Cultivation management system and growth management system

Abstract

This cultivation management system comprises: an imaging unit that captures an image of a cultivation plant (P); a state detection unit that detects the state of a flower cluster (D) of the cultivation plant (P) on the basis of the captured image acquired by the imaging unit; a separation detection unit that detects, on the basis of the captured image, a separation index value that is a value indicating the degree of separation between a stem apex (B) of the cultivation plant (P) and the flower cluster (D); and an index output unit that outputs a growth index, which is an index indicating the growth state of the cultivation plant (P), on the basis of the detection result from the state detection unit and the detection result from the separation detection unit.

Description

Cultivation management system and growth management system

[0001] The present invention relates to a cultivation management system.

[0002] The present invention also relates to a growth management system for cultivated plants.

[0003] [1] The cultivation management system described in Patent Document 1 (referred to as an "irrigation control system" in Patent Document 1) is configured to irrigate cultivated plants according to the degree of leaf firmness.

[0004] [2] For example, Patent Document 2 discloses a cultivation facility that controls the temperature of a greenhouse based on the growth status of the growing point of a cultivated plant (referred to as a "plant stock" in the document).

[0005] Japanese Patent Publication No. 2007-306846 Japanese Patent Publication No. 2011-19438

[0006] [1] The problem corresponding to Background Art [1] is as follows: Patent Document 1 does not include any description of evaluating the growth state of cultivated plants (for example, the degree of bias toward reproductive growth or vegetative growth).

[0007] An object of the present invention is to provide a cultivation management system capable of evaluating the growth state of cultivated plants.

[0008] [2] Another problem corresponding to the background art [1] is as follows: Patent Document 1 does not describe detecting fruit clusters on cultivated plants.

[0009] An object of the present invention is to provide a cultivation management system capable of detecting fruit clusters of cultivated plants with high accuracy.

[0010] [3] The problem corresponding to Background Art [2] is as follows. To grasp the growth status of a cultivated plant, it is desirable to recognize the main parts of the cultivated plant. With the configuration disclosed in Patent Document 2, the growth status near the growing point is measured. Since the appearance (pattern and color) and shape near the growing point tend to change more drastically than the main parts of the cultivated plant, it is difficult to grasp the growth status of the cultivated plant based on the condition near the growing point. The main stem is a particularly useful main part of a cultivated plant, and recognizing the main stem is useful for building a useful growth management system.

[0011] The present invention provides a growth management system capable of calculating data relating to essential parts of cultivated plants.

[0012] [1] The solution to problem [1] is as follows: The present invention is characterized by comprising an imaging unit that captures an image of a cultivated plant, a state detection unit that detects the state of an inflorescence of the cultivated plant based on the captured image acquired by the imaging unit, a separation detection unit that detects a separation index value that is a value indicating the degree of separation between the stem apex of the cultivated plant and the inflorescence based on the captured image, and an index output unit that outputs a growth index that is an index indicating the growth state of the cultivated plant based on the detection results by the state detection unit and the detection results by the separation detection unit.

[0013] According to this configuration, a growth index is output based on the detection results from the state detection unit and the detection results from the separation detection unit. The inventors of the present application have found that the growth index output in this manner makes it possible to evaluate the growth status of cultivated plants (for example, the degree of bias toward reproductive growth or vegetative growth). Therefore, according to this configuration, a cultivation management system capable of evaluating the growth status of cultivated plants can be realized.

[0014] Furthermore, in the present invention, it is preferable that the state detection unit detects the flowering stage of each flower in the inflorescence.

[0015] According to this configuration, a growth index is output based on the flowering stage of each flower in the inflorescence and the detection result by the separation detection unit. The inventors of the present application have found that the growth index output in this manner makes it easy to accurately evaluate the growth state of cultivated plants (e.g., the degree of bias toward reproductive growth or vegetative growth). Therefore, according to this configuration, a cultivation management system can be realized that makes it easy to accurately evaluate the growth state of cultivated plants.

[0016] Furthermore, in the present invention, the index output unit has an identification unit that identifies a reference inflorescence, which is the inflorescence in a predetermined flowering state, based on the detection result by the state detection unit, and the separation detection unit is configured to detect a reference separation index value, which is a value indicating the degree of separation between the stem tip and the reference inflorescence, and it is preferable that the index output unit outputs the growth index based on the reference separation index value.

[0017] According to this configuration, when comparing a growth index for a cultivated plant whose growth state is being evaluated with a growth index to be compared (e.g., a past growth index for the same cropping season, a growth index for a past cropping season, a growth index from last year, a growth index for a plant cultivated in another facility, a standard growth index, etc.), these growth indexes can be output based on the reference distance index value. This allows comparison to be made after the flowering conditions of the inflorescences are consistent. As a result, it becomes easier to accurately evaluate the growth state of cultivated plants.

[0018] Furthermore, in the present invention, the index output unit has an estimation unit that estimates a value indicating the degree of separation between the stem apex and the inflorescence at the time when the inflorescence was in the specified flowering state based on the flowering stage of each flower in the inflorescence that is more advanced in flowering than the specified flowering state and the detection result by the separation detection unit, and it is preferable that the index output unit outputs the growth index based on the estimation result by the estimation unit.

[0019] According to this configuration, when comparing a growth index for a cultivated plant whose growth state is being evaluated with a growth index to be compared with (for example, a past growth index for the same cropping season, a growth index for a past cropping season, a growth index from last year, a growth index for a plant cultivated in another facility, a standard growth index, etc.), the comparison can be performed after aligning the conditions for the flowering state of the inflorescence. As a result, it becomes easier to accurately evaluate the growth state of the cultivated plant.

[0020] Furthermore, in the present invention, it is preferable that the specified flowering state is a state in which there is only one flower at a reference flowering stage, which is a specified flowering stage, in one inflorescence, and there are no flowers that are at a more advanced stage of flowering than the reference flowering stage.

[0021] According to this configuration, the period during which the inflorescence remains in the predetermined flowering state is relatively short. Therefore, when comparing the growth index of the cultivated plant being evaluated with a comparison index (e.g., past growth indexes for the same growing season, growth indexes for previous growing seasons, growth indexes from last year, growth indexes for plants cultivated in other facilities, standard growth indexes, etc.), it is easy to accurately align the inflorescence state conditions. This allows for a cultivation management system that can easily and accurately evaluate the growth state of cultivated plants.

[0022] Furthermore, in the present invention, it is preferable that the separation detection unit detects the length of the stem between the stem apex and the pedicel corresponding to the inflorescence as the separation index value.

[0023] According to this configuration, a growth index is output based on the length of the stem between the shoot apex and the pedicel corresponding to the inflorescence. The inventors of the present application have found that the growth index output in this manner makes it easy to accurately evaluate the growth status of cultivated plants (e.g., the degree of bias toward reproductive growth or vegetative growth). Therefore, according to this configuration, a cultivation management system can be realized that makes it easy to accurately evaluate the growth status of cultivated plants.

[0024] [2] The solution to problem [2] is as follows: The present invention is characterized by comprising an imaging unit that captures an image of a cultivated plant, a fruit detection unit that detects the fruit of the cultivated plant based on the captured image acquired by the imaging unit, and a fruit cluster detection unit that detects the fruit cluster of the cultivated plant based on the detection result by the fruit detection unit.

[0025] According to this configuration, fruit is detected based on a captured image of a cultivated plant. Then, fruit clusters are detected based on the fruit detection results. The inventors of the present application have found that this configuration allows for accurate detection of fruit clusters on cultivated plants. Therefore, this configuration makes it possible to realize a cultivation management system that can accurately detect fruit clusters on cultivated plants.

[0026] Furthermore, in the present invention, it is preferable to provide an identification unit that identifies a reference bunch, which is a bunch that satisfies predetermined conditions, from among the bunches detected by the bunch detection unit, and a measurement unit that measures the number of fruits contained in the reference bunch.

[0027] According to this configuration, by appropriately setting the predetermined conditions, it is possible to predict with high accuracy the number of fruits that will be harvestable in the future, which makes it easier to predict the amount of work that will be required in the future.

[0028] Furthermore, in the present invention, it is preferable that the predetermined condition is that the fruit truss is a predetermined number of stages above the fruit truss located closest to the roots on the cultivated plant.

[0029] According to this configuration, it is easy to predict with high accuracy the number of fruits that will be ready for harvest in the relatively near future (for example, two weeks from now), which makes it easy to predict the amount of work to be done in the relatively near future.

[0030] Furthermore, in the present invention, it is preferable that a stem detection unit is provided that detects the stem of the cultivated plant based on the captured image, and the identification unit identifies the reference bunch based on the detection results by the bunch detection unit and the detection results by the stem detection unit.

[0031] According to this configuration, when multiple cultivated plants (multiple plants) are captured in a captured image, it is possible to identify which cultivated plant (plant) each bunch belongs to based on the positional relationship between the bunch and the stem. This makes it easier to properly identify the reference bunch compared to a configuration that cannot identify which cultivated plant (plant) each bunch belongs to.

[0032] [3] The solution to problem [3] is as follows: The present invention is a growth management system for managing the growth status of cultivated plants, characterized in that it includes an imaging device that images the cultivated plants, a recognition unit that recognizes a main stem of the cultivated plants that is captured in the image acquired by the imaging device, and a stem diameter calculation unit that calculates the stem diameter of the main stem recognized by the recognition unit.

[0033] According to the present invention, the recognition unit recognizes the main stem. The main stem is a key part of a cultivated plant that serves as a criterion for determining the growth status. The stem diameter of this key part, the main stem, is calculated, making it easy to determine the growth status of the cultivated plant based on the stem diameter. Thus, the present invention realizes a growth management system that can calculate data related to key parts of a cultivated plant.

[0034] In the present invention, it is preferable that the stem diameter calculation unit is configured to calculate the stem diameter of a portion of the main stem that is a predetermined length below a reference height of the cultivated plant.

[0035] According to this configuration, a reference height for the cultivated plant is set, and the stem diameter of the main stem located a predetermined length below the reference height is calculated. This allows the stem diameter of the reference portion of the main stem to be calculated, making it easier to determine the growth status of the cultivated plant.

[0036] In the present invention, it is preferable that the recognition unit is configured to be able to recognize an inflorescence portion differentiated from the upper part of the main stem, and the stem diameter calculation unit is configured to define the position of the inflorescence portion as the reference height when the recognition unit recognizes the inflorescence portion at the upper part of the cultivated plant, and to define the position of the upper end of the main stem as the reference height when the recognition unit does not recognize the inflorescence portion at the upper part of the cultivated plant.

[0037] Depending on the state of overgrowth at the top of the cultivated plant, which part is suitable as the reference height changes. With this configuration, if an inflorescence is recognized at the top of the cultivated plant, the vertical position corresponding to the inflorescence is defined as the reference height. Furthermore, if an inflorescence is not recognized at the top of the cultivated plant, the vertical position of the upper end of the main stem is defined as the reference height. With this configuration, even if the state of overgrowth at the top varies greatly between multiple cultivated plants, variation in the vertical position set as the reference height is unlikely to occur. As a result, variation is unlikely to occur in the part of the main stem from which the stem diameter is calculated.

[0038] In the present invention, it is preferable that the stem diameter calculation unit is configured to define the position of the tallest flower as the reference height when the recognition unit recognizes multiple flowers in the inflorescence portion at the top of the cultivated plant.

[0039] This configuration reduces variation in the vertical position set as the reference height, and reduces variation in the location on the main stem where the stem diameter is calculated.

[0040] In the present invention, it is preferable that the stem diameter calculation unit is configured to calculate an approximation curve of the main stem recognized by the recognition unit and calculate the stem diameter in the normal direction or approximately normal direction of the approximation curve.

[0041] With this configuration, even if the main stem has a complex curved shape, the main stem is simplified as an approximate curve, making it easier to calculate the stem diameter.

