Method and system for influencing color of aquatic animals

Abstract

A computer-implemented method for controlling conditions within a volume of water containing aquatic animals is disclosed. The method includes obtaining target color information indicative of a target color of the aquatic animal in the water volume. The method further includes obtaining existing color information indicative of an existing color of the aquatic animal in the water volume, preferably via the input interface described herein. The method then includes determining a light recipe for the aquatic animal based on the target color of the aquatic animal and based on the existing color of the aquatic animal and based on a model correlating characteristics of the light to be provided to the aquatic animal with effects on the color and / or color appearance of the aquatic animal. Further, the method includes providing the determined light recipe to the aquatic animal in order to affect the color of the aquatic animal toward the target color.

Description

Technical Field

[0001] The present disclosure relates to a computer-implemented method for controlling conditions within a volume of water, and more particularly to such a method of providing light recipes to affect the color of aquatic animals. The present disclosure also relates to a controller, system, and computer program for performing the method described herein. Background Art

[0002] The colour and visual appeal of aquatic species (such as salmonids and shrimp) have a significant impact on their market value. For example, consumers prefer and pay a premium for: (a) dark red or pink salmon fillets; (b) the vibrant red of black tiger shrimp (Penaeus monodon); and (c) the lighter colour of white shrimp (Penaeus vannamei).

[0003] Wild-caught salmon and shrimp are known to be more vibrantly colored than farmed salmon and shrimp due to the abundance of carotenoids in their natural diet. Aquaculture farmers compensate for this by adding carotenoids (natural or synthetic) to fish and shrimp feed to promote coloration. This additive not only significantly increases feed costs on farms but also does not guarantee uniform color distribution across each farmed animal.

[0004] Pigmentation in fish and crustaceans is a natural phenomenon that occurs as part of their natural life cycle, with carotenoids playing a major role. Among aquaculture species, particularly salmonids and shrimp, color is an important quality criterion for consumers. For example, the market acceptability of fish depends on pigmentation, which is one of the important factors determining quality in the eyes of consumers. A similar situation is evident in the aquatic ornamental industry, where most fish are selected and kept based on their attractive skin color. Carotenoids are widely used as a source of pigment in aquaculture feeds and are associated with improving the sensory and color quality of fish and crustaceans.

[0005] However, the use of pigment compounds in aquaculture has become expensive. According to one study, it is the most expensive ingredient in salmon and shrimp feed, accounting for nearly 20% of the total feed cost. The study authors found that controlling and optimizing the concentration of pigment compounds in aquatic animal feed is time-consuming and labor-intensive.

[0006] In view of the foregoing, there is a need in the art for improved methods and systems for affecting the color of aquatic animals.

[0007] US 2016 / 0353716 A1 discloses a fish lighting system having an input interface that receives instructions corresponding to desired fish behavior and / or physiological responses. This is converted into lighting control signals (RGB, t) for driving a lighting arrangement, where the intensity and color of the output from the lighting arrangement are selected to obtain the desired fish behavior and / or physiological response. Summary of the Invention

[0008] To this end, a computer-implemented method for controlling conditions within a volume of water containing an aquatic animal is disclosed. The method includes obtaining target color information indicative of a target color for the aquatic animal in the water volume. The method also includes obtaining existing color information indicative of an existing color of the aquatic animal in the water volume, preferably via an input interface as described herein. The method then includes determining a light recipe for the aquatic animal based on the target color for the aquatic animal and based on the existing color of the aquatic animal and based on a model that relates characteristics of light provided to the aquatic animal to an effect on the color and / or color appearance of the aquatic animal. Furthermore, the method includes providing the determined light recipe to the aquatic animal so as to influence the color of the aquatic animal toward the target color.

[0009] One aspect of the present disclosure relates to a controller configured to control a lighting system configured to provide artificial light to aquatic animals contained within a volume of water. The controller includes an input interface for obtaining target color information indicating a target color for the aquatic animals within the volume of water, and current color information indicating an existing color of the aquatic animals within the volume of water. The controller also includes a processor configured to determine a light recipe for the aquatic animals based on the target color of the aquatic animals and based on the existing color of the aquatic animals. The controller also includes an output interface for sending a control signal to the lighting system to cause the lighting system to provide artificial light to the aquatic animals according to the light recipe.

[0010] One aspect of the present disclosure relates to a system for controlling conditions within a volume of water containing aquatic animals.The system includes a lighting system configured to provide artificial light to the aquatic animals and any controller described herein.

[0011] These methods, controllers and systems provide improved ways of influencing the color of aquatic animals.Recent studies have shown that, in addition to diet, lighting conditions also influence the body color of farmed aquatic animals.

[0012] For example, photoperiod (which can be understood as the period of time during which light is available within a 24-hour timeframe) can affect the color of shrimp (see Lakshmi, GJ, A. Venkataramiah, and G. Gunter. "Effects of salinity and photoperiod on the burying behavior of brown shrimp Penaeusaztecus Ives" Aquaculture 8.4 (1976): 327-336). For example, salmon have been shown to exhibit different fillet colors when farmed during summer and winter.

[0013] Additionally, light intensity is known to affect the color of cultured shrimp (Tseng, KF, HM Su, and MS Su. 1998. Culture of Penaeus monodon in a recirculating system. Aquaculture Engineering 17:138-147). Free astaxanthin concentrations (FACs) are higher in wild shrimp than in laboratory-reared shrimp because natural sunlight intensity (no less than 10,000 lx) is much higher than laboratory light intensity (maximum 2,500 lx). Researchers have demonstrated that FAC levels are higher in shrimp exposed to high-intensity light regimes compared to shrimp exposed to lower-intensity treatments (Erickson MC, Bulgarelil MA, Resurreccion AVA, Vendetti RA, Gates KA (2007) Consumer differentiation, acceptance, and demographic patterns to consumption of six varieties of shrimp. Journal of Aquatic Food Product Technology 15: 35-51).

