WO2021219486A1

WO2021219486A1 - Systems and methods for monitoring pollination activity

Info

Publication number: WO2021219486A1
Application number: PCT/EP2021/060552
Authority: WO
Inventors: Fiona EDWARDS-MURPHY; Padraig WHELAN
Original assignee: Apisprotect Ltd
Priority date: 2020-05-01
Filing date: 2021-04-22
Publication date: 2021-11-04
Also published as: GB202006508D0; GB2594524A; GB2594524B

Abstract

The present disclosure relates to a method and system for monitoring pollination activity, including capturing an image; analysing the image; detecting whether the captured image contains both a pollinator and at least one pollen element; and determining a characteristic associated with the at least one pollen element. The characteristic may comprise a colour, a wavelength, or a dimension. Advantageously, the determined characteristic of the at least one pollen element may be compared with a predefined characteristic to assist in evaluating pollination contract adherence.

Description

SYSTEMS AND METHODS FOR MONITORING POLLINATION ACTIVITY

FIELD OF THE INVENTION

This invention relates to systems and methods for monitoring pollination activity, and in particular to a system and method for determining the origin of pollen collected by pollinators in a farm and for tracking pollination contract adherence.

BACKGROUND OF THE INVENTION

The use of pollinator insects to enhance crop yield is a well-known and widely favoured method in commercial agriculture. Pollinator insects include bees, wasps, butterflies, moths, beetles and various types of flies such as midges. These insects are selected in part based on their efficacy in pollinating particular varieties of crops.

Honey bees are currently used commercially to pollinate a variety of crops across the globe, including: almonds, apples, strawberries, blueberries, cranberries, kiwi, melons, canola, and avocado; as well as for seed production. The density of beehives required for commercial pollination varies from 2 to 4 hives per acre typically, but can reach 17 hives per acre in some situations. Pollination contracts are generally based on the delivery of colonies with a certain ‘frame count’ (the proportion of frames covered in bees).

Large numbers of hives arrive to farms for the pollination season, requiring manual evaluation of the ‘hive strength’ (the number of bees in a hive) for every colony. Hives are made up of compartments called ‘brood boxes’ and ‘supers’. Manual evaluation of hive strength is prone to human error, as well as being time consuming and costly both financially and in terms of resources. Generally, compliance to contracts is either not evaluated at all (42% in a 2018-2019 study conducted by the ‘Bee Informed Partnership’), or a subset of colonies (approximately 10 - 15 %) are evaluated and the results are assumed to scale across the entire operation.

However, hive strength is not the only factor impacting pollination effectiveness. Weather conditions, bloom percentage, and the availability of other competing forage for pollinators can impact the actual amount of pollination of the target crop provided to a grower. If a pollinator is foraging from an alternative plant to that which the grower is cultivating, this means the pollinator will not be contributing to the pollination of the grower’s crops. The plant which pollen originates from can be determined from inspection of the pollen colour or pollen wavelength.

One of the most commonly selected pollinators in crop production are honey bees. Certain species of bees have pollen “baskets”, structures disposed on the hind legs and designed for carrying pollen from a harvest point to a hive. Inspection of the wavelength of a pollen basket will indicate on which plant a bee has been foraging. However, as discussed above manual inspection is both financially costly and demanding on resources.

It is therefore desirable to provide systems and methods which overcome at least some of these challenges.

SUMMARY

In a first aspect of the present invention, a method of monitoring pollination activity is provided, the method comprising: capturing an image; analysing the captured image; detecting if the captured image contains at least one pollinator and at least one pollen element; determining a characteristic associated with the at least one pollen element; and comparing the characteristic associated with the at least one pollen element to one or more predefined characteristics to determine the source of the at least one pollen element.

Preferably, detecting if the captured image contains the at least one pollen element comprises detecting if the captured image contains a pollen basket containing the at least one pollen element.

Advantageously, detecting if the captured image contains the at least one pollen element comprises detecting if the captured image contains a scopa having disposed thereon the at least one pollen element. Optionally, the characteristic associated with the at least one pollen element comprises a colour or a wavelength.

Optionally, the characteristic associated with the at least one pollen element comprises a dimension.

Advantageously the source of the at least one pollen element comprises a type of plant.

Further advantageously, the source of the at least one pollen element comprises a geographical location from whence the at least one pollen element was foraged.

Advantageously, the method may further comprise providing a user with information relating to a determined source of pollen. Advantageously, the method may further comprise determining a number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic.

Further advantageously, when the number of pollinators having a pollen element with a characteristic which substantially corresponds to a predefined characteristic is less than, equal to or greater than a predefined threshold value, a notification may be provided to a user.

In a further aspect the method may further comprise storing in memory the determined data relating to one or more of: i) the determined characteristic associated with the at least one pollen element; ii) a number of pollen baskets in the captured image; iii) a number of pollinators in the captured image; iv) a number of pollen elements in the captured image; or v) the number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic.

