Apparatus for identifying and catching insects

Abstract

An apparatus for identifying one or more species of insect comprising: a stage for insects to land, wherein an attractant for attracting the one or more species of insect is provided at or near the stage; a camera device, wherein the stage is positionable within the view of the camera device; processing means adapted to receive images from the camera device and detect the presence of the one or more species of insect; and alerting means which is communicatively connected to the processing means and adapted to send an alert to a remote location when the processing means detects the presence of the one or more species of insect.

Description

[0001] APPARATUS FOR IDENTIFYING AND CATCHING INSECTS

[0002] The present invention relates to apparatus and methods for identifying and / or catching insects. In particular, but not exclusively, the present invention relates to apparatus and methods for identifying and / or catching predating insects such as hornets.

[0003] The Asian hornet is indigenous to Southeast Asia but is an invasive species in some other countries, particularly European countries including the UK. As of September 2022, 140 hornet nests have already been found on the British island of Jersey alone. Asian hornets heavily predate honeybees and other insects. It is estimated that honeybees provide a pollination service worth over€600m per year.

[0004] When Asian hornets find a European honeybee colony, they tend to specialize in honeybees as their prey. In its native range, the eastern honeybee has evolved coping strategies; however, the western honeybee has not and they are easier prey. Typically, Asian hornets are carried from Asia to Europe via shipping routes. Conventionally, authorities such as the Department for Environment Food and Rural Affairs (DEFRA) have relied on public sightings to locate and destroy Asian hornet nests.

[0005] Relying on untrained public sightings and reports is not enough and it is desirable to provide improved means of identifying Asian hornets such that their nests can be located and destroyed.

[0006] According to an aspect of the present invention there is provided an apparatus for identifying one or more species of insect comprising: a stage for insects to land, wherein an attractant for attracting the one or more species of insect is provided at or near the stage; a camera device, wherein the stage is positionable within the view of the camera device; and processing means adapted to receive images from the camera device and detect the presence of the one or more species of insect.

[0007] According to a further aspect of the present invention there is provided an apparatus for identifying one or more species of insect comprising: a stage for insects to land, wherein an attractant for attracting the one or more species of insect is provided at or near the stage; a camera device, wherein the stage is positionable within the view of the camera device; processing means adapted to receive images from the camera device and detect the presence of the one or more species of insect; and alerting means which is communicatively connected to the processing means and adapted to send an alert to a remote location when the processing means detects the presence of the one or more species of insect.

[0008] Aspects and embodiments of the present invention may be useful for combatting invasion by non-native predatory insects, such as invasive Vespid species such as Asian Hornets.

[0009] In order to slow the spread of Asian hornets, for example, nests need to be quickly identified and before each October, when the nest can produce up to 500 queens.

[0010] Some aspects and embodiments may provide or relate to a hornet detection system, such as an artificial intelligence hornet detection system. The system may be configured as an automated system.

[0011] The apparatus may be adapted to attract and / or detect insects in the genus Vespa, such as yellowjackets, wasps or hornets, for example the Asian hornet (Vespa velutina), Asian giant hornet (Vespa mandarinia), Oriental hornet (Vespa orientalis) or Black Shield Hornet (Vespa bicolor).

[0012] Some embodiments may be capable of detecting multiple invasive Vespid species.

[0013] Optionally, the apparatus includes a container for housing one or more of the camera device, processing means and alerting means. Optionally, the apparatus includes support means for supporting the container at a height above the stage. Optionally, the support means comprises a support pole or fixing means for fixing the container to an existing pole, building or the like. Alternatively, the support means may comprise a stand such as a tripod.

[0014] Optionally, the container includes an aperture and / or a transparent screen so that the camera device can view an exterior of the container. Optionally, the camera device is positionable or positioned in a lower region of the container and is orientable or oriented such that the camera device can view below the container.

[0015] Optionally, the apparatus includes a reservoir of attractant. Optionally, a conduit such as a drip tube is fluidly connected to the reservoir such that a small volume of attractant continually or intermittently falls from the conduit and onto the stage. The attractant may be configured to attract insects in the genus Vespa, such as yellowjackets, wasps or hornets, for example the Asian hornet (Vespa velutina) or Asian giant hornet (Vespa mandarinia).