[0014] Furthermore, it is known that the reflected light in water (in particular the spectrum of light) affects the body color of shrimps (Parisenti J, Beirao LH, Tramonte VLCG, et al. Preference ranking of colour in raw and cooked shrimps International Journal of Food Science & technology. 2011., 2011b). For example, the reflected light in the water tank affects the coloration of the peppermint shrimp (You K, Yang H, Liu Y, Liu S, Zhou Y, et al. (2006) Effects of different light sources and illumination methods on growth and body color of shrimp Litopenaeus vannamei. Aquaculture 252: 557-565). In another study, the researchers disclosed that the recipe and the background color of the aquaculture tank had a significant effect on the black tiger shrimp (Penaeus monodon). The shrimp reacted fastest within 15 minutes after being transferred from a black container to a white container (Calvo, Natalia S., et al. "Reflected-light influences the coloration of the peppermint shrimp, Lysmata boggessi (Decapoda: Caridea)." Journal of the World Aquaculture Society 47.5 (2016): 701-711).

[0015] It is also known that the lighting conditions affect the number of pathogens and protists in the water, which is related to the body color of aquatic animals. It is well known that the presence of probiotic microorganisms and pathogenic bacteria in the water of the tank affects the microbiota in the body of fish or shrimp. For example, for Atlantic salmon (Nguyen, Chan DH, et al. "Atlantic Salmon (Salmo salar L., 1758) gut microbiota profile correlates with flesh pigmentation: cause or effect " Marine Biotechnology (2020): 1-19), it has been found that the gut microbiota of salmon is related to the pigmentation of the fish flesh.

[0016] Similarly, the microbial flora within the shrimp affects the appearance of their digestive tract. It is also known that the spectrum of applied light affects the concentration of probiotic microorganisms in the aquaculture tank water, which consequently changes the shrimp's microbial flora.

[0017] Further, [Kang & Kim; Influence of density and background color to stress response, appetite, growth, and blind-side hypermelanosis of flounder, Paralichthys olivaceus ; Fish Physiol Biochem (2013) 39:221–232] investigated the association between density and background color and hypopigmentation (hyperpigmentation) on the blind side of the aquacultured olive flounder (Brown flounder). Two replicate groups of juvenile fish were reared in flat-bottom aquaria with dark green (control) and white backgrounds for 120 days. The study also demonstrated that the inhibitory effect of bright background color on hyperpigmentation is density-dependent.

[0018] The coloration of crustaceans, such as shrimp, can be manipulated by varying the reflected light in their tanks. Like other aquatic animals, shrimp cannot synthesize carotenoids themselves and therefore rely primarily on dietary sources, either in farm settings (for example, astaxanthin in feed pellets) or in their natural habitats (microalgae and phytoplankton). The crustacean's visual and dietary systems still control how carotenoids are converted and incorporated within cells within the body. This process is significantly influenced by environmental conditions, including lighting. For example, crustaceans are known to adjust their body coloration between dark (when in dark waters) and light (when in sunny tropical waters). The shrimp's ability to adjust their body coloration plays an important role in camouflaging themselves from predators.

[0019] Therefore, the coloration of aquatic animals is a complex process and can be greatly helped by adjusting lighting conditions and lighting recipes in real time, as each harvest is different. The technology disclosed herein enables continuous monitoring and adjustment of light recipes to influence the body color of species towards the farmer's harvest goals.

[0020] As used herein, conditions within a volume of water may be understood as circumstances or factors that influence the color and / or appearance of color in aquatic animals within the volume of water.

[0021] As used herein, "color of an aquatic animal" may be understood to refer to the color of the animal, particularly the color of the animal's body, as perceived by a human observer who is looking at the aquatic animal.

[0022] For example, the water volume may be the volume of water in a fish tank.

[0023] For each of the plurality of aquatic animals, the existing color information may in particular indicate the existing colors that the aquatic animal in question has. Thus, the color information may indicate the color distribution of the aquatic animals, in the sense that it indicates how many aquatic animals have which color.

[0024] A light recipe may be understood as an indication of the light to be provided to the aquatic animals for each of a plurality of times. In particular, a light recipe may be understood as defining the lighting conditions that should exist in the water volume for each of the plurality of times. The light recipe may, for example, indicate the spectrum of light to be provided to the aquatic animals and / or the total radiant flux that the aquatic animals should receive. The light recipe defines, for example, light time periods. Optionally, the light recipe also defines, for each of the plurality of times, which light is to be provided and where in the water volume. Providing the determined light recipe may be performed by sending an appropriate one or more control signals to the lighting system, such that the one or more control signals cause the lighting system to provide light to the aquatic animals according to the light recipe.

[0025] Light as indicated by the light recipe may refer to all light received by aquatic animals, including both artificial light and non-artificial light (such as sunlight). Alternatively, light as indicated by the light recipe may specifically refer to artificial light, optionally in addition to sunlight, that should be provided to aquatic animals.

[0026] The target color may be the color that the aquatic animal is desired to be when harvested.

[0027] The aquatic animals may include crustaceans, such as crustaceans belonging to the superfamily Penaeoidea, preferably belonging to the family Penaeidae or Penaeidae, such as gambas and / or tiger prawns and / or whiteleg shrimp and / or Atlantic whiteleg shrimp and / or Indian shrimp. Additionally or alternatively, the aquatic animals include fish, such as grass carp, silver carp, common carp, Nile tilapia, bighead carp, catla (Indian carp), crucian carp, Atlantic salmon, rohu, milkfish, rainbow trout, Wuchang fish, black carp, northern snakehead fish, catfish, etc.