Preferably, the image is captured in the vicinity of a hive. Advantageously, the method may further comprise associating determined data with a hive in the captured image.

Further advantageously the method may further comprise transmitting determined data to one or more of a remotely located server or a user device.

Further advantageously the method may further comprise generating a report based at least in part on one or more of: i) the determined characteristic associated with the at least one pollen element; ii) the number of pollen baskets in the captured image; iii) the number of pollinators in the captured image; iv) the number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic; v) meteorological data; vi) ambient pressure data; vii) audio data; viii) C0₂ data; ix) temperature data; x) humidity data; xi) acceleration data; xii) a bloom percentage; or xiii) a bloom percentage class. Further advantageously, the method may further comprise providing a notification at the user device in response to the report generated.

In a further aspect of the present invention, a system for monitoring pollination activity is provided, the system comprising: an image capture device for capturing an image; and at least one processor configured for analysing the captured image, wherein the image analysis means is configured for detecting if the captured image contains a pollinator and a pollen element, wherein the at least one processor is configured for determining a characteristic associated with the pollen element, wherein the at least one processor is configured to compare the characteristic associated with the pollen element to one or more predefined characteristics to determine the source of the pollen element. Advantageously, the at least one processor is configured to implement a machine learning algorithm.

Preferably, the at least one processor is configured for determining one or both of a number of pollen baskets in the captured image and a number of pollinators in the captured image.

Advantageously, the at least one processor is configured for determining a number of pollinators in the captured image having a pollen element with a characteristic that substantially corresponds to a predefined characteristic.

Preferably, the system may further comprise at least one memory unit for storing the determined data relating to one or more of: i) the determined parameter associated with the pollen element; ii) the number of pollen baskets in the captured image; iii) the number of pollinators in the captured image; or iv) the number of pollinators in the captured image containing a pollen element with a characteristic which substantially corresponds to a predefined characteristic.

Optionally, the characteristic associated with the pollen element comprises one or more of a colour, a wavelength, or a dimension.

Preferably, the image is captured in the vicinity of a hive, and the at least one processor is configured for associating determined data with a hive in the captured image. Further preferably, the at least one processor is configured for generating a report based at least in part on one or more of: i) the determined characteristic associated with the pollen element; ii) the number of pollen baskets in the captured image; iii) the number of pollinators in the captured image; iv) the number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic; v) meteorological data; vi) ambient pressure data; vii) audio data; viii) CO₂ data; ix) temperature data; x) humidity data; xi) acceleration data; xii) a bloom percentage; or xiii) a bloom percentage class.

Advantageously, the system may further comprise a transmission means for transmitting determined data to one or more of: a remotely located server, or a user device.

Advantageously, the remotely located server is configured for generating a report based at least in part on one or more of: i) the determined characteristic associated with the pollen element; ii) the number of pollen baskets in the captured image; iii) the number of pollinators in the captured image; iv) the number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic; v) meteorological data; vi) ambient pressure data; vii) audio data; viii) CO₂ data; ix) temperature data; x) humidity data; xi) acceleration data; xii) a bloom percentage; or xiii) a bloom percentage class. BRIEF DESCRIPTION OF THE DRAWINGS

FIG. l is a block diagram illustrating an exemplary configuration of a system according to an embodiment of the present disclosure;

FIGs. 2-8 are flow diagrams illustrating methods for monitoring pollination activity according to embodiments of the present disclosure.

DETAILED DESCRIPTION OF THE DRAWINGS

The present teaching will now be described with reference to an exemplary method and system for monitoring pollination activity and in particular for determining pollination contract adherence. It will be understood that the exemplary method and system is provided to assist in an understanding of the present teaching and are not to be construed as limiting in any fashion. Furthermore, elements or components that are described with reference to any one Figure may be interchanged with those of other Figures or other equivalent elements without departing from the spirit of the present teaching.

As discussed above, if a pollinator is foraging from an alternative plant to that which the grower is cultivating, the pollinator will not be contributing to the pollination of the grower’s crops. The colour or wavelength of the pollen collected is an indication to the grower whether pollinators are foraging on their crop or on an alternative pollen source. When wavelength is used to determine the origin of pollen, a specific wavelength or a specific range of wavelengths may be used. For example, a particular wavelength may be indicative of the pollen originating from a certain plant, or the wavelength falling within a predefined range of wavelengths may be indicative of the pollen originating from a certain plant. It may therefore be advantageous to compare a determined wavelength with more than one predefined wavelengths. The present disclosure provides a method and system for identifying whether pollinators are foraging on a grower’s crop or on an alternative pollen source. As such, the presently disclosed method and system may allow growers to measure the amount of real pollination that is taking place, as well as identifying when the hives they have rented are no longer providing pollination. This may facilitate material cost savings and production/yield improvements for growers in being able to more precisely determine the hives required and the harvest of crops. Generally, pollinator insects include bees, wasps, butterflies, moths, beetles and various types of flies such as midges. In the present teaching particular attention is given to honey bees which have pollen “baskets”, structures disposed on the hind legs of certain species of bees designed for carrying pollen from a harvest point to a hive. Inspection of the colour or wavelength of pollen in a pollen basket will indicate on which plant a bee has been foraging. However, it is envisaged that the present disclosure may be equally applied to species of pollinators which have scopae instead of pollen baskets, as the source of pollen may be identified by its colour, wavelength, or a specific range of wavelengths within which the wavelength falls.

