Plant growth monitoring system and method

Abstract

A plant growth monitoring system includes an image capture system configured to capture images of a monitored plant over time. The images are used to derive successive moments corresponding to predetermined growth states of the plant. A temperature exposure parameter is obtained between the successive moments based on a function of the monitored temperature over time. Information related to plant health is derived from the temperature exposure parameter.

Description

Technical Field

[0001] The present invention relates to monitoring the growth of plants in environments such as vertical farms and greenhouses. Background Art

[0002] Monitoring plant growth progress (eg, emergence of new leaves, counting new leaves, etc.) through manual inspection is complex and labor-intensive.

[0003] It is known to use local sensors to monitor plant growth in order to provide automated control of climate management systems and / or to report when problems arise. For example, it is known to use sensors or 2D or 3D cameras to capture information over time. For example, a camera can be used to capture images over time, from which measurements (such as plant height, leaf number, leaf color, leaf width, etc.) can be derived.

[0004] Automated decision modules can then be used to adjust control parameters of the climate management system to ensure that growth follows specified criteria (such as an expected development rate). The decision modules can also generate alerts based on deviations of detected growth from a set of specified expected growth criteria.

[0005] During a plant's development, a variety of characteristics can be monitored to assess whether growth is following the expected developmental rate. As a further example, when a plant is grown normally under stable environmental conditions (e.g., temperature, light), the spacing between each new leaf formed along the stem of a given plant remains fairly constant.

[0006] Zhenghong Yu et al., “Automatic image-based detection technology for two critical growth stages of maize: Emergence and three-lead stage,” Agricultural and Forest Meteorology, 174-175 (2013), 65-84, disclose the use of computer vision technology to identify the emergence and three-leaf stages.

[0007] Detection of specific growth stages of a plant or specific growth states of specific parts of a plant enables determination of developmental rates based on the time it takes to reach those specific growth stages or growth states. However, this is not an accurate indicator of whether plant growth is following an expected trajectory, as many factors influence growth conditions, such as temperature, irrigation, fertilizer, etc.

[0008] Therefore, there is a need for a more accurate automated monitoring system that can still be implemented with existing simple and reliable technology. Summary of the Invention

[0009] The invention is defined by the claims.

[0010] According to an example consistent with one aspect of the present invention, there is provided a plant growth monitoring system comprising:

[0011] an image capture system for capturing images of the monitored plants over time;

[0012] an image processing system for processing the captured images to derive successive moments corresponding to predetermined growth states of the plant;

[0013] Temperature monitoring systems for monitoring the temperature of plants or the environment in which they are growing;

[0014] The processor is adapted to:

[0015] deriving a temperature exposure parameter from the monitored temperature between consecutive moments in time based on a function of temperature versus time for the time period between the consecutive moments in time; and

[0016] Provides information related to plant health based on derived temperature exposure parameters.

[0017] The term "growth state" is used to refer to identifiable growth characteristics, such as the emergence of new leaves, the formation of new shoots, etc. A growth state may even refer to a plant's growth phase (i.e., germination, seedling, vegetative phase, sprouting, flowering, maturity). However, more typically, the monitored growth states are separated by time intervals that are shorter than the plant's typical growth phase.

[0018] The term "plant health" is used to refer to the extent to which a plant's growth state corresponds to a desired and feasible growth state. A plant is considered healthy if its growth state is within certain limits of a desired and feasible growth state, as defined by its physical condition (characterized by quantities such as weight, size, form, and color).

[0019] The present invention is based on the recognition that temperature as a function of time is of fundamental and primary importance in assessing whether a time period corresponds to the desired health of a plant, during which a predetermined amount of growth is achieved (i.e., between different growth states). In other words, the present invention is based on the recognition that plant health can be assessed based on temperature exposure parameters for a period of time corresponding to the passage of time between predefined plant states. In examples, as will be discussed in more detail below, these predefined plant states can be the emergence of new leaves. Thus, in these examples, the passage of time can correspond to the time between the emergence of successive new leaves.

[0020] The monitored temperature can be the temperature of the plant itself or the temperature of the environment in which the plant is growing. For example, the temperature of the plant's stem tip at a relevant location in the growth state (e.g., where new leaves will form) may be important. However, the environment can be monitored as a proxy for the plant's temperature.

