Method for counting live larvae of Mealworms or Black Soldier Flies

Abstract

The invention relates to a method for counting live larvae of Mealworms or Black Soldier Flies which comprises at least the following steps: E1 / depositing a mass (M) of larvae and a food substrate (S) onto a support; E2 / distributing said mass (M) in the form of a thin layer (CM); E3 / subjecting the same section (SE) of said thin layer (CM) to at least two light signals of different wavelengths; E4 / using a multispectral optical sensor (5), capturing the images (i1, i2) of said same section (SE) subjected to said light signals; E5 / reconstructing a single image (i3) by interlacing and assembling said images (i1, i2) from step E4 / ; E6 / counting said larvae using a computer program; E7 / If necessary, repeat steps E3 / to E6 / on a new section (SE). Figure for the abbreviation: figure 2

Description

Title of the invention: Method for counting live larvae of mealworms or black soldier flies

[0001] GENERAL TECHNICAL DOMAIN

[0002] The present invention relates to the field of counting live insect larvae.

[0003] It relates more specifically to a method for counting live larvae of Mealworms or Black Soldier Flies.

[0004] CONTEXT AND STATE OF THE TECHNOLOGY

[0005] Entomology has enabled the description of the life cycles of many insect species. Counting very quickly became an essential evaluation method for progress.

[0006] To date, the enumeration of animal and plant species is essential for the assessment of biodiversity within different environments.

[0007] Partial counting represents an important obstacle in entomology, due to the millimeter size of the individuals and the potentially large numbers, which most of the time requires the use of small samples, at the risk of their low representativeness or the use of optical magnification tools.

[0008] Before the advent of livestock farming, pest control saw the development of electronic counters in the 1960s. These counters have drawbacks related to limitations in the number of insects they can count (less than 200), the number of dead insects they can process, and the type of medium they can use (liquid). This device is not suitable for counting large numbers of live insects.

[0009] In 1997, US patent 5646404 highlighted the counting of larvae by infrared detection of flying insects transiting on an airflow in order to control infestation of agricultural storage sites. This method has been adopted and improved on numerous occasions, notably by Wesley et al. (2010).

[0010] For insect farming, the state of the art lists devices that lead to the total or partial automation of a set of operations encountered (separation of the living environment (WO2022 / 119442 or EP3979791 or WO2019 / 053456 Al), sexing (WO2022 / 070195), feeding for example).

[0011] Among the millions of insect species, there are species with an aquatic larval stage, so for their enumeration, it appears more accessible to adapt a technique used in aquaculture (Daoling et al, 2021).

[0012] For applications in entomology, biocontrol is used for development sorted population management (WO 2022 / 070195) or the breeding of edible insects (WO 2022 / 112770).

[0013] Insect farming aims to provide ingredients for livestock or domestic animal food chains, or even for human consumption.

[0014] Industries exploit species, two of which are reared at the larval stage, namely the Mealworm (Tenebrio molitor, abbreviated "TM") and the Black Soldier Fly larva (Hermeti hillucens, abbreviated "MSN"). The millimeter-sized size and large numbers of individuals make it impossible to assess the real-time population levels present at the rearing sites.

[0015] For convenience of language, these two species in the larval stage may be referred to hereafter as TM and MSN.

[0016] Under these conditions, the rearing of such insects requires a tool to measure / evaluate the numbers of larvae in order to control their activity, and particularly the bioconversion yields of the food resources made available to them.

[0017] The rearing of insect larvae requires the development of a new industry compared to the techniques used for livestock farming known until now.

[0018] Indeed, the rearing of these larvae takes the form of large production units (expressed in m2 of rearing area whose productivity is translated in terms of quantity of protein product) and numerous sub-production units (rearing tanks averaging 1m2).

[0019] As with any industrial system, performance measurement is essential for monitoring process execution and validating equipment profitability. Monitoring larval growth is one of the primary levers for controlling and estimating bioconversion (the latter being understood as the change in form of energy or matter (at the molecular level) carried out by a living organism, which includes photosynthesis and cellular respiration).

[0020] To date, industrial control measures are carried out either by weighing production units at the end of growth and before the transformation of "animal products" into proteins, or by sampling in breeding units (with a mass ratio that can be limited to 1 in 25000).

[0021] On these samples of known masses, a count of the individuals makes it possible to project the total biomass of larvae contained in a unit, a subset of a unit or in the plant, but each time with a risk of error.