[0042] In the present invention, it is preferable that a distance measuring device is provided that acquires distance data in three-dimensional coordinates for the cultivated plant imaged by the imaging device, and the stem diameter calculation unit is configured to calculate the stem diameter of the main stem recognized by the recognition unit based on the three-dimensional coordinates.

[0043] This configuration improves the accuracy of calculating the stem diameter.

[0044] In the present invention, the recognition unit is preferably configured to be capable of detecting an inflorescence portion that has differentiated from the upper part of the main stem and is in a bloomed state, and is equipped with a growth determination unit that determines the growth status based on the length of the main stem between the upper end of the main stem and the inflorescence portion in a bloomed state.

[0045] With this configuration, the growth assessment unit can determine whether the cultivated plant is prone to nutrient deficiency or to vine droop, etc., based on the length of the main stem between the upper end of the main stem and the inflorescence portion in a bloomed state.

[0046] 13A and 13B are diagrams showing an example of an image captured by an imaging unit.

[0034] FIG. 13B are diagrams showing an example of an image captured by an imaging unit.

[0035] FIG. 13C are diagrams showing an example of an image captured by an imaging unit.

[0036] FIG. 13D are diagrams showing an example of an image captured by an imaging unit.

[0037] FIG. 13E are diagrams showing an example of an image captured by an imaging unit.

[0038] FIG. 13F are diagrams showing an example of an image captured by an imaging unit.

[0039] FIG. 13F are diagrams showing an example of an image captured by an imaging unit.

[0040] FIG. 13G are diagrams showing an example of an image captured by an imaging unit.

[0041] FIG. 13H are diagrams showing an example of an image captured by an imaging unit.

[0042] FIG. 13I are diagrams showing an example of an image captured by an imaging unit.

[0043] FIG. 13I are diagrams showing an example of an image captured by an imaging unit.

[0044] FIG. 13J are diagrams showing an example of an image captured by an imaging unit.

[0045] FIG. 13J are diagrams showing an example of an image captured by an imaging unit.

[0046] FIG. 13J are diagrams showing an example of an image captured by an imaging unit.

[0047] FIG. 13J are diagrams showing an example of an image captured by an imaging unit.

[0048] FIG. 13J are diagrams showing an example of an image captured by an imaging unit. FIG. 1 is a diagram showing the flowering state of an inflorescence and a weighting coefficient corresponding to the flowering state. FIG. 2 is a diagram showing an example of a method for calculating the length of the main stem (main stem length) from the stem apex to the branching point of a flowered inflorescence in a cultivated plant. FIG. 3 is a diagram showing an index range and discrimination values ​​in a graph with stem diameter and main stem length as axes. FIG. 4 is a flowchart showing a method for determining stem diameter discrimination values ​​and tree vigor discrimination values. FIG. 5 is a flowchart showing a method for determining main stem length discrimination values. FIG. 6 is a diagram showing an example of a method for determining the future growth status of a branch and leaf portion.

[0047] [First Embodiment] An embodiment of the present invention will be described with reference to the drawings. More specifically, the first embodiment will be described with reference to FIGS.

[0048] [Configuration of Horticultural Facility] An embodiment of the present invention will be described with reference to the drawings. In this embodiment, ridges A1 to A8 for planting cultivated plants P (see FIG. 2) are arranged vertically and horizontally in a horticultural facility 10 as shown in FIG. 1. Paths are provided between each ridge A for personnel responsible for caring for the cultivated plants P to pass through. The horticultural facility 10 may be, for example, a greenhouse or a solar-powered plant factory.

[0049] Each ridge A is made of, for example, a non-porous hydrophilic film. A cultivated plant P, such as a tomato, is planted in each ridge A. As shown in Figures 1 and 2, an imaging unit Ca is provided inside the horticultural facility 10. The number of imaging units Ca provided may be one, or two or more.

[0050] The imaging unit Ca is a fixed camera having, for example, a CCD element or a CMOS element, and is configured to be able to capture visible light that is visible to the naked eye. The imaging unit Ca then captures an image of the cultivated plant P.

[0051] More specifically, the imaging unit Ca is located at a position corresponding to the vertical center of the cultivated plant P. The imaging unit Ca is oriented horizontally and is directed toward the cultivated plant P on the ridge A1.

[0052] 3 shows an example of an image captured by the imaging unit Ca. This image captures a first individual P1, a second individual P2, and a third individual P3. The first individual P1, the second individual P2, and the third individual P3 are all cultivated plants P. This image also captures the shoot apex B and inflorescence D of each of the first individual P1, the second individual P2, and the third individual P3. The imaging unit Ca captures an image of the cultivated plant P so that the shoot apex B and inflorescence D of the cultivated plant P are captured in the image.

[0053] Although not shown, the horticultural facility 10 is also equipped with environmental sensors, side windows, blackout curtains, heat pump type air conditioning equipment, and the like.

[0054] [Configuration of the cultivation management system] As shown in Fig. 4, the cultivation management system S in this embodiment includes a management computer 2 and a display 3. The display 3 is capable of displaying various information. The display content on the display 3 is controlled by the management computer 2. The horticultural facility 10 is also included in the cultivation management system S.

[0055] That is, the cultivation management system S is equipped with an imaging unit Ca that captures images of the cultivated plants P.

[0056] [Regarding the Status Detection Unit] As shown in Fig. 4, the management computer 2 has a status detection unit 21. The status detection unit 21 receives captured images acquired by the imaging unit Ca. The status detection unit 21 detects the status of each inflorescence D of the cultivated plant P based on the captured images. More specifically, the status detection unit 21 detects the flowering stage of each flower in the inflorescence D.

[0057] It should be noted that the "flowering stage of each flower in the inflorescence D" is a specific example of the "state of the inflorescence D." The method by which the state detection unit 21 detects the flowering stage of each flower in the inflorescence D is not particularly limited, but the flowering stage of each flower in the inflorescence D may be detected by analyzing the captured image using a machine-learned neural network.

[0058] As described above, the cultivation management system S includes a state detection unit 21 that detects the state of the inflorescence D of the cultivated plant P based on the captured image acquired by the imaging unit Ca.

[0059] In this embodiment, the state detection unit 21 distinguishes the flowering stage of each flower from five stages: "not yet flowered," "early flowering," "mid-flowering," "late flowering," and "fruit bearing," as shown in Fig. 5. Flowering progresses in the order of "not yet flowered," "early flowering," "mid-flowering," "late flowering," and "fruit bearing."

[0060] Each flowering stage is assigned a flowering progress level represented by a symbol (e.g., a number or an alphabet). In this embodiment, the flowering progress levels for "not yet flowered," "early flowering," "mid-flowering," "late flowering," and "fruit setting" are FS0, FS1, FS2, FS3, and FS4, respectively.

[0061] "Unbloomed" means that the sepals have not split, or that the sepals have split but the petals are not visible.

[0062] In the "early flowering" stage, the sepals are split, the petals are visible, the tips of the sepals are pointing inward, the petals are not split, and the flower as a whole is nearly rectangular in shape.

[0063] In the "mid-flowering stage," the petals are split, the sepals are not curled outward, and the flower as a whole is bell-shaped.

[0064] In the "late flowering" stage, the sepals curl outward, and the petals also curl outward except in the morning.

[0065] "Fruit set" refers to the state in which fruit can be visually confirmed.

[0066] In this embodiment, a flower is considered to be in any of the following states: "unflowered," "early flowering," "mid-flowering," "late flowering," or "fruit-bearing," regardless of whether the petals are visible or not.

[0067] The state detection unit 21 individually detects the flowering stage of each flower in all of the inflorescences D that appear in the captured images acquired by the imaging unit Ca. In other words, the state detection unit 21 individually detects the flowering stage of each of the flowers that appear in the captured images acquired by the imaging unit Ca.

[0068] However, the present invention is not limited to this. The state detection unit 21 may detect the flowering stage of each flower for only some of the flower clusters D among the flower clusters D shown in the captured image acquired by the imaging unit Ca. Furthermore, the state detection unit 21 may detect the flowering stage for only some of the flowers among the flowers shown in the captured image acquired by the imaging unit Ca.

[0069] 6 shows an example of the detection result by the state detection unit 21. Here, the detection result of the flowering stage of each flower in the upper inflorescence D of the two inflorescences D of the first individual P1 is shown.

[0070] 6 has four flowers. The state detection unit 21 detects that the flowering stage of the uppermost flower is "early flowering" (in other words, the flowering stage is FS1), and that the flowering stages of all the other flowers are "not yet flowered" (in other words, the flowering stage is FS0).

[0071] The method of dividing the flowering stages (in other words, the definition of each flowering stage) and the number of stages are not limited to those described above, and may be changed as appropriate.

[0072] 4, the management computer 2 has an index output unit 22. The detection result by the status detection unit 21 is sent to the index output unit 22.

[0073] [Regarding the Length Detector] As shown in FIG. 4 , the management computer 2 has a length detector 23 (corresponding to the "separation detector" according to the present invention). The length detector 23 receives captured images acquired by the imaging unit Ca. The length detector 23 detects a separation index value based on the captured images. The separation index value is a value indicating the degree of separation between the shoot apex B and the inflorescence D of the cultivated plant P. In this embodiment, the length detector 23 detects the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D as the separation index value. In other words, the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D is a specific example of the separation index value. The longer the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D, the greater the separation between the shoot apex B and the inflorescence D.

[0074] In this way, the cultivation management system S is equipped with a length detection unit 23 that detects a distance index value, which is a value indicating the degree of distance between the stem tip B of the cultivated plant P and the inflorescence D, based on the captured image.

[0075] The method by which the length detection unit 23 detects the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D is not particularly limited, but the length may be detected by analyzing the captured image using a machine-learned neural network to recognize the shoot apex B and the pedicel E. Furthermore, information indicating the distance from the image capture unit Ca to the cultivated plant P may be used to detect the length. This information may be obtained, for example, by radar or the like.

[0076] For example, when the length detection unit 23 detects the length of the stem between the shoot apex B and the pedicel E of the first individual P1, the length detection unit 23 detects the detected length G1, as shown in Fig. 7. The detected length G1 is the length of the stem between the shoot apex B of the first individual P1 and the pedicel E corresponding to the upper one of the two inflorescences D of the first individual P1.

[0077] However, the present invention is not limited to this. That is, when the length detection unit 23 detects the length of the stem between the shoot apex B of the cultivated plant P and the pedicel E corresponding to the inflorescence D, the inflorescence D may be any inflorescence D on the cultivated plant P.

[0078] Furthermore, the length detection unit 23 may detect the stem lengths of only some of the cultivated plants P shown in the captured image acquired by the imaging unit Ca, or may detect the stem lengths of all of the cultivated plants P. Furthermore, the length detection unit 23 may detect the linear distance between the shoot apex B and the pedicel E (particularly, the base of the pedicel E) corresponding to the inflorescence D. The linear distance between the shoot apex B and the pedicel E (particularly, the base of the pedicel E) corresponding to the inflorescence D is a specific example of a distance index value. The longer the linear distance between the shoot apex B and the pedicel E (particularly, the base of the pedicel E) corresponding to the inflorescence D, the greater the distance between the shoot apex B and the inflorescence D.

[0079] As shown in FIG. 4, the detection result by the length detection unit 23 is sent to the index output unit 22 .

[0080] [Regarding the Index Output Unit] The index output unit 22 outputs a growth index based on the detection result by the state detection unit 21 and the detection result by the length detection unit 23. The growth index is an index that indicates the growth state of the cultivated plant P.

[0081] That is, the cultivation management system S is equipped with an index output unit 22 that outputs a growth index, which is an index indicating the growth state of the cultivated plant P, based on the detection results by the state detection unit 21 and the detection results by the length detection unit 23.

[0082] The growth index may be any index that indicates the growth state of the cultivated plant P. The growth index is preferably one that indicates the degree of bias toward reproductive growth or vegetative growth of the cultivated plant P. The degree of bias toward reproductive growth or vegetative growth of the cultivated plant P is a specific example of the growth state of the cultivated plant P.

