Plant management system and plant management method

Abstract

To provide a realistic solution that can prevent plants from wilting at an actual management site of the plants.SOLUTION: A plant management system 100 comprises a camera 51 and a processor 11. The camera 51 acquires image data of plants by imaging plants which are under the management of a user. The processor 11 calculates a wilting value that indicates a wilting state of the plants, on the basis of the image data. The processor 11 issues an alert to a user device 3 used by the user, if the wilting value exceeds an alert threshold value.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates to plant management systems and methods. [Background technology]

[0002] If plants are not properly managed, they may wilt and eventually die. JP 2018-29568 A (Patent Document 1) proposes a wilting prediction system that predicts the degree of wilting of plants. The wilting prediction system described in Patent Document 1 predicts the sugar content of a plant based on a predicted value of the degree of wilting of the plant, and controls the timing or amount of watering the plant so that the sugar content of the plant approaches a target value (see paragraph

[0037] of Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-29568 [Patent Document 2] International Publication No. 2018 / 235777 Summary of the Invention [Problem to be solved by the invention]

[0004] There is always a demand for preventing plants under user management (management includes growing, nurturing, cultivating, and observing) from withering. When there is a possibility that a plant may wither, it is conceivable to automatically implement countermeasures such as irrigation. However, in actual plant management sites, there are various factors that cause plants to wither, and the inventors have focused on this real-world problem that a uniform countermeasure such as automatic irrigation is not always appropriate.

[0005] The present disclosure has been made to solve the above-mentioned problems, and one of the purposes of the present disclosure is to provide a practical solution that can prevent plants from withering in actual plant management sites. [Means for solving the problem]

[0006] A plant management system according to one aspect of the present disclosure includes a camera and a processor. The camera captures images of plants under a user's management, and the processor calculates a wilting value indicating the degree of wilting of the plants based on the image data. If the wilting value exceeds an alert threshold, the processor notifies a user device used by the user of an alert.

[0007] A plant management method according to another aspect of the present disclosure includes first to third steps. The first step is a step of acquiring image data of a plant by photographing the plant under the user's management. The second step is a step of calculating a wilting value indicating the degree of wilting of the plant based on the image data. The third step is a step of notifying an alert to a user device used by the user if the wilting value exceeds an alert threshold. [Effects of the Invention]

[0008] According to the present disclosure, a practical solution can be provided that can prevent plants from withering in actual plant management sites. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram showing an example of the overall configuration of a plant management system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a perspective view for explaining an example of the configuration of a plant monitoring device. [Figure 3] FIG. 2 is a functional block diagram for explaining an example of functions of the plant monitoring device. [Figure 4] FIG. 10 is a diagram for explaining an example of time-dependent changes in a value quantitatively indicating the degree of wilting of a plant. [Figure 5] FIG. 10 is a diagram for explaining another example of the change over time in the value quantitatively indicating the degree of wilting of a plant. [Figure 6] FIG. 2 is a diagram showing a first example of a display screen of a user device. [Figure 7] FIG. 10 is a diagram showing a second example of a display screen of the user device. [Figure 8] FIG. 10 is a diagram showing a third example of a display screen of a user device. [Figure 9] FIG. 10 is a diagram showing a fourth example of a display screen of a user device. [Figure 10] 10 is a flowchart showing an example of a processing procedure of a plant management method according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, the present embodiment will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are designated by the same reference numerals, and description thereof will not be repeated.

[0011] [Embodiment Mode] <Overall structure> FIG. 1 is a diagram showing an example of the overall configuration of a plant management system according to this embodiment. The plant management system 100 includes a plant monitoring device 1, a server 2, a user device 3, and an irrigation control device 4. Although not shown, the plant management system 100 may include multiple plant monitoring devices 1, or multiple user devices 3. The plant monitoring device 1 and the server 2 are connected to each other via a network NW such as the Internet so that they can communicate bidirectionally. The user device 3 and the server 2 are also connected to each other via the network NW so that they can communicate bidirectionally. The plant monitoring device 1 and the user device 3 may be able to communicate directly without going through the server 2. The user device 3 and the irrigation control device 4 may be able to communicate via the plant monitoring device 1 or the server 2, or they may be able to communicate directly.