[0022] These locks do not allow the exploitation / factory to precisely track the bioconversion yields of the organic resources allocated to feeding the larvae or to monitor the animal welfare of the larvae (mortality).

[0023] Among the techniques implemented to date, a number of disadvantages.

[0024] Several relate to the physical support on which the insects and / or larvae are intentionally placed for the purpose of the counting operation. When the physical support is the habitat, it is almost exclusively aquatic in nature and therefore unsuitable for TM and MSN species, which develop in an opaque organic substrate.

[0025] Moreover, the aforementioned species, in their larval stage, flee the light and burrow into the nourishing substrate.

[0026] The term "feeding substrate" is used throughout this application, including the claims, to mean a solid substrate, at least partly organic, on / in which the larvae are reared and on which they feed.

[0027] Furthermore, existing imaging solutions identify live insect forms recognized as larvae on liquid or solid substrates specifically designed to receive individuals for counting purposes. In any case, these substrates are different from a larval rearing substrate.

[0028] This is explained by the fact that it is difficult to assess large quantities (greater than one kilogram) and especially to distinguish larvae without error of shape and / or color, compared to food particles and / or exuviae (which may have a similar shape and / or color).

[0029] There therefore remains an unmet need for a technique that allows for the counting of live TM and MSN larvae while they are developing on / in a nutrient substrate, even though these larvae tend, as mentioned above, to flee from light and burrow into said nutrient substrate. PRESENTATION OF THE INVENTION

[0030] To this end, the invention relates to a method for counting live larvae of Mealworms (Tenebrio Molitor) or Black Soldier Flies (Hermeti hillucens), characterized in that it comprises at least the following steps:

[0031] To deposit on a support a mass of Mealworm (Tenebrio Molitor) or Black Soldier Fly (Hermeti hillucens) larvae and nutrient substrate;

[0032] E2 / distribute said mass in the form of a thin layer of such thickness that said larvae cannot burrow into said substrate;

[0033] E3 / subject the same section of said thin film to at least two signals luminous with different wavelengths, within the range of 200-1000 nanometers;

[0034] E4 / using a multispectral optical sensor, capture images of said same section subject to said light signals;

[0035] E5 / to reconstruct a single image by interlacing and assembling said images of stage E4 / ;

[0036] E6 / proceed to count said larvae using a computer program image analysis and recognition;

[0037] E7 / if necessary, repeat said steps E3 / to E6 / on a new section (SE).

[0038] Thanks to these characteristics, the exposure of the larvae present on the surface of the substrate (because they cannot bury themselves there) to light signals of different wavelengths allows, in turn, to capture reflectance spectra which, in turn, allows to reliably differentiate the larvae from their substrate.

[0039] Thus, it is then possible to count said larvae using a computer image recognition program. This counting is carried out with a relatively low margin of error compared to known prior art methods.

[0040] According to other advantageous and non-limiting features of the invention, taken alone or according to a technically compatible combination of at least two of them:

[0041] - the thickness of said thin layer is between 1 and 10 millimeters and preferably typically between 1 and 5 millimeters;

[0042] - said different wavelengths are respectively on the order of 560 and 780 nanometers;

[0043] - in step E4, a linear camera incorporating said sensor is used;

[0044] - in step E6, a program is used which operates by learning at automatic;

[0045] - in step El, at least one mobile support is used.

[0046] - said at least one mobile support comprises at least one conveyor or belt rolling;

[0047] - in step E2, a single conveyor or conveyor belt is used, the upper strand, which receives said mass, extends horizontally;

[0048] - in step E2, a pair of conveyors or conveyor belts are used, the upper strands which receive said mass extend horizontally, the downstream end of the first of said conveyors / conveyor belts extending vertically from the upstream end of the second of said conveyors / conveyor belts, and that said steps E3 and E4 are implemented in a drop zone of said thin layer from the first to the second of said conveyors / conveyor belts;

[0049] - In step E2, a pair of conveyors or conveyor belts arranged in the extensions of one another, the first having an upper strand which extends horizontally, while the second is inclined downwards;

[0050] - said step E2 is implemented in a transfer zone from the first to the second of said conveyors or conveyor belts, while said step E4 is implemented at the vertical of the second of said conveyors or conveyor belts. DESCRIPTION OF THE FIGURES

[0051] Other features and advantages of the invention will become apparent from the description which will now be given, with reference to the attached drawings, which represent, by way of example but not limitation, one possible embodiment.

