram showing the calculation of a discrimination value based on the vigor of a cultivated plant. [Figure 7] It is a diagram showing the flowering state of an inflorescence and the weight coefficient corresponding to the flowering state. [Figure 8] It is a diagram showing an example of a method for calculating the length of the main stem (main stem length) from the stem tip to the branching point of the inflorescence part that has flowered in a cultivated plant. [Figure 9] It is a diagram showing the index range and discrimination value in a graph with the stem diameter and main stem length of the main stem as axes. [Figure 10] It is a flowchart showing the determination method of the stem diameter discrimination value and the vigor discrimination value. [Figure 11] It is a flowchart showing the determination method of the main stem length discrimination value. [Figure 12]This figure shows an example of a method for determining the future growth status of the branches and leaves. [Figure 13] This is a scatter plot showing the relationship between stem diameter and the average leaf area after five weeks. [Figure 14] This scatter plot shows the relationship between the average leaf area two weeks after the appearance of a flower cluster and the fruit yield from that flower cluster 12 weeks after its appearance. [Figure 15] This is a scatter plot showing the relationship between main stem length and the number of harvested fruits. [Figure 16] This is a scatter plot showing the relationship between main stem length and harvest weight. [Modes for carrying out the invention]

[0031] Embodiments for carrying out the present invention will be described with reference to the drawings.

[0032] [Composition of horticultural facilities] Embodiments for carrying out the present invention will be described with reference to the drawings. As shown in Figures 1 and 2, the cultivation system SY in this embodiment (corresponding to a "growth management system," or possibly a "growth management support system") includes a horticultural facility 1. The horticultural facility 1 is provided with rows A1 to A8 arranged vertically and horizontally for planting cultivated plants Q. The spaces between each row A are passageways accessible to the manager of the cultivated plants Q (including operators, etc.). The horticultural facility 1 may be, for example, a greenhouse or a solar-powered plant factory.

[0033] Each furrow A is made of, for example, a non-porous hydrophilic film. Then, in each furrow A, a plant Q is planted, for example, a tomato.

[0034] The cultivation system SY is equipped with multiple visual sensing units 3. Visual information of the cultivated plant Q is obtained by the visual sensing units 3. This visual information is used to determine the growth status of the cultivated plant Q. In this embodiment, the horticultural facility 1 is equipped with a fixed sensing unit 30 and a mobile sensing unit 31 as the visual sensing units 3.

[0035] As shown in Figures 1 and 2, the visual sensing unit 3 has an imaging device 3A and a distance measuring device 3B. The fixed sensing unit 30 is positioned above the cultivated plant Q. Therefore, the imaging device 3A in the fixed sensing unit 30 captures images from a bird's-eye view of the main stem 51 (see Figures 4 and 5), the branches and leaves 52 and flower clusters 53 (see Figures 4 and 5) that have branched off from the main stem 51, and the fruit clusters 54 (see Figures 4 and 5) that grow from the flower clusters 53 of the cultivated plant Q.

[0036] The mobile sensing unit 31 travels along pathways between parallel rows A in the horticultural facility 1, and images the cultivated plants Q from a side view. Therefore, the imaging device 3A of the mobile sensing unit 31 images the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. of the cultivated plants Q from a side view.

[0037] The imaging device 3A has, for example, a CCD element or a CMOS element and is configured to capture visible light that can be seen with the naked eye. The imaging device 3A in the fixed sensing unit 30 captures images of the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. of the cultivated plant Q from an overhead view at predetermined time intervals (for example, every 60 seconds). The imaging device 3A in the mobile sensing unit 31 captures images of the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. of the cultivated plant Q while patrolling the rows A1 to A8 of the horticultural facility 1. The image data V captured by each imaging device 3A is sent to the recognition unit 21 (see Figure 3) over time.

[0038] The distance measuring device 3B is, for example, a three-dimensional scanning Lidar, and measures the distance to the cultivated plant Q using, for example, a Time of Flight (ToF) measurement method. When the distance measuring device 3B irradiates the cultivated plant Q with a light beam, such as infrared laser light, the light waves of the light beam propagate through the air and are reflected off the surface of the cultivated plant Q, and the reflected light waves propagate through the air and reach the distance measuring device 3B. The distance measuring device 3B acquires the light waves reflected off the surface of the cultivated plant Q as a reflected signal. Then, the distance measuring device 3B calculates the distance between the distance measuring device 3B and the cultivated plant Q based on the time from when the light beam is irradiated until the reflected signal is acquired. That is, the distance measuring device 3B acquires distance measurement data D1 in three-dimensional coordinates for the cultivated plant Q imaged by the imaging device 3A. The distance measurement data D1 acquired by each distance measuring device 3B is sent to the recognition unit 21 over time.

[0039] Thus, the cultivation system SY includes an imaging device 3A for imaging the leaves of the cultivated plant Q, and a distance measuring device 3B for measuring the distance to the cultivated plant Q. The visual sensing unit 3 may not have a distance measuring device 3B. In this case, the visual sensing unit 3 may have a stereo camera as the imaging device 3A.

[0040] Although not shown in the diagram, the horticultural facility 1 is also equipped with environmental sensors, side windows, and a heat pump type air conditioning system. In addition, it is equipped with an irrigation system 11B, a spraying system 11C, a fertilization system 12B, a curtain opening and closing device 13B for the shading curtain, a carbon dioxide generator 14B, etc., as shown in Figure 3. The dashed line Gh shown in Figure 2 is the reference position where the height of the cultivated plant Q reaches its maximum height, and a support string for guiding the stem of the cultivated plant Q hangs down from around the height of the dashed line Gh. The fixed sensing unit 30 is installed at a position higher than the dashed line Gh. However, the fixed sensing unit 30 may also be installed at a position lower than the dashed line Gh.

[0041] [Device configuration] As shown in Figure 3, at the horticultural facility 1, imaging data V captured by the imaging device 3A, distance measurement data D1 measured by the distance measuring device 3B, and environmental condition data E, which is data representing the environmental conditions measured by the environmental information acquisition unit 10, are transmitted to the management computer 2 via a wide area network (WAN). Although not specifically shown, both the horticultural facility 1 and the management computer 2 are equipped with communication means capable of accessing the wide area network (WAN).

[0042] The environmental information acquisition unit 10 of the horticultural facility 1 is connected to a solar radiation sensor 10A, a temperature sensor 10B, a humidity sensor 10C, and a carbon dioxide concentration sensor 10D. The solar radiation sensor 10A measures the amount of solar radiation received by the cultivated plants Q in the horticultural facility 1. The temperature sensor 10B measures the indoor temperature in the horticultural facility 1. The humidity sensor 10C measures the indoor humidity in the horticultural facility 1. The carbon dioxide concentration sensor 10D measures the indoor carbon dioxide concentration in the horticultural facility 1. In other words, the environmental information acquisition unit 10 can acquire environmental information of the horticultural facility 1 where the cultivated plants Q are grown.

[0043] The management computer 2 is equipped with a recognition unit 21, a stem diameter calculation unit 22, a flowering position calculation unit 23, a flowering state determination unit 24, a storage unit 25, and a growth determination unit 26.