[0083] Although not particularly limited, the index output unit 22 may output a growth index for some of the cultivated plants P (for example, one cultivated plant P) among the multiple cultivated plants P (in other words, all the cultivated plants P in the horticultural facility 10) that are managed by the cultivation management system S, or may output a growth index for all of the cultivated plants P. Furthermore, the index output unit 22 may output a growth index for one or more cultivated plants P selected as representatives of all of the cultivated plants P as the growth index for all of the cultivated plants P. Furthermore, the index output unit 22 may output a growth index for each of the multiple cultivated plants P individually (in other words, may output multiple growth indexes), or may output a single growth index as the growth index for the multiple cultivated plants P.

[0084] Although not particularly limited, the growth index may be a separation index value. Furthermore, the growth index may be the length of the stem between the shoot apex B of the cultivated plant P and the pedicel E corresponding to the inflorescence D, or may be a numerical value or classification determined based on the length. The numerical value may be, for example, a statistical value such as the average or median of a plurality of lengths corresponding to a plurality of cultivated plants P, or may be a numerical value representing the degree of bias toward reproductive growth or vegetative growth of the cultivated plant P. The classification may be, for example, one of the three classifications of "leaning toward reproductive growth," "well-balanced state," and "leaning toward vegetative growth" that corresponds to the state of the cultivated plant P.

[0085] 4 , the index output unit 22 controls the display content on the display 3. When the index output unit 22 outputs a growth index, the index output unit 22 displays the growth index on the display 3. This allows the user to check the growth index output by the index output unit 22.

[0086] In this embodiment, the management computer 2 (index output unit 22) outputs the growth index by two types of processing: a first output processing and a second output processing. The first output processing and the second output processing will be described below.

[0087] 4, the index output unit 22 has an identification unit 24. The identification unit 24 identifies a reference inflorescence DA based on the detection result by the state detection unit 21. The reference inflorescence DA is an inflorescence D in a predetermined flowering state.

[0088] That is, the index output unit 22 has an identification unit 24 that identifies a reference inflorescence DA, which is an inflorescence D in a predetermined flowering state, based on the detection result by the state detection unit 21.

[0089] Although not particularly limited, in this embodiment, the predetermined flowering state is a state in which there is only one flower at the reference flowering stage in one inflorescence D, and no flowers that have flowered further than the reference flowering stage. The reference flowering stage is the predetermined flowering stage.

[0090] In other words, the predetermined flowering state is a state in which there is only one flower at the reference flowering stage, which is a predetermined flowering stage, in one inflorescence D, and there are no flowers that are more advanced in flowering than the reference flowering stage.

[0091] In this embodiment, the reference flowering stage is "early flowering." However, the present invention is not limited to this. For example, the reference flowering stage may be "mid-flowering" or "late flowering."

[0092] In the first output process, first, the state detection unit 21 individually detects the flowering stage of each flower in all inflorescences D captured in the captured image acquired by the imaging unit Ca. For example, in the example shown in Fig. 3, the flowering stage of each flower in all inflorescences D of the first individual P1, the second individual P2, and the third individual P3 is individually detected.

[0093] Next, the identification unit 24 acquires the detection result by the state detection unit 21 and, based on the detection result, identifies a reference inflorescence DA from among the inflorescences D. For example, in the example shown in Figures 3 and 6, of the two inflorescences D owned by the first individual P1, the flowering stage of one flower in the upper inflorescence D is "early flowering," and the flowering stages of all the other flowers are "unflowered." Therefore, this inflorescence D is identified as the reference inflorescence DA.

[0094] Next, the length detection unit 23 obtains the identification result by the identification unit 24 from the index output unit 22 and detects a reference distance index value based on the identification result. The reference distance index value is a value indicating the degree of distance between the reference inflorescence DA and the shoot apex B of the cultivated plant P having the reference inflorescence DA. In this embodiment, the length detection unit 23 detects a reference length as the reference distance index value. The reference length is the length of the stem between the shoot apex B of the cultivated plant P having the reference inflorescence DA and the pedicel E corresponding to the reference inflorescence DA. For example, in the examples shown in Figures 3 and 7, the detected length G1 is the reference length. The reference length is a specific example of a reference distance index value. The longer the reference length, the greater the distance between the shoot apex B of the cultivated plant P having the reference inflorescence DA and the reference inflorescence DA.

[0095] In this way, the length detection unit 23 is configured to detect a reference distance index value, which is a value indicating the degree of distance between the stem apex B and the reference inflorescence DA. As is clear from the above explanation, the reference distance index value is a specific example of a distance index value.

[0096] Next, the index output unit 22 acquires the reference distance index value (more specifically, the reference length) detected by the length detection unit 23, and outputs a growth index based on the reference length. That is, in the first output process, the index output unit 22 outputs a growth index based on the reference distance index value (more specifically, the reference length).

[0097] In the first output process, a growth index is output using the method described above. While not particularly limited, the growth index output by the first output process may be the reference distance index value (more specifically, the reference length) itself, or a numerical value or classification determined based on the reference distance index value (more specifically, the reference length). The numerical value may be, for example, a numerical representation of the degree of bias toward reproductive growth or vegetative growth of the cultivated plant P (more specifically, the cultivated plant P having the reference inflorescence DA). The classification may be, for example, one of the three classifications of "leaning toward reproductive growth," "well-balanced state," and "leaning toward vegetative growth" to which the state of the cultivated plant P (more specifically, the cultivated plant P having the reference inflorescence DA) corresponds.

[0098] Furthermore, a cultivated plant P having an inflorescence D in a predetermined flowering state is evaluated as being more reproductive the smaller the distance between the shoot apex B and the inflorescence D, and more vegetative the greater the distance. For example, the shorter the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D, the more reproductive the plant is evaluated, and the longer the length, the more vegetative the plant is evaluated.

[0099] [Second Output Process] As shown in Figure 4, the index output unit 22 has an estimation unit 25. The estimation unit 25 estimates a value indicating the degree of separation between the shoot apex B and the inflorescence D at the time when the inflorescence D was in the predetermined flowering state, based on the flowering stage of each flower in the inflorescence D that is flowering more advanced than the predetermined flowering state and the detection result by the length detection unit 23. In this embodiment, the estimation unit 25 estimates the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D at the time when the inflorescence D was in the predetermined flowering state as the value. In other words, the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D at the time when the inflorescence D was in the predetermined flowering state is a specific example of a value indicating the degree of separation between the shoot apex B and the inflorescence D at the time when the inflorescence D was in the predetermined flowering state.

[0100] In this way, the index output unit 22 has an estimation unit 25 that estimates a value indicating the degree of distance between the stem apex B and the inflorescence D at the time when the inflorescence D was in the predetermined flowering state, based on the flowering stage of each flower in the inflorescence D that is more advanced in flowering than the predetermined flowering state and the detection result by the length detection unit 23. That is, the estimation unit 25 estimates a past distance index value (more specifically, the distance index value at the time when the inflorescence D was in the predetermined flowering state).

[0101] In the second output process, first, the state detection unit 21 individually detects the flowering stage of each flower in one of the plurality of inflorescences D shown in the captured image acquired by the imaging unit Ca. For example, in the example shown in Fig. 3, the flowering stage of each flower in the upper inflorescence D of the two inflorescences D of the second individual P2 may be individually detected.

[0102] Of the two inflorescences D of the second individual P2, the upper inflorescence D has eight flowers. Of these flowers, one is in "late flowering," two are in "mid-flowering," two are in "early flowering," and three are "unflowered." Therefore, the inflorescence D is one in which each flower has flowered more than the predetermined flowering state. In other words, the inflorescence D was in the predetermined flowering state at a point in the past.

[0103] In addition, the selection condition for the inflorescence D to be detected at this time may be any condition. For example, the inflorescence D may be selected based on the position of the inflorescence D, the number of flowers that the inflorescence D has, etc.

[0104] Next, the length detection unit 23 detects the length of the stem between the apex B of the stem of the cultivated plant P having the inflorescence D that is the detection target of the status detection unit 21 and the pedicel E corresponding to that inflorescence D. For example, if the detection target of the status detection unit 21 is the upper inflorescence D of the two inflorescences D of the second individual P2, the length of the stem between the apex B of the second individual P2 and the pedicel E corresponding to that inflorescence D is detected.

[0105] Next, the index output unit 22 acquires the detection result from the state detection unit 21 and the detection result from the length detection unit 23. Then, based on the detection result from the state detection unit 21 and the detection result from the length detection unit 23, the estimation unit 25 estimates the length of the stem between the shoot apex B of the cultivated plant P having the inflorescence D detected by the state detection unit 21 and the pedicel E corresponding to the inflorescence D at the time when the inflorescence D was in a predetermined flowering state.

[0106] For example, if the detection target by the state detection unit 21 is the upper inflorescence D of the two inflorescences D of the second individual P2, the length of the stem between the stem tip B of the second individual P2 and the pedicel E corresponding to the inflorescence D at the time when the inflorescence D was in a specified flowering state is estimated.

[0107] Although not particularly limited, the estimation result by the estimation unit 25 may be obtained by performing a correction process on the detection result by the length detection unit 23 in accordance with the detection result by the state detection unit 21. The correction process may be performed based on past environmental information. The environmental information may be, for example, the temperature, accumulated temperature, or humidity inside the horticultural facility 10. The correction process may be a process of decreasing a value. The correction process may be, for example, multiplying by a coefficient. The coefficient may be, for example, a value greater than 0 and less than 1, or may be a value calculated in accordance with the detection result by the state detection unit 21.

[0108] Next, the index output unit 22 outputs a growth index based on the estimation result by the estimation unit 25 .

[0109] In the second output process, a growth index is output by the method described above. While not particularly limited, the growth index output by the second output process may be the estimation result by the estimation unit 25 itself, or a numerical value or classification determined based on the estimation result by the estimation unit 25. The numerical value may be, for example, a numerical representation of the degree of bias toward reproductive growth or vegetative growth of the cultivated plant P (more specifically, the cultivated plant P that was the subject of estimation by the estimation unit 25). The classification may be, for example, one of the three classifications of "leaning toward reproductive growth," "well-balanced state," and "leaning toward vegetative growth" that corresponds to the state of the cultivated plant P (more specifically, the cultivated plant P that was the subject of estimation by the estimation unit 25).

[0110] Furthermore, a cultivated plant P having an inflorescence D that has flowered more than the predetermined flowering state is evaluated as being more reproductive the smaller the distance between the shoot apex B and the inflorescence D at the time when the inflorescence D was in the predetermined flowering state, and as being more vegetative the larger the distance. For example, the shorter the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D at that time, the more reproductive the plant is evaluated as being more reproductive, and the longer the length, the more vegetative the plant is evaluated as being more reproductive.

[0111] Furthermore, in this embodiment, each element such as the status detection unit 21 included in the management computer 2 may be a functional unit in software, or may be configured by a physical device such as a microcomputer.

[0112] According to the configuration described above, a growth index is output based on the detection results from the state detection unit 21 and the length detection unit 23. The inventors of the present application have found that the growth index output in this manner makes it possible to evaluate the growth state of the cultivated plant P (for example, the degree of bias toward reproductive growth or vegetative growth). Therefore, according to the configuration described above, it is possible to realize a cultivation management system S that is capable of evaluating the growth state of the cultivated plant P.

[0113] [Alternatives to the First Embodiment] Alternatives to the first embodiment will be described below. Matters other than those described in the following alternative embodiments are the same as those described in the first embodiment.

[0114] [Other embodiments] (1) In the first output process, the state detection unit 21 may detect the flowering stage of each flower in some of the multiple inflorescences D captured in the captured image acquired by the imaging unit Ca.

[0115] (2) In the second output process, the state detection unit 21 may detect the flowering stage of each flower in a plurality of inflorescences D captured in the captured image acquired by the imaging unit Ca.

