Information Processing Method, Non-Temporary Computer-Readable Storage Medium, and Information Processing Apparatus

Abstract

To enable accurate estimation of information regarding schools of fish. [Solution] The information processing method of the present application is an information processing method executed by a computer, and is characterized by including an acquisition step of acquiring values ​​of internal parameters related to the biological characteristics of fish, values ​​of external parameters related to the characteristics of the environment surrounding the fish, and values ​​of school parameters related to the characteristics of school behavior, which is the behavior that fish exhibit toward other fish, and a generation step of generating a simulation image including the behavior of each fish belonging to the school of fish based on the values ​​of the internal parameters, the values ​​of the external parameters, and the values ​​of the school parameters acquired by the acquisition step.

Description

Technical Field

[0001] The present invention relates to an information processing method, a non-transitory computer-readable storage medium, and an information processing apparatus.

Background Art

[0002] Deep Learning has produced excellent results in the fields of computer vision and speech recognition. For example, in a fish farm, counting the number of fish in a fish pen is a problem, but it is expected that such problems can be improved by using deep learning techniques.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, the accuracy of analysis by deep learning depends on training data. That is, in order to obtain highly accurate analysis results, it is necessary to let a machine learning model learn a large amount of training data covering various patterns. For example, in order to accurately estimate information (such as the number of fish) about a school of fish from a captured image of the school of fish in a fish pen using computer vision, it is necessary to let a machine learning model learn a large amount of training data covering various combinations of conditions such as the environment around the fish, the fish species, and the number of fish.

[0005] However, it is not easy to create a large amount of training data covering various patterns. For example, it is very difficult to create a large amount of training data by manually assigning correct data to each of an enormous number of images covering various combinations of conditions.

[0006] Thus, when it is impossible to obtain a large amount of training data covering various patterns, it is difficult to train a machine learning model with high quality, and it may be difficult to accurately estimate information about a school of fish from actual captured images.

Means for Solving the Problem

[0007] An object of the present invention is to at least partially solve the problems of the prior art.

[0008] According to one aspect of the embodiment, an information processing method according to the present application is an information processing method executed by a computer, including: an acquisition step of acquiring a value of an internal parameter related to a biological characteristic of a fish, a value of an external parameter related to a characteristic of an environment around the fish, and a value of a school parameter related to a characteristic of a group behavior that is a behavior taken by the fish with respect to other fish; and a generation step of generating a simulation image including the behavior of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter acquired in the acquisition step.

[0009] Regarding the above and other objects, features, effects, and technical and industrial significance of the present invention, understanding will be deepened by referring to the following detailed description of preferred embodiments of the present invention in conjunction with the accompanying drawings.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Embodiments for Carrying Out the Invention

[0011] Hereinafter, embodiments for implementing the information processing method, non-transitory computer-readable storage medium, and information processing apparatus according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing method, non-transitory computer-readable storage medium, and information processing apparatus according to the present application are not limited by these embodiments. Also, in the following embodiments, the same parts are denoted by the same reference numerals, and redundant descriptions are omitted.

[0012] (Embodiment) [1. Introduction] In recent years, fish farming has attracted attention as a means to solve the global food problem. To supply high-quality fish through fish farming, it is important to accurately know the number of fish, which is closely related to feeding (feeding fish).

[0013] However, in the special environment of the water in a fish farm, it may be difficult to utilize ground IT technologies. Therefore, conventionally, a person would scoop up some fish with a net, weigh them, and then count the number of fish visually. This method has problems such as a large burden on the fish and a lack of accuracy.

[0014] Therefore, in recent years, a method of automatically counting the number of fish in a school in a captured image of the school of fish using computer vision has attracted attention. A specific example is a method of training a machine learning model for image recognition to estimate the number of fish in a captured image. However, in order to accurately estimate the number of fish from a captured image using a machine learning model, it is necessary to train the machine learning model with a large amount of training data covering various combinations of conditions such as the environment around the fish (e.g., season, time, weather, water temperature, illuminance, degree of water pollution, etc.) and the biological characteristics of the fish (e.g., fish species, fish size, fish speed, number of fish, etc.).