[0016] Optionally, the stage is dish or bowl shaped for holding the attractant. Optionally, the apparatus includes a misting device which is fluidly connected to the reservoir and adapted to emit a mist of attractant. Optionally, the apparatus includes a timer device which is communicatively connected to the misting device such that the misting device emits a mist of attractant at regular intervals.

[0017] Optionally, the apparatus includes a level sensor for monitoring the level of the reservoir of attractant. Optionally, the level sensor is communicatively connected to the alerting means such that an alert is sent to a remote location when the level is low.

[0018] Optionally, the apparatus includes a roof for preventing rain water accessing the stage. The roof may be supportable by the support means or the container.

[0019] Optionally, the alerting means comprises a transmitter.

[0020] Optionally, the camera device is adapted to record the image in view. Alternatively or in addition, the camera device is adapted to capture an image.

[0021] Optionally, the processing means is adapted to detect when the one or more species of insect enters the view of the camera device and to start recording or capture an image using the camera device.

[0022] Optionally, the alert sent to the remote location comprises one or more images captured or recorded by the camera device.

[0023] Optionally, a machine learning algorithm is used to train the processing means to identify the one or more species of insect within the view of the camera device or captured images.

[0024] Optionally, the remote location for sending the alert is DEFRA.

[0025] Optionally, the apparatus includes a catching device for catching an identified species of insect. Optionally, the apparatus includes a releasing device for releasing the catching device. Optionally, the releasing device is communicatively connected to the processing means such that the catching device is released when the one or more species of insect is identified. Optionally, the catching device comprises a net. Alternatively, the catching device comprises a trap provided at or by the stage.

[0026] Optionally, the apparatus is adapted to use Power over Ethernet (PoE).

[0027] According to a further aspect of the present invention there is provided a method of identifying one or more species of insect comprising: providing a stage for insects to land, and providing an attractant for attracting the one or more species of insect at or near the stage; positioning a camera device such that the stage is within the view of the camera device; using processing means to receive images from the camera device and detect the presence of the one or more species of insect.

[0028] In some embodiments one or more reference images of insects of interest are provided and used to help determine if an insect of interest is at a bait station.

[0029] According to a further aspect of the present invention there is provided a method of identifying one or more species of insect comprising: providing a bait station including a platform for insects to land, and providing an attractant for attracting the one or more species of insect at or near the platform; providing means for accessing software such as an application for a smartphone or other mobile communication device; said app including means for identifying insects using a mobile communication device.

[0030] The means for accessing software may, for example, .comprise a QR code or a website address.

[0031] According to a further aspect of the present invention there is provided a method of identifying one or more species of insect comprising: providing a stage for insects to land, and providing an attractant for attracting the one or more species of insect at or near the stage; positioning a camera device such that the stage is within the view of the camera device; using processing means to receive images from the camera device and detect the presence of the one or more species of insect; and sending an alert to a remote location when the processing means detects the presence of the one or more species of insect.

[0032] Optionally, the method includes housing one or more of the camera device, processing means and alerting means within a container. Optionally, the method includes supporting the container at a height above the stage. Optionally, the camera device is positionable or positioned in a lower region of the container and is orientable or oriented such that the camera device can view below the container.

[0033] Optionally, the method includes providing a reservoir of attractant. Optionally, the method includes using a conduit such as a drip tube which is fluidly connected to the reservoir to deliver a small volume of attractant continually or intermittently from the conduit and onto the stage. Optionally, the method includes providing a misting device which is fluidly connected to the reservoir and adapted to emit a mist of attractant. Optionally, the method includes providing a timer device which is communicatively connected to the misting device such that the misting device emits a mist of attractant at regular intervals.

[0034] Optionally, the method includes monitoring the level of the reservoir of attractant.

[0035] Optionally, the method includes providing a roof for preventing rain water accessing the stage. The roof may be supportable by the support means or the container.

[0036] Optionally, the method includes recording the image in view. Alternatively, the method includes capturing an image.

[0037] Optionally, the method includes using the processing means to detect when the one or more species of insect enters the view of the camera device and to start recording or capture an image using the camera device.

[0038] Optionally, the method includes using a machine learning algorithm to train the processor to identify the one or more species of insect within the view of the camera device or captured images.

[0039] Optionally, the method includes sending the alert to DEFRA.

[0040] A further aspect provides a system to attract and detect the presence of Asian hornets without bycatch.

[0041] The system may comprise means for automatically informing authorities.

[0042] The system may comprise an artificial intelligence camera.