[0044] When the cultivated plant Q is imaged by the imaging device 3A, the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. are recognized by the recognition unit 21 based on the color information of the image data V. The recognition unit 21 has a neural network that can be trained using deep learning. Neural networks are known to be able to identify nonlinear input-output relationships through deep learning. The recognition unit 21 is configured to be able to identify the types of branches, leaves, stems, etc. in the cultivated plant Q by utilizing the neural network trained using deep learning. The determination of the color information of the image data V may be based on RGB data or on YUV data. That is, the recognition unit 21 recognizes the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. in the cultivated plant Q as captured in the image acquired by the imaging device 3A.

[0045] The distance measurement data D1 measured by the distance measuring device 3B is taken into the recognition unit 21. The recognition unit 21 compares the imaging data V with the distance measurement data D1 and identifies the distances of the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. to the visual sensing unit 3. Among the cultivated plants Q recognized in the imaging data V, cultivated plants Q planted in furrow A that are farther away than the target furrow A will have longer distance measurement data D1 than cultivated plants Q planted in the target furrow A. Therefore, the recognition unit 21 identifies the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. of the cultivated plants Q planted in the target furrow A by excluding those with longer distance measurement data D1 from the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. recognized from the imaging data V.

[0046] As will be explained in more detail later, the stem diameter calculation unit 22 calculates the stem diameter D2 of the main stem 51 of the cultivated plant Q based on the imaging data V and the distance measurement data D1 (see Figures 4 and 5). In other words, the stem diameter calculation unit 22 calculates the stem diameter D2 of the main stem 51 recognized by the recognition unit 21.

[0047] The flowering position calculation unit 23 calculates the main stem length L, which is the length of the main stem 51 between the upper end of the main stem 51 and the flower cluster 53 (see Figure 8).

[0048] As will be explained in more detail later, the flowering state determination unit 24 determines the flowering state of the flower cluster 53 in the cultivated plant Q by dividing it into multiple stages (see Figure 7).

[0049] The memory unit 25 is, for example, RAM (Random Access Memory) or a hard disk, and can store imaging data V, distance measurement data D1, environmental condition data E, analysis results, and judgment results.

[0050] Weather information 4 is weather data information obtained, for example, from a meteorological agency or weather information company via a wide-area communication network (WAN). Weather information 4 is stored in the storage unit 25 over time.

[0051] As will be described in more detail later, the growth determination unit 26 is equipped with a growth balance determination unit 26A and a growth prediction determination unit 26B. The growth determination unit 26 determines the growth status of the cultivated plant Q (calculates data values ​​related to the growth status) based on the stem diameter D2 of the cultivated plant Q, the flowering status of the flower cluster 53, the main stem length L between the upper end of the main stem 51 and the flower cluster 53, environmental condition data E, and weather information 4, etc. The growth status data determined by the growth determination unit 26 is transmitted to various control units of the horticultural facility 1 via the wide-area communication network WAN. As will be described in more detail later, the growth status data includes the stem diameter discrimination value Ga, the main stem length discrimination value Gb, the tree vigor discrimination value Gc, and the future growth status of the branches and leaves 52, etc.

[0052] Furthermore, the stem diameter D2, flowering status of the inflorescence 53, main stem length L, environmental condition data E, weather information 4, and growth status data for the cultivated plant Q, the main stem length discrimination value Gb (first discrimination value) described later, the stem diameter discrimination value Ga (second discrimination value) described later, and multiple regions on a plane including the indicator range G shown in Figure 9 (third discrimination value), etc., can be displayed on a known display monitor, and administrators and operators can check this information on the display monitor. The display monitor may be provided on the management computer 2, or it may be a laptop computer or mobile phone owned by the administrator or operator. In other words, the cultivation system SY is configured to output this data (for example, by transmitting it to various terminals or displaying it on a display device). In addition, if there is an abnormality in at least one of the stem diameter D2, flowering status of the inflorescence 53, main stem length L, environmental condition data E, weather information 4, and growth status data, the system may be configured to output an alarm using a known buzzer or voice guidance.

[0053] The horticultural facility 1 is equipped with a temperature control unit 15A and a temperature control device 15B, which control the temperature within the horticultural facility 1. The temperature control unit 15A transmits an instruction signal to the temperature control device 15B based on growth status data determined by the growth determination unit 26. The temperature control device 15B may be, for example, a device for opening and closing skylights or side windows, a ventilation fan or circulation fan, or an air conditioning system (for example, a heat pump air conditioning system). When the temperature control device 15B receives an instruction signal from the temperature control unit 15A, it adjusts the temperature within the horticultural facility 1 by opening and closing skylights or side windows, ventilating with ventilation fans or circulation fans, operating a heat pump, etc.

[0054] The horticultural facility 1 is equipped with a humidity control unit 16A, a humidity control device 16B, and a spraying device 11C, which control the humidity in the horticultural facility 1. The humidity control unit 16A transmits instruction signals to the humidity control device 16B and the spraying device 11C based on growth status data determined by the growth determination unit 26. The humidity control device 16B is, for example, a humidifier or a dehumidifier. When the humidity control device 16B receives an instruction signal from the humidity control unit 16A, it operates to humidify or dehumidify. Also, when the spraying device 11C receives an instruction signal from the humidity control unit 16A, it opens a valve (not shown) and increases the humidity in the horticultural facility 1 by spraying.

[0055] Horticultural facility 1 is equipped with an irrigation control unit 11A and an irrigation device 11B for irrigating cultivated plants Q. The irrigation control unit 11A transmits instruction signals to the irrigation device 11B and spray device 11C based on growth status data determined by the growth determination unit 26. When the irrigation device 11B and spray device 11C receive the instruction signal from the irrigation control unit 11A, they open the irrigation valve (not shown) and supply water to the cultivated plants Q. The instruction signal from the irrigation control unit 11A may be a voltage value or a current value.

[0056] Furthermore, the horticultural facility 1 is equipped with a fertilization control unit 12A and a fertilization device 12B. The fertilization control unit 12A transmits an instruction signal to the fertilization device 12B based on the growth status data determined by the growth determination unit 26. When the fertilization device 12B receives the instruction signal from the fertilization control unit 12A, it opens a fertilization valve (not shown) and supplies fertilizer. The fertilizer may be supplied mixed with water supplied to the cultivated plants Q by, for example, the irrigation device 11B. This configuration makes it possible to adjust the amount of fertilizer applied based on the instruction signal from the fertilization control unit 12A. The fertilizer mainly contains nitrogen. However, the components of the fertilizer are not limited to nitrogen and may also include phosphorus, potassium, calcium, magnesium, etc.

[0057] The horticultural facility 1 is equipped with a solar radiation control unit 13A and a curtain opening / closing device 13B. The solar radiation control unit 13A transmits an instruction signal to the curtain opening / closing device 13B based on growth status data determined by the growth determination unit 26. The skylight of the horticultural facility 1 is equipped with a shading curtain (not shown), and the curtain opening / closing device 13B is configured to drive the shading curtain to open and close. The curtain opening / closing device 13B is configured, for example, by an electric motor. When the curtain opening / closing device 13B receives an instruction signal from the solar radiation control unit 13A, it opens and closes the shading curtain of the horticultural facility 1 to adjust the amount of photosynthesis of the cultivated plant Q.

[0058] The horticultural facility 1 is equipped with a carbon dioxide amount control unit 14A and a carbon dioxide generator 14B. The carbon dioxide amount control unit 14A transmits an instruction signal to the carbon dioxide generator 14B based on growth status data determined by the growth determination unit 26. The carbon dioxide generator 14B is installed in the horticultural facility 1 and is configured to generate carbon dioxide, for example, by combustion. When the carbon dioxide generator 14B receives an instruction signal from the carbon dioxide amount control unit 14A, it increases the amount of carbon dioxide in the horticultural facility 1 and increases the amount of photosynthesis of the cultivated plant Q.

