Cultivation environment survey method and cultivation environment survey program, and cultivation management method and cultivation management program

Abstract

To determine a place where growth of crops in a field is not successful and hence investigation of cultivation environment needs to be carried out.SOLUTION: A biological investigation unit 102, based on a result of two biological investigations carried out at different timings for each cabbage grown in a field (calculation result of projected leaf area by using an image), calculates an increase amount (measured value) of the projected leaf area. A comparison unit 106 compares an increased amount (target value) of the projected leaf area of each cabbage estimated based on cultivation environment data at the cultivation point of each cabbage with an increased amount (measured amount) of the projection leaf area of each cabbage. A countermeasure determining unit 108, based on the comparison result, determines whether or not growth of each cabbage is successful. The countermeasure determining unit 108, based on the determination result, determines whether or not the cultivation environment of each cabbage needs to be investigated.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a cultivation environment investigation method and a cultivation environment investigation program, and a cultivation management method and a cultivation management program. [Background technology]

[0002] Currently, contract transactions between agricultural producers and end users are increasing, and producers are being asked to ensure stable shipments in accordance with the contracts. This requires producers to implement appropriate cultivation management.

[0003] For proper cultivation management, it is necessary to understand the state of the crops and the state of the field and manage them to maintain an appropriate state. As a method for understanding the state of the crops, a method using images taken from above the field is known (see, for example, Patent Document 1). As a method for understanding the state of the field, a method is known in which the moisture content, electrical conductivity, etc. at multiple points in the field are acquired and analyzed (see, for example, Patent Document 2).

[0004] In addition, a technology is known that detects the growth status of an object by analyzing an image of the entire field, and predicts future growth status based on the detected growth status, current environmental information of the field, and past environmental information (see, for example, Patent Document 3, etc.). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2021-151228 [Patent Document 2] Japanese Patent Publication No. 2020-61984 [Patent Document 3] International Publication No. 2019 / 106733 Summary of the Invention [Problem to be solved by the invention]

[0006] However, even if the condition of the crops can be grasped using images, it is not necessarily possible to identify the cause of poor growth. Furthermore, when acquiring and analyzing the moisture content and electrical conductivity at multiple points in a field, the amount of data to be analyzed increases, and multiple data must be subjected to statistical processing, which may take a long time. Furthermore, while the technology of Patent Document 3 can predict the growth status of the entire field, it cannot be used to investigate the local cultivation environment within the field.

[0007] In one aspect, the present invention aims to provide a cultivation environment investigation method and a cultivation environment investigation program that can determine points in a field where crop growth is not going well and where an investigation of the cultivation environment is necessary, as well as a cultivation management method and a cultivation management program that can perform appropriate cultivation management. [Means for solving the problem]

[0008] A cultivation environment survey method according to a first aspect is a cultivation environment survey method in which a computer executes the following processes: based on the results of two biological surveys conducted at different times on a specific crop growing at a specified point in a field, a value indicating the growth rate of the specific crop is calculated as a measured value; a value indicating the growth rate of the specific crop estimated based on cultivation environment data at the specified point is set as a target value; by comparing the measured value with the target value, it is determined whether the specific crop is growing smoothly; and based on the result of the determination, it is decided whether to survey the cultivation environment at the specified point or in the vicinity of the specified point.

[0009] A cultivation management method according to a second aspect includes the steps of: determining whether to investigate the cultivation environment at the predetermined point or in the vicinity of the predetermined point using the cultivation environment investigation method according to the first aspect; and, when it is determined that the cultivation environment at the predetermined point or in the vicinity of the predetermined point is to be investigated, Determining an investigation to be carried out based on information on whether the specific crop is in the early growth stage, and information obtained by the determined investigation, At or near the specified point Which of irrigation, fertilization, and pest control treatment should be performed based on at least one of information on soil moisture, information on the concentration of fertilizer components at the specified point or in the vicinity of the specified point, and information on the presence or absence of pests based on an image of the specific crop? Determine Decided Displaying the processing to be performed, or Decided notifying the processing device of the processing content to be executed; This is a cultivation management method in which processing is carried out by a computer. [Effects of the Invention]

[0010] The cultivation environment investigation method and cultivation environment investigation program can determine points in a field where crop growth is not going well and where an investigation of the cultivation environment is necessary. Also, the cultivation management method and cultivation management program can perform appropriate cultivation management. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a graph showing the results of an investigation into the relationship between the increase in projected leaf area of ​​cabbage in the early stages of growth and the weight of the cabbage head at harvest time. [Figure 2] 1 is a diagram illustrating a schematic configuration of an agricultural system according to an embodiment. [Figure 3] FIG. 2 is a diagram illustrating a hardware configuration of the server in FIG. [Figure 4] FIG. 2 is a functional block diagram of the server in FIG. 1. [Figure 5] FIG. 5(a) is a diagram showing the survey result table (two weeks after planting), and FIG. 5(b) is a diagram showing the target value table (two weeks after planting). [Figure 6] FIG. 1 is a diagram showing an example of a growth model. [Figure 7] FIG. 10 is a diagram for explaining the processing of a comparison unit. [Figure 8] 10 is a flowchart (part 1) showing the processing of the server. [Figure 9] 10 is a flowchart (part 2) showing the processing of the server. [Figure 10] FIG. 1 is a graph showing the relationship between the fertilizer component concentration in the soil and the increase in projected leaf area in the early growth stage and the head weight at harvest. [Figure 11] FIG. 11(a) is a diagram showing the survey result table (three weeks after planting), and FIG. 11(b) is a diagram showing the target value table (three weeks after planting). DETAILED DESCRIPTION OF THE INVENTION

[0012] An agricultural system according to one embodiment will be described in detail below with reference to FIGS.