[0043] The system may be formed as a trap.

[0044] There may be pole- and wall-mounted versions.

[0045] Some embodiments may provide or relate to a hornet detection and / or alert system.

[0046] Computer vision models installed on an edge camera may be as follows:

[0047] 1) Object-detection model trained on large video datasets of Asian hornets and other commonly mistaken species of insect and;

[0048] 2) Object-tracking model to record return times of individual marked Asian hornets and the bearings of entry and exit onto the bait station. Event data can be stored in an event register (e.g. in the cloud) and the following statistical analyses may be conducted:

[0049] 1 . Interquartile Range (IQR) to remove outliers

[0050] 2. Linear regression for line of best fit

[0051] 3. Analysis of variance (ANO A)

[0052] Analyses may then be sent to a visualisation map dashboard to help the ground team to greatly reduce the time taken to find, locate and destroy the nest. This process currently undertaken manually takes on average 50 hours.

[0053] Some aspects and embodiments are concerned with recognising an insect of interest. Other aspects and embodiments are concerned with recognising an insect of interest and generating an alert. Some aspects and embodiments are concerned with verification of an insect sighting. Other aspects and embodiments are concerned with nest location. Combinations of these functionalities may be provided together or separately.

[0054] Aspects and embodiments of the present invention may comprise one or more of the following features:

[0055] Mains, solar & battery powered

[0056] GPS tagger for anti-theft

[0057] GPS tagger for known location for the dashboard.

[0058] Lorawan alerts

[0059] Event system for detected individuals

[0060] Statistical rending of detection events - removing outliers for interquartile range calculation and linear regression line of best fit.

[0061] Humification I vapour of attractant

[0062] Attractant tank reservoir level sensor - alert

[0063] Bait station rain guard / shade

[0064] Ground Anchor points for pegs on the tripod legs

[0065] External gravity feed attractant reservoirs

[0066] Colour coding of the sides to aid insect recognition

[0067] 360 degrees of access and egress

[0068] Fan cooled

[0069] 4G and / or 5G mobile network technology

[0070] Some embodiments provide or relate to an automated hornet detection system.

[0071] Systems may include a component of artificial intelligence and / or a component of machine learning. Some embodiments are configured to detect the presence of Asian hornets and predict their nest location.

[0072] In some embodiments insect detection devices comprise two main parts: a bait station; and a camera. The parts may be provided as a single unit, or as separate units. Where separate units are provided they may be mounted together e.g. using a stand (such as a tripod).

[0073] Some aspects and embodiments of the present invention are concerned with nest finding. Efficient nest discovery and destruction will reduce the impact of invasive species on pollinators and fruit production.

[0074] Return times of marked insects (e.g. hornets) may, for example, be used to calculate / predict the distance between a nest and a bait station and / or calculate a predicted radius.

[0075] The trajectory / heading / bearing of insects during take-off and / or landing may be used to predict the direction in which a nest may be located.

[0076] Where multiple devices are involved, the information they provide may be used for triangulation and / or overlapping radii may be taken into account.

[0077] A mesh network may be used to aid nest discovery, for example.

[0078] Devices may be sited at fruit farms or honey farms, for example.

[0079] Some embodiments may be capable of vaporising attractant to improve efficiency of attracting insects to the bait station.

[0080] Some embodiments may be provided with a humidifier.

[0081] Embodiments may be supplied with or without a camera.

[0082] The solution of some embodiments provides 3500+ daylight hours of automated surveillance per annum.

[0083] A further aspect of the present invention provides a method of locating or assisting in locating an insect nest comprising the steps of: providing a bait station comprising attractant for attracting insects of interest; determining the bearing of insects entering or leaving the bait station. The bearing of insects may, for example, be used to narrow down the slice of the radius around the bait station for more accurate nest location.

[0084] A further aspect of the present invention provides a method of locating or assisting in locating an insect nest comprising the steps of: providing a bait station comprising attractant for attracting insects of interest; monitoring the return time of individual insects.

[0085] Data from method / systems of the present invention can be used, for example to calculate / predict nest direction and / or nest distance.

[0086] Methods may further comprise the step of identifying insects at the bait station.

[0087] Methods may further comprise the step of marking individual insects.

[0088] Some embodiments use hornets as a tracker.

[0089] Some embodiments may track the return times of marked individual hornets.

[0090] Some methods may provide or facilitate estimated radius of nest distance based on return flight times of marked individuals.