[0059] In addition to the devices described above, the horticultural facility 1 is equipped with a heat storage device, a sterilization device, and the like. These devices may be configured to be driven based on the growth status data determined by the growth determination unit 26.

[0060] Alternatively, the management computer 2 may be equipped with at least one of the irrigation control unit 11A, fertilization control unit 12A, solar radiation control unit 13A, and carbon dioxide control unit 14A, and instruction signals may be transmitted to various devices of the horticultural facility 1 via a wide-area communication network (WAN).

[0061] [Regarding the calculation of stem diameter using the stem diameter calculation unit] The method by which the stem diameter calculation unit 22 calculates the stem diameter D2 of the cultivated plant Q will be explained with reference to Figures 4 and 5. The recognition unit 21 recognizes the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc. of the cultivated plant Q. The data recognized by the recognition unit 21 includes distance measurement data D1 measured by the distance measuring device 3B. Therefore, based on the distance measurement data D1, it is possible to calculate the distance and size of the main stem 51, branches and leaves 52, flower clusters 53, fruit clusters 54, etc.

[0062] The main stem 51 extends vertically, and the stem diameter D2 differs at different vertical positions on the main stem 51. In this embodiment, the stem diameter calculation unit 22 calculates the stem diameter D2 of the main stem 51 in the portion below the stem apex by a predetermined length Lh. The predetermined length Lh is, for example, 10 to 20 centimeters. The predetermined length Lh may be calculated appropriately depending on the type of cultivated plant Q, environmental conditions, etc.

[0063] The stem apex is recognized by the recognition unit 21. However, due to differences in the density of the branch and leaf parts 52 in the cultivated plant Q, the location recognized as the stem apex often varies. Therefore, in this embodiment, among the branch and leaf parts 52 and flower cluster parts 53 that differentiate from the main stem 51, if the flower cluster part 53 is located at the uppermost position, that flower cluster part 53 serves as a marker for the stem apex. This marker is recognized below as the reference height position Rh.

[0064] The recognition unit 21 is configured to recognize the flower cluster 53 that has differentiated from the upper part of the main stem 51. Of the branch leaf parts 52 and flower cluster 53 that differentiate from the main stem 51, if the flower cluster 53 is located at the uppermost position, that flower cluster 53 serves as a marker. In other words, when the recognition unit 21 recognizes a flower cluster 53 at the upper part of the cultivated plant Q, the stem diameter calculation unit 22 recognizes the position of the flower cluster 53 as the reference height position Rh. Furthermore, if the recognition unit 21 recognizes multiple flowers in the upper flower cluster 53 of the cultivated plant Q, the stem diameter calculation unit 22 recognizes the position of the highest flower as the reference height position Rh (see Figure 4).

[0065] Of the branch leaf sections 52 and flower cluster sections 53 that differentiate from the main stem 51, if the flower cluster section 53 is not present at the uppermost position, the upper end of the main stem 51 serves as a landmark. In other words, if the recognition section 21 does not recognize a flower cluster section 53 at the top of the cultivated plant Q, the stem diameter calculation unit 22 recognizes the position of the upper end of the main stem 51 as the reference height position Rh (see Figure 5).

[0066] In this way, the stem diameter calculation unit 22 calculates the stem diameter D2 of the main stem 51 in the portion of the cultivated plant Q that is below a set length Lh from the reference height position Rh. The stem diameter calculation unit 22 may also calculate the stem diameter D2 as the average or median value of the stem diameters D2 of multiple cultivated plants Q.

[0067] The stem diameter calculation unit 22 generates an approximate curve 61 of the main stem 51 and identifies a point located a set length Lh below the reference height position Rh along the approximate curve 61 as the calculation point 61A. Then, it calculates a tangent line 62 that is tangent to the approximate curve 61 at the calculation point 61A and calculates a normal line perpendicular to the tangent line 62.

[0068] The normal line crosses the main stem 51. The stem diameter D2 of the main stem 51 recognized by the recognition unit 21 can be calculated from the three-dimensional coordinates based on the distance measurement data D1. Therefore, the stem diameter calculation unit 22 calculates the length of the portion of the normal line that overlaps with the main stem 51 from the three-dimensional coordinates based on the distance measurement data D1. In other words, the stem diameter calculation unit 22 calculates an approximate curve 61 of the main stem 51 recognized by the recognition unit 21 and calculates the stem diameter D2 in the normal direction (or approximate normal direction) of the approximate curve 61.

[0069] [Regarding the assessment of tree vigor] The calculation location 61A identified by the stem diameter calculation unit 22 is stored in the memory unit 25, along with the characteristics of the calculation location 61A and the characteristics of the area surrounding it. As shown in Figure 6, the stem diameter calculation unit 22 calculates the stem diameter D2 at the calculation location 61A the first time, and then recalculates the stem diameter D2 at the calculation location 61A after a predetermined period has elapsed. Normally, the stem diameter D2 calculated a second time at the calculation location 61A is thicker than the stem diameter D2 calculated the first time at the calculation location 61A. Based on the magnitude of this change in stem diameter D2 at the calculation location 61A, it is possible to determine the vigor of the cultivated plant Q. The period between the first calculation of stem diameter D2 and the second calculation of stem diameter D2 is, for example, two weeks. Alternatively, the system may be configured to determine the vigor of the cultivated plant Q based on the stem diameter D2 at an arbitrary timing (one timing) without comparing it with past stem diameter D2.

[0070] When the environment is favorable for the growth of cultivated plant Q, the stem diameter D2 thickens, and the plant becomes more vigorous. When the plant becomes more vigorous, the main stem 51 elongates, and the branches and leaves 52 become dense. If the plant becomes too vigorous, it becomes prone to so-called vine overgrowth and blossom-end rot, which can lead to reduced yields and irregular fruit shapes.

[0071] If the stem diameter D2 does not thicken, the vigor of the cultivated plant Q will weaken, and the fruit cluster 54 will tend to grow actively, resulting in reproductive growth. If the stem diameter D2 is too thin, the branches and leaves 52 and flower clusters 53 will become smaller, reducing the yield.

[0072] When the vigor of cultivated plant Q is strong, the growth of cultivated plant Q will be rapid. In this case, the stem diameter D2 will thicken rapidly. Therefore, the growth balance determination unit 26A quantifies the vigor of cultivated plant Q using a vigor discrimination value Gc based on the degree of change in stem diameter D2 at the two timings. In other words, the growth balance determination unit 26A represents the growth status with a vigor discrimination value Gc (which may be a discrimination value based on the change in stem diameter D2 over time, or a discrimination value based on the change in stem diameter discrimination value Ga over time) that indicates the speed of growth of the main stem 51 and the branches and leaves 52. In this embodiment, the larger the vigor discrimination value Gc, the stronger the vigor of cultivated plant Q. However, it is also possible to configure the system so that the smaller the vigor discrimination value Gc, the stronger the vigor of cultivated plant Q. Furthermore, the growth balance determination unit 26A may be configured to quantify the vigor of cultivated plant Q using a vigor discrimination value Gc based on the stem diameter D2 at any timing (one timing) rather than the two timings mentioned above.