The term “pollen element” is used in the present disclosure. Generally, a pollen element is an amount of pollen. A pollen element in the present disclosure is any volume of pollen which is visually detectable by a camera.

It will be understood that the term “type” as used with regard to plants in the present disclosure has within its meaning plant species, subspecies, cultivars, and other taxonomic subdivisions, and combinations thereof (i.e. hybrids). The inventors envisage that the determination of a type of plant in the present disclosure is not limited to only one of the determination of a species, the determination of a subspecies, the determination of a cultivar, the determination of another taxonomic subdivision, or the determination of a hybrid.

FIG. 1 is a block diagram illustrating a configuration of a system 100 suitable for monitoring pollination activity, which includes various hardware and software components that, in conjunction with a plurality of external devices it is operationally associated with, function to perform processes according to the present disclosure. Referring to FIG. 1, the system 100 comprises at least one processor 110 in communication with local memory 120. The processor(s) 110 functions to execute software instructions that can be loaded and stored in local memory 120. The processor(s) 110 may include a number of processors, a multi-processor core, or some other type of processor, depending on the particular implementation. Local memory 120 may be accessible by the processor(s) 110, thereby enabling the processor(s) 110 to receive and execute instructions stored on the memory 120. The memory 120 may be, for example, a random access memory (RAM) or any other suitable volatile or non-volatile computer readable storage medium. In addition, the memory

120 may be fixed or removable and may contain one or more components or devices such as a hard drive, a flash memory, a rewritable optical disk, a rewritable magnetic tape, or some combination of the above.

One or more software modules may be encoded in local memory 120. The software modules may comprise one or more software programs or applications having computer program code or a set of instructions configured to be executed by processor(s) 110. Such computer program code or instructions for carrying out operations for aspects of the systems and methods disclosed herein may be written in any combination of one or more programming languages.

In the exemplary embodiment, the software modules comprise image analysis means. Said image analysis means may comprise a single software package or plural software packages with executable code suitable for performing one or more method steps described herein. In the exemplary embodiment, the software modules may comprise one or more machine learning models, such as deep learning algorithms implementing neural networks, for implementing image analysis. Accordingly, the processor(s) 110 may be configured to implement one or more machine learning models. Image analysis will be understood to entail a multitude of techniques known to one skilled in the art, including but not limited to one or more of digital signal processing, Fourier analysis and 3D pose estimation. The image analysis means may further comprise any software package for detecting specific features of an image; it will be understood that this may entail edge detection software, pattern recognition, feature detection and the like. These techniques may be implemented once on any single frame or dynamically on a live feed comprising a plurality of frames.

Other information and/or data relevant to the operation of the present apparatus, systems and methods, such as a database, may also be stored on local memory 120. The database may contain and/or maintain various data items and elements that are utilized throughout the various operations of the apparatus and system described below. The database may be configured locally to the system 100, or in certain implementations the database and/or various other data elements stored therein may be located remotely. Such elements may be located on a remote device or server, and connected to the system 100 through a network in a manner known to those skilled in the art, in order to be loaded into processor(s) 110 and executed. In various embodiments, the apparatus, systems and methods of the present disclosure may implement edge processing architectures and techniques. For example, the system(s) 100 may be connected to one or more edge nodes, said edge node(s) being connected to a cloud infrastructure. In accordance with embodiments of the present disclosure, data processing and/or storage may primarily take place at the edge node(s) to reduce bandwidth consumption and potentially reduce data latency.

Further, the program code of the software modules and one or more computer readable storage devices (such as local memory 120) form a computer program product that may be manufactured and/or distributed in accordance with the present disclosure, as is known to those of skill in the art.

In the exemplary embodiment, the system 100 further comprises at least one image capture device 130 which may be operationally associated with the processor(s) 110. In various embodiments, the system 100 may comprise a plurality of image capture devices 130. The image capture device(s) 130 may be connected to the processor(s) 110 wirelessly via a transmission means 140, or via wired connection not presented. The image capture device(s) 130 may be mounted on a hive(s), in the proximity of the hive(s) or at another desired distance from the hive(s). In the exemplary embodiment the processor(s) 110 may be configured to associate determined data with the hive(s) in a captured image. In some embodiments, the image capture device(s) 130 comprises a spectral camera.