[0091] Some embodiments provide or facilitate the provision of information relating to numbers of visits and / or an estimation of nest locations. Information may be provided on a map dashboard management system, for example.

[0092] Multiple bait stations may be used to provide a mesh coverage for triangulation of nest locations.

[0093] Some embodiments may include the option of live / dead capture of insects.

[0094] Some embodiments may include the option of live / dead capture of foundress queens.

[0095] Some embodiments may include the option of counting of trapped hornets.

[0096] Some embodiments combine insect identification and / or alert capability with nest finding capability.

[0097] Faster R-CNN may be used for real-time object detection. Edge deployment may be used in some embodiments.

[0098] The system may be provided with multiple reference images of species of interest.

[0099] Some embodiments also include reference to satellite imagery (e.g. for chlorophyll analysis) to check for the types of trees the hornets may nest in. This can be used to improve nest location prediction.

[0100] Weather data may be incorporated into predictions.

[0101] Botanical (e.g. dendrological) data may be used.

[0102] A further aspect provides a method for predicting insect nest location.

[0103] Different aspects and embodiments may be used separately or together.

[0104] The present invention will now be more particularly described, by way of example only, with reference to the accompanying drawings, in which:

[0105] Figure 1 shows an insect of concern, in this case being a hornet;

[0106] Figure 2 shows a hornet nest;

[0107] Figure 3 is a cross sectional side view of an apparatus in accordance with the present invention;

[0108] Figure 4 is a schematic representation of how apparatus and a system may function;

[0109] This embodiment provides an Asian hornet identification system which uses computer vision to distinguish between local pollinators and Asian hornets. A device is provided that contains a reservoir of hornet attractant. After an Asian hornet lands on the attractant, an artificial intelligence camera (or a camera that can provide images for analysis by image recognition software, locally or remotely) located above the attractant observes it, and the computer vision model uses object detection to determine whether it is an Asian hornet or not (for example by comparing images with library images). A determination can then be made.

[0110] In this embodiment images used to train the camera have been certified to research grade.

[0111] Figure 5 illustrates species recognition functionality;

[0112] Figure 6 illustrates individual marking of insects; Figure 7 illustrates object tracking functionality;

[0113] Figure 8 illustrates nest location functionality;

[0114] Figure 9 shows an insect detection device formed in accordance with the present invention;

[0115] Figures 10 and 11 show a tracking device formed according to a further embodiment;

[0116] Figure 12 illustrates a mesh network;

[0117] Figures 13 and 14 show a bate station formed according to a further embodiment;

[0118] Figure 15 shows the bate station of Figures 13 and 14 together with an overhead camera system mounted on a stand;

[0119] Figures 16A to 16F illustrate an example of how the companion application may function;

[0120] Figure 17 illustrates an example triangulation strategy;

[0121] Figure 18 illustrates an example system architecture formed in accordance with the principles of the present invention; and

[0122] Figure 19 is a windrose chart.

[0123] Example embodiments are described below in sufficient detail to enable those of ordinary skill in the art to embody and implement the systems and processes herein described. It is important to understand that embodiments can be provided in many alternate forms and should not be construed as limited to the examples set forth herein.

[0124] Accordingly, while embodiments can be modified in various ways and take on various alternative forms, specific embodiments thereof are shown in the drawings and described in detail below as examples. There is no intent to limit to the particular forms disclosed. On the contrary, all modifications, equivalents, and alternatives falling within the scope of the appended claims should be included. Elements of the example embodiments are consistently denoted by the same reference numerals throughout the drawings and detailed description where appropriate.

[0125] The terminology used herein to describe embodiments is not intended to limit the scope. The articles “a,” “an,” and “the” are singular in that they have a single referent, however the use of the singular form in the present document should not preclude the presence of more than one referent. In other words, elements referred to in the singular can number one or more, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes,” and / or “including,” when used herein, specify the presence of stated features, items, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, items, steps, operations, elements, components, and / or groups thereof.

[0126] Unless otherwise defined, all terms (including technical and scientific terms) used herein are to be interpreted as is customary in the art. It will be further understood that terms in common usage should also be interpreted as is customary in the relevant art and not in an idealized or overly formal sense unless expressly so defined herein.

[0127] Figure 1 shows a hornet 1 and Figure 2 shows a hornet nest 2.