[0013] The agricultural system of this embodiment is a system for monitoring the cultivation environment of crops in a field where the crops are grown and managing the field so that the crops are grown in an appropriate environment. The target crops in this embodiment are crops that produce one harvest per stalk, such as cabbage, lettuce, spinach, broccoli, radish, carrot, and leek. Any crop whose leaves unfold or elongate and whose growth process is easy to observe can be targeted. Also targeted are crops that can be regenerated, such as komatsuna (Japanese mustard spinach) and spinach, which are harvested at a height of about a few centimeters above the ground, regenerated from the stump, and then harvested repeatedly. In this embodiment, the crop is described using cabbage as an example.

[0014] Figure 1 is a graph showing the results of an investigation into the relationship between the increase in projected leaf area of ​​cabbage in the early stages of growth (for example, one to two weeks after planting) and the weight of the cabbage head at harvest time. The increase in projected leaf area of ​​cabbage was calculated by measuring the projected leaf area (cm2) obtained from images of the cabbage taken from above (a specified height) at two different times (one week after planting and two weeks after planting). 2 / plant). When calculating the projected leaf area from an image, a known method is to identify individual cabbage plants by image processing (e.g., pixel binarization), and convert the number of pixels included in the area of ​​each individual cabbage plant into an area, which is then used as the projected leaf area.

[0015] As shown in Figure 1, it can be seen that individuals with a small increase in projected leaf area in the early stages of growth have a small bulb weight at harvest, while individuals with a large increase in projected leaf area in the early stages of growth have a large bulb weight at harvest. In the case of Figure 1, if the increase in projected leaf area in the early stages of growth is x and the bulb weight at harvest is y, it can be approximated by a linear function (y = 4.08x + 372.98). The coefficient of determination of this linear function (R 2) is 0.56, which means that there is a high correlation. Therefore, when cultivating cabbage, if the cultivation environment is managed so that the increase in projected leaf area in the early stages of growth is an appropriate value, it is thought that the head weight at harvest can also be an appropriate value. Based on this idea, in this embodiment, the cultivation environment for each crop is managed to be in an appropriate state in the early stages of growth.

[0016] FIG. 2 shows a schematic configuration of an agricultural system 100 according to this embodiment.

[0017] 2, the agricultural system 100 includes a server 10, an environmental data providing device 20, a drone 30, a camera 32, a sensing robot 40, a material spraying device 50 as a processing device, and a user terminal 60. Each component of the agricultural system 100 is connected to a network 80 such as the Internet.

[0018] The server 10 collects data from the environmental data providing device 20, drone 30, camera 32, and sensing robot 40, determines whether the growth of each cabbage cultivated at each point in the field is going well, and if it is not going well, identifies the cause. The server 10 also controls the material spraying device 50 and takes measures (countermeasures) for the cabbages that are not growing well. The hardware configuration, functions, and processing contents of the server 10 will be described in detail later.

[0019] The environmental data providing device 20 is a device that provides past environmental data of a farm field to the server 10. The environmental data providing device 20 may be a device that transmits environmental data obtained by an environmental sensor installed in the farm field to the server 10, or may be a server of the Japan Meteorological Agency that provides mesh environmental data.

[0020] The drone 30 is an unmanned aerial vehicle also known as a multicopter. The drone 30 flies over the field based on instructions from the server 10. The drone 30 is also equipped with a camera 32. While the drone 30 is flying over the field, the camera 32 photographs each cabbage grown in the field from above in accordance with instructions from the server 10. The position of the drone 30 is successively detected by an RTK-GNSS (Real Time Kinematic-Global Navigation Satellite System) device possessed by the drone 30. Therefore, the server 10 can transmit a photographing instruction to the camera 32 according to the position, thereby photographing each cabbage from a predetermined position and a predetermined height.

[0021] The sensing robot 40 is a robot capable of moving within a farm field and is equipped with sensors capable of detecting soil moisture content (hereinafter referred to as "soil moisture") and fertilizer concentration (EC). In response to instructions from the server 10, the sensing robot 40 measures soil moisture and fertilizer concentration in soil near cabbages that are not growing well. EC stands for Electrical Conductivity, which refers to the ease with which electricity flows. It is positively correlated with the concentration of water-soluble salts present in the soil. Except for saline-alkaline soils with high sodium content, EC is generally strongly proportional to the concentration of water-soluble fertilizer components in the soil, particularly the concentration of nitrate nitrogen in farmland. Therefore, EC is often used as an index to estimate the concentration of fertilizer components in the soil.

[0022] The material spraying device 50 is a robot that can move within a farm field, and performs localized treatment on cabbages that are not growing well in accordance with instructions from the server 10. The material spraying device 50 performs, for example, local irrigation to locally spray water, local fertilization to locally apply fertilizer, and local pest control to locally eliminate pests.

[0023] The user terminal 60 is an information processing device that enables a worker to check the processing contents of the server 10 and the positions and operating statuses of the drone 30, the sensing robot 40, and the material spraying device 50. The user terminal 60 is a terminal such as a PC (Personal Computer) or a smartphone.