[0012] The plant monitoring device 1 is installed at the management site of a plant selected by a user (typically a farmer) to monitor the plant's growth status, particularly the degree of wilting. The plant monitoring device 1 may also be called a "wilt watcher" or "wilt watcher" (wilt = wilt).

[0013] More specifically, the plant monitoring device 1 acquires image data of the plant by photographing the plant to be monitored and transmits the image data to the server 2. The plant monitoring device 1 may calculate a predicted value of the degree of wilting of the plant (the "wilting value" described below) by image processing the image data, and transmit the predicted value to the server 2. Details of the image processing for calculating the predicted value of the degree of wilting of the plant will be described later. The plant monitoring device 1 may have installed therein an app (application program) that photographs the plant, calculates a predicted value of the degree of wilting of the plant, and automatically transmits the information obtained thereby (image data and predicted value) to the server 2.

[0014] The plant monitoring device 1 includes a processor 11 and a memory 12. The processor 11 is an arithmetic processing device such as a central processing unit (CPU) or a microprocessing unit (MPU). The memory 12 may include a volatile memory such as a random access memory (RAM) and a rewritable nonvolatile memory such as a solid state drive (SSD) or flash memory. The memory 12 stores system programs including an operating system (OS) and control programs including computer-readable code required for arithmetic processing. The processor 11 performs various processes assigned to the plant monitoring device 1 by reading the system programs and control programs and loading them into the memory 12. The same applies to the processors and memories of the other components of the plant management system 100 (the server 2 and the user device 3).

[0015] In this specification, the term "processor" is not limited to a processor in the narrow sense that executes processing using a stored program, but may also include hardwired circuits such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array). Therefore, the term "processor" can also be interpreted as a processing circuitry whose processing is predefined by computer-readable code and / or hardwired circuitry.

[0016] The server 2 includes a processor 21, a memory 22, and a database 23. The server 2 collects image data of the plants from the plant monitoring device 1, as well as a predicted value of the degree of wilting of the plants. The server 2 may also collect other data (environmental data) described below. The server 2 organizes the various collected data according to predetermined rules and stores them in the database 23. The database 23 may be cloud storage.

[0017] The user device 3 includes a processor 31 and a memory 32. The user device 3 is typically a mobile terminal used by a user (such as a smartphone, smartwatch, tablet, or laptop (Personal Computer)). The user device 3 may also be a fixed terminal (such as a desktop PC) installed in a remote location (away from the plant management site). The user device 3 includes an input unit that accepts user operations and a display that displays information (neither of which are shown), and in this example includes a touch panel display 33 (see FIGS. 5 to 7). The user device 3 is configured to be able to communicate with the plant monitoring device 1 and to be able to access the server 2. The user device 3 may have installed thereon apps for receiving notifications from the plant monitoring device 1 or the server 2 and for viewing various data collected by the server 2.

[0018] The irrigation control device 4 controls an irrigation device (not shown). The irrigation device is a device configured to supply water to the plants being monitored, and specifically, is a sprinkler, an irrigation tube, etc. The irrigation device may also be a device that takes in agricultural water from an irrigation canal.

[0019] <Configuration of plant monitoring device> FIG. 2 is a perspective view illustrating an example of the configuration of the plant monitoring device 1. The plant monitoring device 1 includes a data acquisition unit 5 and a data processing unit 6. The data acquisition unit 5 is attached to a stand 7 installed at the plant management site so that its height can be adjusted. The data acquisition unit 5 and the data processing unit 6 may be formed integrally. For example, a small data processing unit 6 may be housed inside the data acquisition unit 5 as shown in FIG. 2.

[0020] In this example, the data acquisition unit 5 is disposed laterally (horizontally) of the plant and configured to photograph the plant from the side. The data acquisition unit 5 may also be disposed above the plant and configured to photograph the plant from above downward. The data acquisition unit 5 acquires image data by photographing the plant. The data acquisition unit 5 further acquires environmental data (described below). The data acquisition unit 5 outputs the image data and environmental data to the data processing unit 6.

[0021] The data processing unit 6 performs arithmetic processing on the image data and environmental data from the data acquisition unit 5. The data processing unit 6 is also communicably connected to the server 2 and the user device 3. The data processing unit 6 receives commands from the server 2 and / or the user device 3, and transmits the results of arithmetic processing on the image data and environmental data to the server 2 and / or the user device 3.