The processor(s) 110 may also be operationally associated with the transmission means 140 to communicate with external hardware. In the exemplary embodiment the transmission means 140 is a wireless transmission means such as a radio transceiver, but is not limited to a radio transceiver. The transmission means 140 may facilitate communication between the processor(s) 110 and one or both of: a remotely located server(s) 150, and a user device 160. The user device 160 may comprise a smartphone, a tablet, a personal computer or the like.

Referring now to the FIG. 2 there is illustrated an exemplary method 200 for monitoring pollination activity. In a first step, an image is captured 210 by the image capture device 130. An image may comprise a single frame or plural frames.

In a second step, the captured image is analysed 220. As discussed above, the processor(s) 110 may be configured to execute software module(s) comprising image analysis means. In a third step, the processor(s) 110 executing the image analysis means may detect 230 if the captured image contains at least one pollinator and at least one pollen element. In a fourth step, the processor(s) 110 may determine 240 a characteristic associated with the at least one pollen element.

In the exemplary embodiment, the characteristic associated with the at least one pollen element is a colour or a wavelength. In another embodiment, the characteristic associated with the at least one pollen element may be a dimension. In the exemplary embodiment, detecting if the captured image contains the at least one pollen element comprises detecting if the captured image contains a pollen basket containing the at least one pollen element. In another embodiment, detecting if the captured image contains the at least one pollen element comprises detecting if the captured image contains a scopa containing the at least one pollen element.

When a pollinator is detected but no pollen element is detected, the processor(s) 110 may make record of this and, for example, a count may be taken of such incidents. In some embodiments, the method may further comprise determining that a pollen basket is empty.

In embodiments where a pollen basket is detected as being empty the processor(s) 110 may make record of this and, for example, a count may be taken of such incidents. Data such as this may be written to local memory 120 which may be volatile or non-volatile in various embodiments as discussed above. Alternatively, if a pollinator is detected but no pollen basket/pollen element is detected, this may simply be overlooked (i.e. no record taken). Further alternatively, if a pollinator with a pollen basket is detected but the pollen basket is empty, this may simply be overlooked. Image analysis means such as but not limited to those described above may be implemented to determine whether a pollen basket is empty or not. For example, a colour or a wavelength of the pollen basket itself may be compared with a known colour, a known wavelength, or a known range of wavelengths of a pollinator’s pollen basket.

In various embodiments the characteristic associated with the at least one pollen element may comprise one or more of a colour, a wavelength, and a dimension of the pollen element. For example, the dimension of the pollen element may be a diameter, a cross-sectional area or a volume of the pollen element. This may be useful in determining the quantity of pollen a pollinator is carrying. In one embodiment a total quantity of pollen transported by pollinators may be determined by adding up the individually determined amounts from the captured image(s). This may also be useful in determining if a pollen basket is full or partially full and, as such, may indicate whether a pollinator has been harvesting pollen. Embodiments comprising characteristic comparison steps are best presented in FIGs. 3-8.

Referring now to FIG. 3, there is provided a method 300 substantially similar to that of FIG. 2, but comprising the additional step of comparing 320 the determined characteristic associated with the at least one pollen element to one or more predefined characteristics to determine the source of the at least one pollen element. In the exemplary embodiment the predefined characteristic(s) may comprise one or both of a colour and a dimension. As discussed above, the colour of pollen can vary between types of plants It may therefore be advantageous to compare 320 the colour or wavelength of the pollen which a pollinator is carrying, such as in a pollinator’s pollen basket, to a predefined colour, predefined wavelength, or predefined range of wavelengths - this may indicate the source of the pollen. For example, this may indicate what type of plant a pollinator has been foraging from, or the geographical location from whence the pollen was foraged. Advantageously, this may also indicate whether or not a pollinator has been foraging on a grower’s land. For example, the colour or wavelength of the pollen in a pollen basket may substantially match a predefined colour or predefined wavelength, or fall within a predefined range of wavelengths, associated with a particular type of plant which the grower is cultivating. In such a case, one could derive from this that a bee is likely foraging from the desired pollen sources on the grower’s land and therefore that the bee is contributing to pollination activity as desired. Making such a determination collectively for a colony may be useful in evaluating pollination optimisation; such embodiments are best presented in relation to FIGs. 4-8.

FIG. 4 provides an exemplary method 400 substantially similar to the method 300 of FIG.