[0052] On these drawings:

[0053] [Fig.l] is a flowchart which integrates the different steps of the process according to the invention;

[0054] [Fig.2] is a schematic view of a first installation which is likely to be used for the implementation of the process according to the invention;

[0055] [Fig.3] is a schematic view of a second installation which is likely to be used for the implementation of the process according to the invention;

[0056] [Fig.4] is a schematic view of a third installation which is likely to be used for the implementation of the process according to the invention;

[0057] [Fig.5] is a diagram that illustrates how the images resulting from the setting in The work of the process according to the invention is addressed. DETAILED DESCRIPTION OF THE INVENTION

[0058] The process according to the invention, as it will be described according to a possible embodiment and with reference to the attached drawings, is applied to the live larvae of Mealworms (Tenebrio Molitof) or Black Soldier Flies (Hermeti hillucens) which will be referred to hereafter as TM and MSN.

[0059] These larvae have the particularity of seeing their weight multiplied by a factor of 6000 to 10000 in the space of a few weeks.

[0060] It is therefore understood that the number of larvae on their food substrate per rearing unit must be adapted to ensure the most efficient bioconversion possible.

[0061] It is in particular within this framework that the process of the invention can be implemented.

[0062] It can also be used to estimate the total weight of the larvae at the end of growth before possibly carrying out an actual weighing.

[0063] Figures 2 to 4 attached hereto show an installation I which can be used for the implementation of the process according to the present invention.

[0064] Step El: Deposition on a support of a mass of TM or MSN larvae and of nutrient substrate.

[0065] This first step of the process of the invention (see [Fig.1]), which is illustrated in particular in [Fig.2], can be carried out manually or in a mechanized / automated manner, for example using a rotary distributor 1.

[0066] The mass M consists of a mixture of live larvae at a predetermined stage growth and rearing and a nourishing substrate S, namely that it serves not only as a living environment for the larvae, but also as food for them.

[0067] For illustrative purposes only, this substrate S may consist of organic matter from cereals and / or vegetables or plant food by-products (from fruits, vegetables, bakeries, dairies, starch factories, "ethanol plants" (i.e. ethanol production units for example) or animals (depending on the countries and regulations in force.

[0068] At the end of this step, the mass M is deposited in a thick and compact layer on a support constituted here by the upper strand 20 of a motorized conveyor belt or conveyor 2.

[0069] In a possible embodiment not shown in the attached figures, the support may be static, while the distributor 1 is moved along and above it.

[0070] In the embodiment of [Fig.2], we are dealing with a single conveyor belt whose upper strands 20 and lower strands 22 are parallel and horizontal.

[0071] Step E2: mass distribution in the form of a thin layer of such thickness that said larvae cannot burrow into said substrate.

[0072] As previously stated, the larvae have a natural tendency to flee the light and bury themselves in the mass of substrate S that receives them.

[0073] This feature is in contradiction with the desire to implement a correct counting of the number of larvae present in the substrate.

[0074] In order to overcome this difficulty, the present step aims to distribute the mass M in the form of a thin layer CM of a thickness such that the larvae cannot burrow into the substrate S, so that they remain visible on the surface.

[0075] For illustrative purposes only, such a thin CM layer has a thickness of approximately 1 to 5 mm depending on the stage of development of the larvae. This setting can be extended to 10 millimeters depending on the type of larvae, their age, or the physical characteristics (particle size) of the substrate.

[0076] Before obtaining such a thin layer CM, a static tool 3 in the shape of a palette as shown in [Fig.2] can be used, which does not constitute the core of the invention.

[0077] In this alternative embodiment, not shown here, obtaining the CM thin layer can be done manually.

[0078] Step E3: submitting the same section of said thin layer to at least two light signals of different wavelengths.

[0079] As can be seen in [Fig.2], the installation I comprises, vertically above the upper strand 20 of the conveyor belt or conveyor 2, two lighting bars 4 and 4' which are oriented towards the same SE section of the thin layer CM.

[0080] The term "same section" means the surface of the thin film which is illuminated by the two bars 4 and 4'.

[0081] Using these bars 4 and 4', the SE section is subjected to at least two light signals of different wavelengths, within the range of 200-1000 nanometers.