[0024] (About Server 10) FIG. 3 shows an example of the hardware configuration of the server 10. As shown in FIG. 3, the server 10 includes a central processing unit (CPU) 190, a read-only memory (ROM) 192, a random access memory (RAM) 194, storage (a hard disk drive (HDD) or a solid state drive (SSD)) 196, a network interface 197, a display unit 193, an input unit 195, and a portable storage medium drive 199. The display unit 193 includes a liquid crystal display or the like, and the input unit 195 includes a keyboard, a mouse, a touch panel, and the like. These components of the server 10 are connected to a bus 198. In the server 10, the CPU 190 executes a program (including a cultivation environment survey program) stored in the ROM 192 or the HDD 196, or a program read by the portable storage medium drive 199 from the portable storage medium 191, thereby realizing the functions of the components shown in FIG. 4. The functions of the units in FIG. 4 may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0025] Fig. 4 is a functional block diagram of the server 10. As shown in Fig. 4, the server 10 functions as a biological survey unit 102, a growth prediction unit 104, a comparison unit 106, a countermeasure decision unit 108, an information acquisition unit 110, and an instruction unit 112 by the CPU 190 executing a program.

[0026] The living body survey unit 102 calculates a value indicating the growth rate of each cabbage based on the results of two living body surveys conducted at different times for each cabbage cultivated in the field. Specifically, the living body survey unit 102 calculates the projected leaf area (first area) of each cabbage from an image of each cabbage taken by the camera 32 at a first timing after the cabbages are planted in the field, and stores the calculated projected leaf area (first area) in the survey result table 120 in association with the photographing position. The living body survey unit 102 takes an image with one cabbage within the field angle of the camera 32, or with multiple cabbages within the field angle, and divides the photographed image into areas for each cabbage. The projected leaf area obtained from the image is in units of (pixels / plant), but this can be converted to the projected leaf area unit (cm 2 Various methods can be used to convert the projected leaf area (pixels / strain) to the projected leaf area (cm2 / strain). For example, by using a predetermined formula, the projected leaf area (pixels / strain) can be converted to the projected leaf area (cm2 / strain) from the projected leaf area (pixels / strain), the shooting height (cm2), the size of the image sensor (cm2) of the camera 32, the focal length (cm2), the image size (pixels), etc. 2 / share).

[0027] Furthermore, the living body survey unit 102 calculates the projected leaf area (second area) of each cabbage from an image of each cabbage taken by the camera 32 at a second timing after planting, and stores the calculated projected leaf area (second area) in association with the photographing position in the survey result table 120. FIG. 5 shows an example of the survey result table 120. As shown in FIG. 5, the survey result table 120 stores the "photographing date" and the "projected leaf area" in association with the "position." In this embodiment, the process of calculating the projected leaf area (first area) from the image and the process of calculating the projected leaf area (second area) from the image correspond to a living body survey.

[0028] Furthermore, the living body surveying unit 102 calculates the increase (measurement) in projected leaf area by subtracting the projected leaf area (first area) of each cabbage obtained at the first timing from the projected leaf area (second area) of each cabbage obtained at the second timing, and stores the calculated increase in projected leaf area in the survey result table 120 (the "increase (measurement)" column). For example, in the case of cabbage No. 0001 in the survey result table 120, the living body surveying unit 102 calculates the increase (measurement) by subtracting the first area α11 obtained at the first timing from the second area α21 obtained at the second timing (α21-α11). In this embodiment, the increase (measurement) in projected leaf area corresponds to a value indicating the growth rate of the cabbage.

[0029] Returning to Figure 4, the growth prediction unit 104 acquires environmental data (daily average temperature, daily accumulated solar radiation) of the field between the first timing and the second timing described above from the environmental data providing device 20, and estimates the projected leaf area (second area) of each cabbage at the second timing using the acquired environmental data and the projected leaf area (first area) of each cabbage obtained at the first timing.

[0030] Here, the growth prediction unit 104 estimates the second area using a growth model for predicting the growth of cabbage as shown in Fig. 6. Note that the projected leaf area (cm 2 The initial value of the projected leaf area (cm / plant) is the first area calculated by the living body survey unit 102. The growth prediction unit 104 calculates the projected leaf area (cm 2 / share), daily accumulated solar radiation (MJ / m 2 ), and planting density (plants / m 2 ) and calculate the daily accumulated amount of light received (MJ / stock) (S21).

[0031] Next, the growth prediction unit 104 calculates the future daily dry matter production (g / plant) from the calculated daily integrated amount of received light (MJ / plant) (S22). In calculating this daily dry matter production, the solar radiation use efficiency (g / MJ) is used.

[0032] Next, the growth prediction unit 104 calculates the dry matter weight (g / plant) of the plant by adding the daily dry matter production (g / plant) calculated in step S22 to the dry matter weight up to the previous day (the dry matter weight at the first timing is calculated from the first area) (S23).

[0033] Next, the growth prediction unit 104 calculates the outer leaf dry matter weight (g / plant) and the head dry matter weight (g / plant) using the plant dry matter weight (g / plant) and the dry matter distribution rate (%) (S24). The growth prediction unit 104 also calculates the outer leaf fresh weight (g / plant) based on the outer leaf dry matter weight (g / plant) and the outer leaf dry matter rate (%) (S25). Furthermore, the growth prediction unit 104 calculates the head fresh weight (g / plant) based on the head dry matter weight (g / plant) and the head dry matter rate (%) (S26).

[0034] Next, the growth prediction unit 104 calculates the fresh weight of the plant (g / plant) by multiplying the ratio of the projected leaf area / fresh weight (g / plant) by the fresh weight of the plant (g / plant) (S27). 2 The growth prediction unit 104 repeats this process using the environmental data between the first timing and the second timing, thereby estimating the projected leaf area at the second timing.