[0021] This system uses image analysis to monitor plant growth status. Specifically, plant growth states (such as growth in size, leaf size, number of leaves, bud growth, etc.) that are achieved over time are detected. Temperature exposure parameters are related to the evolution of temperature between the time points at which those growth states are achieved, and are dependent on both the duration of the time period and the temperature. The present invention is based on the recognition that temperature exposure parameters can be derived that correlate with the (normal) growth pattern of a plant. Thus, information related to plant health (e.g., compared to a normal growth pattern) can be derived. For example, the present invention is useful for use in vertical farms and greenhouses.

[0022] Information related to plant health may be provided simply as advisory information, or it may be used for automated control of growing conditions.

[0023] The temperature integral has been found to be a parameter that correlates with plant growth rate. Therefore, it can be used as an indicator of whether plant growth is normal or abnormal. This integral includes the temperature offset (which depends on the baseline temperature over which the integration is performed). The integral is, of course, equal to the average temperature over a period of time multiplied by the duration between moments.

[0024] Lighting conditions can be further considered when determining temperature exposure parameters. For example, the photoperiod (the number of hours of light during the day) can be considered. The actual light levels during the lighting period can also be considered. The amount of light also affects plant temperature and has an indirect effect on temperature.

[0025] The method can be applied to plants at any developmental stage.

[0026] The continuous moments include, for example, the time when a new leaf is formed or when a new leaf reaches a predetermined size.

[0027] For a given stem, the oldest leaf is the lowest leaf on the stem. New leaves form at the stem tip. The moments to be determined are, for example, the time when a new leaf emerges and the time when the next new leaf appears along the same stem. More generally, a moment is the time when a new leaf has reached a certain developmental state and the next new leaf has reached the same developmental state.

[0028] For example, measurements may be taken for a plurality of stems and / or for a plurality of plants and then an average time interval may be obtained from which a temperature exposure parameter may be derived.

[0029] The image processing system is, for example, adapted to recognize the formation of leaves of a predetermined size and to extrapolate the time back to a moment corresponding to a smaller or zero leaf size. Detection of leaves of a certain size is more practical, while the moment of initial leaf formation may be a better parameter for determining plant health, but is less practical to detect.

[0030] Alternatively, the continuous moments may include the time of continuous branch formation or continuous flower formation. The temperature exposure parameter may also be defined as being related to the formation of new branches or flowers. For example, in tomatoes, after three leaves have formed, a new flower cluster will form. In this example, the temperature exposure parameter related to flower cluster formation will be three times the temperature exposure parameter related to leaf formation.

[0031] Alternatively, the continuous moments may include the time when the entire plant reaches a predetermined growth condition. "Growth condition" may, for example, relate to a certain number of leaves, branches, or flowers rather than physical size. The physical size of a plant is particularly affected by parameters other than temperature exposure, such as, for example, the duration of light, light levels, CO2 levels, etc.

[0032] Temperature exposure parameters include, for example, the integral of temperature over time (between successive moments). This provides a measure of the area beneath the temperature versus time plot. The baseline for the integral can depend on the plant type. It can, for example, be in the range of 5 to 15 degrees Celsius.

[0033] The temperature can be clamped at a baseline temperature so that if the temperature drops below the baseline, it is set to the baseline. There can also be a maximum temperature (such as 30 degrees), for which a simple integral can be used. More complex functions can be used to allow for higher temperatures. For example, if T(t) is a function of temperature over time, and T0 is a reference baseline temperature, then the temperature integral is the integral of (T(t)-T0) over the time period between consecutive moments. Therefore, there are two parameters in this model, namely T0 and the integral of (T(t)-T0). Therefore, the T0 value can be different for different plants.

[0034] The processor may be adapted to obtain a reference temperature exposure parameter relating to a plant variety of the monitored plant and to compare the reference temperature exposure parameter with the derived temperature exposure parameter.

[0035] Different plant species have different correlations between temperature exposure parameters and developmental rates, and this is represented by a reference temperature exposure parameter, which is the expected temperature exposure associated with the expected growth between the monitored growth states.

[0036] The processor can be adapted to determine a degree of deviation from a reference plant health and can then be further adapted to derive climate adjustment settings based on the deviation. Thus, the system can be used to provide automatic control of the plant climate to ensure desired growth characteristics. The climate adjustment settings, for example, include one or more of the following:

[0037] temperature;

[0038] Irrigation settings;

[0039] Humidity levels;

[0040] CO2 concentration levels;

[0041] Fertilizer dosage; and

[0042] Lighting parameters.