[0073] [Regarding the determination of the flowering status of flower clusters by the flowering status determination unit] As described above, the flowering state determination unit 24 determines the flowering state of the flower cluster 53 in the cultivated plant Q into multiple stages. As shown in Figure 7, the flowering state is divided into stages #0 to #4.

[0074] Stage #0 indicates that the flower cluster 53 is still an unopened bud.

[0075] Stage #1 indicates the state in which the calyx of the flower cluster 53 begins to split, revealing the petals inside. The duration of Stage #1 is about half a day to a day, which is shorter than Stages #0, #3, and #4.

[0076] Stage #2 indicates the state in which the calyx of the flower cluster 53 completely splits open, the inner petals emerge, and the flower begins to bloom. The duration of Stage #2 is about half a day to a day, which is shorter than Stages #0, #3, and #4.

[0077] Stage #3 shows the flower cluster 53 in bloom. In Stage #3, the calyx and petals of the flower cluster 53 repeatedly curl and extend. In Stage #3, when the calyx and petals are extended, the shape is similar to that of the flower cluster 53 in Stage #2.

[0078] Stage #4 shows the state in which the fruit cluster 54 has set fruit on the flower cluster 53. In Stage #4, the flowers on the flower cluster 53 gradually wither, and the fruit cluster 54 gradually grows.

[0079] Thus, in this embodiment, the flowering state determination unit 24 determines the flowering state into stages #0 to #4. The determination result of the flowering state determination unit 24 is used for the determination of the growth balance determination unit 26A.

[0080] [Determination of growth status by the growth balance assessment unit] In this embodiment, the growth balance determination unit 26A determines the growth status of the cultivated plant Q (calculates data values ​​related to the growth status) based on the main stem length L between the upper end of the main stem 51 and the flower cluster portion 53.

[0081] The recognition unit 21 is configured to recognize the state in which the main stem 51 has differentiated from the upper part and the state in which the flower cluster 53 has bloomed. The state in which the flower cluster 53 has bloomed refers to the flowering state being in stage #1 to stage #3. The flowering position calculation unit 23 calculates the length of the main stem 51, i.e., the main stem length L, between the upper end of the main stem 51 and the branching point of the main stem 51 in the bloomed flower cluster 53. The growth balance determination unit 26A then determines the growth status (calculates data values ​​related to the growth status) based on the main stem length L. The flowering position calculation unit 23 may also calculate the main stem length L as the average or median value of the main stem lengths L of multiple cultivated plants Q.

[0082] When the environment is favorable for the growth of cultivated plant Q, the main stem 51 grows, and the main stem length L tends to increase. In this state, cultivated plant Q exhibits a tendency toward vegetative growth, extending the main stem 51, spreading new branches and leaves 52, and expanding the roots. If cultivated plant Q becomes too heavily reliant on vegetative growth, it is prone to so-called vine overgrowth and blossom-end rot, resulting in reduced yields and irregular fruit shape.

[0083] If the environment is unfavorable for the growth of cultivated plant Q, the main stem length L tends to become shorter. In this case, the state of cultivated plant Q tends to be reproductive growth, with the fruit clusters 54 growing actively. If cultivated plant Q is too heavily reliant on reproductive growth, new branches and leaves 52 will not spread easily, which in turn makes it difficult for new flower clusters 53 and fruit clusters 54 to form, resulting in a decrease in yield.

[0084] Figure 9 shows a graph relating to stem diameter D2 and main stem length L. The index range G is shown in the center of this graph. The index range G is the area in the center of the graph that is not shaded. The index range G is used to determine whether or not the cultivated plant Q is growing properly. If the stem diameter D2 and main stem length L of the cultivated plant Q are within the range of index range G, the growth status of the cultivated plant Q is judged to be good. If the stem diameter D2 and main stem length L of the cultivated plant Q are outside the range of index range G, the growth status of the cultivated plant Q is judged to be problematic.

[0085] The growth balance determination unit 26A determines the growth status based on the stem diameter D2 and main stem length L, and transmits instruction signals based on the growth status data to the various control units of the horticultural facility 1. The various control units of the horticultural facility 1 then control the various devices so that the stem diameter D2 and main stem length L are plotted within the range G of the indicator range.

[0086] The indicator range G may be an initial value pre-set and stored in the memory unit 25, or it may be input from a terminal owned by, for example, a farmer, manager, or worker. The indicator range G can be set according to the type and variety of crop, the farmer's farming policy, etc. The range of stem diameter D2 that falls within the indicator range G is, for example, 8 to 12 millimeters, but the range may be set to 7 to 10 millimeters in order to increase the sweetness of the tomatoes. The range of main stem length L that falls within the indicator range G is, for example, 8 to 12 centimeters, but the range may be set to 7 to 11 centimeters in order to increase the sweetness of the tomatoes.

[0087] If the cultivated plant Q is vigorous, the stem diameter D2 will exceed the indicator range G and become thicker. Also, if the cultivated plant Q is predominantly vegetatively growing, the main stem length L will exceed the indicator range G and become longer.

[0088] In Figure 9, the stem diameter D2 is represented by multiple stem diameter discrimination values ​​Ga according to its thickness. In Figure 9, the stem diameter discrimination values ​​Ga are shown as +Ga1, +Ga2, and +Ga3 when the stem diameter D2 is thicker than the index range G. The stem diameter discrimination values ​​Ga indicate that the stem diameter D2 increases in the order of +Ga1, +Ga2, and +Ga3.

[0089] Furthermore, in Figure 9, the stem diameter discrimination values ​​Ga are shown as -Ga1, -Ga2, and -Ga3 as discriminant values ​​when the stem diameter D2 is thin and falls outside the indicator range G. The stem diameter discrimination values ​​Ga indicate that the stem diameter D2 becomes thinner in the order of -Ga1, -Ga2, and -Ga3. When the stem diameter D2 becomes thinner, the vigor of the cultivated plant Q weakens, and the growth of the main stem 51 and the branches and leaves 52 slows down.

[0090] The growth balance determination unit 26A is configured to represent the growth status (data values ​​related to the growth status) using a stem diameter discrimination value Ga (second discrimination value) that indicates the growth rate of the main stem 51 and the branch and leaf parts 52.

[0091] The method for determining the stem diameter discrimination value Ga will be explained based on the flowchart in Figure 10. The stem diameter calculation unit 22 recognizes the reference height position Rh (step #11), calculates the stem diameter D2 in the portion below the reference height position Rh by a set length Lh (step #12), and determines the stem diameter discrimination value Ga based on the graph shown in Figure 9 (step #13). The growth balance determination unit 26A also determines the tree vigor discrimination value Gc by comparing the past stem diameter D2 with the immediately preceding stem diameter D2 calculated in step #12 (step #14). In step #14, the growth balance determination unit 26A may be configured to determine the tree vigor discrimination value Gc based on the immediately preceding stem diameter D2 calculated in step #12, without reading the past stem diameter D2.

[0092] In Figure 9, the main stem length L is represented by multiple main stem length discriminant values ​​Gb according to its length. In Figure 9, the main stem length discriminant values ​​Gb are shown as +Gb1, +Gb2, and +Gb3 when the main stem length L is longer than the indicator range G. The main stem length discriminant values ​​Gb indicate that the main stem length L increases in the order of +Gb1, +Gb2, and +Gb3. When the main stem length L increases, growth tends to be biased towards vegetative growth, where the main stem 51 and the branches and leaves 52 grow.