[0028] In one embodiment, the method includes determining a feed for the aquatic animal (particularly characteristics of the feed) based on a target color for the aquatic animal and based on the existing color of the aquatic animal and based on a model that relates characteristics of the feed provided to the aquatic animal to an effect on the color and / or color appearance of the aquatic animal. In this case, providing the determined feed can be performed by sending one or more appropriate control signals to a feed system.

[0029] In one embodiment, the system includes one or more imaging systems configured to measure the existing color of aquatic animals within the volume of water.

[0030] An advantage of this embodiment is that it enables continuous monitoring of the existing colour of the aquatic animals.

[0031] The one or more imaging systems can be configured to record one or more images of aquatic animals in the water volume and subsequently perform image processing to determine the color of the aquatic animals present in the one or more recorded images. This processing can be performed by a processor of the controller. In this sense, the imaging system can be partially contained within the controller.

[0032] The computer implementation may include, and the controller (particularly the processor of the controller) may be configured to: construct a model based on training data, which training data associates multiple light recipes with corresponding effects on the color of aquatic animals; and use the constructed model to determine the light recipe and / or the second light recipe mentioned below.

[0033] These embodiments enable automatic determination of an appropriate light recipe for influencing the color of aquatic animals towards a target color.

[0034] Building the model can be performed as part of a machine learning approach known in the art. Training data can be obtained quite simply by recording a few parameters (including the existing lighting conditions and the existing color of the aquatic animals) for many batches throughout the lifecycle of each batch. The lighting conditions may include, for example, the spectrum of light provided to the aquatic animals and / or the radiant power of the light provided to the aquatic animals. Machine learning methods known in the art can then be used to construct a model based on the training data, such that when fed a set of parameters, including the lighting conditions, the model outputs a prediction of how the color of the aquatic animals will change.

[0035] The training data may further associate one or more parameters with corresponding effects on the color of the aquatic animal. The method may further include, and the controller may include, one or more sensors for measuring one or more values ​​of the one or more parameters. The constructed model may then be used to determine the light recipe and / or the second light recipe mentioned below based on the one or more values ​​of the measured one or more parameters. The one or more parameters include at least one of the following: - turbidity of water, - the speed of the water, - water temperature, - the amount of oxygen in the water, - pH of the water, - the number and / or type of pathogens in the water, - the number and / or type of probiotic microorganisms in the water, - the number and / or type of pathogenic microorganisms in the water - Quantity and / or type of feed.

[0036] In principle, the more parameters that are used to build the model and then the more parameters that are input into the built model, the more accurately the color appearance of the aquatic animal can be predicted. This will lead to more effective light recipes in the sense that the color of the aquatic animal can be effectively influenced.

[0037] In an embodiment, the light recipe indicates, for each of a plurality of times, an electromagnetic spectrum and / or a radiant flux of the artificial light. Providing the determined light recipe to the aquatic animal then preferably comprises causing the lighting system to provide the artificial light to the aquatic animal in accordance with the light recipe.

[0038] The light recipe can further indicate one or more locations within the water volume at which the artificial light is to be provided. The light recipe can depend on a current location of the fish (e.g. a depth of the fish or a 3D position of the fish). The light recipe can depend on a density of the fish.

[0039] The method can comprise, and the controller (in particular the processor of the controller) can be configured for, determining a feed for the aquatic animal (in particular a characteristic of the feed) based on the target color of the aquatic animal and based on the existing color of the aquatic animal and based on a model associating characteristics of a feed to be provided to the aquatic animal with an influence on the color and / or color appearance of the aquatic animal.

[0040] Such a model can be built based on feed training data associating a plurality of feed characteristics with a respective influence on the color of the aquatic animal.

[0041] In such an embodiment, the determined feed characteristic can comprise at least one of: - a composition of the feed, - a size of the feed pellets, - a feed amount, - a feeding schedule indicating at what time to provide the feed.

[0042] The feed amount can be an amount of feed per unit of time (e.g. per day).

[0043] Preferably, the feeding schedule indicates how much feed to provide at what time.

[0044] Providing the determined feed can comprise sending appropriate control signals to a feed system in order to cause the feed system to provide the determined feed to the aquatic animal.

[0045] This embodiment further improves the ability to influence the color of the aquatic animal, since the color of the aquatic animal also depends on the feed.

[0046] The target color information may indicate a target color for the aquatic animal at a future time. Furthermore, the existing color information may indicate the existing color of the aquatic animal at a specific time prior to the future time. In this case, the method may include, and the controller may be configured to obtain, desired color trajectory information indicating how the color of the aquatic animal is expected to appear in a time period prior to the future time, so that the aquatic animal has the target color at the future time, and to indicate the desired color of the aquatic animal for each of one or more times prior to the future time. In this context, the one or more times include a specific time. The method may then include, and the controller (particularly a processor of the controller) may be configured to: determine a light recipe based on a comparison between the existing color of the aquatic animal, as indicated by the existing color information, and the desired color of the aquatic animal at the specific time, as indicated by the desired color trajectory information; and provide the determined light recipe to the aquatic animal.

[0047] These embodiments allow for an assessment of whether a batch of aquatic animals is expected to have a target color at a future time. Expected color trajectory information can be understood as indicating the expected color development of the aquatic animals over time, resulting in the target color at the future time. The expected color development can be some default color development for a given aquatic animal species. The expected color trajectory information can indicate the harvest time of the aquatic animals. The expected color development can, for example, be an average of how the color of the same species developed in previous batches. If it is determined early in the process (i.e., before the future time) that the currently existing color of the aquatic animals is not on the color trajectory, it can be concluded that the aquatic animals will not achieve the target color at the future time unless measures are taken to influence the color (development) of the aquatic animals. The determined light recipe preferably incorporates some of these measures, such as longer / shorter light periods, or higher / lower radiant flux received by the aquatic animals.