[0035] The growth prediction unit 104 stores the projected leaf area (first area) used in the processing and the estimated projected leaf area (second area) in the target value table 122. As shown in FIG. 5(b), the target value table 122 has a table structure similar to that of the investigation result table 120, but instead of the row of "increase amount (measured value)" in the investigation result table 120, it has a row of "increase amount (target value)".

[0036] Furthermore, the growth prediction unit 104 calculates the increase in projected leaf area (target value) by subtracting the projected leaf area at the first timing (first area) from the estimated projected leaf area at the second timing (second area), and stores the calculated increase in projected leaf area in the target value table 122. For example, in the case of the cabbage No. 0001 in the target value table 122, the growth prediction unit 104 sets the target increase in projected leaf area to the value (α21'-α11) obtained by subtracting the first area α11 obtained at the first timing from the estimated second area α21'. This target increase in projected leaf area can be considered to be the increase in projected leaf area that can be expected if the cabbage is grown in an appropriate cultivation environment from the first timing to the second timing. Therefore, if the increase in projected leaf area obtained from the image calculated by the biological survey unit 102 does not reach the target value calculated by the growth prediction unit 104, it can be said that growth is not going well for some reason.

[0037] The comparison unit 106 compares, for each cabbage in the field, the increase in projected leaf area (measured value) calculated by the biological survey unit 102 with the increase in projected leaf area (target value) calculated by the growth prediction unit 104. The comparison unit 106 transmits the comparison result to the countermeasure determination unit 108.

[0038] In Figure 7, the solid lines show the changes in the projected leaf area of ​​two cabbages (Individual 1 and Individual 2). Individual 1 had a projected leaf area of ​​60 cm2 one week after planting. 2 Two weeks after planting, the projected leaf area was 160 cm 2 (See the ● mark in Figure 7.) For individual 1, the projected leaf area (60 cm) obtained one week after planting was 2 ) and the change in projected leaf area estimated by inputting the environmental data from the first week to the second week into the growth model (Fig. 6) was almost the same as the solid line for individual 1, and the estimated projected leaf area two weeks after planting was 160 cm 2 In this case, the increase in projected leaf area (measured value) is 160-60=100cm 2 The increase in projected leaf area (target value) is 160-60=100cm 2 Therefore, the increase in projected leaf area is Increase (measured value) = Increase (target value).

[0039] On the other hand, individual 2 had a projected leaf area of ​​90 cm within one week after planting. 2 Two weeks after planting, the projected leaf area was 180 cm 2 (See the triangle in Figure 7.) For individual 2, the projected leaf area (90 cm) obtained one week after planting was 2 ) and the environmental data from the first week to the second week were input into the growth model (Fig. 6). The change in projected leaf area estimated by inputting this data is shown by the dashed line in Fig. 7. The estimated projected leaf area two weeks after planting was 230 cm. 2 In this case, the increase in projected leaf area (measured value) is 180-90=90cm 2 The increase in projected leaf area (target value) is 230-90=140cm 2 Therefore, the increase in projected leaf area is increased (measured value) < increased (target value).

[0040] The countermeasure decision unit 108 acquires various information via the information acquisition unit 110 and decides countermeasures to be implemented for cabbages that are not growing well.

[0041] For example, when the countermeasure determination unit 108 needs to measure the soil moisture and fertilizer component concentrations in the soil at or near a location where a cabbage that is not growing well is being grown, the countermeasure determination unit 108 determines to carry out these measurements. In this case, the countermeasure determination unit 108 transmits the location information of the cabbage to the information acquisition unit 110 and requests information on the soil moisture and fertilizer component concentrations.

[0042] Furthermore, for example, when a close-up image of a cabbage that is not growing well is required, the countermeasure determination unit 108 decides to take a close-up image. In this case, the countermeasure determination unit 108 transmits location information of the cabbage to the information acquisition unit 110 and requests the close-up image. Note that the close-up image of the cabbage that is not growing well can also be said to be a close-up image of the location where the cabbage is grown.

[0043] Furthermore, based on the information notified by the information acquisition unit 110 and the acquired close-up images, the countermeasure determination unit 108 determines which countermeasure, local irrigation, local fertilization, or local pest control, should be implemented for the cabbage that is not growing well and the soil in the vicinity thereof, and notifies the instruction unit 112 of the determined result. Furthermore, if the information and images notified by the information acquisition unit 110 indicate that there is no action that should be taken for the cabbage that is not growing well, the countermeasure determination unit 108 stores the location information of the cabbage in question in the location table 124.

[0044] When the countermeasure determination unit 108 requests information on soil moisture and fertilizer component concentrations, the information acquisition unit 110 controls the sensing robot 40 to acquire measurement data on soil moisture and fertilizer component concentrations in the vicinity of cabbages that are not growing well, and notifies the countermeasure determination unit 108. Furthermore, when the countermeasure determination unit 108 requests close-up images of cabbages that are not growing well, the information acquisition unit 110 controls the drone 30 and camera 32 to acquire close-up images of the cabbages that are not growing well, and notifies the countermeasure determination unit 108.

[0045] When the countermeasure decision unit 108 notifies the instruction unit 112 that one of the countermeasures, local irrigation, local fertilization, or local pest control, should be implemented for cabbages that are not growing well, the instruction unit 112 controls the material spraying device 50 to implement the notified countermeasure.