[0022] 3 is a functional block diagram for explaining an example of the functions of the plant monitoring device 1. The data acquisition unit 5 includes a camera 51, an environmental sensor 52, and a data output unit 53.

[0023] The camera 51 captures an image of a plant to be monitored to acquire image data of the plant. The camera 51 associates the image data with time data and outputs the image data associated with the time data (time-series image data) to the data output unit 53.

[0024] The environmental sensor 52 acquires environmental data indicating environmental factors that affect the degree of wilting of plants at the plant management site. Specifically, the environmental factors include temperature (air temperature), humidity (relative humidity), solar radiation (e.g., photosynthetic photon flux density (PPFD)), precipitation, saturation deficit (the difference between saturated water vapor pressure and actual water vapor pressure), atmospheric pressure, gas concentration (e.g., CO2 gas concentration), and wind speed. The environmental sensor 52 includes a temperature sensor, a humidity sensor, a PPFD measuring instrument, a rainfall sensor, a vapor pressure sensor, an atmospheric pressure sensor, a gas sensor, and a wind speed sensor, and may detect environmental data by itself. The environmental sensor 52 may collect environmental data from a wireless sensor network (not shown). The environmental sensor 52 associates the environmental data with time data and outputs the environmental data associated with the time data (time-series environmental data) to the data output unit 53.

[0025] The data output section 53 outputs the time-series image data and the time-series environmental data to the data processing unit 6 at predetermined intervals.

[0026] The data processing unit 6 includes a data input unit 61, an image feature extraction unit 62, an environmental feature extraction unit 63, a wilting calculation unit 64, an alert threshold setting unit 65, a comparison unit 66, an alert generation unit 67, and a notification unit 68.

[0027] The data input unit 61 receives time-series image data and time-series environmental data from the data acquisition unit 5 (data output unit 53). The data input unit 61 outputs the time-series image data to the image feature extraction unit 62, and outputs the time-series environmental data to the environmental feature extraction unit 63.

[0028] Although not shown, the data input unit 61 may acquire weather data indicating weather conditions at the plant management site. The weather data may include information on weather, temperature, humidity, hours of sunlight, precipitation (snowfall), precipitation probability, wind speed, lightning probability, air pressure, etc. The weather data may also include weather advisories and weather warnings. The data input unit 61 can acquire the weather data by communicating with the server 2. The data input unit 61 may output the time-series weather data to the environmental feature extraction unit 63.

[0029] The image feature extraction unit 62 extracts (performs segmentation) multiple features (hereinafter referred to as "image features") from the time-series image data. Specifically, the image feature extraction unit 62 performs preprocessing (such as resizing, data expansion, color correction, and normalization) on the time-series image data, and then extracts the multiple image features using a well-known machine learning technique such as a convolutional neural network (CNN). The multiple image features may include the position (e.g., height, depth), shape (e.g., outline, size, thickness), and color of the leaves, stems, or branches of the plant. The image feature extraction unit 62 outputs the multiple image features to the wilting calculation unit 64.

[0030] The environmental feature extraction unit 63 extracts multiple features (hereinafter referred to as "environmental feature values") from the time-series environmental data (and time-series weather data). For example, the environmental feature extraction unit 63 may cut out the time-series environmental data (waveform data) at a fixed time length, remove noise, and extract statistics (such as average, variance, maximum value, and minimum value) as environmental feature values. The environmental feature extraction unit 63 may also perform differential transformation of the time-series environmental data (calculating the difference between previous and next data) and extract the statistics as environmental feature values. The environmental feature extraction unit 63 may also extract environmental feature values ​​by calculus (calculating slope, area, etc.), peak detection (calculating the number of peaks, peak height, peak interval, etc.), and frequency analysis (Fourier analysis, wavelet analysis, etc.) of the time-series environmental data. The environmental feature extraction unit 63 outputs the multiple environmental feature values ​​to the wilting calculation unit 64.

[0031] The wilting calculation unit 64 calculates a value (hereinafter referred to as "wilting value") that quantitatively indicates the degree of wilting of the monitored plant based on multiple image feature amounts and multiple environmental feature amounts. The larger the wilting value, the greater the degree of wilting of the plant. The wilting value may be normalized. For example, when the wilting value is 100%, the plant is completely wilted. When the wilting value is 0%, the plant is not wilted at all.