[0048] Preferably, the determined light recipe defines the characteristics of light provided to the aquatic animals for a period between a specific time up to and including a future time.

[0049] As described herein, the step of comparing the existing color to the desired color can be understood as determining whether the difference between the existing color and the desired color is above a threshold. Then, based on the determination that the difference is indeed above the threshold, a light recipe, or a second light recipe as described below, can be determined. In particular, if it is determined that the difference between the existing color and the desired color is greater than the threshold, then in response, it can be determined whether another light recipe can be put in place that enables the target color to be achieved or better approximated at a future time.

[0050] The existing color of the aquatic animal can be repeatedly (e.g., continuously) measured so that it can be repeatedly (e.g., continuously) checked whether the existing color appearance (as indicated by the existing color locus information) deviates, and optionally the extent to which it deviates from the desired color appearance as indicated by the desired color locus information. If the deviation becomes too great, a new light recipe and associated color locus information are required. Of course, this cycle can be repeated over and over again so that the aquatic animal is provided with a suitable light recipe most of the time.

[0051] In one embodiment, the method includes, and the controller (particularly, the processor of the controller) is configured to determine, based on the determined light recipe, second color trajectory information, the second color trajectory information indicating how the color of the aquatic animal is expected to appear during a time period between a specific time and a future time by providing the determined light recipe, and indicating the expected color of the aquatic animal for each of one or more times between the specific time and the future time, wherein the one or more times include a second specific time. In such an embodiment, the method may include, and the controller (particularly, the processor of the controller) is configured to obtain second existing color information, the second existing color information indicating the existing color of the aquatic animal at a second specific time between the specific time and the future time. The method may then include, and the controller (particularly, the processor of the controller) is configured to compare the existing color of the aquatic animal, as indicated by the second existing color information, with the expected color of the aquatic animal at the second specific time, as indicated by the second color trajectory information.

[0052] This embodiment therefore enables continuous monitoring of whether the newly determined color trajectory is actually followed. If this is not the case, a new light recipe can be determined again.

[0053] Of course, preferably, the second color trajectory leads to the target color at a future time. However, it is possible that the target color can no longer be reached at the future time. In this case, the second color trajectory preferably makes the target color as close as possible to the future time. Additionally or alternatively, the second color trajectory can indicate that the target color is reached at a certain time period after the future time. In this case, it can be decided to postpone the harvest of the aquatic animals so that they will have the target color at the time of harvest.

[0054] In one embodiment, the method includes, and the controller (particularly, a processor of the controller) is configured to determine a second light recipe based on comparing the existing color of the aquatic animal, as indicated by the second existing color information, with the desired color of the aquatic animal at a second specific time, as indicated by the second color trajectory information. The method may then include, and the controller may be configured to provide the determined second light recipe to the aquatic animal, so as to influence the color of the aquatic animal toward the target color.

[0055] These embodiments illustrate that the existing color can be checked with virtually any desired color, as indicated by any currently "valid" desired color trajectory information. As used herein, valid desired color trajectory information means that the trajectory information has been determined based on the light recipe currently being provided to the aquatic animal. In other words, the existing color appearance of the aquatic animal should, in principle, conform to the color appearance indicated by the valid desired color trajectory information. If not, then another light recipe may need to be determined to influence the color of the aquatic animal.

[0056] The method may include, and the controller (in particular the processor of the controller) may be configured to determine, based on the determined second light recipe, third color trajectory information, the third color trajectory information indicating how the color of the aquatic animal is expected to appear in a time period between the second specific time and the future time by providing the determined second light recipe.

[0057] The first color trajectory information and the determined second color trajectory information may indicate a harvest time of the aquatic animal.

[0058] Preferably, the method comprises, and the controller is configured to cause the aquatic animal to be harvested at a harvest time as indicated by the second color track information.

[0059] The aquatic animals may be crustaceans. Additionally or alternatively, the aquatic animals may include fish, preferably salmon. The color (appearance) of these types of aquatic animals is affected by the light recipe provided.

[0060] Various aspects of the present disclosure relate to a computer program comprising instructions which, when executed by a data processing system, cause the data processing system to perform any one of the computer-implemented methods described herein. The data processing system may be a controller as described herein.

[0061] The present disclosure also relates to a computer-readable medium having stored thereon any one of the computer programs disclosed herein.

[0062] Various aspects of the present disclosure relate to a computer comprising: a computer-readable storage medium embodying computer-readable program code, and A processor, preferably a microprocessor, coupled to a computer-readable storage medium, wherein in response to executing the computer-readable program code, the processor is configured to perform any one of the computer-implemented methods described herein.

[0063] Different aspects of the present disclosure relate to a computer program or computer program suite comprising at least one software code portion, or a computer program product storing at least one software code portion, which, when run on a computer system, is configured to perform any one of the computer-implemented methods described herein.

[0064] Various aspects of the present disclosure relate to a non-transitory computer-readable storage medium storing at least one software code portion that, when executed or processed by a computer, is configured to perform any one of the computer-implemented methods described herein.

[0065] As will be appreciated by those skilled in the art, aspects of the present invention may be embodied as systems, methods, or computer program products. Thus, aspects of the present invention may take the form of entirely hardware embodiments, entirely software embodiments (including firmware, resident software, microcode, etc.), or embodiments combining software and hardware aspects, which may all be generally referred to herein as "circuits," "modules," or "systems." The functions described in this disclosure may be implemented as algorithms executed by a processor / microprocessor of a computer. Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer-readable media having computer-readable program code embodied (e.g., stored) thereon.