[0082] Advantageously, these signals are emitted alternately.

[0083] Preferably, wavelengths of the order of 560 to 860 nanometers are used.

[0084] As an indication, for this lighting phase, Chromasens brand equipment can be used, and more specifically the Corona II model LED bar.

[0085] Step E4: Image capture of the section subjected to light signals.

[0086] Between bars 4 and 4' is positioned a multispectral optical sensor 5, for example integrated within a linear camera, which is configured to capture and record the images reflected by the illuminated section SE. These images represent the reflectance spectrum of the substrate S and the larvae at the considered wavelength.

[0087] These images are referenced pet i2 in [Fig.5].

[0088] With regard to images reflected by the SE section, because the light signals emitted in the previous step have different wavelengths, these images have distinctly different characteristics, in terms of contrast of the larvae with respect to the substrate, etc.

[0089] Step E5: Reconstruction of a single image by interlacing and assembling the images from step E4.

[0090] Using software such as that known as Aurora Vision from the Zebra company, the previously obtained pet i2 images are then interlaced and assembled to obtain a single i3 image (see [Fig.5]) in which the lines of pet i2 images are arranged alternately.

[0091] Although this is not visible, we thus obtain a single image whose contrast and sharpness are a priori sufficient to allow the larvae to be distinguished and identified in relation to the substrate S.

[0092] Step 5 bis: Image processing to differentiate the larvae

[0093] The image processing method uses a pattern recognition algorithm based on machine learning. This algorithm was built and trained on a set of images labeled by subject matter experts.

[0094] Step E5 ter: Sequencing of the relative displacement of the image to allow the calculation.

[0095] This step corresponds to the segmentation of the linear image into several images processed individually with the aim of losing as little information as possible, especially if one or more larvae overlap several images.

[0096] Step E6: counting of larvae using image analysis and recognition software.

[0097] To implement this step, preferential use will be made of an image analysis algorithm (called "deep learning", which uses a multilayer deep neural network) which, after learning, will identify areas labeled as "larvae", in order to count them.

[0098] Such a learning method, with "human" labeling, in "deep learning" makes it possible to improve the differentiation of larvae in relation to the substrate, regardless of their size, whether they are agglutinated or not, and regardless of the direction of their arrangement in the substrate.

[0099] The evolution of the neural network depends on the weighting values ​​determined by learning. The initial and iterated values ​​during the implementation of the present technique can evolve according to the development of new criteria made possible by the present invention.

[0100] Among the new criteria, it may be possible to identify the shape, size, thickness, length, sexual dimorphism, color, and any other element of definitive or temporary dimorphism linked in particular to the appearance of pathology, relating to the larvae.

[0101] Step E7: repeat steps E3 to E6 on a new section.

[0102] If necessary, the steps just described are again implemented on a new section of the CM thin film. Step E8: Observation Results

[0103] The output data differ depending on the criterion. For counting, it is the number of larvae present per image. For size, thickness, or length, the individual results are expressed in millimeters. For sex, it is the number of larvae per sex type per image. Step E9: Exit Information

[0104] All output information is expressed per batch. For counting, this refers to the total number of larvae and / or the number per sexual type. For size, thickness, or length, individual results are expressed using traditional descriptive indicators (mean, median, standard deviation, etc.).

[0105] Installation I of [Fig. 3] differs from that of [Fig. 2] in that it uses a pair of conveyors or conveyor belts 2 and 2', the upper sections 20 and 20' of which, respectively, receive said mass M and extend horizontally. The downstream end of the first 2 of these conveyors / conveyor belts extends vertically from the upstream end of the second 2'. Furthermore, steps E3 and E4 described above are implemented in the drop zone of the thin layer from the first to the second of said conveyors / conveyor belts. conveyors / conveyor belts.

[0106] For this purpose, the materials 4, 4' and 5 are arranged in an appropriate manner.

[0107] Such an arrangement can be used for reasons of compactness, for example in a room where the available space is reduced.

[0108] The installation of [Fig. 4] differs from that of [Fig. 2] in that it uses a pair of conveyors or belts 2 and 2' arranged end-to-end. The first 2 has an upper strand 20 that extends horizontally. The second 2' is inclined downwards. The aforementioned step E2 is carried out in the transition zone from the first to the second belt / conveyor. As for steps E3 and E4 described above, they are carried out in the central region of the second belt / conveyor 2'.

