JP2015133971A - Plant cultivation plant - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a plant raising model creation system capable of managing a harvesting period, a plant cultivation plant, and a plant raising model creation method.SOLUTION: A plant raising model creation system comprises: an imaging part which captures an image of a plant to create image information of the plant; imaging position moving means for moving a position at which the imaging part captures an image to a specified position to enable the imaging part to capture the image of the plant from the specified direction; a detection part which detects a position of a flower in blooming on the basis of image information of the plant whose image is captured from the position moved by the imaging position moving means; and a model creation part which creates a raising model, in which a position of a fruit when the flower is transformed into a fruit is estimated on the basis of the position of the flower in blooming which is detected by the detection part and weight of the fruit when the flower is transformed into a fruit.

Description

  The present invention relates to a plant growth model generation system, a plant cultivation plant, and a plant growth model generation method.

  The plant cultivation system is attracting attention as being capable of reducing the load caused by cultivation work and stabilizing the supply of plants (for example, see Patent Document 1 and Non-Patent Document 1).

Japanese Utility Model Publication No. 5-17505

Hiroshige Nishina, “Progress of“ Regional Base Type Intelligent Solar Plant Factory ””, Science Council of Japan, Public Symposium “Intelligent Solar Plant Plant”, July 3, 2009.

By the way, in the plant cultivation system, further management cost reduction is desired, and enlargement of cultivation facilities (plant cultivation plant) is desired. Until now, cultivation has been carried out depending on the experience and intuition of the producer.
However, a cultivation method capable of managing the harvesting time is required as the cultivation scale increases, but it has been difficult to manage the harvesting time with a management method that relies on conventional experience and intuition.
This invention is made | formed in view of such a situation, and it aims at providing the plant growth model production | generation system which can manage a harvest time, a plant cultivation plant, and a plant growth model production | generation method.

In order to solve the above-described problem, the present invention captures an image of a plant, generates an image information of the plant, and moves a position captured by the image capturing unit to an instructed position, thereby instructing an instructed direction. An imaging position moving means that can image a plant from, a detection unit that detects a position of a flower at the time of flowering based on image information of a plant imaged from a position moved by the imaging position moving unit, and the detection unit A model generation unit that generates a breeding model that estimates the actual position when the flower has grown, based on the position of the flower at the time of flowering detected and the weight of the fruit when the flower has grown, A plant growth model generation system characterized by comprising:
Moreover, this invention is provided with the plant growth model production | generation system as described in the said invention, It is a plant cultivation plant characterized by the above-mentioned.
Further, the present invention provides an imaging position moving process in which a position where the imaging unit captures an image is moved to an instructed position so that the plant can be imaged from the instructed direction, and the plant is imaged by the imaging unit. An imaging process for generating image information, a detection process for detecting a position of a flower at the time of flowering based on image information of a plant imaged in the imaging process, and a flower at the time of flowering detected in the detection process And a model generation process for generating a breeding model that estimates the position of the fruit when the flower has grown based on the position of the flower and the weight of the fruit when the flower has grown. It is a training model generation method.

  As described above, according to the present invention, the harvest time can be managed.

It is a figure which shows the outline | summary of the plant cultivation plant by this embodiment of this invention. It is a figure which shows the mobile detection apparatus in this embodiment. It is a block diagram which shows the structure of the plant cultivation system in this embodiment. It is a figure which shows control of the harvest time of the plant in this embodiment. It is a figure which shows the positional relationship of the flower and fruit in this embodiment. It is a figure explaining the detection of the actual maturity in this embodiment. It is a figure which shows the state of the leaf in this embodiment.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing an outline of a plant cultivation plant according to this embodiment. FIG. 1A shows a cross-sectional view thereof, and FIG. 1B shows a plan view thereof.
The plant cultivation plant 4 of the present invention is a facility that includes the plant cultivation system 1 (FIG. 3) and that grows plants.
As shown in FIG. 1, the plant cultivation plant 4 illuminates a vegetation floor 6 for plant cultivation, a plant enclosure 8 for separating the vegetation floor 6 from the outside air space 7, and a plant 9 vegetated on the vegetation floor 6. Is provided. The plant cultivation plant atmosphere adjusting device 2 adjusts the atmosphere of the inner space 13 of the plant enclosure 8. The vegetation floor 6 is a soil floor in the illustrated example, but may be a hydroponic floor for hydroponics that includes a liquid fertilizer circulation device (not shown).

  The plant enclosure 8 is for keeping the vegetation floor 6 and the outside air space 7 in an atmosphere suitable for the plant to be cultivated. The lamp 10 is installed inside the plant enclosure 8 in the illustrated example.

  Furthermore, the plant cultivation plant 4 includes an air conditioner 12 for supplying air adjusted to a predetermined condition inside the plant enclosure 8. Normally, the air conditioner 12 takes air from the inner space 13 through the suction port 16, adjusts it, and returns it from the discharge port 18 to the inner space 13.