[0066] Any combination of one or more computer-readable media may be utilized. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of the present invention, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0067] A computer-readable signal medium may include a propagated data signal having computer-readable program code embodied therein (e.g., in baseband or as part of a carrier wave). Such a propagated signal may take any of a variety of forms, including but not limited to electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and that can communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0068] The program code embodied on the computer-readable medium may be transmitted using any suitable medium (including but not limited to wireless, wired, optical fiber, cable, RF, etc., or any suitable combination of the foregoing). The computer program code for implementing the operations of aspects of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Java (TM), Smalltalk, C++, etc.) and conventional procedural programming languages ​​(such as the "C" programming language or similar programming languages). The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0069] Aspects of the present invention are described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor (particularly a microprocessor or central processing unit (CPU)) of a general-purpose computer, a special-purpose computer, or other programmable data processing device to generate a machine, such that instructions executed by the processor of the computer, other programmable data processing device, or other device create a device for implementing the functions / actions specified in the flowchart and / or one or more block diagram blocks.

[0070] These computer program instructions may also be stored in a computer-readable medium, which may direct a computer, other programmable data processing apparatus, or other device to operate in a particular manner so that the instructions stored in the computer-readable medium produce an article of manufacture that includes instructions for implementing the functions / actions specified in the flowchart and / or one or more block diagram blocks.

[0071] The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in the flowchart and / or block diagram blocks.

[0072] The flowcharts and block diagrams in the various figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of code that includes one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions described in the blocks may not appear in the order described in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order, depending on the functions involved. It will also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified function or action, or a combination of dedicated hardware and computer instructions.

[0073] Furthermore, a computer program for carrying out the methods described herein and a non-transitory computer-readable storage medium storing the computer program are provided. The computer program can, for example, be downloaded (updated) to an existing data processing system (eg, an existing controller) or stored when these systems are manufactured.

[0074] Unless otherwise expressly stated, elements and aspects discussed for or about a particular embodiment may be appropriately combined with elements and aspects of other embodiments. Embodiments of the present invention will be further described with reference to the accompanying drawings, which schematically illustrate embodiments according to the present invention. It will be understood that the present invention is not limited to these specific embodiments in any way. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Aspects of the present invention will be explained in more detail with reference to exemplary embodiments shown in the accompanying drawings, in which: Figure 1 A system for controlling conditions within a volume of water is shown according to one embodiment; Figure 2A-2D shows a color trajectory according to one embodiment; Figure 3 is a flow chart illustrating a method according to one embodiment; Figure 4 A data processing system according to one embodiment is shown. DETAILED DESCRIPTION

[0076] In the drawings, the same reference numbers refer to the same or similar elements.

[0077] Figure 1 A system 2 for controlling conditions (particularly lighting conditions) within a volume of water 6 containing aquatic animals 4 is shown, according to one embodiment. System 2 includes a lighting system 12 configured to provide artificial light to aquatic animals 4. As shown, lighting system 12 may include a plurality of light sources 12a, 12b, 12c, and 12d. System 2 also includes a controller 100 configured to control lighting system 12. The controller may, for example, be configured to provide artificial light to aquatic animals 4 within the volume of water 6. In particular, the controller may be configured to control the radiant power of the artificial light, as received by the aquatic animals, and / or the electromagnetic spectrum (color) of the provided artificial light.

[0078] like Figure 1 As shown in , the water volume 6 can be the water volume in a fish tank in which aquatic animals are grown. The fish can be grown in such a fish tank until they have a certain size and can then be harvested.

[0079] The controller 100 comprises an input interface for obtaining target color information indicating a target color of an aquatic animal in the water volume.Such an input interface may be a user interface via which a user can input a certain target color for the aquatic animal 4 in question.

[0080] Figure 1 Embodiments further include a plurality of imaging systems 10a, 10b, which may be, for example, corresponding multispectral imagers (e.g., RGB imagers) within the water volume 6. These imaging systems may be configured, for example, to briefly (e.g., 1 second) illuminate a portion of the water volume 6 with white light, which facilitates acquiring images from which the color of the aquatic animals in these images can be derived. The imaging systems may include embedded grow lights and / or flashlights. Preferably, these imaging systems are attached to the illuminator of the lighting system, the fish tank, the feeding tray / box, or the fish enclosure at a location suitable for capturing the full-body color of the aquatic animals (e.g., the bottom of the floor, below an automatic feeder, or from a side view).

[0081] In any case, the controller's input interface allows the controller to receive existing color information indicating the existing color of an aquatic animal. This color information can be embodied in an image captured by the imaging system. The controller (particularly a processor of the controller) can then execute an algorithm known in the art to identify the aquatic animal in the recorded image and determine the color (e.g., body color) of the identified aquatic animal.

[0082] The processor of the controller 100 is then configured to determine a light recipe for the aquatic animal based on the target color of the aquatic animal and based on the existing color of the aquatic animal. A light recipe can be understood as an indication of which light (e.g., which radiant flux and which electromagnetic spectrum) is to be provided at which times and, optionally, also at which locations in the water volume 6. Figure 3 How the controller can determine the appropriate light recipe is explained in more detail.

[0083] The controller 100 further includes an output interface for sending a control signal to the lighting system 12 so that the lighting system provides artificial light to the aquatic animals according to the light distribution.

[0084] Although Figure 1 Shrimp are schematically depicted as aquatic animals 4 , but in principle the technology disclosed herein can be advantageously used for any aquatic animal whose color depends on lighting conditions.

[0085] Figure 2A is a graph showing a desired color trajectory 20. The horizontal axis indicates time, and the vertical axis indicates the red component of the existing color of the aquatic animal (as determined by reference, for example). Figure 1 The red component is, for example, the red component of an RGB color coding scheme. As indicated, the target color of the aquatic animal is approximately 75% for the red component. It should be appreciated that for clarity, Figure 2A-2D Only the target value and color trajectory of the red component are shown, however, typically the target value is defined based on more values ​​(e.g., all three values ​​of the RGB color encoding scheme.) In this case, the color trajectory will have four dimensions (the three RGB values ​​and time).