[0043] These various parameters can be used to influence plant growth and plant health characteristics.

[0044] The present invention also provides a gardening system comprising:

[0045] The space (volume) in which the plants will grow;

[0046] a climate and lighting control system for controlling at least the temperature and lighting within the space; and

[0047] A plant growth monitoring system as hereinbefore defined.

[0048] The present invention also provides a plant growth monitoring method, comprising:

[0049] Capturing images of monitored plants over time;

[0050] processing the captured images to derive successive moments corresponding to predetermined growth states of the plant;

[0051] monitoring the temperature of plants or the environment in which they are growing;

[0052] deriving a temperature exposure parameter from the monitored temperature between consecutive moments in time based on a function of temperature versus time for the time period between the consecutive moments in time; and

[0053] Provides information related to plant health based on derived temperature exposure parameters

[0054] Examples of consecutive moments include:

[0055] the time it takes for new leaves to form or reach a predetermined size;

[0056] the timing of successive lateral branch formation or successive flower formation; or

[0057] The moment when the plant reaches a predetermined size.

[0058] The method may include identifying the formation of a leaf of a predetermined size, and extrapolating back in time to a moment corresponding to a smaller or zero leaf size.

[0059] Temperature exposure parameters include, for example, the integral of temperature over time (between consecutive moments).

[0060] The invention also provides a computer program comprising computer program code adapted to implement the method defined above when said program is run on a computer.

[0061] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] For a better understanding of the present invention, and in order to show more clearly how it may be put into practice, reference will now be made, by way of example only, to the accompanying drawings, in which:

[0063] Figure 1 A horticultural system for growing plants is shown; and

[0064] Figure 2 A plant growth monitoring method is shown. DETAILED DESCRIPTION

[0065] The present invention will be described with reference to the accompanying drawings.

[0066] It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the above-described devices, systems, and methods, are intended for illustrative purposes only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the devices, systems, and methods of the present invention will become better understood from the following description, the appended claims, and the accompanying drawings. It should be understood that the drawings are merely schematic and not drawn to scale. It should also be understood that throughout the drawings, the same reference numerals are used to indicate the same or similar parts.

[0067] The present invention provides a plant growth monitoring system comprising an image capture system for capturing images of a monitored plant over time. These images are used to derive successive moments corresponding to predetermined growth states of the plant. Based on a function of the monitored temperature versus time, a temperature exposure parameter is obtained for the time period between the successive moments. Information related to the plant's health is derived from the temperature exposure parameter.

[0068] Figure 1 shows a horticultural system for growing plants, Figure 1 Only one plant 10 is shown. The plants are provided in a space such as a greenhouse or a vertical farm enclosure. For example, this gardening system is used in controlled environment agriculture.

[0069] In such a system, various variables can be controlled, such as:

[0070] temperature;

[0071] relative humidity;

[0072] Carbon dioxide concentration;

[0073] light (intensity, spectrum, duration, and interval);

[0074] nutrient concentrations;

[0075] nutrient pH;

[0076] Irrigation control (i.e., watering); and

[0077] Pest control measures.

[0078] The temperature of one or more of the ambient air, nutrient solution, root zone, or foliage may be controlled.

[0079] By way of example, Figure 1 Shown schematically are a lighting system 20 and a heating system 22. These form part of a climate and lighting control system for controlling at least the temperature and lighting within the space.

[0080] The present invention provides a plant growth monitoring system comprising an image capture system 12 for capturing images of monitored plants 10 over time. Image capture system 12 may, for example, comprise a set of 2D and / or 3D cameras located at various locations (e.g., above the plants or on the sides of a plant growth rack). A temperature monitoring system 14 is also provided. The monitored temperature may simply be the ambient temperature, but surface temperature sensors (such as infrared temperature sensors) may also or alternatively be used to monitor, for example, leaf temperature.

[0081] Image processing system 16 processes the captured images. It derives successive moments t1, t2 corresponding to predetermined growth states of the plant. The image processing system analyzes the time series of images received from image capture system 12 to extract growth information. The goal is to identify when specific growth states have been reached. These may relate to the formation or development of a single plant stem, or they may relate to the development of the entire plant. Growth states may relate to the formation of leaves, lateral branches, or flowers. The current growth stage of the plant (for example, the flowering stage for some plant types) can also be determined.