  In the plant cultivation plant atmosphere adjusting device 2, the lamp 10 is surrounded by a lamp enclosure 20. At least a part of the wall of the lamp enclosure 20 is transparent. Connected to the lamp enclosure 20 is one conduit 22 that selectively connects the inside of the lamp enclosure 20 to the inner space 13 and the outside air space 7. The lamp enclosure 20 is connected to another duct 24 that selectively connects the inside of the lamp enclosure 20 to the inner space 13 and the outside air space 7. That is, one pipe line 22 branches off at the base of the bifurcated pipe 26, and one of the bifurcated pipes 26 communicates with the inner space 13 and the other communicates with the outside air space 7. The other duct 24 branches off at the base of the bifurcated pipe 28, and one of the bifurcated pipes 28 communicates with the inner space 13 and the other communicates with the outside air space 7. Two-way switching valve portions 30 and 32 are provided at the roots of the bifurcated tubes 26 and 28, respectively.

  When the temperature of the outside air space 7 is higher than the set temperature of the inner space 13, both the one pipe line 22 and the other pipe line 24 are set by the two-way switching valve portions 30 and 32 so as to communicate with the outside air space 7. When the temperature of the outside air space 7 is lower than the set temperature of the inner space 13, both the one pipe line 22 and the other pipe line 24 are set by the two-way switching valve portions 30 and 32 so as to communicate with the inner space 13.

  With this selective setting, when the temperature of the outside air space 7 is higher than the set temperature of the inner space 13, air is taken in from the outside air space 7, and the air passes through the one pipe line 22, the lamp enclosure 20, and the other pipe line 24. The lamp 10 is cooled by this air because it proceeds in the direction of the arrow A through this order and is discharged again into the outside air space 7. Further, the air heated by the heat of the lamp 10 does not flow into the inner space 13. Therefore, an increase in the cooling load of the air conditioner 12 due to the heat of the lamp 10 is prevented, and the air conditioning load is reduced.

Further, by selective setting, when the temperature of the outside air space 7 is lower than the set temperature of the inner space 13, air is taken in from the inner space 13, and the air is one conduit 22, the lamp enclosure 20, and the other conduit 24. Since the lamp 10 is cooled by this air and the air warmed by the heat of the lamp 10 returns to the inner space 13. . Therefore, the heating load of the air conditioner 12 can be reduced by the heat of the lamp 10.
Note that one duct 22 is provided with a blowing means 36 such as a fan for blowing air in the direction of arrow A or arrow B.
Moreover, as shown in FIG.1 (b), the inner space 13 of the plant enclosure 8 is divided | segmented by the movable partition 38, and is divided into inner space 13-1 and 13-2. Each of the inner spaces 13-1 and 13-2 can be set to different environmental conditions.
In the passage between the vegetation floor 6 where the plant 9 is cultivated, the mobile detection device 40 is self-propelled to detect the state of the plant 9.

Moreover, in the plant cultivation plant 4, the case where the movement type | mold detection apparatus 40 detects the state of a plant is moving is illustrated.
With reference to FIG. 2, the mobile detection apparatus 40 which detects the state of the plant in the plant cultivation plant 4 is shown.
FIG. 2 is a diagram showing the mobile detection device 40 in the present embodiment.
The mobile detection device 40 uses the mobile vehicle body 41 as a carriage. The mobile vehicle body 41 includes wheels 41W serving as moving means, and moves by power supplied from a drive unit (not shown).
A bracket 42B is provided on the upper surface of the movable vehicle body 41 so as to be rotatably supported in the horizontal direction. The bracket 42B is provided with an arm portion 42, and the bracket 42B supports the arm portion 42 so as to roll freely in the front-rear direction. As shown in FIG. 2, the mobile detection device 40 includes a plurality of arm portions 42 (42-1, 42-2, 42-3, and 42-4) that are connected in series, and the arm portion 42. An imaging unit 300 is provided at the tip opposite to the movable vehicle body 41.

The mobile detection device 40 includes a power supply unit that allows the arm unit 42, the imaging unit 300, and the control unit of the mobile detection device 40 to function and allow self-running.
The mobile detection device control unit controls the movement of the mobile vehicle main body 41, drives the arm unit 42 as required, determines the position and direction of the imaging unit 300, and performs imaging control for causing the imaging unit 300 to function. Communication control for communicating detection processing, processing results, and the like based on the captured image information is performed.
The mobile detection device 40 detects the state of the plant 9 (FIG. 1) cultivated in the plant cultivation plant 4 while moving.
Further, the mobile detection device 40 may be a pedestal provided in place of the mobile vehicle body 41.

An outline of a plant cultivation system for controlling cultivation of plants, that is, agricultural crops will be described.
The plant cultivation system can increase the harvest amount at the scheduled harvest time by controlling the harvest time by performing various controls in the process from harvesting and shipping the plant to be cultivated.
In order to increase the amount of harvest at the scheduled harvest time, there are direct control for managing plant growth and indirect control in each process from germination to harvest.
Direct control includes processing the plant itself by thinning, pruning, or the like.
The indirect control includes setting various environmental conditions.
The plant cultivation system controls the plant and the environment in which the plant is cultivated as an object to be controlled, and optimizes the growth status and harvest time of the plant so as to increase the harvest amount at the scheduled harvest time.