[0046] (Regarding Server 10 processing) Next, the processing of the server 10 will be described in detail with reference to the flowcharts in Figures 8 and 9, and other drawings as appropriate. The processing in Figures 8 and 9 is executed one week after the planting date entered by the worker from the user terminal 60.

[0047] First, in step S200, the biological survey unit 102 controls the drone 30 and the camera 32 to photograph the entire farm field. As a result, the biological survey unit 102 acquires images of each cabbage and information on the photographing position of each image.

[0048] Next, in step S202, the living body inspection unit 102 records the position and projected leaf area (first area) of each cabbage in the inspection result table 120. The living body inspection unit 102 calculates the projected leaf area (first area) of each cabbage by image processing the acquired image of each cabbage. Then, the living body inspection unit 102 records the calculated projected leaf area (first area) of each cabbage in the inspection result table 120, linking it to the position information of each cabbage.

[0049] Next, in step S204, the biological inspection unit 102 waits until a predetermined time has passed. For example, the biological inspection unit 102 waits until one week has passed, that is, until two weeks have passed since the planting date. After that, the process proceeds to step S206.

[0050] In step S206, the living body inspection unit 102 controls the drone 30 and the camera 32 to photograph the entire farm field, as in step S200. As a result, the living body inspection unit 102 acquires images of each cabbage and information on the photographing position of each image.

[0051] Next, in step S208, the living body inspection unit 102 records the position and projected leaf area (second area) of each cabbage in the inspection result table 120. The living body inspection unit 102 calculates the projected leaf area (second area) of each cabbage by image processing the acquired image of each cabbage. Then, the living body inspection unit 102 records the calculated projected leaf area (second area) of each cabbage in the inspection result table 120, linking it to the position information of each cabbage.

[0052] Next, in step S210, the living body inspection unit 102 calculates the increase (measurement) of the projected leaf area of ​​each cabbage. For cabbage No. 0001 stored in the inspection result table 120 shown in Figure 5(a), the living body inspection unit 102 determines the increase (measurement) of the projected leaf area to be the value (α21 - α11) obtained by subtracting the projected leaf area (first area) α11 from the projected leaf area (second area) α21. For cabbage No. 0002, the living body inspection unit 102 determines the increase (measurement) of the projected leaf area to be the value (α22 - α12) obtained by subtracting the projected leaf area (first area) α12 from the projected leaf area (second area) α22.

[0053] Next, in step S212, the growth prediction unit 104 inputs the first area of ​​each cabbage and environmental data for a predetermined time period (one to two weeks after planting) into a growth model (FIG. 6) to estimate the projected leaf area (second area) of each cabbage two weeks after planting. Then, the growth prediction unit 104 subtracts the first area from the estimated second area for each cabbage to estimate an increase in the projected leaf area (target value) of each cabbage and stores the estimated increase in the projected leaf area in the target value table 122. For the cabbage No. 0001 stored in the target value table 122 shown in FIG. 5(b), the growth prediction unit 104 determines the increase in the projected leaf area (target value) to be the value (α21'-α11) obtained by subtracting the projected leaf area (first area) α11 from the estimated projected leaf area (second area) α21'. For the cabbage No. 0002, the growth prediction unit 104 determines the increase in the projected leaf area (target value) to be the value (α22'-α12) obtained by subtracting the projected leaf area (first area) α12 from the estimated projected leaf area (second area) α22'. Then, the process proceeds to step S220 in FIG. 9.

[0054] When the process proceeds to step S220, the comparison unit 106 identifies one crop (cabbage) in the field. For example, the comparison unit 106 identifies the cabbage with No.=0001 in the investigation result table 120 and the target value table 122. The crop (cabbage) identified in step S220 will be referred to as the "specific crop (specific cabbage)" hereinafter.

[0055] Next, in step S222, the comparison unit 106 compares the increase in the projected leaf area (measured value) of the specific cabbage with the increase in the projected leaf area (target value).

[0056] Next, in step S224, the countermeasure decision unit 108 determines whether the comparison result of the comparison unit 106 shows that the increase (measured value) is smaller than the increase (target value) (increase (measured value)<increase (target value)). If the determination in step S224 is negative, that is, if the increase (measured value) is equal to or greater than the increase (target value), then nothing needs to be done for the specific cabbage, and the process proceeds to step S248. On the other hand, if the determination in step S224 is positive, the process proceeds to step S226.

[0057] In step S226, the countermeasure determination unit 108 determines whether or not the plant is in the early growth stage. In the case of cabbage, the early growth stage may be, for example, within three weeks after planting. If the determination in step S226 is affirmative, the process proceeds to step S228.

[0058] In step S228, the countermeasure determination unit 108 instructs the sensing robot 40 via the information acquisition unit 110 to measure the soil moisture and fertilizer component concentrations at the location where the specific cabbage is being grown or in the vicinity of that location. The information acquisition unit 110 notifies the countermeasure determination unit 108 of the measurement results of the soil moisture and fertilizer component concentrations transmitted from the sensing robot 40. Note that the vicinity of the location where the specific cabbage is being grown refers to the range in which the soil moisture and fertilizer component concentrations have an effect on the growth of the specific cabbage. Specifically, in the early stages of growth, the range in which the soil moisture and fertilizer component concentrations have an effect on the specific cabbage can be the area between adjacent cabbages (the area between plants or between rows).