[0082] The growth state to be identified can be based on, for example, growth guidelines provided by the user. Examples of such growth guidelines are the expected rate of new leaf production, the number of leaves over time, and the expected amount of plant pixel coverage in a plant image (e.g., on day 3, 50% of the image pixels are expected to correspond to one or more plant species).

[0083] As an alternative to user-defined growth guidelines, the system can automatically extract guidelines without requiring input from the user. In this case, the system is trained to consider what a normal growth cycle for the monitored plant should be based on, for example, monitoring multiple simultaneous or sequential growth cycles occurring at one or more premises with connectivity to a cloud storage and central processing deployment.

[0084] The image processing system can use a trained deep learning network, for example, trained to count the number of leaves in an image of a plant, or in images of a plant over time, or in a set of images over time (where the images may contain multiple plants). For example, for images with multiple plants, the system can be adapted to first separate the different instances of a plant and then process each instance of a plant separately to count its leaves. Additionally or alternatively, if the interest is in overall plant growth in a section of a horticultural facility, rather than individual plant growth, the image processing system can analyze each image as a whole, for example, to monitor plant cover compared to the background as a measure of growth. In this case, a group of plants can be considered a single entity.

[0085] Thus, the growth state monitored by image analysis can be any identifiable growth feature, such as the emergence of new leaves, the emergence of new side branches, the formation of buds, the height of the plant, etc. It has been found that two consecutive growth states can be defined, between which a known temperature exposure parameter is expected. This temperature exposure parameter is a measure of the overall temperature exposure of the plant (or a part of the plant) during a specific time period, and is therefore preferably an integral function of the temperature as a function of time. The monitored temperature can be the temperature of the plant itself or the temperature of the environment in which the plant is growing. For example, the temperature of the plant's stem tip at a relevant location in the growth state (e.g., where new leaves will form) may be important.

[0086] By way of example, for certain types of healthy plants, the number of leaves on a plant depends linearly on the product of temperature and time. The same applies to the number of flowers (or flower clusters). Therefore, this information can be used as a guide to assess the health of the plant and / or identify how to activate the climate and lighting control system to restore growth to the expected growth corresponding to a healthy plant. There may be additional constraints, such as constraints on resource use (such as energy used by lighting or heating systems) or constraints on the capacity of the growing system to be considered when identifying climate and lighting control system settings to drive growth toward the expected growth.

[0087] A particularly preferred example is to obtain consecutive moments related to the time when new leaves are formed on the same branch, or equivalently, to obtain the moment when new leaves on the same branch reach a predetermined size.

[0088] For a given stem, the oldest leaf is the lowest leaf on the stem. New leaves form at the stem tip. The moments to be determined are, for example, the time a new leaf emerges and the time the next new leaf appears along the same stem.

[0089] However, an image processing system can be used to identify the formation of leaves of a predetermined size and extrapolate the time back to a moment corresponding to a smaller or zero leaf size. Using image processing, detection of leaves of a certain size is more practical and feasible than detection of initial leaf formation, although the moment of initial leaf formation may be a better parameter for determining plant health.

[0090] In all cases, the image processing generates a pair of consecutive moments t1, t2 corresponding to the point in time at which the predetermined growth state is identified. Over time, during the entire monitoring period, there will be multiple pairs of consecutive moments.

[0091] The processor 18 then derives a temperature exposure parameter from the monitored temperatures between consecutive times based on a function of temperature versus time for the period between consecutive times t1 and t2. This is a metric related to the plant's cumulative temperature exposure and therefore has at least one component having units of the product of temperature and time (e.g., degrees·days).

[0092] The processor can also derive additional information. For example, the time periods between consecutive moments can be added together to derive the absolute time (from start time) of the occurrence of a particular (macro)growth state. This (macro)growth state is achieved, for example, after a longer plant development period (than the period monitored between a pair of consecutive moments).

[0093] The processor and image processing system can be located locally or remotely, such as cloud-based storage and processing.

[0094] Comparing the temperature exposure parameters with a reference TE_ref allows information related to plant health to be derived.

[0095] This information can be provided as an output for consultation purposes (e.g., as a wirelessly transmitted data message to a remote unit). Thus, an interface is provided that allows the user to be informed of growth monitoring outputs in real time and to compare actual growth with reference growth in the guideline. The interface can also provide the user with automatically generated guidelines and allow the user to modify these guidelines or enter metadata that allows the guidelines to be generated and / or annotated in a more controlled / precise manner.