[0032] The wilting value may be the wilting rate (or a parameter correlated with the wilting rate). The wilting rate is the ratio of the current leaf area to the maximum leaf area. The lower the wilting rate, the larger the wilting value. When using such a parameter, "the wilting rate is lower than the alert threshold (described below)" corresponds to "the wilting value is greater than the alert threshold" (the wilting value exceeds the alert threshold).

[0033] The wilting value is not limited to the wilting rate. Generally, the more a plant wilts, the more its branches droop, so the degree of wilting can be estimated from the movement of the branches (the degree of branch drooping). The wilting value may be a parameter indicating the movement of the branches. As the plant wilts, the leaves, stems, or branches discolor more (for example, turn yellow), so the degree of wilting can be estimated from the color of the leaves, stems, or branches. The wilting value may be a parameter indicating the color of the leaves, stems, or branches. As the stems become thinner as a plant wilts, the degree of wilting can be estimated from the thickness of the stems (stem diameter). The wilting value may be a parameter indicating the thickness of the stems. The wilting calculation unit 64 may calculate the wilting value by combining two or more parameters (two or more of the wilting rate, the movement of the branches, the color of the leaves, stems, or branches, and the thickness of the stems).

[0034] The wilting calculation unit 64 calculates the wilting value using, for example, an image feature tracking technique that vectorizes differences in image features in time-series image data (i.e., the movement of plant leaves, stems, or branches). Image feature tracking techniques may include known techniques such as optical flow and deep learning. Alternatively, the wilting calculation unit 64 may calculate the wilting value using a trained model that uses multiple image features and multiple environmental features as explanatory variables and the wilting value after a predetermined time period (typically several hours) as the objective variable. The trained model may use a model that uses a known machine learning algorithm such as a support vector machine, logistic regression, or deep learning.

[0035] It is not essential that the data acquisition unit 5 acquires time-series environmental data using the environmental sensor 52 and supplies the data to the data processing unit 6. The data processing unit 6 may calculate the wilting value without using the time-series environmental data. The data processing unit 6 may calculate the current wilting value based on the current image data, or may calculate the current wilting value based on time-series image data from the past to the present, but may not calculate (predict) the future wilting value.

[0036] FIG. 4 is a diagram illustrating an example of how the wilting value changes over time. FIG. 5 is a diagram illustrating another example of how the wilting value changes over time. The horizontal axis represents time. The vertical axis represents the wilting value. Assume that it is currently 11:00. The wilting values ​​after 9:00 and before 11:00 are actual values. In FIG. 5, the wilting values ​​after 11:00 are predicted values. As shown in FIGS. 4 and 5, the wilting value can change relatively significantly over time.

[0037] Hereinafter, data showing the time change of wilting value (which may include not only actual values ​​but also predicted values ​​of wilting value) will be referred to as "wilting data." The wilting data is not limited to a graph (time chart) that visualizes the time change of wilting value, but may also be a table that organizes the time change of wilting value.

[0038] Referring again to FIG. 3, the alert threshold setting unit 65 accepts a user operation for setting an "alert threshold." The alert threshold is a threshold for issuing an alert regarding plant wilting. The alert threshold setting unit 65 sets the alert threshold based on a user operation. In the examples shown in FIGS. 4 and 5, the alert threshold is set to 50%. However, the alert threshold may be automatically set by the server 2. The alert threshold setting unit 65 outputs the alert threshold to the comparison unit 66.

[0039] The comparison unit 66 compares the wilting value at each time in the wilting data with the alert threshold to determine whether the wilting value is greater than the alert threshold (whether the wilting value will become greater in the future). The comparison unit 66 outputs the determination result of whether the wilting value is greater than the alert threshold to the alert generation unit 67 and the notification unit 68. If the wilting value is greater than the alert threshold, the determination result may include the time when the wilting value exceeded the alert threshold or a predicted time when the wilting value will exceed the alert threshold. The determination result may also include the maximum wilting value (how much the wilting value is predicted to increase).

[0040] 4, the wilting value exceeds the alert threshold of 50% at the current time, 11:00 a.m. When this happens, the comparison unit 66 outputs information that the wilting value has exceeded the alert threshold to the alert generation unit 67 and the notification unit 68.