[0086] Figure 2A Also shown is a color trajectory indicating the harvest time at t3. Thus, at t3, the color of the aquatic animals is expected to reach the target value.

[0087] The color track 20 that may be indicated by the color track information described herein may be a default color track for a given species of aquatic animal.

[0088] At time t1, the existing color of the aquatic animal is measured, as indicated by point 22. It should be appreciated that the measured existing color may be the average color of several aquatic animals at or near t1, in this case the average red component percentage. In any case, the existing color has a red component percentage that is too low relative to the color trajectory 20.

[0089] Therefore, a new light recipe was determined, which Figure 2B , is associated with the new color trajectory 24 shown in . Color trajectory 24 also leads to the target color at time t3.

[0090] like Figure 2C As shown in FIG, at time t2, the existing color of the aquatic animal is measured again (see point 26). Thus, another light recipe associated with the color locus 28 is determined (see Figure 2D Unfortunately, the color trajectory 28 does not reach the target color at time t3, but does reach the target color at time t4. In view of this, the farmer may decide to postpone the harvest so that the aquatic animals will hopefully have the target color at time t4.

[0091] Figure 3 4 is a flow chart illustrating a computer-implemented method according to one embodiment. The method begins at step 40 and then proceeds to step 41, which includes obtaining target color information indicating a target color of the aquatic animal in the water volume. Preferably, the target color is the color that the aquatic animal is desired to have at the time of harvest. Obtaining the target color can be performed simply by retrieving the target color from a database.

[0092] Then, step 42 is executed, which involves determining a light recipe. In a first iteration, the light recipe may simply be some default recipe, meaning it is a default light recipe for the specific species of aquatic animal being grown. In further iterations, an updated light recipe is determined using a model (as output by step 66) that relates the characteristics of the light provided to the aquatic animal to the effect on the aquatic animal's color and / or color appearance, as will be explained in more detail below. The light recipe indicates the electromagnetic spectrum and / or radiant flux of the artificial light for each of a plurality of times.

[0093] In step 44, a desired color trajectory is determined, which indicates how the colors of the desired aquatic animals appear. The desired color trajectory and the light recipe determined in step 42 are related to each other in the sense that the desired color trajectory is the expected color appearance when the light recipe determined in step 42 is applied.

[0094] In step 46, the determined light recipe is provided to the aquatic animal in order to influence the color of the aquatic animal towards the target color. This step may be performed by sending appropriate control signals to the lighting system described herein.

[0095] After the light recipe has been validated, the existing color of the aquatic animal is measured (step 48 ), which means that existing color information indicative of the existing color of the aquatic animal and further parameters are obtained (step 50 ).

[0096] For step 48, a computer vision algorithm can be executed that causes the controller to process the images to locate the fish / shrimp and quantify their current body color. In the case of salmon, the body color is observed from underwater images, and the flesh color can be observed from mobile phone images of sampled fish fillets (e.g., generated by the farmer). Statistical aggregation of the body color of the animals over a period of time can be performed. Thus, a computer vision-based algorithm can be used to estimate the true color of the live animals in water. At the time of imaging, several techniques can be used to maximize the quality of the images. By manipulating the lighting and sound environment, the aquatic animals can be attracted to the camera. In addition, rapid motion actions (such as tail flips for shrimp) can be induced, causing the animals to be in a favorable position for high-quality imaging. In addition, the animals can be photographed from feeding structures such as feeding trays and feeding boxes.

[0097] Step 48 can be repeated at different times of the day, and the body color of the animals can be aggregated over a longer period of time, such as 60 minutes. When sampling at different times of the day, the current animal activity (such as feeding, burrowing, molting, etc.) can be taken into account to estimate the true color of a representative population. To address the issue of finding the true body color in turbid water, a reference object can be utilized for active illumination. For example, a reference object can be placed within the water volume that represents the expected color of the shrimp for a given day in the growth cycle of the shrimp. Then, image recognition techniques can detect and extract the observed color from the reference object and use this information to understand the true body color of the shrimp. This approach overcomes practical challenges such as the constantly changing turbidity, reflected wavelengths, and light levels inside the water volume.

[0098] These parameters can relate to the lighting conditions (however, this is not strictly necessary, as the lighting conditions are controlled and thus known), and preferably also to any one or all of - the turbidity of the water, - the speed of the water, - the water temperature, - the amount of oxygen in the water, - the pH of the water, - the number and / or type of pathogenic organisms in the water, - the number and / or type of probiotic microorganisms in the water, - the number and / or type of pathogenic microorganisms in the water.

[0099] If the target color is reached (which is checked in step 52), then (“yes”), step 54 can be executed (including causing the harvesting of the aquatic animals), after which the method ends at 56.

[0100] If the target color has not been reached, then ("No"), step 58 is performed, which involves comparing the existing color measured in step 48 with the desired color as indicated by the color trajectory determined in step 44. If the difference does not exceed a certain threshold (which is checked in step 60) - then ("No"), step 48 is performed again. The cycle of steps 48, 52, 58 and 60 can be performed repeatedly (for example, several times a day).

[0101] If it is determined in step 60 that the difference between the existing color and the desired color exceeds a certain threshold, then ("yes"), step 42 is executed again. In this second iteration, and in further iterations, a light recipe is determined based on the target color of the aquatic animal (obtained in step 41), based on the existing color of the aquatic animal (measured in step 48), and based on a model (as output by step 66) that relates the characteristics of the light provided to the aquatic animal to the effect on the aquatic animal's color and / or color appearance. Preferably, the light recipe is also determined based on the parameter values ​​measured in step 50.