In the plant cultivation system shown in this embodiment, control of each cultivation process is facilitated by modeling the plant cultivation environment as a control target.
In that control, the plant itself cannot be completely controlled by a direct method, and even in an indoor environment, it is difficult to ensure the uniformity of the environment so that there is no variation, It becomes a factor which makes control difficult. In addition, the degree of growth depends on individual differences between plants, and even within the same individual, the actual harvest time varies, which makes it difficult to control.
In this embodiment, the control target is modeled, the factors that make control difficult are regarded as disturbances, and the model is optimized according to the growth situation, thereby making it easy to control the amount of harvest at the scheduled harvest time. To.
A configuration example of such a plant cultivation system will be described.

FIG. 3 is a block diagram showing the configuration of the plant cultivation system in the present embodiment.
The plant cultivation system 1 illustrated in FIG. 3 includes, for example, a control target unit 100, a determination unit 200, an imaging unit 300, a position control unit 400, and a control unit 500.

The control target unit 100 includes a plant 9 that is a management target and an environment driving unit 120 that controls the growing environment of the plant 9.
The growth status of the plant 9 can be determined by the state of leaves, stems, flowers / fruits, and roots after germination. The growth state can be determined in relation to the elapsed time from the reference time (such as germination).
For example, in the determination based on the leaf state, the number of leaves, the size of the leaf, the projected area of the overgrown leaf, the wilting condition (angle, aspect ratio), and the like can be given. In the judgment based on the state of the stem, the height, the condition of the branch, the thickness, and the like can be given. In the determination based on the state of the flower / fruit, the number, density, arrangement, maturity of the fruit, etc. are raised. In the determination based on the state of the root, the length, the extent of spread, etc. are raised.

The environment driving unit 120 controls the growing environment where the plant is cultivated according to the amount of environment control supplied from the control unit 500.
The environment driving unit 120 includes a light control unit 121, an air conditioning facility 122, a carbon dioxide processing unit 123, and a water adjustment facility 124.

The light control unit 121 (light control means) includes a light emitting unit or a light shielding unit, and controls the light amount or wavelength of light given to the plant 9. The general plant 9 is subjected to photosynthesis by the amount of light depending on appropriate light intensity and irradiation time, and growth is promoted. Moreover, the irradiation direction of light is controlled using the circadian nature of the plant 9, and the growth direction of the plant 9 is controlled. Moreover, unlike natural light such as the sun, the light control unit 121 promotes specific growth by limiting and giving a specific wavelength.
For example, light emitting units that can limit the emission wavelength include light emitting diodes and high pressure neon lamps. When the wavelength is limited by the light shielding portion, a wavelength selective filter is used.

The air conditioner 122 controls the ambient temperature, humidity, and air volume where the plant 9 is placed.
Growth can be promoted without damaging the growth of the plant 9 by providing a sufficient volume of air while controlling the air to an appropriate ambient temperature, humidity, and air volume.
The carbon dioxide processing unit 123 controls the carbon dioxide concentration in the air managed by the air conditioning equipment 122. Photosynthesis can be promoted by maintaining an appropriate amount of carbon dioxide. The carbon dioxide processing unit 123 does not simply generate carbon dioxide, but may reuse carbon dioxide generated by other equipment.

The water conditioning facility 124 controls at least one of the amount of water supplied to the plant 9, the water temperature, and the nutrient concentration. Especially in the case of hydroponics, water temperature and nutrient concentration are important management items.
Thus, in the plant cultivation system 1, by providing the environment driving unit 120, while shielding the change of the outdoor environment, and using the form of building the cultivation environment under the artificial environment and the change of the outdoor environment, The present invention can be applied to any management support type cultivation environment in which an appropriate environment is supplementarily constructed. Which form is adopted is appropriately selected depending on conditions such as the type of plant to be cultivated, the cultivation period, the growth process, and the environment in which the facility is placed.
For example, it is known that there is a plant whose growth is promoted by continuous irradiation using artificial light for a predetermined period from germination. In addition, by selecting the wavelength to be irradiated, it is possible to control the growth amount and promote the target growth.

The determination unit 200 determines the growth status of the plant 9 based on the image information captured by the imaging unit 300 and the growth model of the plant 9.
The determination unit 200 includes a detection unit 210, a growth model unit 220, a situation storage unit 230, and a growth situation determination unit 240.
The detection unit 210 detects the growth status of the plant 9 from the imaged image information of the plant 9 and causes the status storage unit 230 to store the image information and the growth status.
Moreover, the detection unit 210 detects the position of the feature point of the plant 9 included in the image information from the image information of the captured plant 9 and the position information where the image is captured, and images the detected position information. The time information is stored in association with the image information stored in the status storage unit 230.
The training model unit 220 includes a plurality of training models. The plurality of breeding models set in the breeding model unit 220 are, for example, the breeding situation model 221 (first breeding model) based on the elapsed time, which associates the elapsed time from the reference time (such as germination) with the growth situation of the plant 9. An object to be detected using an actual arrangement model 222 (second breeding model) with respect to the position of the flower and a pattern based on the size, shape or color, in which the actual position when the flower has grown is estimated Are extracted, and a harvest time determination model 223 (third breeding model) for determining the harvest time is included.