[0109] For this purpose, the materials 4, 4' and 5 are arranged in an appropriate manner.

[0110] Such an arrangement can be used for reasons of compactness, for example in a room where the collection of the larvae which have undergone counting cannot be done in the same room as the deposit of mass M on the conveyor belt / conveyor2, but in another room at a lower level.

[0111] Thus, the present invention aims to carry out a count of larvae by analysis of still or dynamic images taken by a multi-spectral sensor / camera after the alternating illumination at two wavelengths of a mixture of organic matter composed of insect larvae and its substrate (feeding and habitat).

[0112] The difficulties of counting larvae in imaging, as with the human eye, are based both on the efficiency of shape recognition attributable to the object sought, but also in our application on the differentiation between the larvae and the living / feeding substrate itself, the heterogeneity of larval sizes (linked among other things to differences in growth rate), and the mobility of the larvae which tend to flee into the substrate to avoid the light.

[0113] The process according to the invention makes it possible not only to differentiate larvae from the substrate formed of food particles, but also from foreign bodies and / or dead particles (exuviae).

[0114] It also offers the possibility of using the information captured to evaluate other key performance indicators of larval rearing and / or their morphological details (length, width, thickness, arrangement of morphological details, posture curvature, ...), both on average values ​​and their dispersions.

[0115] This process also allows counting the larvae separated from their living environment, upstream (i.e. from hatching) downstream (at the end of growth or before slaughter).

Claims

Demands

1. A method for counting live larvae of mealworms (Tenebrio molitor) or black soldier flies (Hermeti hillucens), characterized in that it comprises at least the following steps: E1 / depositing on a support a mass (M) of mealworm (Tenebrio molitor) or black soldier fly (Hermeti hillucens) larvae and of a feeding substrate (S); E2 / distributing said mass (M) in the form of a thin layer (CM) of a thickness such that said larvae cannot burrow into said substrate (S) and remain visible on the surface; E3 / subjecting the same section (SE) of said thin layer (CM) to at least two light signals of different wavelengths, in the range of 200-1000 nanometers; E4 / using a multispectral optical sensor (5), capture the images (ib i2) of said same section (SE) subjected to said light signals;E5 / reconstruct a single image (i3) by interlacing and assembling said images (il, i2) from step E4 / ; E6 / proceed to count said larvae using a computer program for image analysis and recognition; E7 / if necessary, repeat said steps E3 / to E6 / on a new section (SE).;

2. A method according to claim 1, characterized in that said different wavelengths are respectively on the order of 560 and 780 nanometers.

3. A method according to claim 1 or 2, characterized in that the thickness of said thin layer (CM) is between 1 and 10 millimeters and preferably between 1 and 5 millimeters.

4. A method according to any one of claims 1 to 3, characterized in that, in step E4, a linear camera incorporating said sensor (5) is used.

5. A method according to any one of the preceding claims, characterized in that, in step E6, a program which operates by machine learning is used.

6. A method according to any one of the preceding claims, characterized in that, in step 11, at least one movable support is used.

7. A method according to claim 6, characterized in that said at least one moving support comprises at least one conveyor or belt rolling (2, 2').

8. Method according to claim 7, characterized in that, in step E2, a single conveyor or conveyor belt (2) is used, the upper strand (20) of which, which receives said mass (M), extends horizontally.

9. A method according to claim 7, characterized in that, in step E2, a pair of conveyors or conveyor belts (2,2') is used, the upper strands (20,20') of which receive said mass (M) extend horizontally, the downstream end of the first (2) of said conveyors / conveyor belts extending vertically from the upstream end of the second (2') of said conveyors / conveyor belts, and that said steps E3 and E4 are carried out in a drop zone of said thin layer (CM) from the first (2) to the second (2') of said conveyors / conveyor belts.

10. A method according to claim 7, characterized in that, in step E2, a pair of conveyors or conveyor belts (2,2') arranged in line with each other are used, the first (2) having an upper strand (20) which extends horizontally, while the second (2') is inclined downwards.

11. A method according to claim 10, characterized in that said step E2 is carried out in a transfer zone from the first (2) to the second (2') of said conveyors or conveyor belts, while said step E4 is carried out vertically from the second (2') of said conveyors or conveyor belts.

Images