3, but further comprising determining 410 a number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic. For example, and as presented in FIG. 5, it may be desirable to determine 510 the colour(s) or wavelength of pollen in the pollen basket(s) of pollinator(s) in the captured image, compare 520 the determined colour(s) or wavelength(s) of the pollen in the pollen basket(s) to one or more predefined colours or wavelengths to determine the source of the pollen element, and then determine 530 a number of pollinators having a pollen element in the captured image with pollen of a colour or wavelength which substantially corresponds to a predefined colour, wavelength, or which falls within a range of wavelengths. It will be understood that in certain embodiments when the determined wavelength is compared with more than one predefined wavelength, the determined wavelength may be compared with a range of wavelengths. That is, whether the determined wavelength of pollen falls between a first predefined wavelength and a second predefined wavelength. What is more, the process of comparison may be repeated iteratively as desired. This would facilitate calculation of a percentage of pollinators foraging from a particular type of plant, and therefore possibly a percentage of pollinators foraging from a grower’s land. As elucidated above, such determinations are crucial in evaluating pollination optimisation. If the percentage of pollinators with a target pollen colour or target wavelength is less than a predefined threshold, this would indicate that the pollinators are not working as they should and grower intervention may be required. For example, intervention may comprise one or more of: replacing a colony or colonies, adding a further colony or colonies, identifying the existence of competing foragers, or simply removing pollinators if the flowering season has ended. If the percentage of pollinators (e.g.) with pollen baskets containing a target pollen colour or target wavelength is greater than a predefined threshold, this would indicate to the grower that the pollinators are working well. A target wavelength may comprise a single pollen wavelength, or any pollen wavelength falling within a predefined range of wavelengths. When the target wavelength comprises a single pollen wavelength, the comparison to a predefined wavelength may be made to within a predefined margin, i.e. plus or minus an amount. These data may be utilised in generation of a report evaluating contract adherence and the like, which is discussed in greater detail in relation to FIG. 6

Determining a colour, wavelength, and/or a dimension of the contents of a pollen basket may also indicate that the pollen basket is, in fact, empty. That is, the pollinator has not collected any pollen. If the percentage of pollinators returning with pollen is lower than a predefined threshold, this may be indicative of several potential problems which the grower may need to investigate. Examples of such problems include parasitism at or in the vicinity of the grower’s land or biocide poisoning caused by pesticides or the like. In either case, intervention would be required to close the hives to treat or move the pollinators respectively. Growers may find great utility in having this information at hand to act rapidly to limit the extent of damage and to monitor accurate pollination statistics. As noted above, the determined data may also be utilised in generation of a report; embodiments discussing report generation are best presented below in relation to FIGs. 6-8. Such a report may be presented appropriately to a user at user device 160; such embodiments are best presented below in relation to FIGs. 7 and 8.

Since an image can mean a frame or plural frames, a number/percentage of pollen baskets and/or pollinators may be computed based on the count from a single frame or a combined count from plural frames. The plural frames may have been captured immediately subsequently (i.e. approaching a moving image, a video) or they may have been captured with a time delay. In addition or separately, the plural frames may have been captured with a spatial interval - that is, a frame(s) may be captured at a hive A, and a frame(s) may be captured at a hive B located some distance away from hive A such that hive A and hive B are not in the field of view of the same image capture device(s) 130. When captured with a spatial interval, the plural frames may have also been captured with a time delay, or they may have been captured simultaneously, as desired. The utility of this variety of possibilities is that a grower may wish to know statistics for a particular hive, or particular set of hives, or the entirety of the hives on his/her farm/crop. The grower may also desire to know the statistic across some temporal interval of interest. This data may be utilised in report generation, which is discussed in greater detail in relation to FIG. 6.

Referring now to FIG. 6, there is presented an exemplary method substantially similar to that of FIGs. 4 and 5, but additionally comprising the step of generating 610 a report. In various embodiments, the report may be generated 610 based on one or more of: the determined characteristic associated with at least one pollen element; a number of pollen baskets in the captured image; a number of pollinators in the captured image; a number of pollinators having a pollen element with a characteristic which substantially corresponds to a predefined characteristic; meteorological data; audio data; acceleration data; a bloom percentage or a bloom percentage class; a C0₂ level, a temperature or temperature range; or a humidity or a humidity range. The temperature(s) and humidity may be an ambient temperature(s) and an ambient humidity. The bloom percentage class may comprise a range of percentages; for example, a first class may comprise percentage values in the range of 0- 5%, a second class may comprise percentage values in the range of 6-10%, third class may comprise percentage values in the range of 11-15%, and so on. The number of pollinators having a pollen element with a characteristic which substantially corresponds to a predefined characteristic may be a number determined over a period of time T, from subsequent frames and/or frames captured with a temporal/spatial interval, and is not confined to being determined from a singular captured image frame. What is more, data sets may be compared to determine any change in characteristics over time or location. For example, on a first day 85% of pollen in pollen baskets is the same colour, wavelength, or within a specific range of wavelengths; a second day 70% is the same colour, wavelength, or within a specific range of wavelengths; a third day 30% is the same colour, wavelength, or within a specific range of wavelengths and so forth. In this example a farmer might infer from the change that pollinators are moving to other pollen sources without needing to know the main crop colour, wavelength, or specific range of wavelengths in advance.