The situation storage unit 230 stores the image information of the plant 9, the growth situation, the position information of the feature points of the plant 9 included in the image information, and the captured time information in association with each other.
The growth status determination unit 240 determines the growth status based on the growth model of the plant 9 using at least one of the stored image information and the growth status.
The breeding situation determination unit 240 includes a breeding situation model 221 (first breeding model) based on elapsed time, an actual arrangement model 222 (second breeding model) with respect to the position of the flower, and a harvest time judgment included in the breeding model unit 220. The growth status of the plant 9 is determined based on at least one of the models 223 (third growth model).

The imaging unit 300 images the plant 9 (and the situation around the plant 9), and generates image information.
The imaging unit 300 includes an imaging device equipped with a CCD or CMOS sensor and a light emitting device for auxiliary light for imaging.
The imaging unit 300 is mounted on the distal end portion of the arm unit 42 included in the movable detection device 40 (FIG. 2) included in the imaging position moving unit 400. The imaging position is changed according to the movement of the tip of the arm part 42, and the relative position with respect to the plant 9 as the subject changes. In addition, the imaging unit 300 is mounted on a swivel provided at the tip of the arm unit 42, and can be swung in an arbitrary direction by controlling the swivel. By combining these controls, the imaging unit 300 can image the plant 9 from an arbitrary position and an arbitrary direction.

The imaging position moving unit 400 (imaging position moving unit) moves the position captured by the imaging unit 300 to the instructed position so that the plant 9 can be imaged from the instructed direction.
The imaging position moving unit 400 (imaging position moving means) includes a movable detection device 40 (FIG. 2) that moves an imaging position. The movable detection device 40 (FIG. 2) includes an (articulated) arm unit. 42 (robot arm) is provided.
An optical system that guides light from the subject to the imaging unit 300 is provided at the tip of the arm unit 42, and the imaging position moving unit 400 rotates the optical axis of the optical system in a designated direction.

The control unit 500 (control unit) determines the growth status based on the growth model of the plant 9 based on the image information of the plant 9 imaged from the position moved by the imaging position moving unit 400 (imaging position moving unit). According to the result, the growing environment of the plant 9 is controlled.
The control unit 500 includes a growth model generation unit 510, an environment control unit 520, a position control unit 530, a production plan design unit 540, a harvest plan creation unit 550, and a pruning plan design unit 570.
The training model generation unit 510 generates a training model based on the image information, and updates the training model held in the training model unit 220.
The growth model generation unit 510 is a first model generation unit that determines the first growth model according to the growth status generated from the image information, and a second model that detects the position of the flower at the time of flowering from the image information and generates a second growth model. The model generation unit includes a third model generation unit that generates a third breeding model for determining the harvest time from the image information.

The environment control unit 520 generates an environment control amount that controls the growing environment according to the determined growing situation. For example, when the environment control unit 520 controls the light given to the plant 9 according to the determined growing situation, the light control unit 120 controls the light amount or wavelength of the light given to the plant 9. The environment control unit 520 controls the carbon dioxide concentration at which the plant 9 is placed by the carbon dioxide generation unit 123 when the carbon dioxide concentration to be given to the plant 9 is controlled according to the determined growing situation. When the environment control unit 520 controls the air supplied to the plant 9 according to the determined growth status, the air conditioning equipment 121 supplies at least one of ambient temperature, humidity, and air volume supplied to the plant 9. To control. When the environment control unit 520 controls the water to be supplied to the plant 9 according to the determined growth situation, the water adjustment facility 124 supplies at least water amount, water temperature, ambient temperature, and nutrient concentration supplied to the plant 9. Control one of them.
The position control unit 530 controls the imaging position moving unit 400 to instruct the position and direction in which the plant 9 is imaged. The position control unit 530 controls the imaging position moving unit 400 in order to change the position and imaging direction of the imaging unit 300 and capture image information according to the purpose.

The production plan design unit 540 designs a production plan based on the captured image information.
The harvest plan creation unit 550 creates a harvest plan based on the third breeding model.
The arrangement plan design unit 560 designs an arrangement plan for other plants 9 located around the target plant 9 according to the first growing model of the target plant 9.
The pruning plan design unit 570 (first pruning plan design unit) designs a pruning plan for pruning the plant 9 according to the first breeding model. Further, the pruning plan design unit 570 (second pruning plan design unit) designs a pruning plan for pruning the flowers (fruits) of the plant 9 according to the second growth model.

(Control of plant harvest time)
With reference to FIG. 4, control of the harvest time of the plant in this embodiment is demonstrated.
FIG. 4 is a diagram illustrating the control of the plant harvest time in the present embodiment.
In the graph shown in FIG. 4, the horizontal axis indicates the number of days (hours) elapsed from germination, the vertical axis indicates the degree of plant growth, and has a so-called growth curve shape. As shown in this graph, the degree of growth can be defined as a function according to the number of days elapsed. The standard.

The graph S4a is a breeding model showing a growth curve that is used as a reference for the management of the cultivation status of the plant 9. The harvest time can be set based on this graph S4a.
The graph S4b shows a process of growing later than the growth model shown in the graph S4a without managing the plant growth status. When growing as shown in the graph S4b, the harvesting time is delayed from the plan. Therefore, in the present plant cultivation system 1, the delay of the breeding situation detected in the process of breeding is controlled so as to promote the breeding situation by controlling the surrounding environment.
When promoting the growing situation, the processing content is selected according to the type of the plant 9 to be controlled and the time when the countermeasure is to be implemented. For example, as a breakdown of the measures, there are methods such as increasing the amount of light irradiation, increasing the ambient temperature and water temperature, and increasing the required nutrient amount.