[0116] (3) The imaging direction and position of the imaging unit Ca may be changeable by an actuator (e.g., an electric motor). In this case, in the first output process, if none of the inflorescences D shown in the captured images are in the predetermined flowering state, the imaging direction and position of the imaging unit Ca may be automatically changed, a new captured image may be acquired, and detection by the state detection unit 21 may be performed based on the new captured image. With this configuration, it is possible to change the imaging range of the imaging unit Ca until the reference inflorescence DA is identified (in other words, until an inflorescence D in the predetermined flowering state is captured).

[0117] (4) In the first output process, if none of the inflorescences D shown in the captured image are in the specified blooming state, the first output process may be stopped and the second output process may be executed.

[0118] (5) The state detection unit 21 may be configured not to detect the flowering stage of each flower in the inflorescence D. For example, the state of the inflorescence D of the cultivated plant P detected by the state detection unit 21 may be the number of flowers in the inflorescence D.

[0119] (6) The index output unit 22 may not have the identifying unit 24. That is, the management computer 2 (index output unit 22) may be configured not to be able to execute the first output process.

[0120] (7) The index output unit 22 does not have to include the estimation unit 25. That is, the management computer 2 (index output unit 22) may be configured not to be able to execute the second output process.

[0121] (8) The length detection unit 23 may detect, as the distance index value, a value other than the length of the stem between the shoot apex B and the pedicel E corresponding to the inflorescence D. For example, the length detection unit 23 may detect, as the distance index value, the linear distance between the shoot apex B and the inflorescence D, or the linear distance between the shoot apex B and any flower in the inflorescence D. In other words, the linear distance between the shoot apex B and the inflorescence D and the linear distance between the shoot apex B and any flower in the inflorescence D are both specific examples of the distance index value.

[0122] It can be said that the longer the linear distance between the shoot apex B and the inflorescence D, the greater the distance between the shoot apex B and the inflorescence D. Also, it can be said that the longer the linear distance between the shoot apex B and any flower in the inflorescence D, the greater the distance between the shoot apex B and the inflorescence D.

[0123] (9) The length detection unit 23 may detect a value other than the reference length as the reference distance index value. For example, the length detection unit 23 may detect, as the reference distance index value, the linear distance between the stem apex B of a cultivated plant P having a reference inflorescence DA and the reference inflorescence DA, or the linear distance between the stem apex B and any flower in the reference inflorescence DA. In other words, the linear distance between the stem apex B and the reference inflorescence DA and the linear distance between the stem apex B and any flower in the reference inflorescence DA are both specific examples of the reference distance index value.

[0124] (10) The estimation unit 25 may estimate, as the distance index value at the time when the inflorescence D was in the predetermined flowering state, a value other than the length of the stem between the stalk B and the pedicel E corresponding to the inflorescence D. For example, the estimation unit 25 may estimate, as the distance index value at the time when the inflorescence D was in the predetermined flowering state, the linear distance between the stalk B and the inflorescence D at the time when the inflorescence D was in the predetermined flowering state, or the linear distance between the stalk B and any flower in the inflorescence D at the time when the inflorescence D was in the predetermined flowering state. In other words, the linear distance between the stalk B and the inflorescence D at the time when the inflorescence D was in the predetermined flowering state and the linear distance between the stalk B and any flower in the inflorescence D at the time when the inflorescence D was in the predetermined flowering state are both specific examples of the distance index value at the time when the inflorescence D was in the predetermined flowering state.

[0125] The configurations disclosed in the above-described embodiments (including other embodiments, the same applies hereinafter) can be applied in combination with the configurations disclosed in other embodiments, unless a contradiction occurs. Furthermore, the embodiments disclosed in this specification are merely examples, and the present invention is not limited to these, and can be modified as appropriate within the scope of the present invention.

[0126] Second Embodiment A mode for carrying out the present invention will be described with reference to the drawings. More specifically, the second embodiment will be described mainly with reference to Figures 8 to 13. In the following description, components that are assigned the same reference numerals as those in the first embodiment are the same as those in the first embodiment, and detailed description thereof will be omitted.

[0127] [Configuration of Horticultural Facility] Figure 8 shows an example of a captured image acquired by the imaging unit Ca. This captured image shows a first individual P1, a second individual P2, and a third individual P3. The first individual P1, the second individual P2, and the third individual P3 are all cultivated plants P. This captured image also shows the fruit clusters J and stems K of each of the first individual P1, the second individual P2, and the third individual P3. The imaging unit Ca captures an image of the cultivated plant P so that the fruit clusters J and stems K of the cultivated plant P are captured in the captured image.

[0128] Furthermore, it is preferable that the imaging unit Ca captures an image of the cultivated plant P so that the root portion of the cultivated plant P is captured in the captured image, as shown in FIG.

[0129] [Configuration of the cultivation management system] As shown in Fig. 9, the cultivation management system SA in this embodiment includes a management computer 102 and a display 103. The display 103 is capable of displaying various types of information. The display content on the display 103 is controlled by a display control unit 121 included in the management computer 102. The horticultural facility 10 is also included in the cultivation management system SA.

[0130] That is, the cultivation management system SA is provided with an imaging unit Ca that captures images of the cultivated plants P.

[0131] [Regarding the bunch detection unit] As shown in Fig. 9, the management computer 102 has a fruit detection unit 122 and a bunch detection unit 123. The fruit detection unit 122 receives the captured image acquired by the imaging unit Ca. The fruit detection unit 122 detects each fruit M appearing in the captured image. Fig. 10 shows an example of the detection result by the fruit detection unit 122.

[0132] The method by which the fruit detection unit 122 detects the fruit M is not particularly limited, but the fruit M may be detected by analyzing the captured image using a machine-learned neural network.

[0133] As described above, the cultivation management system SA includes a fruit detection unit 122 that detects the fruit M of the cultivated plant P based on the captured image acquired by the imaging unit Ca.

[0134] 9 , the bunch detection unit 123 acquires the detection result by the fruit detection unit 122. Based on the detection result, the bunch detection unit 123 detects the bunch J of the cultivated plant P. An example of the detection result by the bunch detection unit 123 is shown in FIG.

[0135] The method by which the bunch detection unit 123 detects bunch J is not particularly limited, but bunch J may be detected by analyzing the detection results of fruit M by the fruit detection unit 122 using a known clustering technique.

[0136] In this way, the cultivation management system SA is equipped with a fruit bunch detection unit 123 that detects the fruit bunch J of the cultivated plant P based on the detection result by the fruit detection unit 122.

[0137] 9, the management computer 102 includes an identification unit 124. The detection result by the bunch detection unit 123 is sent to the identification unit 124.

[0138] [Regarding the Stem Detection Unit] As shown in Fig. 9, the management computer 102 has a stem detection unit 125. The stem detection unit 125 receives the captured image acquired by the imaging unit Ca. The stem detection unit 125 detects each stem K appearing in the captured image. Fig. 12 shows an example of the detection result by the stem detection unit 125.

[0139] The method by which the stem detection unit 125 detects the stem K is not particularly limited, but the stem K may be detected by analyzing the captured image using a machine-learned neural network.

[0140] In this way, the cultivation management system SA is provided with a stem detection unit 125 that detects the stem K of the cultivated plant P based on the captured image.

[0141] As shown in FIG. 9, the detection result by the stem detection unit 125 is sent to the identification unit 124.

[0142] [Regarding the Identification Unit and the Measurement Unit] The identification unit 124 identifies a reference bunch JA (see FIGS. 8 and 13) from among the bunches J detected by the bunch detection unit 123. A reference bunch JA is a bunch J that satisfies predetermined conditions. In other words, the cultivation management system SA is equipped with an identification unit 124 that identifies a reference bunch JA, which is a bunch J that satisfies predetermined conditions, from among the bunches J detected by the bunch detection unit 123.

[0143] Although not particularly limited, in this embodiment, the predetermined condition is that the truss J is a predetermined number of steps above the lowest truss J (see FIGS. 8 and 13). The lowest truss J is the truss J located closest to the roots of the cultivated plant P. That is, in this embodiment, the predetermined condition is that the truss J is a predetermined number of steps above the truss J located closest to the roots of the cultivated plant P.

[0144] In addition, if the cultivated plant P is, for example, a tomato, the fruits M are harvested in order, starting with the fruit bunch J closest to the root. Therefore, after all the fruits M of the fruit bunch J closest to the root of the cultivated plant P are harvested, the fruits M of the fruit bunch J one level above that fruit bunch J are harvested. Here, the lowest fruit bunch JB may be the fruit bunch J closest to the root at the time before the first harvest of the cultivated plant P (in other words, the fruit bunch J that is the first fruit bunch J), or it may be the fruit bunch J closest to the root among the fruit bunches J that currently have one or more fruits M remaining. In other words, the lowest fruit bunch JB may remain constant regardless of the harvest status of the cultivated plant P (for example, the fruit bunch J that is the first fruit bunch J), or it may move up one level as the harvest progresses.

[0145] In this embodiment, the "predetermined number of stages" is specifically one stage. However, the present invention is not limited to this, and the "predetermined number of stages" may be any number of stages equal to or greater than two stages.

[0146] The identification unit 124 identifies the reference bunch JA based on the detection results from the bunch detection unit 123 and the detection results from the stalk detection unit 125 .

[0147] 13, the identification unit 124 superimposes the detection result by the fruit bunch detection unit 123 and the detection result by the stem detection unit 125. Next, the identification unit 124 identifies which stem K each fruit bunch J corresponds to (in other words, which cultivated plant P each fruit bunch J belongs to) based on the positional relationship between the fruit bunch J and the stem K.

[0148] Next, the identification unit 124 identifies the tuft J located closest to the root of each stem K (or each cultivated plant P) as the lowest tuft JB. Next, among the tufts J that correspond to the same stem K as the lowest tuft JB and are not the lowest tuft JB, the identification unit 124 identifies the tuft J located closest to the lowest tuft JB (in other words, adjacent to the lowest tuft JB) as the reference tuft JA.

[0149] The identification unit 124 identifies the reference bunch JA through the process described above. For example, in the example shown in Fig. 13, the identification unit 124 identifies the reference bunch JA of the first individual P1 and the reference bunch JA of the second individual P2.

[0150] However, the present invention is not limited to this, and any process may be used by the identification unit 124 to identify the reference bunch JA.

[0151] 9 , information indicating the reference bunch JA identified by the identification unit 124 is sent to the measurement unit 126. The measurement unit 126 also acquires the detection result by the fruit detection unit 122 from the fruit detection unit 122. The measurement unit 126 then counts the number of fruits M contained in the reference bunch JA based on the information indicating the reference bunch JA and the detection result by the fruit detection unit 122. The measurement unit 126 outputs the measurement result.

[0152] In this way, the cultivation management system SA is equipped with a measurement unit 126 that measures the number of fruits M contained in the reference fruit bunch JA.

[0153] 13, the measurement unit 126 outputs information indicating that the number of fruits M contained in the reference bunch JA of the first individual P1 is two. The measurement unit 126 also outputs information indicating that the number of fruits M contained in the reference bunch JA of the second individual P2 is three.

[0154] The measurement unit 126 may measure the number of fruits M contained in all reference fruit bunches JA that appear in the captured image. That is, the measurement result output by the measurement unit 126 may be the total number of fruits M contained in all reference fruit bunches JA that appear in the captured image. Furthermore, for example, if multiple imaging units Ca are provided within the horticultural facility 10 and all cultivated plants P within the horticultural facility 10 are covered by the imaging ranges of these imaging units Ca, the measurement unit 126 may measure each of all cultivated plants P within the horticultural facility 10 individually, or may measure the total number of fruits M contained in the reference fruit bunches JA of all cultivated plants P within the horticultural facility 10.

[0155] Furthermore, when a plurality of reference bunches JA are captured in the captured image, the measurement unit 126 may perform measurements on only one of the reference bunches JA.