[0128] Referring now to Figure 3, there is shown an apparatus 10 for identifying one or more species of insect. In this embodiment, the insect species is the Asian hornet. The apparatus 10 comprises a raised container or cannister 20 and a stage 30.

[0129] The stage 30 is provided for insects to land. It can simply be a dish or bowl, as long as it can hold a volume of attractant for attracting Asian hornets. A suitable attractant could be a brand such as Trappit™ or Suterra™.

[0130] The cannister 20 is mounted to a tripod 40 so that it is at a height from the ground. Typically, this height is about 30 cm. Mounted to the exterior of the cannister 20 is a roof 42 for preventing rain water accessing the stage 30.

[0131] The base of the cannister 20 includes an aperture and a camera device 24 is provided in a lower region of the cannister 20 viewing downwards through the aperture 22. The stage 30 is positioned directly under the cannister 20 and thus within the view of the camera device 24.

[0132] Processing means 26 such as a microcomputer is also provided within the cannister 20. The processing means 26 is connected to the camera device 24 so that it can receive images from the camera device 24. These are used to detect the presence of an Asian hornet. Also provided is alerting means in the form of a transmitter 28. This is communicatively connected to the processing means 26 and adapted to send an alert to a remote location when the processing means detects the presence of an Asian hornet.

[0133] In an upper region of the cannister 20 is a reservoir 32 of attractant. Typically, the reservoir 32 can hold a volume of around 2 litres. A conduit in the form of a drip tube 34 is fluidly connected to the reservoir 32 so that a small volume of attractant intermittently falls from the drip tube 34 and into the stage 30. This replenishes any attractant lost due to evaporation. Mounted to the top surface of the cannister 20 is a misting device 36 which is fluidly connected to the reservoir. The misting device 36 is adapted to emit a mist of attractant. It is connected to a timer device 38 so that the misting device 36 emits a mist of attractant at regular intervals, such as every 30 minutes.

[0134] A level sensor 40 is provided in a lower region of the reservoir 32 for monitoring the level of the attractant. The level sensor 40 is communicatively connected to the transmitter 28 and an alert is sent to a remote location, such as the operator, when the level is low.

[0135] A machine learning algorithm is used to train the processing means 26 to identify Asian hornets within the view of the camera device 24. The processing means 26 also controls the operation of the camera device 24. When an Asian hornet is detected, the processing means 26 causes the camera device 24 to capture the image in view, thereby capturing an image of the Asian hornet.

[0136] When an Asian hornet is detected, the image is captured and an alert is sent by the transmitter 28 to a remote location such as DEFRA. The alert can include the captured image to allow verification that the insect is an Asian hornet. It will also include information such as the geographical location of the apparatus 10, date and time and so on.

[0137] DEFRA will typically send personnel to the site of the apparatus 10 within a short time of receiving the alert. It is likely that the Asian hornet will return to the site. The personnel can then catch the insect and fit it with a radio transmitter. The Asian hornet will at some point return to the nest, which is likely to be within 1 km of the apparatus 10. The personnel can track the Asian hornet to the nest which can then be destroyed.

[0138] In other embodiments, the apparatus 10 can include a catching device such as a net and a releasing device for releasing the net. The releasing device can be communicatively connected to the processing means so that the net is released when an Asian hornet is identified.

[0139] Figure 4: a system for attracting and detecting the presence of Asian hornets without bycatch to automatically inform authorities, this minimising the reliance on public sightings for their prevention. An artificial intelligence camera trap is provided.

[0140] Figure 5 shows a bait station 150 with a platform / stage 155 having attractant positioned generally centrally (in this embodiment), in this embodiment using a wick 160. Some embodiments attract hornets within a 1 km radius, for example.

[0141] A camera (not shown) takes images of the stage 155 and compares insects on the stage to a library of images of insects. This process is used to identify insects. This information could, for example, be used to generate an alert as described above upon recognition of a species of concern.

[0142] In Figure 6 individual insects have been marked and are shown on a stage 255. A camera system (not shown) identifies the individuals. This individual recognition capability allows, for example, return times of marked insects (e.g. hornets) to calculate / predict the distance between a nest and a bait station and / or calculate a predicted radius.

[0143] In Figure 7 object tracking is used to determine the bearing of insects as they land / leave the bait station. This information may be used in combination with return times to predict nest location, as illustrated in Figure 8.