[0102] Steps 61, 62, 64, and 66 are not necessarily performed as part of the method. However, these steps indicate how a model for determining a light recipe can be obtained. In step 61, lighting conditions are measured. In step 62, parameters are measured, preferably the same parameters as those measured in step 50. Step 64 includes measuring the color of the aquatic animal. Steps 62 and 64 can be performed on different historical batches and are used to collect training data on how the measured parameters are related to the color development of the aquatic animal. In step 66, machine learning methods known in the art can be used to find these correlations and build a model. It should be appreciated that the color development and associated parameters measured in steps 48 and 50 can also be input into step 66 as training data, which provides continuous improvement of the model.

[0103] Following the determination of the new light recipe in step 42, an associated color trajectory is also determined (step 44). It will be appreciated that these steps can be performed simultaneously. For example, it is possible that the method can determine several candidate light recipes and determine an associated color trajectory for each candidate light recipe. The candidate light recipe with the best color trajectory, for example, in terms of achieving the target color at a future time, can then be selected as the light recipe to be implemented in step 46.

[0104] Performing step 46 may include controlling a spotlight (optionally with an adjustable spectrum and dimmable control) to change the illumination direction and / or level and color of incident / reflected light in the body of water. Additionally or alternatively, performing step 46 may include controlling a wall-grazing illuminator (with an adjustable spectrum and dimmable control) to counteract unwanted reflections from the wall lining. For example, such a illuminator can compensate for a non-reflective, dark lining in a water tank.

[0105] As shown, steps 42, 44, 46, 48, 50, 52, 58, 60 may be repeatedly performed in a loop until the target color is reached, which is checked in step 52. Thus, the light recipe may be repeatedly adjusted during the life cycle of the batch.

[0106] The desired concentration of probiotic microorganisms was determined based on the current color appearance of the salmon fillet and shrimp. For example, as shown in Figure 2, the color of salmon fillets is influenced by the Bacillaceae family. The activity spectrum of Bacillus pumilus in water is available in the literature. This enabled us to purposefully select the illumination wavelength to selectively promote Bacillus pumilus, which positively contributes to the color appearance of the salmon fillet relative to other microorganisms present in the water (see our patent application regarding the microbiome).

[0107] Figure 4 Depicted is a block diagram illustrating a data processing system according to one embodiment.

[0108] like Figure 4 As shown in , data processing system 100 may include at least one processor 102 coupled to memory element 104 via system bus 106. In this way, the data processing system may store program code in memory element 104. In addition, processor 102 may execute program code accessed from memory element 104 via system bus 106. In one aspect, the data processing system may be implemented as a computer suitable for storing and / or executing program code. However, it should be appreciated that data processing system 100 may be implemented in the form of any system including a processor and memory that is capable of performing the functions described in this specification.

[0109] The memory elements 104 can include one or more physical memory devices such as, for example, local memory 108 and one or more bulk storage devices 110. Local memory can refer to random access memory or other non-persistent memory device(s) generally used during actual execution of the program code. A bulk storage device can be implemented as a hard disk drive or other persistent data storage device. The processing system 100 can also include one or more cache memories (not shown) that provide temporary storage of at least some program code in order to reduce the number of times program code must be retrieved from the bulk storage device 110 during execution.

[0110] Optionally, input / output (I / O) devices 112 and 114, depicted as input and output devices, can be coupled to the data processing system. Examples of input devices can include, but are not limited to, a keyboard, a pointing device such as a mouse, a touch-sensitive display, an imaging system configured to measure the color of an aquatic animal as described herein, or the like. Examples of output devices can include, but are not limited to, a monitor or display, speakers, a lighting system for providing artificial light to an aquatic animal as described herein, or the like. Input and / or output devices can be coupled to the data processing system either directly or through an intermediate I / O controller.

[0111] In embodiments, the input and output devices can be implemented as a combined input / output device (illustrated in Figure 4 with a dashed line surrounding the input device 112 and the output device 114). An example of such a combined device is a touch-sensitive display, sometimes also referred to as a "touchscreen display" or simply "touchscreen". In such embodiments, input to the device can be provided by movement of a physical object, such as for example a stylus or a user's finger, on or near the touchscreen display.

[0112] A network adapter 116 can also be coupled to the data processing system to enable it to become coupled to other systems, computer systems, remote network devices, and / or remote storage devices through intervening private or public networks. The network adapter can comprise a data receiver for receiving data that is transmitted by said systems, devices and / or networks to the data processing system 100, and a data transmitter for transmitting data from the data processing system 100 to said systems, devices and / or networks. Modems, cable modems, and Ethernet cards are examples of different types of network adapters that can be used with the data processing system 100.

[0113] As Figure 4As depicted, memory element 104 may store application programs 118. In various embodiments, application programs 118 may be stored in local memory 108, one or more mass storage devices 110, or separate from local memory and mass storage devices. It should be appreciated that data processing system 100 may further execute an operating system (OS) that may facilitate the execution of application programs 118. Figure 4 ). Application 118, implemented in the form of executable program code, may be executed by data processing system 100 (eg, by processor 102). In response to executing the application, data processing system 100 may be configured to perform one or more operations or method steps described herein.

[0114] In one aspect of the invention, data processing system 100 may represent a controller as described herein.

[0115] Various embodiments of the present invention can be implemented as a program product for use with a computer system, where the program(s) of the program product define functionality of the embodiments (including the methods described herein). In one embodiment, the program(s) may be embodied on various non-transitory computer-readable storage media, where, as used herein, the term "non-transitory computer-readable storage medium" includes all computer-readable media with the sole exception of transitory propagated signals. In another embodiment, the program(s) may be embodied on various transitory computer-readable storage media. Illustrative computer-readable storage media include, but are not limited to: (i) non-writable storage media on which information is permanently stored (e.g., read-only memory devices within a computer, such as CD-ROM disks readable by a CD-ROM drive, ROM chips, or any type of solid-state non-volatile semiconductor memory); and (ii) writable storage media on which information is stored that can be modified (e.g., flash memory, a floppy disk within a floppy disk drive or hard drive, or any type of solid-state random-access semiconductor memory). The computer program(s) may be executed on the processor 102 described herein.