[0156] 9 , the measurement results output by the measurement unit 126 are sent to the display control unit 121. The display control unit 121 displays the measurement results on the display 103. This allows the user to check the measurement results output by the measurement unit 126.

[0157] The measurement unit 126 or the display control unit 121 may also be configured to predict the number of fruits M that will be harvestable in the future based on the measurement results. Furthermore, the measurement unit 126 or the display control unit 121 may output information indicating a recommended date for performing harvesting work and the predicted workload of the harvesting work (e.g., the time required for the work and the number of people required) based on the prediction result of the number of fruits M that will be harvestable in the future. The information may be displayed on the display 103.

[0158] In this embodiment, each element such as the display control unit 121 included in the management computer 102 may be a functional unit in software, or may be configured by a physical device such as a microcomputer.

[0159] According to the configuration described above, the fruit M is detected based on the captured image of the cultivated plant P. Then, the fruit bunch J is detected based on the detection result of the fruit M. The inventors of the present application have found that this configuration allows for accurate detection of the fruit bunch J of the cultivated plant P. Therefore, according to this configuration, it is possible to realize a cultivation management system SA that is capable of accurately detecting the fruit bunch J of the cultivated plant P.

[0160] [Alternatives to the Second Embodiment] Alternatives to the second embodiment will be described below. Matters other than those described in the following alternative embodiments are the same as those described in the above embodiment.

[0161] Other Embodiments (1) The specifying unit 124 does not have to be provided.

[0162] (2) The measuring unit 126 does not have to be provided.

[0163] (3) The stem detection unit 125 does not have to be provided. That is, the identification unit 124 may identify the reference bunch JA without relying on the detection result by the stem detection unit 125.

[0164] The configurations disclosed in the above-described embodiments (including other embodiments, the same applies hereinafter) can be applied in combination with the configurations disclosed in other embodiments, unless a contradiction occurs. Furthermore, the embodiments disclosed in this specification are merely examples, and the present invention is not limited to these, and can be modified as appropriate within the scope of the present invention.

[0165] [Third Embodiment] A mode for carrying out the present invention will be described with reference to the drawings. More specifically, the third embodiment will be described mainly with reference to Figures 14 to 25. In the following description, components that are assigned the same reference numerals as those in the first embodiment are the same as those in the first embodiment, and detailed description thereof will be omitted.

[0166] [Configuration of Horticultural Facility] An embodiment of the present invention will be described with reference to the drawings. As shown in Figures 14 and 15, a cultivation system SY (corresponding to the "growth management system" of the present invention) in this embodiment includes a horticultural facility 201. The horticultural facility 201 has rows of ridges A1 to A8 arranged vertically and horizontally for planting cultivated plants Q. Passages are provided between each row of ridges A so that managers of the cultivated plants Q (including operators, etc.) can pass through. The horticultural facility 201 may be, for example, a greenhouse or a solar-powered plant factory.

[0167] Each ridge A is made of, for example, a non-porous hydrophilic film, and a cultivated plant Q, for example, a tomato, is planted in each ridge A.

[0168] The cultivation system SY is equipped with a plurality of visual sensing units 203. The visual sensing units 203 obtain visual information of the cultivated plants Q. This visual information is used to determine the growth state of the cultivated plants Q. In this embodiment, the horticultural facility 201 is equipped with a fixed sensing unit 230 and a mobile sensing unit 231 as the visual sensing units 203.

[0169] 14 and 15 , the visual sensing unit 203 has an imaging device 203A and a distance measuring device 203B. The fixed sensing unit 230 is disposed above the cultivated plant Q. Therefore, the imaging device 203A in the fixed sensing unit 230 captures images from a bird's-eye view of the main stem 251 (see FIGS. 17 and 18 ), the branches and leaves 252 and inflorescence 253 (see FIGS. 17 and 18 ) differentiated from the main stem 251, and the fruit cluster 254 (see FIGS. 17 and 18 ) growing from the inflorescence 253, etc., of the cultivated plant Q.

[0170] The mobile sensing unit 231 captures images of the cultivated plant Q from a side view while traveling along paths between parallel rows A in the horticultural facility 201. For this reason, the imaging device 203A in the mobile sensing unit 231 captures images of the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. of the cultivated plant Q from a side view.

[0171] The imaging device 203A has, for example, a CCD element or a CMOS element, and is configured to be able to capture visible light visible to the naked eye. The imaging device 203A in the fixed sensing unit 230 captures images of the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. of the cultivated plant Q from a bird's-eye view at predetermined time intervals (for example, every 60 seconds). The imaging device 203A in the mobile sensing unit 231 also captures images of the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. of the cultivated plant Q while patrolling the ridges A1 to A8 of the horticultural facility 201. The imaging data V captured by each imaging device 203A is sent over time to the recognition unit 221 (see FIG. 16 ).

[0172] The distance measuring device 203B is, for example, a three-dimensional scanning Lidar, and measures the distance to the cultivated plant Q, for example, by a ToF (Time of Flight) measurement method. When the distance measuring device 203B irradiates the cultivated plant Q with a light beam, such as an infrared laser beam, the light waves of the light beam propagate through the air and are reflected by the surface of the cultivated plant Q, and the reflected light waves propagate through the air and reach the distance measuring device 203B. The distance measuring device 203B acquires the light waves reflected by the surface of the cultivated plant Q as a reflected signal. The distance measuring device 203B then calculates the distance between the distance measuring device 203B and the cultivated plant Q based on the time from when the light beam is irradiated to when the reflected signal is acquired. That is, the distance measuring device 203B acquires distance measurement data D1 in three-dimensional coordinates for the cultivated plant Q imaged by the imaging device 203A. The distance measurement data D1 acquired by each distance measurement device 203B is sent to the recognition unit 221 over time.

[0173] As described above, the cultivation system SY includes an imaging device 203A that captures images of the leaves of the cultivated plant Q and a distance measuring device 203B that measures the distance to the cultivated plant Q. The visual sensing unit 203 may be configured without the distance measuring device 203B. In this case, the visual sensing unit 203 may be configured to include a stereo camera as the imaging device 203A.

[0174] Although not shown, the horticultural facility 201 is also equipped with environmental sensors, side windows, and heat pump air conditioning equipment. Also, as shown in FIG. 16 , the facility is equipped with an irrigation device 211B, a spray device 211C, a fertilizer applicator 212B, a curtain opening / closing device 213B for blackout curtains, a carbon dioxide generator 214B, and the like. The dashed line Gh shown in FIG. 15 indicates the reference position where the height of the cultivated plant Q is at its maximum, and a guide string for guiding the stems of the cultivated plant Q hangs down from near the height of the dashed line Gh. The fixed sensing unit 230 is provided at a position higher than the dashed line Gh. The fixed sensing unit 230 may also be provided at a position lower than the dashed line Gh.

[0175] 16 , at the horticultural facility 201, imaging data V captured by an imaging device 203A, distance measurement data D1 measured by a distance measuring device 203B, and environmental condition data EA obtained by digitizing the environmental condition measured by an environmental information acquisition unit 210 are transmitted to a management computer 202 via a wide area network WAN (Wide Area Network). Although not specifically shown, the horticultural facility 201 and the management computer 202 are each provided with communication means capable of accessing the wide area network WAN.

[0176] An insolation sensor 210A, a temperature sensor 210B, a humidity sensor 210C, and a carbon dioxide concentration sensor 210D are connected to the environmental information acquisition unit 210 of the horticultural facility 201. The insolation sensor 210A measures the amount of insolation received by the cultivated plant Q in the horticultural facility 201. The temperature sensor 210B measures the air temperature indoors in the horticultural facility 201. The humidity sensor 210C measures the humidity indoors in the horticultural facility 201. The carbon dioxide concentration sensor 210D measures the carbon dioxide concentration indoors in the horticultural facility 201. In other words, the environmental information acquisition unit 210 can acquire environmental information about the horticultural facility 201 where the cultivated plant Q is cultivated.

[0177] The management computer 202 includes a recognition unit 221 , a stem diameter calculation unit 222 , a flowering position calculation unit 223 , a flowering state determination unit 224 , a memory unit 225 , and a growth determination unit 226 .

[0178] When the image capture device 203A captures an image of the cultivated plant Q, the recognition unit 221 recognizes the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. based on the color information, etc., of the image capture data V. A neural network capable of learning using deep learning is constructed in the recognition unit 221. Neural networks are known for their ability to identify input-output relationships with nonlinear characteristics through deep learning. The recognition unit 221 is configured to be able to identify the types of branches, leaves, stems, etc. of the cultivated plant Q by utilizing the neural network trained using deep learning. The determination of the color information, etc., of the image capture data V may be performed based on RGB data or YUV data. That is, the recognition unit 221 recognizes the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. of the cultivated plant Q captured in the image captured by the image capture device 203A.

[0179] The distance measurement data D1 measured by the distance measuring device 203B is input into the recognition unit 221. The recognition unit 221 compares the imaging data V with the distance measurement data D1 to identify the distances of the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc., relative to the visual sensing unit 203. Of the cultivated plants Q recognized in the imaging data V, cultivated plants Q planted in ridges A farther away than the imaging target ridge A will have longer distance measurement data D1 than cultivated plants Q planted in the imaging target ridge A. Therefore, the recognition unit 221 recognizes the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. of the cultivated plants Q planted in the imaging target ridge A by excluding those with longer distance measurement data D1 from the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. recognized from the imaging data V.

[0180] The stem diameter calculation unit 222 calculates the stem diameter D2 of the main stem 251 of the cultivated plant Q based on the image data V and the distance measurement data D1 (see Figures 17 and 18). In other words, the stem diameter calculation unit 222 calculates the stem diameter D2 of the main stem 251 recognized by the recognition unit 221.

[0181] The flowering position calculation unit 223 calculates the main stem length L, which is the length of the main stem 251 between the upper end of the main stem 251 and the inflorescence part 253 (see Figure 21).

[0182] The flowering state determination unit 224 determines the flowering state of the inflorescence part 253 of the cultivated plant Q by dividing it into a plurality of stages (see FIG. 20), as will be described in detail later.

[0183] The storage unit 225 is, for example, a RAM (Random Access Memory) or a hard disk, and is capable of storing the imaging data V, the distance measurement data D1, the environmental condition data EA, the analysis results, the determination results, and the like.

[0184] The weather information 204 is weather data information obtained from, for example, a meteorological organization or a weather information company via a wide area network WAN. The weather information 204 is stored in the storage unit 225 over time.

[0185] The growth determination unit 226 includes a growth balance determination unit 226A and a growth prediction determination unit 226B, details of which will be described later. The growth determination unit 226 determines the growth status of the cultivated plant Q based on the stem diameter D2 of the cultivated plant Q, the flowering state of the inflorescence 253, the main stem length L between the upper end of the main stem 251 and the inflorescence 253, the environmental condition data EA, the meteorological information 204, and the like. The growth status data determined by the growth determination unit 226 is transmitted to various control units of the horticultural facility 201 via the wide area communication network WAN. The growth status data includes a stem diameter discrimination value Ga, a main stem length discrimination value Gb, a tree vigor discrimination value Gc, and the future growth status of the branch and leaf portion 252, and the like.

[0186] The stem diameter D2, the flowering state of the inflorescence 253, the main stem length L, the environmental condition data EA, the weather information 204, and the growth status data of the cultivated plant Q can be displayed on a known display monitor, allowing a manager or operator to check this information on the display monitor. The display monitor may be provided in the management computer 202, or may be a laptop computer or mobile phone carried by the manager or operator. Furthermore, if an abnormality is found in at least one of the stem diameter D2, the flowering state of the inflorescence 253, the main stem length L, the environmental condition data EA, the weather information 204, and the growth status data, an alarm may be output using a known buzzer or voice guidance.