[0041] 5, the predicted value exceeds the alert threshold of 50% at around 12:20, and then reaches 55%. The comparison unit 66 outputs the information that the wilting value will exceed the alert threshold, as well as the predicted time (12:20) at which the wilting value will exceed the alert threshold and the maximum wilting value (55%) to the alert generation unit 67 and the notification unit 68.

[0042] The comparison unit 66 may determine whether the rate of increase of the wilting value (the rate of change of the wilting value over a predetermined period of time) is greater than a threshold rate, and output the determination result to the alert generation unit 67 and the notification unit 68. While it usually takes a certain amount of time (e.g., several hours) for the wilting value to increase by a specified value, there are cases where the wilting value increases by the specified value in an extremely short time (e.g., just a few minutes). In preparation for such a sudden increase in the wilting value, it is desirable to take into account the rate of increase of the wilting value (the rate of change of the wilting value over time). The comparison unit 66 may compare both whether the wilting value is greater than the alert threshold and whether the rate of increase of the wilting value is greater than the threshold rate.

[0043] As shown in Figure 5, an "attention threshold" may be set to alert the user to a certain level of caution, but not enough to trigger an alert. The attention threshold is smaller than the alert threshold. The attention threshold may be set manually by the user, or may be set automatically in conjunction with the setting of the alert threshold (for example, set to a value smaller than the alert threshold by a predetermined value or percentage).

[0044] The alert generation unit 67 generates an alert to notify the user of the possibility that the plant will wither, in accordance with the determination result from the comparison unit 66. The alert generation unit 67 outputs the alert to the notification unit 68.

[0045] The notification unit 68 notifies the user device 3 of the alert. Instead of notifying the alert immediately when the wilting value exceeds the alert threshold, the notification unit 68 may notify the alert after a specified period has elapsed since the wilting value exceeded the alert threshold. In response to a request from the user device 3, the notification unit 68 may transmit the wilting data to the user device 3 or may transmit the determination result to the user device 3.

[0046] In FIG. 3, it has been described that various data processing operations based on the image data and environmental data acquired by the data acquisition unit 5 are performed by the data processing unit 6. However, some or all of the functions of the data processing unit 6 may be implemented in the server 2. For example, the server 2 may execute a process for extracting multiple image features and multiple environmental features. The server 2 may use a trained model to calculate a wilting value from the multiple image features and multiple environmental features to generate wilting data. The server 2 may compare the wilting data with an alert threshold. An alert may be sent from the server 2 to the user device 3.

[0047] <Display on user device> 6 is a diagram showing a first example of a display screen of the user device 3. In this example, the user device 3 is a smartphone equipped with a touch panel display 33. Assume a situation in which a change in the wilting value as shown in FIG. 5 is predicted.

[0048] When an alert is issued, the user device 3 displays a message 81 indicating that the wilting value has exceeded the alert threshold or that the wilting value is predicted to exceed the alert threshold. Note that the notification (alert) to the user that the wilting value has exceeded the alert threshold or that the wilting value is predicted to exceed the alert threshold is not limited to being sent via an app as shown in FIG. 6. While the app is running in the background, a pop-up notification (banner notification) may be sent on a screen other than the app (on the standby screen, lock screen, or on another app). A notification may also be sent via sound (voice, warning sound, etc.).

[0049] The user device 3 may display more detailed information regarding the change in the wilting value over time. Specifically, the user device 3 may further display a predicted time 821 when the wilting value will exceed the alert threshold (which may be a predicted time period or the time when the wilting value exceeds the alert threshold) and a maximum wilting value 822.

[0050] The user device 3 may display the increase rate of the wilting value 823. The increase rate 823 may be expressed in words (fast, normal, slow, etc.) or may be displayed as a specific numerical value. By checking the increase rate of the wilting value 823, the user can easily understand whether a sudden increase in the wilting value is predicted to occur (or has occurred).

[0051] The user device 3 may display at least one of the number of times (not shown) that the wilting value exceeded the alert threshold during a predetermined period (e.g., the last hour, the current day, the last 24 hours), the length of time 824 that the wilting value exceeded the caution threshold during the predetermined period, and the number of times 825 that the wilting value exceeded the caution threshold during the predetermined period.