  On the other hand, also in the case of delaying the breeding status, the processing content is selected according to the type of the plant 9 to be controlled and the timing of implementing the countermeasure. For example, as a breakdown of the measures, there are methods such as reducing the amount of light irradiation, reducing the ambient temperature and water temperature, and reducing the amount of necessary nutrients.

In addition, the detection of the breeding status by the detection unit 210 can be performed by detecting the status of each individual and making a comprehensive determination based on the detected results. In the comprehensive determination, various statistical processing techniques such as averaging the detected detection results and detecting variations can be applied.
For example, it is also possible to divide the whole into a plurality of sections and collectively determine the results detected from the plants 9 included in the sections. By dividing the partition in this way, it is possible to detect variations due to the arranged positions.

It is also possible to set different environments by arranging different types of plants for each section.
The detection of the growth status of the plant 9 may be detected based on one determination criterion or based on a plurality of variables detected based on a plurality of determination criteria.

(Detection of plant growth state)
With reference to FIGS. 5 to 7, detection of the plant growth status in this embodiment will be described.
For the detection of the growth status of the plant 9, a plurality of methods can be selected depending on the detection target.
The detection target can be selected from leaves, stems, flowers / fruits, and roots.

In the determination based on the leaf state, the number of leaves, the size of the leaf, the projected area of the overgrown leaf, the wilting condition (angle, aspect ratio of one leaf), and the like can be given.
The number of leaves is detected by counting the number of leaves existing within a predetermined range or the number of leaves attached to a stem (specified branch).
The size of one leaf is the size of the specified leaf, the average of the size of the leaf existing within a predetermined range, or the size of the leaf attached to the stem (specified branch) It is detected by calculating the average of. The size of the leaves can be the length in the longitudinal direction (vertical), the length in the direction orthogonal to the longitudinal direction (horizontal), and the area.
The projected area of the overgrown leaves detects the area projected from the side surface of the plant 9 onto the vertical plane.
The degree of leaf wilting can easily detect stress such as lack of moisture. In the wilted state, the leaf tip faces downward, and therefore, it can be detected from the angle formed by the horizontal plane and the leaf surface. Alternatively, the aspect ratio of one leaf may be calculated. By wilting, there is no leaf tension, and the apparent width becomes narrower. Therefore, the aspect ratio of a single leaf changes depending on the condition of wilting.

In the judgment based on the state of the stem, the height, the condition of the branch, the thickness, and the like can be given.
The height detects the height of the tip of the stem (or the leaf at the tip). The height of the imaging unit 300 can be detected from the height of the imaging unit 300 by matching the height of the imaging unit 300 with the height of the stem.
The degree of branch tension detects the number of branches or the length of the branches.
The thickness of the stem detects the thickness of the stem having a reference height.

In the determination based on the state of the flower / fruit, the number, density, arrangement, maturity of the fruit, etc. are raised.
FIG. 5 is a diagram showing the positional relationship between flowers and fruits.
FIGS. 5 (a) and 5 (c) show the flowering state, and FIGS. 5 (b) and 5 (d) show the fruiting state.
Since the actual position depends on the position of the flower, the actual number and position can be specified by specifying the number and position of the flowers. Flowers f1 and f2 shown in the flowering period change as fruits F1 and F2 in the mature period.
The number of flowers (fruits) is detected by counting the quantity existing within a predetermined range or the number of flowers (fruits) attached to the stem (specified branch).
The density of the flower (fruit) can be calculated by dividing the quantity of the detected flower (fruit) by the unit capacity. Or, simply, the number of flowers (fruits) existing in a predetermined range of the captured image is counted.
The arrangement of flowers (fruits) is detected by using a three-dimensional measurement technique. Moreover, the actual position of the fruiting period can be estimated from the detected position of the flower. The actual estimated position can be calculated based on the three-dimensional position of the flower by assuming the actual size and weight and using the strength and length of the branch from which the fruit hangs as calculation conditions.
From this calculated estimated position, it is possible to estimate interference with an adjacent actual object. That is, it can be estimated that interference occurs when the relative distance is closer than the actual size.

Actual maturity may be detected based on actual color changes.
FIG. 6 is a diagram for explaining detection of actual maturity.
As shown in FIG. 6A, the present invention can be applied when the color of the ripe fruit F3 is different from the color of the fruit F4 that is not fully ripe. The degree of maturity can be detected by detecting the change in color of the actual fruit F4 that is not fully ripe to the color C2 of the fruit F3 that is ripe.
As shown in FIG. 6B, a part of the actual color C2 (for example, the lower side) is discolored, and the maturity can be detected by detecting the discolored range (Z2).
The actual maturity level may change higher as the maturity level increases. Actually, a predetermined amount of light (measurement auxiliary light) is irradiated to detect the amount of transmitted light. For example, the imaging unit 300 detects the transmitted light by irradiating measurement auxiliary light from a position close to the actual lower part (or side surface). At that time, the positional relationship is adjusted so that direct light from the auxiliary light source does not enter the angle of view of the imaging unit 300.