[0187] The horticultural facility 201 is equipped with a temperature control unit 215A and a temperature control device 215B that control the temperature in the horticultural facility 201. The temperature control unit 215A sends an instruction signal to the temperature control device 215B based on data on the growth status determined by the growth determination unit 226. The temperature control device 215B may be, for example, an opening and closing device for a skylight or a side window, a ventilation fan or a circulation fan, or an air conditioning device (e.g., a heat pump air conditioning device). Upon receiving an instruction signal from the temperature control unit 215A, the temperature control device 215B adjusts the temperature in the horticultural facility 201 by opening and closing the skylight or side window, ventilating with the ventilation fan or circulation fan, operating the heat pump, etc.

[0188] The horticultural facility 201 is equipped with a humidity control unit 216A, a humidity control device 216B, and a spray device 211C, which control the humidity in the horticultural facility 201. The humidity control unit 216A sends instruction signals to the humidity control device 216B and the spray device 211C based on data on the growth status determined by the growth determination unit 226. The humidity control device 216B is, for example, a humidifier or a dehumidifier. Upon receiving an instruction signal from the humidity control unit 216A, the humidity control device 216B operates to humidify or dehumidify. Furthermore, upon receiving an instruction signal from the humidity control unit 216A, the spray device 211C opens a valve (not shown) and increases the humidity in the horticultural facility 201 by spraying.

[0189] The horticultural facility 201 is equipped with an irrigation control unit 211A and an irrigation device 211B for irrigating cultivated plants Q. The irrigation control unit 211A transmits instruction signals to the irrigation device 211B and the spray device 211C based on data on the growth status determined by the growth determination unit 226. Upon receiving the instruction signal from the irrigation control unit 211A, the irrigation device 211B and the spray device 211C open irrigation valves (not shown) to supply water to the cultivated plants Q. The instruction signal from the irrigation control unit 211A may be a voltage value or a current value.

[0190] The horticultural facility 201 is also equipped with a fertilization control unit 212A and a fertilizer application device 212B. The fertilization control unit 212A transmits an instruction signal to the fertilizer application device 212B based on data on the growth status determined by the growth determination unit 226. Upon receiving the instruction signal from the fertilization control unit 212A, the fertilizer application device 212B opens a fertilization valve (not shown) to supply fertilizer. The fertilizer may be supplied in a state where it is mixed with water supplied to the cultivated plants Q by the irrigation device 211B, for example. This configuration makes it possible to adjust the amount of fertilizer application based on the instruction signal from the fertilization control unit 212A. The fertilizer mainly contains nitrogen. Note that the components of the fertilizer are not limited to nitrogen, and may also include phosphoric acid, potassium, calcium, magnesium, etc.

[0191] The horticultural facility 201 is equipped with a solar radiation amount control unit 213A and a curtain opening / closing device 213B. The solar radiation amount control unit 213A sends an instruction signal to the curtain opening / closing device 213B based on data on the growth status determined by the growth determination unit 226. A shading curtain (not shown) is provided on a skylight of the horticultural facility 201, and the curtain opening / closing device 213B is configured to be able to open and close the shading curtain. The curtain opening / closing device 213B is configured, for example, with an electric motor. Upon receiving an instruction signal from the solar radiation amount control unit 213A, the curtain opening / closing device 213B opens or closes the shading curtain of the horticultural facility 201 to adjust the amount of photosynthesis of the cultivated plants Q.

[0192] The horticultural facility 201 is equipped with a carbon dioxide amount control unit 214A and a carbon dioxide generation device 214B. The carbon dioxide amount control unit 214A sends an instruction signal to the carbon dioxide generation device 214B based on data on the growth status determined by the growth determination unit 226. The carbon dioxide generation device 214B is equipped in the horticultural facility 201 and is configured to be able to generate carbon dioxide by, for example, combustion. Upon receiving the instruction signal from the carbon dioxide amount control unit 214A, the carbon dioxide generation device 214B increases the amount of carbon dioxide in the horticultural facility 201 and increases the amount of photosynthesis of the cultivated plants Q.

[0193] In addition to the above-mentioned devices, the horticultural facility 201 is also equipped with a heat storage device, a sterilization device, etc. These devices may be configured to be driven based on data on the growth status determined by the growth determination unit 226.

[0194] In addition, at least one of the irrigation control unit 211A, fertilization control unit 212A, solar radiation control unit 213A, and carbon dioxide amount control unit 214A may be provided in the management computer 202, and instruction signals may be transmitted to various devices in the horticultural facility 201 via the wide area communication network WAN.

[0195] 17 and 18 , the method by which the stem diameter calculation unit 222 calculates the stem diameter D2 of the cultivated plant Q will be described. The recognition unit 221 recognizes the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. of the cultivated plant Q. The data recognized by the recognition unit 221 includes distance measurement data D1 measured by the distance measurement device 203B. Therefore, it is possible to calculate the distances and sizes of the main stem 251, branches and leaves 252, inflorescence 253, fruit cluster 254, etc. based on the distance measurement data D1.

[0196] The main stem 251 extends vertically, and the stem diameter D2 varies depending on the vertical position of the main stem 251. In this embodiment, the stem diameter calculation unit 222 calculates the stem diameter D2 of the portion of the main stem 251 that is a preset length Lh below the stem apex. The set length Lh is, for example, 10 to 20 centimeters. The set length Lh may be calculated as appropriate depending on the type of cultivated plant Q, environmental conditions, etc.

[0197] The shoot apex is recognized by the recognition unit 221. However, the location recognized as the shoot apex often varies depending on the state of growth of the branches and leaves 252 in the cultivated plant Q. For this reason, in this embodiment, if the uppermost inflorescence 253 of the branches and leaves 252 and inflorescence 253 differentiated from the main stem 251 is present, the inflorescence 253 serves as a mark for the shoot apex. This mark is recognized below as the reference height position Rh.

[0198] The recognition unit 221 is configured to be able to recognize an inflorescence 253 differentiated from the upper part of the main stem 251. When the inflorescence 253 is located at the top of the branches and leaves 252 and inflorescence 253 differentiated from the main stem 251, the inflorescence 253 serves as a landmark. In other words, when the recognition unit 221 recognizes the inflorescence 253 at the top of the cultivated plant Q, the stem diameter calculation unit 222 recognizes the position of the inflorescence 253 as the reference height position Rh. Note that when the recognition unit 221 recognizes multiple flowers in the upper inflorescence 253 of the cultivated plant Q, the stem diameter calculation unit 222 recognizes the position of the tallest flower as the reference height position Rh (see FIG. 17 ).

[0199] If the uppermost inflorescence 253 is not present among the branched leaves 252 and inflorescence 253 differentiated from the main stem 251, the upper end of the main stem 251 serves as a landmark. In other words, if the recognition unit 221 does not recognize the inflorescence 253 at the top of the cultivated plant Q, the stem diameter calculation unit 222 recognizes the position of the upper end of the main stem 251 as the reference height position Rh (see FIG. 18 ).

[0200] In this way, the stem diameter calculation unit 222 calculates the stem diameter D2 of the part of the main stem 251 that is the set length Lh below the reference height position Rh of the cultivated plant Q. The stem diameter calculation unit 222 may also calculate the average or median of the stem diameters D2 of multiple cultivated plants Q as the stem diameter D2.

[0201] The stem diameter calculation unit 222 generates an approximate curve 261 of the main stem 251 and identifies the calculation point 261A as a portion that is a set length Lh away from the reference height position Rh along the approximate curve 261. Then, it calculates a tangent line 262 that touches the approximate curve 261 at the calculation point 261A, and calculates a normal line that is perpendicular to the tangent line 262.

[0202] The normal line crosses the main stem 251. The stem diameter D2 of the main stem 251 recognized by the recognition unit 221 can be calculated from three-dimensional coordinates based on the distance measurement data D1. Therefore, the stem diameter calculation unit 222 calculates the length of the part of the normal line that overlaps with the main stem 251 from three-dimensional coordinates based on the distance measurement data D1. In other words, the stem diameter calculation unit 222 calculates an approximation curve 261 of the main stem 251 recognized by the recognition unit 221, and calculates the stem diameter D2 in the normal direction (or approximately normal direction) of the approximation curve 261.

[0203] [Determining Tree Vigor] The calculation point 261A identified by the stem diameter calculation unit 222 is stored in the memory unit 225 together with the characteristics of the calculation point 261A and the characteristics of the area around the calculation point 261A. As shown in Figure 19, after the stem diameter calculation unit 222 first calculates the stem diameter D2 at the calculation point 261A, it recalculates the stem diameter D2 at the calculation point 261A after a preset period has elapsed. Normally, the stem diameter D2 calculated for the second time at the calculation point 261A is thicker than the stem diameter D2 calculated for the first time at the calculation point 261A. The tree vigor of the cultivated plant Q can be determined based on the magnitude of the change in stem diameter D2 at the calculation point 261A. The period between the first and second calculations of the stem diameter D2 is, for example, two weeks. In addition, the configuration may be such that the stem diameter D2 is not compared with past values, but the tree vigor of the cultivated plant Q is determined based on the stem diameter D2 at any given time (one time).

[0204] In an environment favorable for the growth of cultivated plant Q, the stem diameter D2 increases and the vigor of cultivated plant Q increases. When the vigor of cultivated plant Q increases, the main stem 251 elongates and the branches and leaves 252 become lush. If the vigor of cultivated plant Q is too strong, the so-called vine fading and end rot are likely to occur, resulting in a reduced yield and distorted fruit shape.

[0205] If the stem diameter D2 is not large, the vigor of the cultivated plant Q will weaken, and the plant will tend to undergo reproductive growth, with the fruit cluster 254 growing actively. If the stem diameter D2 is too small, the branches and leaves 252 and the inflorescence 253 will become small, resulting in a reduced yield.

[0206] When the cultivated plant Q has strong vigor, the cultivated plant Q grows rapidly. In this case, the stem diameter D2 rapidly thickens. Therefore, the growth balance determination unit 226A quantifies the vigor of the cultivated plant Q using a vigor determination value Gc based on the degree of change in the stem diameter D2 at the two timings. In other words, the growth balance determination unit 226A expresses the growth status using a vigor determination value Gc that indicates the growth rate of the main stem 251 and the branches and leaves 252. In this embodiment, the larger the vigor determination value Gc, the stronger the vigor of the cultivated plant Q. Note that the smaller the vigor determination value Gc, the stronger the vigor of the cultivated plant Q. Furthermore, the growth balance determination unit 226A may be configured to quantify the vigor of the cultivated plant Q using the vigor determination value Gc based on the stem diameter D2 at any timing (one timing) instead of the two timings.

[0207] [Determination of the flowering state of the inflorescence by the flowering state determination unit] As described above, the flowering state determination unit 224 determines the flowering state of the inflorescence portion 253 of the cultivated plant Q into a plurality of stages. As shown in Fig. 20 , the flowering state is divided into stages #0 to #4.

[0208] Stage #0 indicates a state in which the inflorescence 253 is an unopened bud.

[0209] Stage #1 indicates a state in which the sepals of the inflorescence 253 begin to split and the inner petals begin to appear. The duration of Stage #1 is about half a day to a day, which is shorter than Stage #0, Stage #3, and Stage #4.

[0210] Stage #2 indicates the state in which the sepals of the inflorescence 253 have completely split open, revealing the inner petals and beginning to bloom. The duration of Stage #2 is about half a day to a day, which is shorter than Stage #0, Stage #3, and Stage #4.

[0211] Stage #3 shows the state in which the inflorescence 253 is in bloom. In stage #3, the sepals and petals of the inflorescence 253 repeatedly curl and elongate. When the sepals and petals elongate in stage #3, the shape of the inflorescence 253 resembles that of stage #2.

[0212] Stage #4 shows a state in which a fruit cluster 254 has been set on the inflorescence part 253. In stage #4, the flowers on the inflorescence part 253 gradually wither, and the fruit cluster 254 gradually grows.

[0213] In this manner, in this embodiment, the flowering state determination unit 224 determines the flowering state as one of stages 0 to 4. The determination result of the flowering state determination unit 224 is used for determination by the growth balance determination unit 226A.