[0096] Additionally or alternatively, this information can be used to control climate and lighting control systems 20, 22. This is based on identifying differences between expected growth and actual growth. The mapping from these differences to required steps can be hard-coded (i.e., provided by the user and stored for later use) or can be identified by a module that analyzes data from one or more facilities and builds a machine learning model that maps input features (such as temperature, light level, light spectrum, etc.) to output variables (such as number of leaves, leaf production rate, plant height, etc., growth rate).

[0097] Reference TE_ref is shown as an input to processor 18. It can, of course, be stored in memory. Such memory can store sensor data as well as growth guidelines for specific plant types, i.e., guidelines for how the plant type in question is expected to grow. The memory can be cloud storage. The memory can further include a map showing the effects of changing climate and lighting control parameters (e.g., temperature, lighting variables) on growth / development rates.

[0098] As mentioned above, the temperature exposure parameter is a cumulative metric. The temperature integral has been found to be a parameter that reliably correlates with plant development rate. Therefore, it can be used as an indicator of whether plant development rate is normal or abnormal.

[0099] The integral provides a measure of the area under a plot of temperature versus time. The baseline temperature can be used as a temperature offset in the integral calculation. A suitable baseline temperature may depend on the plant type and may indicate the minimum temperature required for plant growth. It may, for example, be in the range of 5 to 15 degrees Celsius. If T(t) is a function of temperature over time, and T0 is a reference baseline temperature, then the temperature integral is the integral of (T(t)-T0) over the time period between successive moments. Therefore, there are two parameters in this model, namely T0 and the integral of (T(t)-T0). The T0 value may be different for different plants.

[0100] The temperature can be clamped at a baseline temperature so that if the temperature drops below the baseline, it is set to the baseline. Thus, the temperature exposure parameter is based on a function of temperature versus time for the time period between consecutive moments, but it can be a more complex function than a simple integral (particularly if the temperature may fall outside the range where the basic integral function is considered valid).

[0101] There can also be a maximum temperature (such as 30 degrees), for which a simple integral can be used. This temperature can indicate the maximum temperature above which temperature changes no longer affect plant growth. More complex functions can be used to allow for higher temperatures.

[0102] Lighting conditions can be further considered when determining temperature exposure parameters. For example, the photoperiod (the number of hours of light during a day, e.g., 24 hours) can be considered. The actual light levels during the lighting period can also be considered. The amount of light also affects plant temperature and has an indirect effect on temperature.

[0103] In any case, temperature is the primary influencing factor and the temperature versus time function is considered between moments in time to assess plant health. However, additional sensor inputs may also be considered when determining temperature exposure parameters and comparing with reference values.

[0104] In all cases, for a plurality of stems and / or for a plurality of plants, the time intervals between consecutive growth states can be taken and then an average time interval can be obtained, from which the temperature exposure parameter is derived.

[0105] Figure 2 A plant growth monitoring method is shown, comprising: in step 30, capturing images of a monitored plant over time, and in step 32, processing the captured images to derive successive time instants t1, t2 corresponding to predetermined growth states of the plant.

[0106] Optionally, step 34 involves extrapolating time values, for example, from a detected leaf of a certain size back to the initial leaf formation.

[0107] In step 36, the temperature of the device is monitored. Figure 2 As shown, this occurs in parallel with image capture, or as image capture occurs.

[0108] In step 38 , a temperature exposure parameter is derived from the monitored temperature between consecutive moments in time based on a temperature versus time function for the time period between the consecutive moments in time.

[0109] Information related to plant health is provided based on the derived temperature exposure parameters. This information is used for climate adjustment in step 40 and / or for providing an output to a user in step 42.

[0110] Image analysis algorithms for detecting plant growth status are known, for example, as disclosed in the article by Zhenghong Yu et al. (see above). Such image analysis is based on, for example, trained machine learning algorithms using image segmentation and analysis techniques. Further examples are presented in "An automated, high-throughput plant phenotyping system using machine learning-based plant segmentation and image analysis" by Unseok Lee et al. (doi.org / 10.1371 / journal.pone.0196615) and KR2018 / 0027778.

[0111] As discussed above, the system utilizes a processor to perform image processing and sensor data processing. The processor can be implemented in numerous ways using software and / or hardware, using a single processor or multiple processors, to perform the various functions required. The processor typically employs one or more microprocessors that can be programmed using software (e.g., microcode) to perform the required functions. The processor can be implemented as a combination of dedicated hardware to perform some functions and one or more programmed microprocessors and associated circuitry to perform other functions.