[0093] Furthermore, in Figure 9, the discriminant values ​​Gb for the main stem length when the main stem length L is shorter than the indicator range G are shown as -Gb1, -Gb2, and -Gb3. The discriminant values ​​Gb indicate that the main stem length L decreases in the order of -Gb1, -Gb2, and -Gb3. When the main stem length L decreases, the growth tends to be biased towards reproductive growth, where the fruit cluster 54 of the flower cluster 53 grows.

[0094] The growth balance determination unit 26A is configured to represent the growth status (data values ​​related to the growth status) using a main stem length discrimination value Gb (first discrimination value) that indicates the bias between vegetative growth, in which the main stem 51 and branch leaves 52 grow, and reproductive growth, in which the fruit cluster 54 grows.

[0095] Furthermore, while the main stem length discrimination value Gb (first discrimination value) includes multiple stages (+Gb1 to +Gb3, -Gb1 to -Gb3) on both the positive and negative sides of the indicator range G, the main stem length discrimination value Gb may consist of only one value on both the positive and negative sides of the indicator range G. For example, a region of simply '+Gb' may be set on the positive side (the side with longer main stem length L) of the indicator range G, and a region of simply '-Gb' may be set on the negative side (the side with shorter main stem length L). Similarly, while the stem diameter discrimination value Ga (second discrimination value) includes multiple stages (+Ga1 to +Ga3, -Ga1 to -Ga3) on both the positive and negative sides of the indicator range G, the stem diameter discrimination value Ga may consist of only one value on both the positive and negative sides of the indicator range G. For example, a region simply labeled "+Ga" may be set on the positive side (where the stem diameter D is thicker) of the index range G, and a region simply labeled "-Ga" may be set on the negative side (where the stem diameter D is thinner) of the index range G.

[0096] In Figure 9, multiple regions on a plane (third discriminant value), including the indicator range G, are defined by a main stem length discriminant value Gb (first discriminant value) delimited by a horizontal axis representing the main stem length L, and a stem diameter discriminant value Ga (second discriminant value) delimited by a vertical axis representing the stem diameter D. In the example shown in Figure 9, 49 regions (third discriminant values) are delimited by seven levels of main stem length discriminant value Gb (first discriminant value) according to the main stem length L, and seven levels of stem diameter discriminant value Ga (second discriminant value) according to the stem diameter D. In other words, the growth balance determination unit 26A is configured to represent the growth status (data values ​​related to the growth status) with a third discriminant value that indicates which of the multiple regions on a plane with the stem diameter discriminant value Ga and the main stem length discriminant value Gb as axes the growth status belongs to. With this configuration, it is possible to precisely set what instruction signals are sent to each control unit 11A, 12A, 13A, 14A, 15A, and 16A in the horticultural facility 1, depending on which region the plotted points on the graph based on stem diameter D and main stem length L are located in.

[0097] Figure 9 illustrates plot points P1, P2, and P3 for the main stem length L and stem diameter D of an arbitrary cultivated plant Q. At plot point P1, both the main stem length L and stem diameter D fall within the indicator range G. This indicates that, at the state of plot point P1, cultivated plant Q has a balanced relationship between vegetative and reproductive growth, and its vigor is also moderate.

[0098] At plot point P2, the main stem length L falls within the indicator range G, but the stem diameter D is outside the indicator range G, at +Ga1. This indicates that, at plot point P2, the cultivated plant Q has a balance between vegetative and reproductive growth, but tends to be overly vigorous. This allows managers to determine measures to suppress the vigorous growth of cultivated plant Q (e.g., reducing sunlight).

[0099] At plot point P3, the stem diameter D falls within the indicator range G, but the main stem length L is outside the indicator range G, at -Gb2. This indicates that, at plot point P3, the cultivated plant Q has moderate vigor, but tends to be biased towards reproductive growth. From this, managers can determine measures to promote vegetative growth in the cultivated plant Q (for example, increasing the amount of liquid fertilizer supplied from the fertilizer application device 12B).

[0100] The indicator range G is also the basis for calculating the stem diameter discrimination value Ga and the main stem length discrimination value Gb. In other words, the basis for calculating the stem diameter discrimination value Ga and the main stem length discrimination value Gb may be initial values ​​set and stored in the memory unit 25 in advance, or they may be input from a terminal owned by, for example, a farmer, manager, worker, etc.

[0101] The main stem length L increases over time as the cultivated plant Q grows. When the next flower cluster 53 differentiates from the main stem 51 and blooms (the flowering state changes from stage #0 to stage #1), the flowering position calculation unit 23 uses a different flower cluster 53 for calculation, and therefore the main stem length L changes to a shorter value. Even if the cultivated plant Q is growing properly, if the main stem length L increases over time and the growth balance determination unit 26A represents the growth status with a main stem length discrimination value Gb (first discrimination value) that falls outside the indicator range G, it may be inconvenient. For this reason, the growth balance determination unit 26A weights the main stem length L according to the flowering stage of the flower cluster 53.

[0102] As shown in Figure 7, the weight coefficient α is used differently depending on the flowering stage of the inflorescence 53. When the flowering stage of the inflorescence 53 is Stage #1, the main stem length L is converted to the value of 'L × α²'. When the flowering stage of the inflorescence 53 is Stage #2, the main stem length L is converted to the value of 'L × α³'. When the flowering stage of the inflorescence 53 is Stage #3, the main stem length L is converted to the value of 'L × α⁴'. When the flowering stage of the inflorescence 53 is Stage #4, the main stem length L is converted to the value of 'L × α⁵'. The main stem length L converted based on the weight coefficient α is then plotted on the graph shown in Figure 9. In other words, the growth balance determination unit 26A determines the growth status of the cultivated plant Q (calculates data values ​​related to the growth status) by performing weight conversion according to which stage the flowering stage of the inflorescence 53 is. Furthermore, if the flowering status of multiple flowers in the inflorescence 53 differs, weight transformation is performed according to the proportion of flowers in stage #1, stage #2, stage #3, and stage #4. For example, if in one inflorescence 53, the proportion of flowers in stage #1 is 25%, the proportion of flowers in stage #2 is 35%, the proportion of flowers in stage #3 is 30%, and the proportion of flowers in stage #4 is 10%, then the main stem length L is weight transformed using, for example, the following formula. "L × (α2 × 0.25 + α3 × 0.35 + α4 × 0.3 + α5 × 0.1)"

[0103] The method for determining the main stem length discrimination value Gb will be explained based on the flowchart in Figure 11. The flowering position calculation unit 23 calculates the main stem length L (step #21), and the flowering state discrimination unit 24 determines the flowering stage of the flower cluster 53 (step #22). Then, the growth balance determination unit 26A transforms the main stem length L with a weighting coefficient α corresponding to the flowering stage (step #23), and determines the main stem length discrimination value Gb based on the graph shown in Figure 9 (step #24).

[0104] In this way, the growth balance determination unit 26A determines the growth status of the cultivated plant Q based on the condition of the main stem 51 and the flower cluster 53 (calculates data values ​​related to the growth status). The growth balance determination unit 26A then transmits the stem diameter discrimination value Ga, the main stem length discrimination value Gb, and the tree vigor discrimination value Gc to the irrigation control unit 11A, the fertilization control unit 12A, the solar radiation control unit 13A, and the carbon dioxide amount control unit 14A, etc. The stem diameter discrimination value Ga, the main stem length discrimination value Gb, and the tree vigor discrimination value Gc are numerical representations of the growth status of the cultivated plant Q.