  In the determination based on the state of the root, the length, the extent of spread, and the like can be given. If it is hydroponics, the length of a root may be detectable. The length of the root is detected from the position of the strain. The extent of root detection detects the area where the root has spread from the position of the strain. Although both the length and extent of roots are underwater, they are difficult to detect directly, but it is possible to indirectly detect shadows by roots by irradiating auxiliary light.

In addition to the direct detection method described above, information that cannot be directly measured may be indirectly detected by creating a three-dimensional model based on the directly detected result.
FIG. 7 is a diagram showing the state of leaves.
FIG. 7A shows a bird's-eye view of four stems with leaves.
The image information captured from the side surface of the plant 9 can acquire the image information as shown in this figure, but it is difficult to detect a planar state. Therefore, four leaves are extracted as three-dimensional information.
FIG. 7B shows the result of projecting on the horizontal plane based on the result of using the four leaves shown in FIG. 7A as the three-dimensional information. By adopting such an order conversion method, even when it is difficult to image from the upper part of the plant 9, it is possible to create a planar projection view of leaves of any height. A broken-line circle indicates a circle passing near the tip of the leaf.

FIG. 7C shows a state where the four leaves shown in FIG. The state where the tip of each leaf hangs down toward the ground is shown. The four leaves in this state are extracted as three-dimensional information.
FIG. 7 (d) shows the result of projection on the horizontal plane based on the result of using the four leaves shown in FIG. 7 (c) as three-dimensional information in the same manner as FIG. 7 (b). Since the four leaves are in a wilted state, the circle passing near the tip of the leaf is smaller than the circle passing near the tip of the leaf shown in FIG.
By detecting the diameter of the circle passing through the vicinity of the tip of the leaf indicated by the projected leaf image, it is possible to detect the degree of leaf growth, the condition of wilting, and the like.
Moreover, it can be applied to detecting the state of a plant flower such as “chrysanthemum” where a flower blooms at the tip of the stem.

(Generation of training model)
Next, the training model will be described.
In the above-mentioned “(Detection of plant growth state)”, the growth state of the plant 9 under the detection condition suitable for the purpose is shown. It shows about the production | generation of the breeding model used as a reference | standard for determining the detected breeding state.
First, in order to determine the growth status of the plant 9 according to the elapsed time from the reference time (such as germination), the process of associating the elapsed time from the reference time (such as germination) with the growth status of the plant 9 A training situation model by time (first training model) is required.
Various items can be selected for the first breeding model. For example, in the determination based on the leaf state, the number of leaves, the size of the leaf, the projected area of the overgrown leaf, the wilting condition (angle, aspect ratio), and the like can be given. In the judgment based on the state of the stem, the height, the condition of the branch, the thickness, and the like can be given. In the determination based on the state of the flower / fruit, the number, density, arrangement, maturity of the fruit, etc. are raised. In the determination based on the state of the root, the length, the extent of spread, etc. are raised.
In the selected item, modeling can be performed by using a numerical value based on the growth curve as a reference value according to the elapsed time from the reference time (such as germination).
This first breeding model can be used not only as a reference for growth of an individual but also when determining interference with an adjacent individual.

In addition, an actual arrangement model (second breeding model) with respect to the position of the flower, which estimates the actual position when the flower has grown, is required.
In this second breeding model, the number, density, arrangement, and the like are raised in the determination based on the state of the flower / fruit.
In the selected item, the model can be modeled by using the position and size of the actual arrangement with respect to the position of the flower as reference values.
This second breeding model can be used not only as a reference for individual actual growth, but also when determining adjacent real interference based on the size and isolation distance of each adjacent real.

  Further, a harvest time determination model (third breeding model) for determining the harvest time, which extracts the characteristics of the target to be detected using a pattern based on the size, shape, or color, is required.

That is, the breeding model generation unit 510 generates a reference value by modeling a numerical value corresponding to the item selected as the determination item, and sets it as the initial value of the growth model unit 220.
The growth model generation unit 510 generates and updates the generation of the growth model based on the image information. If there is a large discrepancy between the generated breeding model and the actual state, an unreasonable amount of control may be given. In that case, the growth model generation unit 510 makes a determination based on a predetermined threshold value, corrects the growth model, and updates the value held in the growth model unit. The update of the breeding model may be changed by a growth process determined in stages.

  In the determination unit 200, a value detected by determining (calculating) the growth status determination unit 240 based on the value detected by the detection unit 210 and the value of each growth model held in the growth model unit 220. And the difference with the value of each breeding model held in breeding model part 220 is calculated, and the breeding situation is judged.

  The breeding model generation unit 510 may calculate the value of the breeding model by statistically processing the detected value detected in the past, the value of the model set in the past, and the like.