[0116] The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that when used in this specification, the terms "include" and / or "comprise" specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0117] The corresponding structures, materials, actions, and equivalents of all means or step plus function elements in the following claims are intended to include any structure, material, or action for performing a function in combination with other claimed elements as specifically claimed. The description of the embodiments of the present invention has been presented for illustrative purposes, but is not intended to be exhaustive or limited to the embodiments in the disclosed form. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the invention. The embodiments are selected and described in order to best explain the principles of the invention and some practical applications, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications suitable for the particular use envisioned.

Claims

1. A computer-implemented method for controlling conditions within a volume of water containing aquatic animals, the method comprising: obtaining target color information indicative of a target color of an aquatic animal in the volume of water, and obtaining existing color information indicative of an existing color of an aquatic animal in the volume of water, and determining a light recipe for the aquatic animal based on a target color for the aquatic animal and based on the existing color of the aquatic animal and based on a model relating properties of light provided to the aquatic animal to effects on the color and / or color appearance of the aquatic animal, and The determined light recipe is provided to the aquatic animal so as to influence the color of the aquatic animal toward a target color.

2. The method according to claim 1, further comprising constructing the model based on training data that correlates a plurality of light recipes with corresponding effects on the color of aquatic animals, and The constructed model is used to determine the light recipe.

3. The method of claim 2, wherein the training data further associates one or more parameters with corresponding effects on the color of the aquatic animal, the method further comprising: measuring one or more values ​​of one or more parameters, and Determining a light recipe using the constructed model and based on one or more values ​​of the measured one or more parameters, wherein the one or more parameters include at least one of the following: - turbidity of water, - the speed of the water, - water temperature, - the amount of oxygen in the water, - pH of the water, - the number and / or type of pathogens in the water, - the number and / or type of probiotic microorganisms in the water, - the number and / or type of pathogenic microorganisms in the water, - Quantity and / or type of feed.

4. A method according to any one of the preceding claims, wherein The light recipe indicates an electromagnetic spectrum and / or radiant flux of the artificial light for each of a plurality of times, and wherein providing the determined light recipe to the aquatic animal comprises causing the lighting system to provide the artificial light to the aquatic animal according to the light recipe.

5. A method according to any one of the preceding claims, wherein the method comprises determining the characteristics of feed for aquatic animals, in particular feed, based on the target color of the aquatic animals and based on the existing color of the aquatic animals and based on a model that relates the characteristics of the feed provided to the aquatic animals to the effects on the color and / or color appearance of the aquatic animals.

6. A method according to any one of the preceding claims, wherein target color information indicating the target color of the aquatic animal at a future time, and The existing color information indicates an existing color of the aquatic animal at a specific time before a future time, and the method further includes: obtaining desired color trajectory information indicating how the color of the aquatic animal is desired to appear in a time period prior to a future time, so that the aquatic animal has a target color at the future time, and indicating the desired color of the aquatic animal for each of one or more times prior to the future time, wherein the one or more times include a specific time, and determining a light recipe based on a comparison between an existing color of the aquatic animal at a particular time as indicated by the existing color information and a desired color of the aquatic animal at a particular time as indicated by the desired color trajectory information, and Provide the aquatic animals with the determined light recipe.

7. The method according to claim 6, further comprising: determining second color trajectory information based on the determined light recipe, the second color trajectory information indicating how a color of a desired aquatic animal appears during a time period between the specific time and the future time by providing the determined light recipe, and indicating a desired color of the aquatic animal for each of one or more times between the specific time and the future time, wherein the one or more times include a second specific time, obtaining second existing color information indicating an existing color of the aquatic animal at a second specific time between the specific time and the future time, and The existing color of the aquatic animal at the second specific time, as indicated by the second existing color information, is compared to the desired color of the aquatic animal at the second specific time, as indicated by the second color trajectory information.

8. The method according to claim 7, further comprising determining a second light recipe based on comparing the existing color of the aquatic animal at the second specific time as indicated by the second existing color information with the desired color of the aquatic animal at the second specific time as indicated by the second color trajectory information, and The determined second light recipe is provided to the aquatic animal to influence the color of the aquatic animal toward the target color.

9. The method according to any one of claims 7 to 8, wherein The determined second color trajectory information indicates a harvest time of the aquatic animal.

10. The method of any one of claims 1 to 9, wherein the aquatic animal comprises a crustacean.

11. The method according to any one of claims 1 to 9, wherein the aquatic animal comprises fish, preferably salmon.

12. A controller configured to Controlling a lighting system configured to provide artificial light to aquatic animals contained in a volume of water, the controller comprising: - an input interface for obtaining target color information indicative of a target color of an aquatic animal in the water volume, and for obtaining existing color information indicative of an existing color of an aquatic animal in the water volume, and a processor configured to determine a light recipe for the aquatic animal based on a target color for the aquatic animal and based on an existing color of the aquatic animal and based on a model relating properties of light provided to the aquatic animal to effects on the color and / or color appearance of the aquatic animal, and - Output interface, used to send control signals to the lighting system so that the lighting system provides artificial light to aquatic animals according to the light distribution direction.

13. A system for controlling conditions within a volume of water containing aquatic animals, the system comprising a lighting system configured to provide artificial light to aquatic animals, and The controller according to claim 12.

14. The system according to claim 12 or 13, further comprising One or more imaging systems are configured to measure existing color of aquatic animals within the volume of water.

15. A computer program comprising instructions which, when executed by a processor of a system according to claim 13, cause the system to perform the method according to any one of claims 1 to 11.

Images