[0105] The irrigation control unit 11A controls irrigation based on the growth status of the cultivated plant Q. If at least one of the following conditions is met: the stem diameter D2 is thick, the main stem length L is long, or the cultivated plant Q is vigorous, the irrigation control unit 11A controls the irrigation device 11B and the spray device 11C to reduce the amount of water supplied to the cultivated plant Q.

[0106] If at least one of the following conditions is met: the stem diameter D2 is thin, the main stem length L is short, or the vigor of the cultivated plant Q is weak, the irrigation control unit 11A controls the irrigation device 11B and the spraying device 11C to increase the amount of irrigation water supplied to the cultivated plant Q.

[0107] The solar radiation control unit 13A controls the amount of solar radiation based on the growth status of the cultivated plant Q. If at least one of the following conditions is met: the stem diameter D2 is thick, or the cultivated plant Q is vigorous, the solar radiation control unit 13A drives the curtain opening and closing device 13B so that the shading curtain blocks sunlight. This suppresses photosynthesis in the cultivated plant Q and reduces its vigor.

[0108] If the stem diameter D2 is thin, or if the vigor of the cultivated plant Q is weak, the solar radiation control unit 13A drives the curtain opening / closing device 13B to open the shading curtain. This promotes photosynthesis in the cultivated plant Q and strengthens its vigor.

[0109] The fertilizer control unit 12A controls the amount of fertilizer applied based on the growth status of the cultivated plant Q. The carbon dioxide control unit 14A controls the amount of carbon dioxide based on the growth status of the cultivated plant Q. If at least one of the following conditions is met, namely the stem diameter D2 is thick or the cultivated plant Q is vigorous, the fertilizer control unit 12A will not operate the fertilizer application device 12B. Also, if at least one of the following conditions is met, namely the stem diameter D2 is thick or the cultivated plant Q is vigorous, the carbon dioxide control unit 14A will not operate the carbon dioxide generator 14B.

[0110] If at least one of the following conditions is met: the stem diameter D2 is thin, or the cultivated plant Q is weak, the fertilization control unit 12A activates the fertilizer applicator 12B. Also, if at least one of the following conditions is met: the stem diameter D2 is thin, or the cultivated plant Q is weak, the carbon dioxide amount control unit 14A activates the carbon dioxide generator 14B.

[0111] [Determination of future growth status by the growth prediction unit] In this embodiment, the management computer 2 is equipped with a growth prediction and determination unit 26B. The growth prediction and determination unit 26B determines the future growth status of the branches and leaves 52 based on the stem diameter D2 of the main stem 51 (calculates data values ​​related to the growth status).

[0112] Specifically, as shown in Figure 12, at the moment when the branch and leaf portions 52 begin to differentiate from the main stem 51, a small branch and leaf portion 52 (hereinafter referred to as "first branch and leaf portion 52A") is imaged by the imaging device 3A, and the first branch and leaf portion 52A is then recognized by the recognition unit 21. The recognition unit 21 recognizes the first branch and leaf portion 52A, which has begun to differentiate from the upper part of the main stem 51, among the multiple branch and leaf portions 52 present in the cultivated plant Q.

[0113] Flower clusters 53 develop flowers, fruit clusters 54 ripen on the flower clusters 53, and the fruit clusters 54 are harvested when they reach an appropriate size. Branches and leaves 52 near the flower clusters 53 from which the fruit clusters 54 have been harvested are removed. The growth prediction and determination unit 26B acquires the stem diameter D2 calculated by the stem diameter calculation unit 22 at the time when the first branch and leaf section 52A begins to be recognized by the recognition unit 21. Based on the stem diameter D2, the growth prediction and determination unit 26B then determines the growth status of the first branch and leaf section 52A at the time of removal. The time when the first branch and leaf section 52A is removed is usually about five weeks from the time when it begins to differentiate from the upper part of the main stem 51. Figure 12 shows the second branch and leaf section 52B at the time of removal.

[0114] The growth prediction and judgment unit 26B predicts the leaf area of ​​the first branch and leaf section 52A at the time when the leaves of the first branch and leaf section 52A will be removed, as a future growth condition of the first branch and leaf section 52A. The leaf area is the area of ​​the densely growing region of the first branch and leaf section 52A. In other words, the growth prediction and judgment unit 26B calculates the future area of ​​the densely growing region of the branch and leaf section 52 based on the stem diameter D2. The area of ​​the densely growing region may be the total surface area of ​​multiple leaves in the first branch and leaf section 52A, or it may be the average or median of the surface areas of multiple leaves in the first branch and leaf section 52A. Since the area of ​​the densely growing region (including the leaf area) is an important element in understanding the growth rate and management status of the plant, workers and managers, for example, can use the area of ​​the densely growing region as a criterion for managing the cultivated plant Q.

[0115] Figure 13 shows a scatter plot illustrating the relationship between stem diameter D2 and the average leaf area after five weeks. In Figure 13, the points corresponding to the stem diameter D2 and average leaf area of ​​multiple cultivated plants Q in the first furrow A are indicated by circles. The approximation line between these points is shown as a solid line. The correlation coefficient between these points is 0.76.

[0116] Figure 13 shows the plotted points of the average stem diameter D2 and leaf area of ​​multiple cultivated plants Q in the second furrow A, indicated by triangles. The dashed line in Figure 13 represents the approximate line of these triangular plotted points. The correlation coefficient of these triangular plotted points is 0.71.

[0117] Figure 13 shows the plotted points corresponding to the average stem diameter D2 and leaf area of ​​multiple cultivated plants Q in the third furrow A, indicated by diamond marks. The dashed line in Figure 13 represents the approximate line of these diamond-marked plotted points. The correlation coefficient of these diamond-marked plotted points is 0.5.

[0118] The first furrow A is one or more predetermined furrows A1 to A8 shown in Figure 1. The second furrow A is one or more predetermined furrows A other than the first furrow A among the furrows A1 to A8 shown in Figure 1. The third furrow A is one or more predetermined furrows A other than the first furrow A and other than the second furrow A among the furrows A1 to A8 shown in Figure 1.

[0119] From the above, a positive correlation is observed between stem diameter D2 and the average leaf area after five weeks. In other words, the thicker the stem diameter D2, the larger the leaf area after five weeks tends to be. This correlation can be used to calculate a predicted value of the future leaf area (e.g., after five weeks) based on the stem diameter D2. The calculation of the future leaf area by the growth prediction and judgment unit 26B may be performed using a simple linear function, other functions, or a neural network (so-called artificial intelligence) generated by machine learning.

[0120] Leaf area can vary because it is affected by factors other than stem diameter D2, such as solar radiation, temperature, carbon dioxide concentration, and irrigation rate. For this reason, the growth prediction and judgment unit 26B may be configured to construct a model function that takes into account stem diameter D2, solar radiation, temperature, carbon dioxide concentration, and irrigation rate, and to calculate the future leaf area (the area of ​​the future dense growth region) based on this model function. Alternatively, stem diameter D2, solar radiation, temperature, carbon dioxide concentration, and irrigation rate may be used as input values ​​for a neural network, and the future leaf area (the area of ​​the future dense growth region, for example, five weeks from now) may be identified by mechanical deep learning. With this configuration, the growth prediction and judgment unit 26B can calculate the future leaf area (the area of ​​the future dense growth region) based on stem diameter D2, solar radiation, temperature, carbon dioxide concentration, and irrigation rate, using artificial intelligence.