[0052] The user device 3 may further display a button 83 for displaying detailed information. Specifically, the user device 3 may display a button 831 for displaying image data, or a button 832 for displaying time-series environmental data.

[0053] The user device 3 may further display a button 833 for displaying time-series weather data, which allows the user to easily grasp time-varying weather conditions such as temperature, humidity, solar radiation, precipitation, saturation deficit, air pressure, gas concentration, and wind speed in the past, present, and future.

[0054] The user equipment 3 may further display a button 834 for displaying wilting data so that the user can check details of the time variation of the wilting value.

[0055] 7 is a diagram showing a second example of the display screen of the user device 3. In response to the user selecting button 831 in FIG. 6, for example, the user device 3 displays image data 84 of a plant to be monitored. Preferably, the user device 3 also displays the image capture time (the time the image data was acquired) 85. This allows the user to check the condition of the plant (how wilted it is) at the desired time. Note that the user device 3 may also display the image data 84 and the image capture time 85 on the same initial screen as the alert message 81, without the user operating button 831.

[0056] 8 is a diagram showing a third example of a display screen of the user device 3. The user device 3 may display wilting data 86 in response to the user selecting button 834 in FIG. 6. The user need not operate button 834. The user device 3 may display the wilting data 86 on the same screen as the alert message 81. The user device 3 may superimpose an alert threshold 871, a predicted time 872 at which the wilting value will exceed the alert threshold, and a maximum wilting value 873 on the wilting data 86. Although not shown, the user device 3 may also superimpose a caution threshold.

[0057] The user device 3 may display a button 88 for the user to set (change) the alert threshold value in reference to the change in the wilting value over time (see S201 and S202 in FIG. 10).

[0058] 9 is a diagram showing a fourth example of the display screen of the user device 3. The user device 3 may display a button 89 that allows the user to manually set the irrigation conditions (conditions related to irrigation start / stop, irrigation amount, irrigation time, etc.) of the irrigation control device 4 (see FIG. 1). The user device 3 transmits the irrigation conditions set by the user to the irrigation control device 4. The user device 3 may transmit the irrigation conditions to the plant monitoring device 1 or the server 2, and the plant monitoring device 1 or the server 2 may then transmit the irrigation conditions to the irrigation control device 4. The irrigation control device 4 controls the irrigation device so that irrigation is performed in accordance with the irrigation conditions set by the user.

[0059] <Effects of alerts> When wilting of a plant is detected, it is possible to automatically take measures such as irrigation to prevent the plant from wilting further and dying, but such automatic measures are not always appropriate.

[0060] For example, because the monitoring target is a specific subset of plants, it is possible that while a specific plant may be wilting due to specific circumstances, the plants growing around it may not be wilting. Furthermore, if the monitored plant is wilting due to a malfunction of the irrigation equipment or incorrect settings for irrigation conditions, predetermined irrigation measures may not be able to adequately prevent the plant from wilting. Alternatively, the wilting of the plant may be due to other environmental factors (temperature, humidity, solar radiation, air pressure, etc.) that cannot be resolved by irrigation. It is practically difficult to automate countermeasures for the various factors that may occur in actual plant management sites.

[0061] In contrast, in this embodiment, the plant monitoring device 1 (which may be the server 2) sends an alert to the user device 3 when the wilting value exceeds the alert threshold or when the wilting value is predicted to exceed the alert threshold. Upon receiving the alert, the user using the user device 3 can go to the plant management site and actually check the degree of wilting of the monitored plant. The user may also check the degree of wilting of surrounding plants. Furthermore, the user can check whether there are any abnormalities or setting errors in the irrigation device at the plant growth site. In addition, the user can check whether various environmental factors at the plant management site are appropriate. This allows users such as farmers to take appropriate measures (such as water supply, temperature adjustment, humidity adjustment, and solar radiation adjustment) to prevent plants from wilting based on their own experience and intuition.

[0062] Thus, according to the findings of the present inventors, a practical solution is for the user to visually check the plant management site and determine for themselves what measures are appropriate. Therefore, in this embodiment, the user is notified of the possibility of plant wilting by an alert, and the subsequent measures are left to the user. Even if the wilting value is predicted to exceed the alert threshold, a predetermined, uniform measure is not automatically implemented without the user's operation of the user device 3.