[0214] [Determination of growth status by growth balance determination unit] In this embodiment, the growth balance determination unit 226A determines the growth status of the cultivated plant Q based on the stem diameter D2 of the cultivated plant Q and the main stem length L between the upper end of the main stem 251 and the inflorescence portion 253.

[0215] The recognition unit 221 is configured to be able to recognize a state in which the main stem 251 has differentiated from the upper part and a state in which the inflorescence portion 253 has bloomed. The bloomed state of the inflorescence portion 253 refers to a flowering state in stages #1 to #3. The flowering position calculation unit 223 calculates the length of the main stem 251 between the upper end of the main stem 251 and the branching point of the inflorescence portion 253 in the bloomed state from the main stem 251, i.e., the main stem length L. The growth balance determination unit 226A then determines the growth status based on the main stem length L. Note that the flowering position calculation unit 223 may calculate the average or median of the main stem lengths L of multiple cultivated plants Q as the main stem length L.

[0216] In an environment favorable for the growth of cultivated plant Q, the main stem 251 grows, and the main stem length L tends to become long. At this time, the state of cultivated plant Q tends to be vegetative, and the cultivated plant Q extends the main stem 251, spreads new branches and leaves 252, and spreads roots. If cultivated plant Q is too biased toward vegetative growth, it is prone to develop so-called vine shriveling and end rot, which reduces the yield and distorts the shape of the fruit.

[0217] In an environment that is difficult for the cultivated plant Q to grow, the main stem length L tends to become shorter. At this time, the state of the cultivated plant Q tends to be reproductive growth, with the fruit cluster 254 growing vigorously. If the cultivated plant Q is too biased towards reproductive growth, it becomes difficult for new branches and leaves 252 to spread, which makes it difficult for new inflorescences 253 and fruit clusters 254 to be produced, resulting in a reduced yield.

[0218] Figure 22 shows a graph relating to stem diameter D2 and main stem length L. An index range G is indicated at the center of this graph. Index range G is the portion of the graph without any diagonal lines. The growth balance determination unit 226A determines the growth status based on 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 201. The various control units of the horticultural facility 201 then control the various devices so that stem diameter D2 and main stem length L are plotted within index range G.

[0219] If the cultivated plant Q has strong vigor, the stem diameter D2 will be thicker and outside the index range G. Also, if the cultivated plant Q is biased towards vegetative growth, the main stem length L will be longer and outside the index range G.

[0220] In Figure 22, stem diameter D2 is expressed as a stem diameter discrimination value Ga in multiple stages according to thickness. In Figure 22, the stem diameter discrimination value Ga is shown as +Ga1, +Ga2, and +Ga3 as discrimination values ​​when the stem diameter D2 is thick and outside the index range G. The stem diameter discrimination value Ga indicates that the stem diameter D2 becomes thicker in the order +Ga1, +Ga2, and +Ga3.

[0221] In addition, in Figure 22, the stem diameter discrimination value Ga is shown as -Ga1, -Ga2, and -Ga3 as a discrimination value when the stem diameter D2 is thin and outside the index range G. The stem diameter discrimination value Ga indicates that the stem diameter D2 becomes thinner in the order of -Ga1, -Ga2, and -Ga3.

[0222] The growth balance determination unit 226A represents the growth status as a first discrimination value (+Ga1, +Ga2, +Ga3) indicating vegetative growth in which the main stem 251 and the branch and leaf parts 252 grow, and a second discrimination value (-Ga1, -Ga2, -Ga3) indicating reproductive growth in which the fruit clusters 254 grow.

[0223] The method for determining the stem diameter discriminant value Ga will be explained based on the flowchart in Figure 23. The stem diameter calculation unit 222 recognizes the reference height position Rh (step #11), calculates the stem diameter D2 at a point a set length Lh below the reference height position Rh (step #12), and determines the stem diameter discriminant value Ga based on the graph shown in Figure 22 (step #13). The growth balance determination unit 226A compares the past stem diameter D2 with the immediately preceding stem diameter D2 calculated in step #12 to determine the tree vigor discriminant value Gc (step #14). Note that in step #14, the growth balance determination unit 226A may be configured to determine the tree vigor discriminant value Gc based on the immediately preceding stem diameter D2 calculated in step #12, without reading the past stem diameter D2.

[0224] In Figure 22, the main stem length L is expressed as a main stem length discrimination value Gb in multiple stages according to the length. In Figure 22, the main stem length discrimination value Gb is shown as +Gb1, +Gb2, and +Gb3 as a discrimination value when the main stem length L is long and outside the index range G. The main stem length discrimination value Gb indicates that the main stem length L increases in the order of +Gb1, +Gb2, and +Gb3.

[0225] In addition, in Figure 22, the main stem length discrimination value Gb is shown as -Gb1, -Gb2, and -Gb3 as a discrimination value when the main stem length L is short and outside the index range G. The main stem length discrimination value Gb indicates that the main stem length L becomes shorter in the order of -Gb1, -Gb2, and -Gb3.

[0226] The first discrimination value may be +Gb1, +Gb2, or +Gb3. The second discrimination value may be −Ga1, −Ga2, or −Ga3. In this embodiment, the growth balance determination unit 226A represents the growth status using a plurality of discrimination values ​​including the first discrimination value, the second discrimination value, and a third discrimination value (index range G between the first discrimination value and the second discrimination value).

[0227] Although the first discrimination value includes multiple levels (+Ga1 to +Ga3 and +Gb1 to +Gb3), the first discrimination value may consist of only one value. Furthermore, although the second discrimination value includes multiple levels (-Ga1 to -Ga3 and -Gb1 to -Gb3), the second discrimination value may consist of only one value. The growth balance assessment unit 226A may be configured to represent the growth status in three levels: a first discrimination value having a single value, a second discrimination value having a single value, and a third discrimination value (an index range G between the first discrimination value and the second discrimination value). Alternatively, the growth balance assessment unit 226A may be configured to represent the growth status in two levels: a first discrimination value having a single value and a second discrimination value having a single value.

[0228] The main stem length L increases over time as the cultivated plant Q grows. Then, when the next inflorescence 253 differentiates from the main stem 251 and blooms (the flowering state changes from stage #0 to stage #1), the inflorescence 253 targeted by the flowering position calculation unit 223 changes, and the main stem length L decreases. Even if the cultivated plant Q is growing appropriately, there may be problems if the growth balance determination unit 226A expresses the growth status with a first discrimination value outside the index range G simply because the main stem length L increases over time. For this reason, the growth balance determination unit 226A weights the main stem length L according to the flowering stage of the inflorescence 253.

[0229] As shown in FIG. 20 , the weighting coefficient α is used depending on the flowering state of the inflorescence 253. When the flowering state of the inflorescence 253 is stage #1, the main stem length L is converted to the value of "L × α2." When the flowering state of the inflorescence 253 is stage #2, the main stem length L is converted to the value of "L × α3." When the flowering state of the inflorescence 253 is stage #3, the main stem length L is converted to the value of "L × α4." When the flowering state of the inflorescence 253 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 weighting coefficient α is then plotted on the graph shown in FIG. 22 . That is, the growth balance determination unit 226A determines the growth status of the cultivated plant Q by performing weighting conversion depending on the flowering state of the inflorescence 253. If the blooming states of the multiple flowers in the inflorescence 253 are different, weighting is performed according to the proportion of flowers in stage #1, stage #2, stage #3, and stage #4. For example, if the proportion of flowers in one inflorescence 253 is 25% in stage #1, 35% in stage #2, 30% in stage #3, and 10% in stage #4, the main stem length L is weighted using the following formula: "L x (α2 x 0.25 + α3 x 0.35 + α4 x 0.3 + α5 x 0.1)"

[0230] The method for determining the main stem length discriminant value Gb will be explained based on the flowchart in Fig. 24. The flowering position calculation unit 223 calculates the main stem length L (step #21), and the flowering state discrimination unit 224 discriminates the flowering stage of the inflorescence portion 253 (step #22). The growth balance determination unit 226A then converts the main stem length L using a weighting coefficient α corresponding to the flowering stage (step #23), and determines the main stem length discriminant value Gb based on the graph shown in Fig. 22 (step #24).

[0231] In this way, the growth balance determination unit 226A determines the growth status of the cultivated plant Q based on the state of the main stem 251 and the inflorescence 253. The growth balance determination unit 226A 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 211A, the fertilization control unit 212A, the solar radiation control unit 213A, the carbon dioxide amount control unit 214A, etc. The stem diameter discrimination value Ga, the main stem length discrimination value Gb, and the tree vigor discrimination value Gc are numerical values ​​that represent the growth status of the cultivated plant Q.

[0232] The irrigation control unit 211A controls irrigation based on the growth status of the cultivated plant Q. When 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 has strong vigor, the irrigation control unit 211A controls the irrigation device 211B and the spray device 211C to reduce the amount of water irrigated to the cultivated plant Q.

[0233] When at least one of the following conditions is met: the stem diameter D2 is thin, the main stem length L is short, or the cultivated plant Q has weak vigor, the irrigation control unit 211A controls the irrigation device 211B and the spray device 211C to increase the amount of irrigation water applied to the cultivated plant Q.

[0234] The solar radiation amount control unit 213A controls the amount of solar radiation based on the growth status of the cultivated plant Q. When at least one of the following conditions is met: the stem diameter D2 is thick, or the cultivated plant Q has strong vigor, the solar radiation amount control unit 213A drives the curtain opening / closing device 213B so that the light-blocking curtain blocks sunlight. This suppresses photosynthesis of the cultivated plant Q, and the vigor of the cultivated plant Q is reduced.

[0235] When at least one of the cases where the stem diameter D2 is thin and the vigor of the cultivated plant Q is weak is met, the solar radiation amount control unit 213A drives the curtain opening / closing device 213B to open the shading curtain, thereby promoting photosynthesis of the cultivated plant Q and strengthening the vigor of the cultivated plant Q.

[0236] The fertilization control unit 212A controls the amount of fertilization based on the growth status of the cultivated plant Q. The carbon dioxide amount control unit 214A controls the amount of carbon dioxide based on the growth status of the cultivated plant Q. When at least one of the cases where the stem diameter D2 is thick and the cultivated plant Q has strong vigor is met, the fertilization control unit 212A does not operate the fertilizer applicator 212B. When at least one of the cases where the stem diameter D2 is thick and the cultivated plant Q has strong vigor is met, the carbon dioxide amount control unit 214A does not operate the carbon dioxide generator 214B.

[0237] The fertilization control unit 212A operates the fertilizer application device 212B when at least one of the following conditions is met: the stem diameter D2 is thin, or the vigor of the cultivated plant Q is weak. Furthermore, the carbon dioxide amount control unit 214A operates the carbon dioxide generation device 214B when at least one of the following conditions is met: the stem diameter D2 is thin, or the vigor of the cultivated plant Q is weak.

[0238] [Determination of future growth status by growth prediction determination unit] In this embodiment, a growth prediction determination unit 226B is provided in the management computer 202. The growth prediction determination unit 226B determines the future growth status of the branch / leaf portion 252 based on the stem diameter D2 of the main stem 251.

[0239] 25 , at the timing when the branch and leaf portions 252 start to differentiate from the main stem 251, the small branch and leaf portion 252 (hereinafter referred to as the “first branch and leaf portion 252A”) is imaged by the imaging device 203A, and the first branch and leaf portion 252A is further recognized by the recognition unit 221. The recognition unit 221 recognizes the first branch and leaf portion 252A that has started to differentiate from the upper part of the main stem 251, among the multiple branch and leaf portions 252 present in the cultivated plant Q.