Accordingly, the processor(s) 110 which execute image analysis may be configured to determine: a characteristic associated with at least one pollen element, a number of pollen baskets in the captured image, and a number of pollinators in the captured image. Meteorological data and bloom percentage and bloom percentage class may be retrieved from remote data sources, whilst C02 level, temperature or humidity may be measured locally using various sensors (not presented). Any of the foregoing data may be written to local memory 120 or transmitted by transmission means 140 to the remotely located server(s) 150 for temporary or prolonged storage.

In various embodiments, machine learning models such as deep learning models implementing neural networks may be implemented in report generation 610. Accordingly, the remotely located server(s) 150 and/or the processor(s) 110 may be suitably configured to execute machine learning models. Generally, report generation may comprise compiling and packaging said determined data for later inspection. Report generation may comprise processing data in a diagnostic sense - that is, processing determined data and determining a course of action to be taken by a computer programme or by a human user in view of said determined data.

In some embodiments the remotely located server(s) 150 may be configured to generate 610 a report. For example, the transmission means 140 may transmit the raw determined data to the remotely located server(s) 150 and a report may be generated 610 at the remotely located server(s) 150. In the same or alternative embodiments the processor(s) 110 may be configured to generate 610 a report. Referring to FIG. 7, once the report has been generated 610, a signal containing the raw determined data may be directed 710 to the user device 160. In some embodiments, the report is generated at the remotely located server(s) 150 and the signal is directed to the user device 160 in response to the report being generated. In some embodiments, the report is generated at the processor(s) 110 and the signal is directed to the user device 160 in response to the report being generated.

Generally, the signal from the transmission means 140 or the signal from the remotely located server(s) 150 may comprise data. These data may comprise one or more pieces of raw determined data as described above, or the data may comprise a report compiled by the processor(s) 110 locally or by processor(s) at the remotely located server 150. Accordingly, the user device 160 may be configured for displaying raw determined data, or presenting data in some other manner such as graphically or in another simplified manner, as desired. Various means of displaying raw determined data in a user-friendly way exist in the art and it is not the intention of the present disclosure to discuss these in any great detail. The user device 160 may also be configured provide a notification to a user with, for example, instructions on a course of action to take in response to the outcome of the report generated. Accordingly, the processor(s) 110 of the system 100 or the processor(s) of the remotely located server 150 may be configured to, in response to the outcome of the report generated, transmit a signal containing the instructions for the course of action to be displayed at the user end.

The foregoing data described as being desirable for report generation is not to be construed as limiting in nature. By way of example only, other data such as pollinator vectors and an average flow of pollinators in the vicinity of a hive may be determined. In various embodiments a report may be generated based at least in part on these.

Referring to FIG. 8, there is provided an exemplary method substantially similar to the method 700 of FIG. 7, albeit further comprising the step of providing 810 a notification at the user device 160 in response to the report generated. Accordingly, the user device 160 may be configured to provide a notification in a variety of ways: audio, visual or a combination of the two. In some embodiments, a notification at the user device 160 may comprise raw determined data displayed in lists, tables or the like. In some embodiments, a notification at the user device 160 may comprise graphical representations of raw determined data such as in the form of line charts, bar charts, pie charts, area-proportional diagrams and the like. In some embodiments, a notification at the user device 160 may comprise simple audio and/or visual notifications such as an audio and/or visual alert detailing whether or not intervention is required. In some embodiments, a notification at the user device 160 may comprise a cartographic display geographically associating determined data with hives on a grower’s land. In some embodiments, a notification at the user device 160 may comprise a cartographic display detailing the location of hives requiring intervention on the grower’s land. In some embodiments, a notification at the user device 160 may comprise a cartographic display detailing where pollinators have been foraging.

It will be understood from the above disclosure that the exemplary system and methods provide numerous advantages to growers utilising pollinators on their crops. In one regard, the exemplary system 100 and methods it may implement allow one to measure the amount of required pollination taking place, and to identify when hives are no longer providing the required pollination. Moreover, existing methods for identifying whether pollinators are foraging on a grower’s crops are manual and as such are prone to human observational error. Manual methods are also more cost intensive and demanding on resources. Accordingly, the invention of the present disclosure may facilitate material cost savings, production/yield improvement, more precise determination of the number of hives required, and more precise determination of crop yield and commercial value.

The invention is not limited to the embodiment(s) described herein but can be amended or modified without departing from the scope of the present invention.

It will be understood that while exemplary features of an apparatus for monitoring pollination activity have been described that such an arrangement is not to be construed as limiting the invention to such features. The exemplary methods for monitoring pollination activity may be implemented in software, firmware, hardware, or a combination thereof. In one mode, the methods are implemented in software, as an executable program, and is executed by one or more special or general purpose digital computer(s), such as a personal computer (PC; IBM®-compatible, Apple®-compatible, or otherwise), personal digital assistant, workstation, minicomputer, or mainframe computer. The steps of the methods may be implemented by a server or computer in which the software modules reside or partially reside.