[0063] <Processing Procedure> Fig. 10 is a flowchart showing an example of the processing procedure of the plant management method according to this embodiment. In the figure, the left side shows a series of processes executed by the plant monitoring device 1 when a predetermined condition is met (at a specified interval, when the app is launched, etc.). Some of these processes may be executed by the server 2. The right side shows a series of processes executed by the user device 3 when a predetermined condition is met. Each process is typically realized by software processing using a processor (processor 11, processor 21, or processor 31). However, some or all of the processes may also be realized by hardware (electrical circuits). Each step is denoted as S.

[0064] In S201, the user device 3 determines whether an alert threshold has not been set or whether the set alert threshold should be changed to another value. The user device 3 may determine whether the alert threshold has not been set by communicating with the plant monitoring device 1. If the alert threshold has not been set or if the alert threshold should be changed (YES in S201), the user device 3 sets (or changes) the alert threshold based on a user operation and transmits the alert threshold to the plant monitoring device 1 (S202). A user who is unfamiliar with setting alert thresholds may find it difficult to visualize the degree of wilting that the wilting value represents (the relationship between the wilting value and the actual degree of wilting). Therefore, when setting the alert threshold, it is desirable to display image data acquired in the past and the wilting values ​​corresponding to the image data so that the user can refer to them. This allows the user to understand how large the wilting value must be before an alert is issued, making it easy for the user to set the alert threshold. The plant monitoring device 1 sets the alert threshold from the user device 3. If the alert threshold has already been set and is not to be changed (NO in S201), the process of S202 is skipped.

[0065] In S101, the plant monitoring device 1 acquires image data (time-series image data) and environmental data (time-series environmental data). The plant monitoring device 1 generates wilting data based on the image data and environmental data (S102). This process has been described in detail with reference to FIG. 3, so the description will not be repeated here. As mentioned above, environmental data is not essential for generating wilting data.

[0066] In S103, the plant monitoring device 1 determines whether the wilting value in the wilting data is greater than (will become greater than) the alert threshold. If the wilting value is greater than the alert threshold (YES in S103), the plant monitoring device 1 determines that the plant is wilting and is likely to wither within, for example, several hours (S104). Then, the plant monitoring device 1 notifies the user device 3 of an alert indicating that the plant may wither (S105).

[0067] In S203, the user device 3 determines whether or not an alert has been received from the plant monitoring device 1. If an alert has not been received (NO in S203), the subsequent processing is skipped. If an alert has been received (YES in S203), the user device 3 displays the alert on the touch panel display 33 (S204, see FIG. 6).

[0068] In S205, the user device 3 determines whether to request detailed display of the wilting data. For example, when a user operation of touching the button 834 for detailed display in FIG. 6 is accepted (YES in S205), the user device 3 requests detailed display of the wilting data from the plant monitoring device 1 (S206). In response to the request from the user device 3, the plant monitoring device 1 transmits the wilting data to the user device 3 (S106). The user device 3 displays the wilting data on the touch panel display 33 (S207, see FIG. 8). This completes the series of processes for the plant monitoring device 1 and the user device 3.

[0069] If the wilting value is consistently smaller than the alert threshold in S103 (NO in S103), the plant monitoring device 1 determines that no abnormality that could lead to the plant withering has occurred (S107). The plant monitoring device 1 does not notify the user device 3 of an alert.

[0070] Although not shown, when an alert is received from the plant monitoring device 1, the user device 3 may accept an operation by the user to set irrigation conditions and transmit the irrigation conditions directly or indirectly to the irrigation control device 4 (see Figure 1).

[0071] As described above, the plant management system 100 may include multiple user devices 3. In this case, it is desirable that various data such as time-series image data, time-series environmental data, and wilting data be shared among the multiple user devices 3. Also, only specific administrators who have been given authorization in advance may be allowed to set (change) the alert threshold. The administrator may be able to set the alert so that only some of the multiple user devices 3 are notified.

[0072] As described above, in this embodiment, when the wilting value exceeds the alert threshold or is predicted to exceed the alert threshold, an alert is sent from the plant monitoring device 1 (or the server 2) to the user device 3. This allows the user to actually check the monitored plant, its surrounding plants, the plant's growing environment, whether there are any abnormalities in the irrigation device, etc. at the plant management site, and take appropriate measures to prevent the plant from withering based on their own experience and intuition. Therefore, according to this embodiment, it is possible to prevent the plant from withering at the actual plant management site.