[0144] Figure 9 shows a tripod-based version of a device - providing 360 degrees access - unhindered ability for insects to approach and take off. The tripod 370 supports a bait station 350 and a camera enclosure 375. The camera enclosure 375 is supported above and in line with the bait station. The bait station provides an attractant (e.g. pheromones) to attract insects of interest. The bait station includes a well for holding a supply of attractant. A light may be provided (not shown) by the camera enclosure.

[0145] This version includes a field-deployable tripod mounted Al camera bait station incorporating vapourised wasp attractant and a wind speed and direction anemometer to attract Asian hornets from a considerable range.

[0146] Figures 10 and 11 show a mountable version, in this case being mounted on a wall. A bait station 450 and a camera enclosure 475 are shown - they are provided as separate units and mountable e.g. on a wall spaced from each other as shown.

[0147] The bait station is white to provide high contrast for the camera system.

[0148] Mesh networks can aid nest discovery. E.g. Figure 12 illustrates a proposed mesh network of fifty devices for Jersey.

[0149] Figures 13 shows a cuboidal bait station 550 formed according to a further embodiment. In this embodiment a humidifier is provided as part of the bait station and this vaporises attractant 552 for enhanced release. In this embodiment an image 554 of an insect of interest (in this example an Asian hornet) is provided on the side of the station to help untrained members of the public with identification.

[0150] Figure 14 shows a bait station 650 formed according to a further embodiment. The station 650 is similar to the station 550 except that there is a conical opening 651 formed on one side. This allows the station to function as a trap, with insects captured inside. A QR code 657 Is provided on the side of the station which allows a passerby to download a companion app (an example of which is discussed further below).

[0151] Figure 15 shows the bait station 550 of Figure 13 together with an overhead camera clamp 570 provided on a stand 575. This allows a smartphone 580 to be mounted over the station. This embodiment therefore does not require a dedicate camera system, but rather provides the means for any smartphone to be used. Untrained people can thereby become involved in identifying insects of interest, with the process of recognition / identification being performed automatically.

[0152] This embodiment can provide the general public with a way to check whether an insect they have spotted is an Asian hornet, rather than a native lookalike insect. Currently, only approximately 0.05% of submitted suspected sightings are subsequently confirmed as Asian hornets.

[0153] A mobile reporting companion app may be provided. A QR code is provided on the side of the bait station, allowing anyone to download the app onto their phone and use the camera on their phone to take images of insects on the bait station.

[0154] This can provide a rapid way for people to report their (verified / validated) sightings including a photo and a location.

[0155] Effective, automated monitors deployed in areas in which insects of interest are suspected could greatly assist in detection and / or nest locating.

[0156] An example of how the companion app may function is illustrated in Figures 16A to 16F.

[0157] An example triangulation strategy is illustrated in Figure 17, tracking hornets (H) to predict the location of a nest (N).

[0158] Figure 18 illustrates an example system architecture formed in accordance with the principles of the present invention.

[0159] A method of mark-release-recapture is used in this embodiment.

[0160] The system employs cutting-edge technology and models to pinpoint individual hornets and their nests with precision.

[0161] Key components include: a Species Detection Model to identify Asian hornets as well as an Individual Tracking Model which monitors return flight times and entry / exit bearings to provide valuable distance and direction information to the nests. Additionally, wind speed and direction is incorporated to monitor vapour dispersal. Real-time data analysis is facilitated through Edge Event Register Data Processing.

[0162] The system can operate autonomously, providing real-time data and alerts to enable a swift and targeted response for ground teams responsible for its management.

[0163] Monitoring the speed and direction of vapour dispersal while object tracking enhances the ability to follow the movements of Asian hornets. The windrose chart in Figure 19 demonstrates windspeed and wind direction as a predictor of nest locations. The windrose can be used for both wind direction and the estimated trajectories and distances - it could use colour coding as well.

[0164] Some embodiments also include reference to satellite imagery (e.g. for chlorophyll analysis) to check for the types of trees the hornets may nest in. This can be used to improve nest location prediction.

[0165] Weather data may be incorporated into predictions.

[0166] Botanical (e.g. dendrological) data may be used.

[0167] Although illustrative embodiments of the invention have been disclosed in detail herein, with reference to the accompanying drawings, it is understood that the invention is not limited to the precise embodiments shown and that various changes and modifications can be effected therein by one skilled in the art without departing from the scope of the invention as defined by the appended claims and their equivalents.