[0112] Examples of circuitry that may be used in various embodiments of the present disclosure include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field programmable gate arrays (FPGAs).

[0113] In various embodiments, the processor can be associated with one or more storage media, such as volatile and non-volatile computer memory, such as RAM, PROM, EPROM, and EEPROM. The storage medium can be encoded with one or more programs that, when executed on one or more processors and / or controllers, perform the desired functions. The various storage media can be fixed within the processor or controller, or can be removable so that one or more programs stored thereon can be loaded into the processor.

[0114] Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0115] A single processor or other unit may fulfill the functions of several items recited in the claims.

[0116] The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0117] The computer program may be stored / distributed on suitable media such as optical storage media or solid-state media provided with or as part of other hardware, but may also be distributed in other forms such as via the Internet or other wired or wireless telecommunications systems.

[0118] If the term "adapted to" is used in the claims or the description, it should be noted that the term "adapted to" is intended to be equivalent to the term "configured to".

[0119] Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. A plant growth monitoring system comprising: an image capture system (12) for capturing images of the monitored plant (10) over time; an image processing system (16) for processing the captured images to derive successive moments (t1, t2) corresponding to predetermined growth states of the plant; a temperature monitoring system (14) for monitoring the temperature of the plant or the environment in which the plant is growing; A processor (18) adapted to: deriving a temperature exposure parameter from the monitored temperature between the consecutive moments in time based on a function of temperature versus time for the time period between the consecutive moments in time; and Provides information related to plant health based on derived temperature exposure parameters. 2 . The system of claim 1 , wherein the continuous moments include moments when a new leaf is formed or when the new leaf reaches a predetermined size.

3. The system of claim 2, wherein the image processing system is adapted to identify the formation of leaves of a predetermined size and to extrapolate back in time to a moment corresponding to zero leaf size.

4. The system of claim 1, wherein the consecutive moments include times of consecutive side branch formation or consecutive flower formation. The system of claim 1 , wherein the continuous moments include times when plants reach predetermined growth conditions.

6. The system of any one of claims 1 to 5, wherein the temperature exposure parameter comprises an integral of temperature over time between the consecutive moments.

7. The system according to any one of claims 1 to 5, wherein the processor is adapted to: obtain reference temperature exposure parameters associated with a plant variety of the monitored plant, and compare the reference temperature exposure parameters with the derived temperature exposure parameters.

8. The system of any one of claims 1 to 5, wherein the processor is adapted to determine an extent of deviation from a reference plant health and further adapted to derive climate adjustment settings based on the deviation.

9. The system of claim 6, wherein the processor is adapted to determine a degree of deviation from a reference plant health and further adapted to derive climate adjustment settings based on the deviation.

10. The system of claim 7, wherein the processor is adapted to determine a degree of deviation from a reference plant health and further adapted to derive climate adjustment settings based on the deviation.

11. The system of claim 8, wherein the climate adjustment settings include one or more of the following: temperature; Irrigation settings; Humidity levels; Fertilizer dosage; CO2 concentration levels; and Lighting parameters.

12. A gardening system comprising: the space in which the plants will grow; a climate and lighting control system for controlling at least the temperature and lighting within the space; as well as A plant growth monitoring system according to any one of claims 1 to 11.

13. A plant growth monitoring method comprising: (30) capturing images of the monitored plants over time; (32) processing the captured images to derive successive moments corresponding to predetermined growth states of the plant; (36) monitoring the temperature of the plant or the environment in which the plant is growing; (38) deriving a temperature exposure parameter from the monitored temperature between the consecutive moments based on a function of temperature versus time for the time period between the consecutive moments; as well as Provides information related to plant health based on derived temperature exposure parameters.

14. The method of claim 13, wherein the consecutive moments comprise: the time it takes for new leaves to form or reach a predetermined size; the timing of successive lateral branch formation or successive flower formation; or The moment when the plant reaches a predetermined size.

15. The method according to claim 14, comprising: The formation of a leaf of a predetermined size is identified, and the time is extrapolated back to a moment corresponding to zero leaf size.

16. The method of any one of claims 13 to 15, wherein the temperature exposure parameter comprises the integral of temperature over time between the consecutive moments.

17. A computer program product comprising a computer program for implementing the method of any one of claims 13 to 16 when the computer program is run on a computer.

Images