[0240] The inflorescence 253 flowers, and a fruit cluster 254 grows on the inflorescence 253. The fruit cluster 254 is harvested when it reaches an appropriate size. The branch and leaf 252 near the inflorescence 253 from which the fruit cluster 254 has been harvested is defoliated. The growth prediction determination unit 226B acquires the stem diameter D2 calculated by the stem diameter calculation unit 222 when the first branch and leaf 252A begins to be recognized by the recognition unit 221. The growth prediction determination unit 226B then determines the growth status of the first branch and leaf 252A at the time of defoliation based on the stem diameter D2. The time of defoliation of the first branch and leaf 252A is usually about five weeks after it begins to differentiate from the upper part of the main stem 251. Figure 25 shows the second branch and leaf 252B at the time of defoliation.

[0241] The growth prediction determination unit 226B predicts the leaf length at the time when the first branch and leaf portion 252A will be defoliated as the future growth status of the first branch and leaf portion 252A. The leaf length is the length from any part at the base of each leaf in the first branch and leaf portion 252A to the tip of the leaf. The leaf length may be the maximum value of the leaf lengths of the multiple leaves in the first branch and leaf portion 252A, or the average or median of the leaf lengths of the multiple leaves in the first branch and leaf portion 252A.

[0242] In addition to the leaf length, the growth prediction determination unit 226B predicts the leaf area at the time when the first branch and leaf portion 252A will be defoliated as the future growth status of the first branch and leaf portion 252A. The leaf area is the area of ​​the lush region in the first branch and leaf portion 252A. In other words, the growth prediction determination unit 226B calculates the area of ​​the future lush region in the branch and leaf portion 252A based on the stem diameter D2. The area of ​​the lush region may be the total surface area of ​​the multiple leaves in the first branch and leaf portion 252A, or it may be the average or median of the surface areas of the multiple leaves in the first branch and leaf portion 252A. Because the area of ​​the lush region (including the leaf area) is an important factor in understanding the growth rate and management status of a plant, for example, workers and managers can easily manage the cultivated plant Q by using the area of ​​the lush region as a judgment criterion. The growth prediction determination unit 226B is configured to calculate the number of future leaves in the branch and leaf portion 252 based on the calculated area of ​​the future growth region in the branch and leaf portion 252.

[0243] The growth prediction determination unit 226B is also configured to calculate at least one of the number of leaves to be thinned and the number of fruits to be thinned based on the determined number of future leaves in the branch and leaf portion 252. The number of leaves to be thinned is, for example, the number of leaves appropriate for thinning at the time when the first branch and leaf portion 252A is thinned. The number of fruits to be thinned is, for example, the appropriate number of fruits to be thinned in the inflorescence portion 253 near the first branch and leaf portion 252A. At least one of the number of future leaves, the number of leaves to be thinned, and the number of fruits to be thinned in the branch and leaf portion 252 is displayed on, for example, a known display monitor provided in the management computer 202. Therefore, for example, a manager can appropriately manage the cultivated plant Q based on the number of leaves, the number of leaves to be thinned, and the number of fruits to be thinned displayed on the display monitor.

[0244] Additionally, the growth prediction determination unit 226B may calculate, as the future growth condition of the first branch / leaf portion 252A, the distribution degree, degree of dispersion, standard deviation, skewness, kurtosis, etc. of the leaf length and leaf area of ​​the first branch / leaf portion 252A of each of the plurality of cultivated plants Q. Furthermore, the growth prediction determination unit 226B may be configured to calculate, for example, the harvest yield of the fruit bunches 254 in the vicinity of the branch / leaf portion 252, such as the first branch / leaf portion 252A, as the future growth condition of the first branch / leaf portion 252A.

[0245] Then, just as when data is sent from the growth balance determination unit 226A, the air temperature control unit 215A, humidity control unit 216A, irrigation control unit 211A, fertilization control unit 212A, solar radiation control unit 213A, and carbon dioxide amount control unit 214A, etc., perform control based on future growth conditions. The air temperature control unit 215A performs temperature control based on future growth conditions. The humidity control unit 216A performs humidity control based on future growth conditions. The irrigation control unit 211A performs irrigation control based on future growth conditions. The solar radiation control unit 213A controls the amount of solar radiation based on future growth conditions. The fertilization control unit 212A controls the amount of fertilizer based on future growth conditions. The carbon dioxide amount control unit 214A controls the amount of carbon dioxide based on future growth conditions.

[0246] [Alternatives to the Third Embodiment] Alternatives to the third embodiment will be described below. Matters other than those described in the following alternative embodiments are the same as those described in the above embodiment.

[0247] Other Embodiments The present invention is not limited to the configurations exemplified in the above-described embodiments, and other representative embodiments of the present invention will be exemplified below.

[0248] (1) In the above-described embodiment, the stem diameter calculation unit 222 calculates the approximate curve 261 of the main stem 251 recognized by the recognition unit 221, but the stem diameter calculation unit 222 may be configured not to calculate the approximate curve 261. In this case, the stem diameter calculation unit 222 may be configured to calculate the stem diameter D2 based on at least one of the imaging data V and the distance measurement data D1.

[0249] (2) In the above-described embodiment, the horticultural facility 201 and the management computer 202 are connected via a wide area network (WAN), but this is not limited to the above-described embodiment. The management computer 202 may be provided in the horticultural facility 201, and devices such as the visual sensing unit 203 in the horticultural facility 201 may be connected to the management computer 202 via an in-facility network. The in-facility network may be wired or wireless.

[0250] (3) In the above-described embodiment, tomatoes are exemplified as cultivated plants Q, but the cultivated plants Q are not limited to tomatoes and may be strawberries, melons, cucumbers, eggplants, gourds, bitter melons, paprika, green peppers, etc. Furthermore, the cultivated plants Q are not limited to those cultivated inside the horticultural facility 201 and may be cultivated plants Q outdoors. Furthermore, the ridges A do not have to be made of a non-porous hydrophilic film and may be made of cultivated soil.

[0251] (4) The above-mentioned growth assessment unit 226 can output statistical quantities that can grasp the growth status, including, but not limited to, 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 branch and leaf portion 252, as growth status data.

[0252] The configurations disclosed in the above-described embodiments (including other embodiments, the same applies hereinafter) can be applied in combination with the configurations disclosed in other embodiments, unless a contradiction occurs. Furthermore, the embodiments disclosed in this specification are merely examples, and the present invention is not limited to these, and can be modified as appropriate within the scope of the purpose of the present invention.

[0253] The present invention can be used in a cultivation management system.

[0254] The present invention can also be applied to a growth management system for managing the growth status of cultivated plants.

[0255] (First embodiment) 21: State detection unit 22: Index output unit 23: Length detection unit (separation detection unit) 24: Identification unit 25: Estimation unit B: Shoot tip Ca: Imaging unit D: Inflorescence DA: Reference inflorescence E: Peduncle P: Cultivated plant S: Cultivation management system

[0256] (Second embodiment) 122: Fruit detection unit 123: Bunch detection unit 124: Identification unit 125: Stem detection unit 126: Measurement unit Ca: Imaging unit J: Bunch JA: Reference bunch K: Stem M: Fruit P: Cultivated plant SA: Cultivation management system

[0257] (Third embodiment) 203A: Imaging device 203B: Distance measuring device 221: Recognition unit 222: Stem diameter calculation unit 226: Growth determination unit 251: Main stem 252: Branch and leaf portion 253: Inflorescence 261: Approximation curve D1: Distance measurement data D2: Stem diameter L: Main stem length (length of main stem) Q: Cultivated plant Rh: Reference height position (reference height) Lh: Set length (predetermined length)

Claims

1. A cultivation management system comprising: an imaging unit that images a cultivated plant; a condition detection unit that detects a condition of an inflorescence of the cultivated plant based on the image acquired by the imaging unit; a separation detection unit that detects a separation index value that is a value indicating the degree of separation between the stem tip of the cultivated plant and the inflorescence based on the image; and an index output unit that outputs a growth index that is an index indicating the growth condition of the cultivated plant based on the detection result by the condition detection unit and the detection result by the separation detection unit.

2. A cultivation management system as claimed in claim 1, wherein the state detection unit detects the flowering stage of each flower in the inflorescence.

3. The cultivation management system of claim 2, wherein the index output unit has an identification unit that identifies a reference inflorescence, which is the inflorescence in a predetermined flowering state, based on the detection result by the state detection unit, the separation detection unit is configured to detect a reference separation index value that is a value indicating the degree of separation between the stem tip and the reference inflorescence, and the index output unit outputs the growth index based on the reference separation index value.

4. The cultivation management system described in claim 2, wherein the index output unit has an estimation unit that estimates a value indicating the degree of separation between the stem tip and the inflorescence at the time when the inflorescence was in the specified flowering state based on the flowering stage of each flower in the inflorescence that is more advanced in flowering than a specified flowering state and the detection result by the separation detection unit, and the index output unit outputs the growth index based on the estimation result by the estimation unit.

5. A cultivation management system as described in claim 3 or 4, wherein the specified flowering state is a state in which in one inflorescence, there is only one flower at a reference flowering stage which is a specified flowering stage, and there are no flowers that are more flowered than the reference flowering stage.

6. A cultivation management system as described in any one of claims 1 to 5, wherein the separation detection unit detects the length of the stem between the stem tip and the pedicel corresponding to the inflorescence as the separation index value.

7. A cultivation management system comprising: an imaging unit that images a cultivated plant; a fruit detection unit that detects the fruit of the cultivated plant based on the image acquired by the imaging unit; and a fruit cluster detection unit that detects the fruit cluster of the cultivated plant based on the detection result by the fruit detection unit.

8. A cultivation management system as described in claim 7, comprising: an identification unit that identifies a reference bunch, which is a bunch that satisfies a predetermined condition, from among the bunches detected by the bunch detection unit; and a measurement unit that measures the number of fruits contained in the reference bunch.

9. A cultivation management system according to claim 8, wherein the specified condition is that the tuft is a specified number of steps above the tuft located closest to the root of the cultivated plant.

10. A cultivation management system as described in claim 8 or 9, further comprising a stem detection unit that detects the stem of the cultivated plant based on the captured image, and the identification unit identifies the reference bunch based on the detection result by the bunch detection unit and the detection result by the stem detection unit.

11. A growth management system for managing the growth status of a cultivated plant, comprising: an imaging device for imaging the cultivated plant; a recognition unit for recognizing a main stem of the cultivated plant captured in an image acquired by the imaging device; and a stem diameter calculation unit for calculating the stem diameter of the main stem recognized by the recognition unit.

12. A growth management system as described in claim 11, wherein the stem diameter calculation unit is configured to calculate the stem diameter of a portion of the main stem that is a predetermined length below a reference height of the cultivated plant.

13. A growth management system as described in claim 12, wherein the recognition unit is configured to be able to recognize an inflorescence portion differentiated from an upper part of the main stem, and the stem diameter calculation unit is configured to define the position of the inflorescence portion as the reference height when the recognition unit recognizes the inflorescence portion at the upper part of the cultivated plant, and to define the position of the upper end of the main stem as the reference height when the recognition unit does not recognize the inflorescence portion at the upper part of the cultivated plant.

14. A growth management system as described in claim 13, wherein the stem diameter calculation unit is configured to define the position of the tallest flower as the reference height when the recognition unit recognizes a plurality of flowers in the inflorescence portion at the upper part of the cultivated plant.

15. A growth management system as described in any one of claims 11 to 14, wherein the stem diameter calculation unit is configured to calculate an approximation curve of the main stem recognized by the recognition unit, and to calculate the stem diameter in a normal direction or an approximately normal direction to the approximation curve.

16. A growth management system as described in any one of claims 11 to 15, further comprising a distance measuring device that acquires distance data in three-dimensional coordinates for the cultivated plant imaged by the imaging device, and the stem diameter calculation unit is configured to calculate the stem diameter of the main stem recognized by the recognition unit based on the three-dimensional coordinates.

17. A growth management system as described in any one of claims 11 to 16, wherein the recognition unit is configured to be capable of detecting an inflorescence portion that has differentiated from the upper part of the main stem and is in a bloomed state, and is provided with a growth determination unit that determines the growth status based on the length of the main stem between the upper end of the main stem and the inflorescence portion in a bloomed state.

Images