[0059] Next, in step S230, the countermeasure determination unit 108 determines whether the soil moisture is below the reference value. If the determination in step S230 is affirmative (soil moisture<reference value), the process proceeds to step S232, where the countermeasure determination unit 108 acquires a future weather forecast (e.g., a 10-day weather forecast) from the environmental data providing device 20 or a server of the Japan Meteorological Agency and determines whether the soil moisture will exceed the reference value in the near future. For example, the countermeasure determination unit 108 determines whether a predetermined amount of rain is forecast for the next 10 days. If the determination in step S232 is negative, that is, if it is predicted that the soil moisture will not exceed the reference value in the near future, the process proceeds to step S234, where the countermeasure determination unit 108 notifies the instruction unit 112 of the location information of the specific cabbage and of an instruction to perform local irrigation. The instruction unit 112 issues an instruction to the material spraying device 50 to perform local irrigation near the specific cabbage. Thereafter, the process proceeds to step S248.

[0060] On the other hand, if the determination in step S232 is positive, i.e., if it is predicted that the soil moisture will exceed the reference value in the near future, the process proceeds to step S236. Also, if the determination in step S230 is negative, i.e., if the soil moisture is equal to or greater than the reference value, the process proceeds to step S236.

[0061] In step S236, the countermeasure determination unit 108 determines whether the fertilizer component concentration is below the reference value.

[0062] FIG. 10 shows the relationship between the soil fertilizer concentration (EC) and the projected leaf area increment during the early growth period and the head weight at harvest. Each cabbage was grown in a cultivation environment with sufficient soil moisture. As shown in FIG. 10, when fertilizer is not applied (when the fertilizer concentration is low), the projected leaf area increment during the early growth period is small, and as a result, the head weight at harvest is also small. Even when fertilizer is applied and the soil fertilizer concentration is sufficient, the projected leaf area increment during the early growth period and the head weight at harvest may be small. This is thought to be due to causes other than fertilizer insufficiency, such as pests and diseases. In this embodiment, the countermeasure determination unit 108, based on the relationship shown in FIG. 10, determines that fertilization is necessary when it is determined that there is a fertilizer insufficiency (when the determination in step S236 is positive), and determines that it is necessary to investigate causes other than fertilizer when it is determined that there is no fertilizer insufficiency (when the determination in step S236 is negative).

[0063] That is, if the determination in step S236 is affirmative (fertilizer component concentration<reference value), the process proceeds to step S238, where the countermeasure determination unit 108 notifies the instruction unit 112 of the position information of the specific cabbage and of the intention to perform local fertilization. The instruction unit 112 issues an instruction to the material spraying device 50 to perform local fertilization near the specific cabbage. Thereafter, the process proceeds to step S248.

[0064] On the other hand, if the determination in step S236 is negative (there is no problem with the soil moisture or fertilizer component concentrations), the process proceeds to step S240. Note that if the determination in step S226 is negative, that is, if the plant is not in the early stages of growth and the plant is in a period where changing the soil moisture or fertilizer component concentrations will not affect the plant's growth, the process also proceeds to step S240.

[0065] In step S240, the countermeasure determination unit 108 instructs the information acquisition unit 110 to take close-up photographs of the specific cabbages along with the location information of the specific cabbages. The information acquisition unit 110 controls the drone 30 and the camera 32 to take close-up photographs of the specific cabbages. When the countermeasure determination unit 108 acquires the close-up images, it processes the images to check for the presence of pests or diseases.

[0066] Next, in step S242, the countermeasure determination unit 108 determines whether or not a pest has been detected. If the determination in step S242 is positive, the process proceeds to step S244, where the countermeasure determination unit 108 notifies the instruction unit 112 of the location information of the specific cabbage and of an instruction to carry out local control. The instruction unit 112 issues an instruction to the material spraying device 50 to carry out local control near the specific cabbage. Thereafter, the process proceeds to step S248.

[0067] On the other hand, if the determination in step S242 is negative, the process proceeds to step S246, where the countermeasure decision unit 108 records the location information of the specific cabbage in the location table 124. The cabbage recorded in the location table 124 means a cabbage that is not growing well but for which no action needs to be taken. Thereafter, the process proceeds to step S248.

[0068] In step S248, the countermeasure determination unit 108 determines whether all cabbages in the field have been identified. If the determination in step S248 is negative, the process returns to step S220, where the next cabbage is identified, and the processes in step S222 and thereafter are repeated. On the other hand, if the determination in step S248 is positive because all cabbages in the field have been identified, the process returns to step S204 in FIG. 8.

[0069] In step S204, the process waits until a predetermined time (for example, one week) has passed. For example, when one week has passed and it is three weeks since planting, the process proceeds to step S206. At this stage, the projected leaf area recorded in the inspection result table 120 two weeks after planting is treated as the projected leaf area (first area). In addition, the projected leaf area (second area) (α21', α22') estimated two weeks after planting in the target value table 122 is rewritten with the projected leaf area (second area) (α21, α22) stored in the inspection result table 120 (see FIG. 11(b)).

[0070] Thereafter, the processing from step S204 onward is repeatedly executed until harvest. This makes it possible to appropriately implement local countermeasures for the cabbages in the field. For example, three weeks after planting, as shown in FIG. 11(a), α31, α32, ... are newly stored as projected leaf areas in the inspection result table 120. In addition, (α31-α21) and (α32-α22) are stored as the increments (measured values) of the projected leaf area. In addition, as shown in FIG. 11(b), α31', α32', ... are newly stored as projected leaf areas in the target value table 122. In addition, (α31'-α21) and (α32'-α22) are stored as the increments (measured values) of the projected leaf area. Therefore, in the processing from step S220 onward in FIG. 9, processing is executed using the tables in FIGS. 11(a) and 11(b).