Claims

CLAIMS1 . An apparatus for identifying one or more species of insect comprising: a stage for insects to land, wherein an attractant for attracting the one or more species of insect is provided at or near the stage; a camera device, wherein the stage is positionable within the view of the camera device; processing means adapted to receive images from the camera device and detect the presence of the one or more species of insect; and alerting means which is communicatively connected to the processing means and adapted to send an alert to a remote location when the processing means detects the presence of the one or more species of insect.

2. An apparatus as claimed in Claim 1 , including a container for housing one or more of the camera device, processing means and alerting means.

3. An apparatus as claimed in Claim 2, including support means for supporting the container at a height above the stage.

4. An apparatus as claimed in Claim 2 or 3, wherein the camera device is positionable or positioned in a lower region of the container and is orientable or oriented such that the camera device can view below the container.

5. An apparatus as claimed in any preceding claim, including a reservoir of attractant.

6. An apparatus as claimed in Claim 5, including a conduit fluidly connected to the reservoir such that a small volume of attractant continually or intermittently falls from the conduit and onto the stage.

7. An apparatus as claimed in Claim 5 or 6, including a misting device which is fluidly connected to the reservoir and adapted to emit a mist of attractant.

8. An apparatus as claimed in Claim 7, including a timer device which is communicatively connected to the misting device such that the misting device emits a mist of attractant at regular intervals.

9. An apparatus as claimed in any of Claims 5 to 8, including a level sensor for monitoring the level of the reservoir of attractant.

10. An apparatus as claimed in Claim 9, wherein the level sensor is communicatively connected to the alerting means such that an alert is sent to a remote location when the level is low.

11. An apparatus as claimed in any preceding claim, including a roof for preventing rain water accessing the stage.

12. An apparatus as claimed in Claim 11 , wherein the roof is supportable by the support means or the container.

13. An apparatus as claimed in any preceding claim, wherein the processing means is adapted to detect when the one or more species of insect enters the view of the camera device and to start recording or capture an image using the camera device.

14. An apparatus as claimed in any preceding claim, wherein the alert sent to the remote location comprises one or more images captured or recorded by the camera device.

15. An apparatus as claimed in any preceding claim, wherein a machine learning algorithm is used to train the processing means to identify the one or more species of insect within the view of the camera device or captured images.

16. An apparatus as claimed in any preceding claim, including a catching device for catching an identified species of insect.

17. An apparatus as claimed in Claim 16, including a releasing device for releasing the catching device, wherein the releasing device is communicatively connected to the processing means such that the catching device is released when the one or more species of insect is identified.

18. A method of identifying one or more species of insect comprising: providing a stage for insects to land, and providing an attractant for attracting the one or more species of insect at or near the stage; positioning a camera device such that the stage is within the view of the camera device; using processing means to receive images from the camera device and detect the presence of the one or more species of insect; and sending an alert to a remote location when the processing means detects the presence of the one or more species of insect.

19. A method as claimed in Claim 18, including housing one or more of the camera device, processing means and alerting means within a container.

20. A method as claimed in Claim 10, including supporting the container at a height above the stage, and wherein the camera device is positionable or positioned in a lower region of the container and is orientable or oriented such that the camera device can view below the container.21 . A method as claimed in Claim 20, including providing a reservoir of attractant and a conduit which is fluidly connected to the reservoir to deliver a small volume of attractant continually or intermittently from the conduit and onto the stage.

22. A method as claimed in Claim 21 , including providing a misting device which is fluidly connected to the reservoir and adapted to emit a mist of attractant, and wherein the method includes providing a timer device which is communicatively connected to the misting device such that the misting device emits a mist of attractant at regular intervals.

23. A method as claimed in Claim 21 or 22, including monitoring the level of the reservoir of attractant.

24. A method as claimed in any of Claims 18 to 23, including providing a roof for preventing rain water accessing the stage.

25. A method as claimed in Claim 18, including using a machine learning algorithm to train the processor to identify the one or more species of insect within the view of the camera device or captured images.

26. A method of locating or assisting in locating an insect nest comprising the steps of: providing a bait station comprising attractant for attracting insects of interest; and determining the bearing of insects entering or leaving the bait station.

27. A method of locating or assisting in locating an insect nest comprising the steps of: providing a bait station comprising attractant for attracting insects of interest; and monitoring the return time of individual insects.

Images