(Control of the surrounding environment)
The environment control unit 520 generates an environment control amount that controls the growing environment according to the determined growing situation. For example, when the environment control unit 520 controls the light given to the plant 9 according to the determined growing situation, the light control unit 120 controls the light amount or wavelength of the light given to the plant 9. The environment control unit 520 controls the carbon dioxide concentration at which the plant 9 is placed by the carbon dioxide generation unit 123 when the carbon dioxide concentration to be given to the plant 9 is controlled according to the determined growing situation. When the environment control unit 520 controls the air supplied to the plant 9 according to the determined growth status, the air conditioning equipment 121 supplies at least one of ambient temperature, humidity, and air volume supplied to the plant 9. To control. When the environment control unit 520 controls the water to be supplied to the plant 9 according to the determined growth situation, the water adjustment facility 124 supplies at least water amount, water temperature, ambient temperature, and nutrient concentration supplied to the plant 9. Control one.
The control of the surrounding environment is repeatedly performed at a relatively short period during cultivation, and by detecting an abnormal value early, damage to the plant 9 is reduced and cultivation can be performed in an appropriate environment.

(Control of imaging position)
The position control unit 530 controls the imaging position moving unit 400 to instruct the position and direction in which the plant 9 is imaged. The position control unit 530 controls the imaging position moving unit 400 in order to change the position and imaging direction of the imaging unit 300 and capture image information according to the purpose.
Since the imaging position control unit 400 includes the movable detection device 40 including the multi-indirect type arm unit 42, the position of the imaging unit 300 can be set flexibly.
Even if the fruit of the plant 9 becomes a shadow of a leaf or other fruit, the imaging unit 300 can be easily moved to a position that is not affected by them. Thereby, even if the fruit of the plant 9 to be photographed is hidden in the shadow of the leaves or other fruits, the fruit of the plant 9 to be photographed can be reliably imaged by the imaging unit 300 without being hindered by them. it can.
In addition, although the imaging part 300 shall be arrange | positioned at the front-end | tip part of the arm part 40, you may be provided in the arm near the front-end | tip of the arm part 40, or the pan head provided in the arm. Moreover, although it was set as the front-end | tip of the arm part 40, you may incorporate in the arm part 40. FIG.

(Design of production plan)
The production plan design unit 540 designs a production plan based on the captured image information. By designing a production plan based on the image information, it is possible to efficiently cultivate the plant 9 by effectively using the facilities of the plant cultivation system 1 as well as determining whether or not to harvest. This production plan can also be used to adjust the shipment amount at the target time.

(Design of harvest plan)
The harvest plan creation unit 550 designs a harvest plan based on the third breeding model.
By designing based on the third breeding model, the system for determining whether or not harvesting is possible can be enhanced. By performing this determination, for example, the actual harvest time can be optimized, and the quality can be made uniform.
The image information for creating the harvest plan can be earned when approaching when performing other processing on each plant 9. Alternatively, if the harvesting order is formulated by a harvesting plan designed in the past, the detection frequency can be controlled according to the harvesting order. That is, it is possible to increase the detection frequency for the fruits whose harvest time is determined to be delayed by the harvest plan and to increase the detection frequency for the fruits whose harvest time is near, so that the detection efficiency can be increased.
It can also be used as a determination condition for raising or postponing the harvest time. Thereby, the quantity according to the required shipment quantity can be harvested.

(Design of layout plan)
The arrangement plan design unit 560 designs an arrangement plan of the plants 9 located around according to the first breeding model. By designing based on the first breeding model, the size of the individual plant 9 after growth can be calculated.
By formulating this arrangement plan, it is possible to efficiently arrange plants while preventing interference with adjacent plants or facilities in the growth process. This arrangement plan is a criterion for determining an appropriate arrangement or the like when so-called thinning is performed or when different types of plants do not match each other.

(Design of pruning plan)
The pruning plan design unit 570 designs a pruning plan for pruning the plant 9 according to the first breeding model.
Thereby, the case where it interferes with the adjacent plant 9 or its own branch can be estimated, and the branch to be pruned and its position can be selected appropriately.
Moreover, the pruning plan design part 570 designs the pruning plan which prunes the flower (fruit) of the plant 9 according to a 2nd growth model.
Thereby, the case where it interferes with an own branch and a fruit can be estimated by calculating the position which grows in the plant 9, the branch and the fruit to be pruned can be selected, and the pruning position can be appropriately selected. .

(Control of plant cultivation system)
In the plant cultivation system 1 shown in the present embodiment, the imaging unit 300 images the plant 110 and generates image information.
The imaging position moving unit 400 (imaging position moving unit) includes an (articulated) arm unit 42 (robot arm) that moves the position captured by the imaging unit 300, so that the plant 9 can be moved from any position and direction. The situation can be measured, and the harvesting time can be controlled by controlling the environmental conditions based on the measured image information.
The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes changes and the like without departing from the gist of the present invention.
For example, in the configuration illustrated in FIG. 3, the control unit 500 may be configured to control a plurality of plant cultivation systems without having to be provided independently.

  Moreover, the plant cultivation plant 4 of this embodiment does not restrict | limit that it is a land facility. For example, the plant cultivation plant 4 can also move on the sea by providing a moving means for navigating on the water. The plant cultivation plant 4 can reduce the temperature difference between the climate and the plant cultivation plant by moving to an appropriate latitude according to the temperature fluctuations of the four seasons, and the loss due to the air conditioning equipment and water temperature control equipment Can be reduced. For example, the movement may be set according to the four seasons and be about four times.