Generally, in terms of hardware architecture, such a computer will include, as will be well understood by the person skilled in the art, a processor, memory, and one or more input and/or output (I/O) devices (or peripherals) that are communicatively coupled via a local interface. The local interface can be, for example, but not limited to, one or more buses or other wired or wireless connections, as is known in the art. The local interface may have additional elements, such as controllers, buffers (caches), drivers, repeaters, and receivers, to enable communications. Further, the local interface may include address, control, and/or data connections to enable appropriate communications among the other computer components.

The processor(s) may be programmed to perform the functions of the methods for monitoring pollination activity. The processor(s) is a hardware device for executing software, particularly software stored in memory. Processor(s) can be any custom made or commercially available processor, a primary processing unit (CPU), an auxiliary processor among several processors associated with a computer, a semiconductor based microprocessor (in the form of a microchip or chip set), a macro-processor, or generally any device for executing software instructions.

Memory is associated with processor(s) and can include any one or a combination of volatile memory elements (e.g., random access memory (RAM, such as DRAM, SRAM, SDRAM, etc.)) and non-volatile memory elements (e.g., ROM, hard drive, tape, CDROM, etc.). Moreover, memory may incorporate electronic, magnetic, optical, and/or other types of storage media. Memory can have a distributed architecture where various components are situated remote from one another, but are still accessed by processor(s).

The software in memory may include one or more separate programs. The separate programs comprise ordered listings of executable instructions for implementing logical functions in order to implement the functions of the modules. In the examples of heretofore described, the software in memory includes the one or more components of the methods and is executable on a suitable operating system (O/S).

The present disclosure may include components provided as a source program, executable program (object code), script, or any other entity comprising a set of instructions to be performed. When a source program, the program needs to be translated via a compiler, assembler, interpreter, or the like, which may or may not be included within the memory, so as to operate properly in connection with the O/S. Furthermore, a method implemented according to the teaching may be expressed as (a) an object oriented programming language, which has classes of data and methods, or (b) a procedural programming language, which has routines, subroutines, and/or functions, for example but not limited to, C, C++, Pascal, Basic, Fortran, Cobol, Perl, Java, and Ada.

When the methods are implemented in software, it should be noted that such software can be stored on any computer readable medium for use by or in connection with any computer related system or methods. In the context of this teaching, a computer readable medium is an electronic, magnetic, optical, or other physical device or means that can contain or store a computer program for use by or in connection with a computer related system or methods. Such an arrangement can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer- based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In the context of this disclosure, a "computer-readable medium" can be any means that can store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer readable medium can be for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. Any process descriptions or blocks in the Figures, should be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, as would be understood by those having ordinary skill in the art.

The above detailed description of embodiments of the disclosure is not intended to be exhaustive nor to limit the disclosure to the exact form disclosed. While specific examples for the disclosure are described above for illustrative purposes, those skilled in the relevant art will recognize various modifications are possible within the scope of the disclosure. For example, while processes and blocks have been demonstrated in a particular order, different implementations may perform routines or employ systems having blocks, in an alternate order, and some processes or blocks may be deleted, supplemented, added, moved, separated, combined, and/or modified to provide different combinations or sub combinations. Each of these processes or blocks may be implemented in a variety of alternate ways. Also, while processes or blocks are at times shown as being performed in sequence, these processes or blocks may instead be performed or implemented in parallel or may be performed at different times. The results of processes or blocks may be also held in a non-persistent store as a method of increasing throughput and reducing processing requirements.

Claims

1. A method of monitoring pollination activity, comprising: capturing an image; analysing the captured image; detecting if the captured image contains at least one pollinator and at least one pollen element; determining a characteristic associated with the at least one pollen element; and comparing the characteristic associated with the at least one pollen element to one or more predefined characteristics to determine the source of the at least one pollen element.

2. The method of claim 1, wherein detecting if the captured image contains the at least one pollen element comprises detecting if the captured image contains a pollen basket containing the at least one pollen element.

3. The method of claim 1, wherein detecting if the captured image contains the at least one pollen element comprises detecting if the captured image contains a scopa having disposed thereon the at least one pollen element.

4. The method of claims 1-3, wherein the characteristic associated with the at least one pollen element comprises a colour or a wavelength.

5. The method of claim 1, wherein the characteristic associated with the at least one pollen element comprises a dimension.

6. The method of claim 4, wherein the predefined characteristic comprises: one or more predefined colours; or one or more wavelengths.

7. The method of claim 6, wherein comparing the wavelength associated with the at least one pollen element to a first predefined wavelength and a second predefined wavelength comprises determining whether the wavelength falls between the two predefined wavelengths.