[0071] The location table 124 stores location information of cabbages that are not growing properly for unknown reasons. Therefore, after returning to step S204, processing may be performed based on the information recorded in the location table 124. For example, the processing from step S204 onwards may be performed only on cabbages that are located at locations recorded in the location table 124. Also, for example, the processing from step S204 onwards may be performed preferentially on cabbages that are located at locations recorded in the location table 124. Also, for example, information on cabbages that are located at locations recorded in the location table 124 may be notified to the user terminal 60. This allows the worker to visually check for cabbages that are not growing properly for unknown reasons.

[0072] As described above in detail, according to this embodiment, the living body survey unit 102 calculates the increase in projected leaf area (measured value) of each cabbage based on the results of two living body surveys (calculation results of projected leaf area using images) conducted at different times for each cabbage growing in the field (S210). The comparison unit 106 compares the increase in projected leaf area (measured value) of each cabbage with the increase in projected leaf area (target value) of each cabbage (S222). The countermeasure determination unit 108 determines whether each cabbage is growing normally or not based on the comparison results (S224). The countermeasure determination unit 108 then determines whether to investigate the cultivation environment of each cabbage based on the determination results (S228, S240). This makes it possible to locally investigate the cultivation environment of cabbages that are not growing normally. Therefore, since it is not necessary to investigate the entire field, the time required for the investigation can be shortened. In addition, the countermeasure decision unit 108 determines whether growth is going well by comparing the increase in projected leaf area (measured value) in the early stages of growth, which is correlated with the head weight at harvest, with the increase in projected leaf area (target value), so it is possible to accurately determine whether growth of cabbage is going well in the early stages of growth.

[0073] In this embodiment, the growth prediction unit 104 inputs the projected leaf area value obtained in the in vivo survey and the environmental data between the two in vivo surveys into the growth model, and determines the increase amount (target value) of the projected leaf area using the estimated projected leaf area. This makes it possible to accurately determine the increase amount (target value) of the projected leaf area for each individual cabbage.

[0074] In this embodiment, the images of the cabbages were taken from above during the two live surveys. This allows the projected leaf area of ​​the cabbages to be calculated easily and accurately. However, this is not limiting, and the projected leaf area may be calculated based on measurements taken by an operator.

[0075] In this embodiment, if the cabbage is not growing well, the soil moisture and fertilizer component concentration are measured (S228). This makes it possible to determine whether the cause of the poor growth is soil moisture, fertilizer component concentration, or some other factor. Note that in step S228, only either the soil moisture or the fertilizer component concentration may be measured. In this case, any one of steps S230, 232, 234 and steps S236, 238 in FIG. 9 may be omitted.

[0076] In this embodiment, the countermeasure determination unit 108 identifies the cause of poor cabbage growth based on the measurement results of soil moisture and fertilizer component concentrations and / or close-up images, and determines the measures (countermeasures) to be taken on the cabbage. This makes it possible to take localized and appropriate measures on the cabbages that are not growing well.

[0077] In this embodiment, the instruction unit 112 instructs the material spraying device 50 to execute the countermeasure determined by the countermeasure determination unit 108. This allows appropriate cultivation management to be performed to improve the growth of cabbage.

[0078] In the above embodiment, the growth prediction unit 104 inputs the value of the projected leaf area obtained in the first biological survey into the growth model as the initial value of the projected leaf area in step S212 of Fig. 8, but this is not limited to this. A predetermined value (a general projected leaf area size in the early stage of growth) may be input as the initial value of the projected leaf area.

[0079] In the above embodiment, the case where two live inspections (calculation of projected leaf area using images) are performed one week after planting and two weeks after planting has been described, but this is not limited to this. For example, the interval between the two live inspections may be about 2 to 6 days. Furthermore, the first live inspection may be performed either one week before or one week after planting.

[0080] In the above embodiment, the increase in projected leaf area is calculated as an index value indicating the crop growth rate, but this is not limiting. The increase rate of projected leaf area can also be used as an index value indicating the crop growth rate. The increase rate of projected leaf area can be calculated by dividing the increase in projected leaf area by the number of days. The index value indicating the crop growth rate may also be the increase or rate of crop height, or the increase or rate of crop volume. Methods for measuring crop height include using distance images (images captured by a stereo camera) using parallax images, and measuring the distance to the crop using a ToF (Time of Flight) sensor. Methods for measuring crop volume include creating a three-dimensional model from multiple images and measuring the volume, and using a laser to three-dimensionally measure the crop volume.

[0081] In the above embodiment, the case where the cultivation environment is automatically managed using the drone 30, the camera 32, the sensing robot 40, and the material spraying device 50 has been described, but the present invention is not limited thereto. That is, the tasks performed by the drone 30, the camera 32, the sensing robot 40, and the material spraying device 50 may be performed by an operator. For example, in steps S200 and S206 of FIG. 8, the biological survey unit 102 may notify (display) on the user terminal 60 that it is time to photograph the entire field. In this case, the operator may operate the drone 30 to photograph the entire field, or may photograph the entire field using the camera while walking through the field. Also, for example, in steps S228 and S240 of FIG. 9, the countermeasure determination unit 108 may notify (display) on the user terminal 60 information on the locations where soil moisture and fertilizer component concentrations should be measured, or information on the locations where close-up photography should be performed. In this case, the worker may measure soil moisture and fertilizer component concentrations using a sensor or take close-up images using a camera at the notified positions while walking within the field. Furthermore, for example, in steps S234, S238, and S244 of Fig. 9, the instruction unit 112 may notify (display) information on positions where local irrigation, local fertilization, and local pest control should be performed on the user terminal 60. In this case, the worker may perform local irrigation, local fertilization, and local pest control at the notified positions while walking within the field.