[0121] Furthermore, the growth prediction and determination unit 26B may be configured to calculate the future number of leaves in the branch and leaf section 52 based on the calculated area of ​​the future dense growth region in the branch and leaf section 52.

[0122] The growth prediction and determination unit 26B predicts the leaf length at the time when the first branch and leaf section 52A will be pruned, as a future growth condition for the first branch and leaf section 52A. Leaf length is the length from any point at the base of each leaf in the first branch and leaf section 52A to the tip of the leaf. The leaf length may be the maximum value of the leaf lengths of multiple leaves in the first branch and leaf section 52A, or it may be the average or median value of the leaf lengths of multiple leaves in the first branch and leaf section 52A.

[0123] Since it is obvious that larger leaves result in larger leaves, there is a positive correlation between leaf length and leaf area. Furthermore, as mentioned above, there is a positive correlation between stem diameter D2 and leaf area, so it can be recognized that there is also a positive correlation between stem diameter D2 and leaf length. This correlation can be used to calculate a predicted value for future leaf length based on stem diameter D2. The calculation of future leaf length by the growth prediction and judgment unit 26B may be performed using a simple linear function, other functions, or a neural network generated by machine learning.

[0124] Furthermore, leaf length can vary because it is affected by factors other than stem diameter D2, such as solar radiation, temperature, carbon dioxide concentration, and irrigation volume. For this reason, the growth prediction and determination unit 26B may be configured to construct a model function that takes into account stem diameter D2, solar radiation, temperature, carbon dioxide concentration, and irrigation volume, and to calculate future leaf length based on this model function. Alternatively, the growth prediction and determination unit 26B may be configured to calculate future leaf length based on stem diameter D2, solar radiation, temperature, carbon dioxide concentration, and irrigation volume using artificial intelligence.

[0125] Furthermore, the growth prediction and determination unit 26B is configured to calculate at least one of the number of leaves to be removed and the number of fruits to be removed based on the area of ​​the future dense growth region (future leaf area) in the determined branch and leaf section 52. The number of leaves to be removed is, for example, the number of leaves appropriate for removal at the time when the first branch and leaf section 52A is to be removed. The number of fruits to be removed is, for example, the number of fruits appropriate for removal in the flower cluster section 53 near the first branch and leaf section 52A. If the vigor of the cultivated plant Q is too strong, so-called vine overgrowth and blossom end rot are likely to occur, resulting in a decrease in yield and an irregular shape of the fruit. For this reason, leaf removal and fruit removal are performed to prevent the vigor of the cultivated plant Q from becoming too strong. Since a larger leaf area indicates stronger vigor, it is preferable to increase the number of leaves to be removed and the number of fruits to be removed as the leaf area increases. In other words, it is preferable for the growth prediction and determination unit 26B to calculate a larger number of leaves to be removed and the number of fruits to be removed as the area of ​​the future dense growth region (future leaf area) increases.

[0126] At least one of the future number of leaves, the number of leaves removed, and the number of fruits removed in the branch and leaf section 52 is displayed on a known display monitor, for example, provided in the management computer 2. Therefore, for example, the manager can appropriately manage the cultivated plant Q based on the number of leaves, the number of leaves removed, and the number of fruits removed, respectively, displayed on the display monitor. The growth prediction and determination unit 26B may also be configured to calculate at least one of the number of leaves removed and the number of fruits removed based on the determined future number of leaves in the branch and leaf section 52.

[0127] In addition, the growth prediction and determination unit 26B may calculate the distribution degree, variance degree, standard deviation, skewness, kurtosis, etc., of the leaf length and leaf area of ​​each leaf in the first branch and leaf section 52A of multiple cultivated plants Q as future growth conditions in the first branch and leaf section 52A. Furthermore, the growth prediction and determination unit 26B may also be configured to calculate the yield of fruit clusters 54 near the branch and leaf section 52, such as the first branch and leaf section 52A, as future growth conditions in the first branch and leaf section 52A.

[0128] Figure 14 shows a scatter plot illustrating the relationship between the average leaf area two weeks after the appearance of a flower cluster and the fruit yield from that flower cluster 12 weeks after its appearance. Tomatoes complete harvesting from a flower cluster 12 weeks after its appearance. In Figure 14, the plotted points for the average leaf area and fruit yield are indicated by circles. The approximate straight line for these plotted points is shown as a dashed line. The correlation coefficient for these plotted points is 0.7.

[0129] Based on the above, a positive correlation is observed between the average leaf area two weeks after the appearance of the flower cluster and the fruit yield from that flower cluster. In other words, the larger the leaf area, the greater the fruit yield tends to be. This relationship can be understood as follows: The larger the leaves, the greater the amount of photosynthesis in the cultivated plant Q, and the easier it is for photosynthetic products to be supplied to the fruit. Therefore, it is thought that the larger the leaf area, the greater the fruit yield.

[0130] Furthermore, as mentioned above, since there is a positive correlation between stem diameter D2 and leaf area, there is also a positive correlation between stem diameter D2 and fruit yield. In other words, the thicker the stem diameter D2, the greater the fruit yield tends to be. This correlation can be used to calculate a predicted fruit yield based on stem diameter D2. The calculation of future yield by the growth prediction and judgment unit 26B may be performed using a simple linear function, other functions, or a neural network generated by machine learning.

[0131] Figure 15 shows a scatter plot illustrating the relationship between the main stem length L of multiple cultivated plants Q in a given furrow A and the average number of fruits harvested from the 11th to 13th inflorescences 53 from the bottom. In Figure 15, the plotted points based on the main stem length L after weight transformation using the weight coefficient α described above are indicated by triangles. Also in Figure 15, the plotted points based on the main stem length L before weight transformation using the weight coefficient α described above are indicated by circles.

[0132] Figure 15 shows a solid line representing the approximate line for the plotted points marked with circles. The correlation coefficient for these plotted points is 0.45. Also in Figure 15, the dashed line represents the approximate line for the plotted points marked with triangles. The correlation coefficient for these plotted points is 0.66.

[0133] Figure 16 shows a scatter plot illustrating the relationship between the main stem length L of multiple cultivated plants Q in a given furrow A and the average harvest weight of the fruit from the 11th to 13th flower clusters 53 from the bottom. In Figure 16, the plotted points based on the main stem length L after weight transformation using the weight coefficient α described above are indicated by triangles. Also in Figure 16, the plotted points based on the main stem length L before weight transformation using the weight coefficient α described above are indicated by circles.

[0134] Figure 16 shows a solid line representing the approximate line for the plotted points marked with circles. The correlation coefficient for these plotted points is 0.2. Also in Figure 16, the dashed line represents the approximate line for the plotted points marked with triangles. The correlation coefficient for these plotted points is 0.4.

[0135] A positive correlation is observed between the main stem length L before weighting transformation using the aforementioned weighting coefficient α and the average number of fruits harvested. Furthermore, a positive correlation is observed between the main stem length L after weighting transformation using the aforementioned weighting coefficient α and the average number of fruits harvested. In other words, as the main stem length L after weighting transformation using the weighting coefficient α increases, the average number of fruits harvested tends to increase.

[0136] Furthermore, a positive correlation is observed between the main stem length L before weighting transformation using the aforementioned weighting coefficient α and the average harvest weight of the fruit. Additionally, a positive correlation is observed between the main stem length L after weighting transformation using the aforementioned weighting coefficient α and the average harvest weight of the fruit. This suggests that as the main stem length L increases, the average harvest weight of the fruit tends to increase.