8. The method of claim 5, wherein the predefined characteristic comprises a predefined dimension.

9. The method of claims 1-8, wherein the source of the at least one pollen element comprises a type of plant.

10. The method of claims 1-9, wherein the source of the at least one pollen element comprises a geographical location from whence the at least one pollen element was foraged.

11. The method of claims 1-10, further comprising providing a user with information relating to a determined source of pollen.

12. The method of claims 1-11, further comprising determining a number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic.

13. The method of claim 12, wherein when the number of pollinators having a pollen element with a characteristic which substantially corresponds to a predefined characteristic is less than, equal to or greater than a predefined threshold value, providing a notification to a user.

14. The method of claim 12 or claim 13, further comprising storing in memory the determined data relating to one or more of: vi) the determined characteristic associated with the at least one pollen element; vii) a number of pollen baskets in the captured image; viii) a number of pollinators in the captured image; ix) a number of pollen elements in the captured image; or x) the number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic.

15. The method of claims 12-14, wherein the image is captured in the vicinity of a hive.

16. The method of claims 12-15, further comprising associating determined data with a hive in the captured image.

17. The method of claims 12-16, further comprising transmitting determined data to one or more of a remotely located server or a user device.

18. The method of claims 12-17, further comprising generating a report based at least in part on one or more of: xiv) the determined characteristic associated with the at least one pollen element; xv) the number of pollen baskets in the captured image; xvi) the number of pollinators in the captured image; xvii) the number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic; xviii) meteorological data; xix) ambient pressure data; xx) audio data; xxi) CO2 data; xxii) temperature data; xxiii) humidity data; xxiv) acceleration data; xxv) a bloom percentage; or xxvi) a bloom percentage class.

19. The method of claim 18, further comprising providing a notification at the user device in response to the report generated.

20. A system for monitoring pollination activity, comprising: an image capture device for capturing an image; and at least one processor configured for analysing the captured image, wherein the image analysis means is configured for detecting if the captured image contains a pollinator and a pollen element, wherein the at least one processor is configured for determining a characteristic associated with the pollen element, wherein the at least one processor is configured to compare the characteristic associated with the pollen element to one or more predefined characteristics to determine the source of the pollen element.

21. The system of claim 20, wherein the at least one processor is configured to implement a machine learning algorithm.

22. The system of claim 20 or claim 21, wherein the at least one processor is configured for determining one or both of a number of pollen baskets in the captured image and a number of pollinators in the captured image.

23. The system of claim 22, wherein the at least one processor is configured for determining a number of pollinators in the captured image having a pollen element with a characteristic that substantially corresponds to a predefined characteristic.

24. The system of claim 23, further comprising at least one memory unit for storing the determined data relating to one or more of: v) the determined parameter associated with the pollen element; vi) the number of pollen baskets in the captured image; vii) the number of pollinators in the captured image; or viii) the number of pollinators in the captured image containing a pollen element with a characteristic which substantially corresponds to a predefined characteristic.

25. The system of claims 20-24, wherein the characteristic associated with the pollen element comprises one or more of a colour, a wavelength or a dimension.

26. The system of claim 25, wherein the predefined characteristic comprises one or more predefined colours, one or more predefined wavelengths, and/or one or more predefined dimensions,

27. The system of claim 26, wherein the at least one processor is configured to compare the determined wavelength to a first predefined wavelength and a second predefined wavelength and compute whether the determined wavelength falls between the two.

28. The system of claims 20-27, wherein the image is captured in the vicinity of a hive, and wherein the at least one processor is configured for associating determined data with a hive in the captured image.

29. The system of claims 20-28, wherein the at least one processor is configured for generating a report based at least in part on one or more of: xiv) the determined characteristic associated with the pollen element; xv) the number of pollen baskets in the captured image; xvi) the number of pollinators in the captured image; xvii) the number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic; xviii) meteorological data; xix) ambient pressure data; xx) audio data; xxi) CO2 data; xxii) temperature data; xxiii) humidity data; xxiv) acceleration data; xxv) a bloom percentage; or xxvi) a bloom percentage class.

30. The system of claims 20-29, further comprising a transmission means for transmitting determined data to one or more of: a remotely located server, or a user device.

31. The system of claims 30, wherein the remotely located server is configured for generating a report based at least in part on one or more of: xiv) the determined characteristic associated with the pollen element; xv) the number of pollen baskets in the captured image; xvi) the number of pollinators in the captured image; xvii) the number of pollinators in the captured image having a pollen element with a characteristic which substantially corresponds to a predefined characteristic; xviii) meteorological data; xix) ambient pressure data; xx) audio data; xxi) CO₂ data; xxii) temperature data; xxiii) humidity data; xxiv) acceleration data; xxv) a bloom percentage; or xxvi) a bloom percentage class.