[0082] The above processing functions can be realized by a computer. In this case, a program is provided that describes the processing contents of the functions that the processing device should have. By executing the program on a computer, the above processing functions are realized on the computer. The program that describes the processing contents can be recorded on a computer-readable storage medium (excluding carrier waves).

[0083] When distributing a program, it is sold in the form of a portable storage medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. The program can also be stored in the storage device of a server computer and transferred from the server computer to other computers via a network. In addition to being sold, the program can also be provided as a paid network service.

[0084] A computer that executes a program stores, for example, a program recorded on a portable storage medium or a program transferred from a server computer in its own storage device. The computer then reads the program from its own storage device and executes processing in accordance with the program. Note that the computer can also read the program directly from a portable storage medium and execute processing in accordance with that program. The computer can also execute processing in accordance with the program received each time a program is transferred from the server computer.

[0085] The above-described embodiment is a preferred example of the present invention, but the present invention is not limited to this and can be modified in various ways without departing from the spirit of the present invention. [Explanation of symbols]

[0086] 10 Servers 20 Environmental data providing device 30 Drone 32 Camera 40 Sensing Robot 50 Material spreading device (processing device) 60 User terminal 102 Biological Survey Department 104 Growth Forecasting Department 106 Comparison Section 108 Countermeasures Decision Department 110 Information Acquisition Department 112 Instruction section 120 Survey Results Table 122 Target Value Table 124 Position Table

Claims

1. Based on the results of two biological surveys conducted at different times on a specific crop growing at a predetermined point in the field, a value indicating the growth rate of the specific crop is calculated and used as a measurement value; a value indicating the growth rate of the specific crop estimated based on the cultivation environment data of the predetermined location is set as a target value, and the measured value is compared with the target value to determine whether the growth of the specific crop is going well; Based on the result of the determination, it is determined whether or not to investigate the cultivation environment at or near the predetermined point. A cultivation environment investigation method characterized in that processing is executed by a computer.

2. 2. The cultivation environment survey method according to claim 1, wherein the target value is a value indicating the growth rate of the specific crop estimated from information from a first of the two bio-surveys conducted at different times for the specific crop and cultivation environment data for the specified location during the period between the two bio-surveys.

3. The cultivation environment survey method described in claim 2, characterized in that the information from the first bio-survey and the cultivation environment data at the specified location for the period between the two bio-surveys are input into a growth model for predicting the growth of the specific crop, thereby obtaining the results expected to be obtained in the second bio-survey, and a value indicating the growth rate of the specific crop based on the expected results and the information from the first bio-survey is set as the target value.

4. 4. The cultivation environment investigation method according to claim 1, wherein the living body investigation is an investigation using an image of the specific crop.

5. 5. The cultivation environment investigation method according to claim 4, wherein the biological investigation is an investigation of any one of projected leaf area, height, and volume.

6. 6. The cultivation environment investigation method according to claim 1, wherein the investigation of the cultivation environment is an investigation of at least one of soil moisture content and fertilizer component concentration.

7. Using the cultivation environment investigation method according to any one of claims 1 to 6, it is determined whether or not to investigate the cultivation environment at the predetermined point or in the vicinity of the predetermined point; When it is decided to investigate the cultivation environment at or near the predetermined point, decide which investigation to conduct based on information on whether the specific crop is in the early growth stage or not, and decide which of irrigation, fertilization, and pest control treatment to perform based on at least one of information obtained from the decided investigation, namely, information on soil moisture at or near the predetermined point, information on fertilizer component concentration values ​​at or near the predetermined point, and information on the presence or absence of pests based on an image of the specific crop; displaying the determined content of the processing to be executed, or notifying the processing device of the determined content of the processing to be executed; A cultivation management method in which processing is performed by a computer.

8. Based on the results of two biological surveys conducted at different times on a specific crop growing at a predetermined point in the field, a value indicating the growth rate of the specific crop is calculated and used as a measurement value; a value indicating the growth rate of the specific crop estimated based on the cultivation environment data of the predetermined location is set as a target value, and the measured value is compared with the target value to determine whether the growth of the specific crop is going well; Based on the result of the determination, it is determined whether or not to investigate the cultivation environment at or near the predetermined point. A cultivation environment survey program characterized by causing a computer to execute processing.

9. Based on the results of two biological surveys conducted at different times on a specific crop growing at a predetermined point in the field, a value indicating the growth rate of the specific crop is calculated and used as a measurement value; a value indicating the growth rate of the specific crop estimated based on the cultivation environment data of the predetermined location is set as a target value, and the measured value is compared with the target value to determine whether the growth of the specific crop is going well; Based on the result of the judgment, it is determined whether or not to investigate the cultivation environment at or near the predetermined point; When it is decided to investigate the cultivation environment at or near the predetermined point, decide which investigation to conduct based on information on whether the specific crop is in the early growth stage or not, and decide which of irrigation, fertilization, and pest control treatment to perform based on at least one of information obtained from the decided investigation, namely, information on soil moisture at or near the predetermined point, information on fertilizer component concentration values ​​at or near the predetermined point, and information on the presence or absence of pests based on an image of the specific crop; displaying the determined content of the processing to be executed, or notifying the processing device of the determined content of the processing to be executed; A cultivation management program in which processing is carried out by a computer.

Images