[0137] By utilizing this correlation, it is possible to calculate predicted values ​​for the number of fruits to be harvested in the future and the harvest weight based on the main stem length L (especially the main stem length L after weight transformation using the weight coefficient α). The calculation of the predicted number of fruits to be harvested and the harvest weight by the growth prediction and judgment unit 26B may be performed using a simple linear function, other functions, or a neural network (so-called artificial intelligence) generated by machine learning.

[0138] Furthermore, fruit yield can vary because it is affected not only by stem diameter D2 and main stem length L, but also by factors such as solar radiation, temperature, carbon dioxide concentration, and irrigation level. For this reason, the growth prediction and determination unit 26B may be configured to construct a model function that takes into account stem diameter D2, solar radiation, temperature, carbon dioxide concentration, and irrigation level, and to calculate the future fruit yield based on this model function. Alternatively, stem diameter D2, main stem length L, solar radiation, temperature, carbon dioxide concentration, and irrigation level may be used as input values ​​for a neural network, and the future yield (for example, 12 weeks later) may be identified through mechanical deep learning. With this configuration, the growth prediction and determination unit 26B can calculate the future yield based on stem diameter D2, main stem length L, solar radiation, temperature, carbon dioxide concentration, and irrigation level, using artificial intelligence.

[0139] Then, similar to when data is sent from the growth balance determination unit 26A, the temperature control unit 15A, humidity control unit 16A, irrigation control unit 11A, fertilization control unit 12A, solar radiation control unit 13A, and carbon dioxide control unit 14A, etc., perform control based on future growth conditions. The temperature control unit 15A performs temperature control based on future growth conditions. The humidity control unit 16A performs humidity control based on future growth conditions. The irrigation control unit 11A performs irrigation control based on future growth conditions. The solar radiation control unit 13A performs solar radiation control based on future growth conditions. The fertilization control unit 12A performs fertilization amount control based on future growth conditions. The carbon dioxide control unit 14A performs carbon dioxide amount control based on future growth conditions.

[0140] [Another embodiment] The present invention is not limited to the configurations exemplified in the embodiments described above, and other representative embodiments of the present invention are described below.

[0141] (1) The growth determination unit 26 described above is configured to determine the growth status (calculate data values ​​related to the growth status) by performing weight conversion according to which stage the flowering state is, but the growth determination unit 26 may also be configured not to perform said weight conversion.

[0142] (2) In the embodiments described above, the horticultural facility 1 and the management computer 2 are connected via a wide-area communication network (WAN), but the embodiments are not limited to those described above. The management computer 2 may be installed in the horticultural facility 1, and equipment such as the visual sensing unit 3 in the horticultural facility 1 may be connected to the management computer 2 via a network within the facility. The network within the facility may be a wired connection or a wireless connection.

[0143] (3) In the embodiments described above, tomatoes are given as an example of cultivated plants Q, but the plant Q is not limited to tomatoes and may be strawberries, melons, cucumbers, eggplants, gourds, bitter melons, bell peppers, etc. Furthermore, the plant Q is not limited to cultivated plants Q inside the horticultural facility 1, but may be cultivated plants Q outdoors. Moreover, the ridge A does not have to be a non-porous hydrophilic film, but may be topsoil.

[0144] (4) The growth determination unit 26 described above can output statistical quantities that allow for understanding the growth status, not limited to stem diameter discrimination value Ga, main stem length discrimination value Gb, tree vigor discrimination value Gc, and future growth status of the branches and leaves 52, in addition to the growth status data.

[0145] (5) In the example in Figure 9, the index range G is defined by an upper limit (boundary with +Ga1 and +Gb1) and a lower limit (boundary with -Ga1 and -Gb1), but it may also be defined by a central value and a width. Furthermore, the index range G may be a square, rectangle, circle, or ellipse, as in the example in Figure 9.

[0146] Furthermore, the configurations disclosed in the above-described embodiments (including other embodiments, the same applies hereinafter) can be applied in combination with configurations disclosed in other embodiments, as long as no inconsistencies arise. In addition, the embodiments disclosed herein are illustrative, and the embodiments of the present invention are not limited thereto, and can be modified as appropriate without departing from the object of the present invention. [Industrial applicability]

[0147] This invention can be applied to a growth management system for managing the growth status of cultivated plants. [Explanation of Symbols]

[0148] 3A: Imaging device 11A: Irrigation Control Unit 13A: Solar radiation control unit 14A: Carbon dioxide amount control unit 21: Recognition part 24: Flowering state determination unit 26:Growth Judgment Department 51: Main stem 52: Branches and leaves 53: Inflorescence part 54: Fruit bunch D2: Stem diameter G: Indicator range (third discriminant value) Ga: Stem diameter discrimination value (second discrimination value) Gb: Main stem length discriminant value (first discriminant value) Gc: Tree vigor discrimination value L: Main stem length (length of the main stem) Q: Cultivated plants

Claims

1. A growth management system for managing the growth status of cultivated plants, An imaging device for imaging the aforementioned cultivated plants, A recognition unit that recognizes the main stem, the branch and leaf parts differentiated from the main stem, and the flower cluster parts differentiated from the main stem of the cultivated plant as captured in the image acquired by the imaging device, A growth management system comprising: a growth determination unit that determines the growth status based on the state of the main stem and the flower cluster;

2. The recognition unit is configured to recognize the fruit clusters that develop from the flower clusters. The growth management system according to claim 1, wherein the growth determination unit is configured to represent the growth status with a first discriminant value that indicates a bias between vegetative growth, in which the main stem and the branches and leaves grow, and reproductive growth, in which the fruit cluster grows.

3. The growth management system according to claim 2, wherein the growth determination unit is configured to represent the growth status with a second discriminant value indicating the growth rate of the main stem and the branches and leaves.

4. The growth determination unit is configured to represent the growth status with a third discriminant value indicating which of a plurality of regions on a plane with the first discriminant value and the second discriminant value as axes the growth status belongs to.

5. The growth determination unit is configured to determine the future growth status based on the stem diameter of the main stem, according to any one of claims 1 to 4.

6. The growth determination unit is configured to determine the future growth status based on the main stem length, which indicates the length of the main stem between the upper end of the main stem and the flower cluster in a bloomed state, according to any one of claims 1 to 4.

7. The system is equipped with a flowering state determination unit that determines the flowering state of the flower cluster in multiple stages. The growth determination unit is configured to determine the growth status by performing weight conversion according to which stage the flowering state is in, according to any one of claims 1 to 4.

8. The growth determination unit is configured to determine the growth status based on the stem diameter of the main stem, according to any one of claims 1 to 4.

9. The growth determination unit is configured to determine the growth status based on the main stem length, which indicates the length of the main stem between the upper end of the main stem and the flower cluster in a bloomed state, according to any one of claims 1 to 4.

10. A growth management system according to any one of claims 1 to 4, further comprising an irrigation control unit that controls irrigation based on the aforementioned growth status.

11. A growth management system according to any one of claims 1 to 4, further comprising a solar radiation control unit that controls the amount of solar radiation based on the aforementioned growth conditions.

12. A growth management system according to any one of claims 1 to 4, further comprising a carbon dioxide control unit that controls the amount of carbon dioxide based on the aforementioned growth conditions.

Images