[0073] The plant monitoring device 1 provides image data at a photographing time designated by the user to the user device 3. This allows the user to refer to the image data at the designated time, check the state of the plant at that time, and consider what measures are appropriate.

[0074] The plant monitoring device 1 provides the user device with a graph showing the change in the wilting value over time. If the wilting value increases sharply or monotonically, a serious abnormality (such as a malfunction of the irrigation device) may have occurred. On the other hand, if the wilting value increases slowly or if the wilting value increases gradually while fluctuating, a more minor abnormality (such as insufficient adjustment of some environmental factors) may be present. In this way, the user can infer the cause of the alert based on the change in the wilting value over time and, based on this, consider what measures are appropriate.

[0075] The plant monitoring device 1 provides the user device with the predicted time when the wilting value will exceed the alert threshold. If the predicted time is imminent, urgent measures are required. On the other hand, if there is time until the predicted time, the user can take their time to consider measures. In this way, the user can understand the urgency of the measures.

[0076] The alert threshold can be variably set by the user, allowing the user to freely set the stage at which they would like to receive an alert regarding the extent to which wilting is likely to progress. Additionally, previously acquired image data and the corresponding wilting values ​​are displayed for the user to refer to. This allows the user to easily set the alert threshold.

[0077] The plant monitoring device 1 receives user operation on the user equipment 3 for manually setting irrigation conditions for the irrigation control device 4, and transmits the irrigation conditions set by the user to the irrigation control device 4. This allows the user to set irrigation conditions based on their own experience and intuition.

[0078] The embodiments disclosed herein should be considered to be illustrative in all respects and not restrictive. The scope of the present disclosure is defined by the claims, not by the description of the above embodiments, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0079] 100 Plant management system, 1 Plant monitoring device, 11 Processor, 12 Memory, 2 Server, 21 Processor, 22 Memory, 23 Database, 3 User equipment, 31 Processor, 32 Memory, 33 Touch panel display, 4 Irrigation control device, 5 Data acquisition unit, 51 Camera, 52 Environmental sensor, 53 Data output section, 6 Data processing unit, 61 Data input section, 62 Image feature extraction section, 63 Environmental feature extraction section, 64 Prediction section, 65 Alert threshold setting section, 66 Comparison section, 67 Alert generation section, 68 Notification section, 7 Stand, NW network.

Claims

1. a camera that captures image data of a plant under the user's control by photographing the plant; a processor for calculating a wilting value indicating a degree of wilting of the plant based on the image data, The processor notifies a user device used by the user of an alert when the wilting value exceeds an alert threshold.

2. 2. The plant management system of claim 1, wherein the processor does not implement measures to prevent the plant from wilting and dying even if the wilting value exceeds the alert threshold unless the user operates the user device.

3. The plant management system of claim 1 or 2, wherein the processor notifies the user equipment of the rate of increase of the wilting value.

4. The plant management system of claim 1 or 2, wherein the processor notifies the user device of at least one of a period during which the wilting value exceeds a warning threshold that is lower than the alert threshold and a number of times the wilting value exceeds the warning threshold during the predetermined period.

5. The plant management system according to claim 1 , wherein the processor provides the user device with at least one of the image data at a photographing time designated by the user and a graph showing the change in the wilting value over time.

6. the alert threshold is variably set by the user; 3. The plant management system according to claim 1, wherein the user device displays the image data previously acquired and the wilting value corresponding to the image data so that the user can refer to the image data when setting the alert threshold.

7. an environmental sensor for acquiring environmental data indicating environmental factors that affect the degree of wilting of the plant at a management site of the plant; The plant management system of claim 1 , wherein the processor predicts a time change in the wilting value based on the image data and the environmental data.

8. The plant management system of claim 7 , wherein the processor provides the user device with a predicted time when the wilting value will exceed the alert threshold.

9. acquiring image data of a plant by photographing the plant under the user's control; predicting a time change in a wilting value indicating a degree of wilting of the plant based on the image data; and if the wilting value is predicted to exceed an alert threshold, sending an alert to a user device used by the user.

Images