  For example, the plant cultivation plant 4 can construct | assemble the environment with few changes of temperature by constructing in the ground and underwater.

In addition, the plant cultivation plant 4 of this embodiment can grow several types of plants 9 together in one plant.
It can be realized by providing a partition that divides the space inside the plant cultivation plant 4 and setting the type of the plant 9 that is cultivated in a separated space unit. Moreover, by making the structure of the partition wall movable, the size (capacity) of the space to be divided can be changed. By providing such a partition, a space can be divided according to the amount of plants to be cultivated.
For example, preparation for the next cultivation can be started using the space where the harvest is finished.
Moreover, when growing the same kind, environmental conditions can be changed and the harvest time can be controlled for each divided space.

  In addition, the above-mentioned plant cultivation system 1 and the mobile detection apparatus 40 have a computer system inside. The operation process of each functional unit is stored in a computer-readable recording medium in the form of a program, and the above processing is performed by the computer system reading and executing the program. The computer system here includes a CPU, various memories, an OS, and hardware such as peripheral devices.

Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used.
The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Furthermore, the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory in a computer system serving as a server or a client in that case, and a program that holds a program for a certain period of time are also included. The program may be a program for realizing a part of the functions described above, and may be a program capable of realizing the functions described above in combination with a program already recorded in a computer system.

1 ... Plant cultivation system,
9 ... plants,
100 ... control target part,
200 ... determination part,
300 ... Imaging unit 400 ... Imaging position moving unit,
500 ... control unit

The present invention relates to a plant cultivation plant .

A plant cultivation plant has been attracting attention as being capable of reducing the load caused by cultivation work and stabilizing the supply of plants (for example, see Patent Literature 1 and Non-Patent Literature 1).

By the way, in the plant cultivation plant , further management cost reduction is desired, and the enlargement of cultivation facilities (plant cultivation plant) is desired. Until now, cultivation has been carried out depending on the experience and intuition of the producer.
However, a cultivation method capable of managing the harvesting time is required as the cultivation scale increases, but it has been difficult to manage the harvesting time with a management method that relies on conventional experience and intuition.
This invention is made | formed in view of such a situation, and it aims at providing the plant cultivation plant which can manage a harvest time.

In order to solve the above problems, the present invention provides a vegetation floor for plant cultivation, a plant enclosure that keeps the periphery of the vegetation floor separated from an outside air space, and maintains an atmosphere suitable for a plant to be cultivated, and the vegetation floor. A plant cultivation plant atmosphere adjustment device including a lamp for irradiating light to a plant to be vegetated, the vegetation floor, the plant enclosure, and a moving means that enables the plant cultivation plant atmosphere adjustment device to be able to navigate on the water. It is a plant cultivation plant characterized by providing.

Claims (10)

An imaging unit that images a plant and generates image information of the plant;
An imaging position moving unit that moves the position where the imaging unit captures an image to an instructed position so that the plant can be imaged from the instructed direction;
Based on the image information of the plant imaged from the position moved by the imaging position moving means, a detection unit for detecting the position of the flower at the time of flowering;
Model generation for generating a breeding model that estimates the actual position when the flower has formed based on the position of the flower at the time of flowering detected by the detection unit and the actual weight when the flower has grown And
A plant growth model generation system comprising: The model generation unit
Furthermore, the said growth model is produced | generated based on the elapsed time from the reference time. The plant growth model production | generation system of Claim 1 characterized by the above-mentioned. The breeding model includes information indicating a standard of the plant growth status,
Based on the image information and information indicating a standard of the plant growth status, a determination unit that determines the plant growth status;
The plant growth model generation system according to claim 1, further comprising: a control unit that controls a growth rate of the plant based on the growth status of the plant determined by the determination unit. The model generation unit
The plant growth model according to any one of claims 1 to 3, wherein the generated growth model is updated, and an update cycle of the growth model is changed based on a growth status of the plant. Generation system. The model generation unit
Furthermore, the said growth model is produced | generated based on the intensity | strength of the branch which the said flower attaches estimated based on the said image information. The plant growth as described in any one of Claims 1-4 characterized by the above-mentioned. Model generation system. The plant growth model generation system according to any one of claims 1 to 5, further comprising a pruning plan design unit that designs a pruning plan for pruning the plant based on the growing model. The pruning plan includes a flower pruning plan for pruning the flowers of the plant,
The pruning plan design unit
The plant growing model generation system according to claim 6, wherein the flower pruning plan for pruning the flowers of the plant is designed based on the growing model. The plant growth model generation system according to any one of claims 1 to 7, further comprising: a harvest time determination unit that determines an actual harvest time from the image information. A plant cultivation plant comprising the plant growth model generation system according to any one of claims 1 to 8. An imaging position moving process that allows the imaging unit to move to a designated position and image a plant from the designated direction,
An imaging process in which a plant is imaged by the imaging unit and image information of the plant is generated;
Based on the image information of the plant imaged in the imaging process, a detection process of detecting the position of the flower at the time of flowering;
A model that generates a breeding model that estimates the actual position of the flower when the flower has formed, based on the position of the flower that has been detected in the detection process and the actual weight of the flower when the flower has grown Generation process,
A plant growth model generation method comprising:

Images