[0015] However, it is not easy to create a large amount of training data that covers various combinations of conditions as described above. For example, it is very difficult to create a large amount of training data by manually assigning correct data to each of a huge number of images covering various combinations of conditions. Also, in order to accurately estimate the mantissa from a captured image using a machine learning model, the quality of the training data is also important. However, when correct data is manually assigned, the quality of the training data may not always be high.

[0016] As described above, when it is not possible to obtain a large amount of training data that covers various patterns, it is not possible to make the machine learning model learn with high quality. Therefore, conventionally, it has sometimes been difficult to accurately estimate information regarding a school of fish from an actual captured image.

[0017] On the other hand, the information processing apparatus according to the embodiment generates a simulation image including the behavior of each fish belonging to a school of fish based on the value of an internal parameter regarding the biological characteristics of the fish, the value of an external parameter regarding the characteristics of the environment around the fish, and the value of a school parameter regarding the characteristics of the schooling behavior, which is the behavior that the fish takes with respect to other fish.

[0018] FIG. 1 is a diagram for explaining an overview of nine parameters used for generating a simulation image according to the embodiment. The information processing apparatus according to the embodiment generates a simulation image including the behavior of each fish belonging to a school of fish based on the values of the nine parameters shown in FIG. 1. The upper row of FIG. 1 shows school parameters regarding the characteristics of three types of schooling behaviors (alignment, cohesion, separation). Also, the middle row of FIG. 1 shows external parameters regarding water temperature, illuminance, a net of a fish trap, and the like. Also, the lower row of FIG. 1 shows internal parameters such as the range in which the fish takes a schooling behavior, the relationship between the size and moving speed of the fish, and the time required for the fish to make a decision. Details of the nine parameters will be described later.

[0019] In this way, based on information regarding the biological characteristics of fish, information regarding the environment around the fish, and information regarding the characteristics of fish schooling behavior, the information processing apparatus 100 can accurately reproduce the behavior of a school of fish located in an actual fish cage. Further, the information processing apparatus 100 can easily generate a large number of simulation images covering a variety of patterns by changing the values of a plurality of parameters used for generating the simulation images. Also, since the information processing apparatus 100 can utilize the values of the parameters used for generating the simulation images as correct answer data, it is possible to easily generate a large amount of high-quality training data as compared with the case where correct answer data is manually provided.

[0020] As a result, the information processing apparatus 100 enables, for example, a machine learning model that estimates information (such as the number of fish) regarding a school of fish from a captured image to be trained with a large amount of high-quality training data. That is, by training the machine learning model with a large amount of high-quality training data, the information processing apparatus 100 can improve the estimation accuracy of the machine learning model that estimates information (such as the number of fish) regarding a school of fish from a captured image. Therefore, the information processing apparatus 100 can accurately estimate information regarding a school of fish.

[0021] [2. Configuration of Information Processing Apparatus] FIG. 2 is a diagram showing a configuration example of the information processing apparatus 100 according to the embodiment. The information processing apparatus 100 includes a communication unit 110, a storage unit 120, an input unit 130, an output unit 140, and a control unit 150.

[0022] (Communication Unit 110) The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information to and from, for example, a terminal device used by an administrator who manages fish.

[0023] (Memory unit 120) The memory unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. Specifically, the memory unit 120 stores various programs (an example of an information processing program) used for simulation. Also, the memory unit 120 stores the values of various parameters used for simulation.

[0024] (Input unit 130) The input unit 130 receives various operations from the user. For example, the input unit 130 may receive various operations from the user via a display surface (e.g., the output unit 140) by means of a touch panel function. Also, the input unit 130 may receive various operations from buttons provided on the information processing apparatus 100 or from a keyboard or a mouse connected to the information processing apparatus 100.

[0025] (Output unit 140) The output unit 140 is, for example, a display screen realized by a liquid crystal display or an organic EL (Electro-Luminescence) display, etc., and is a display device for displaying various information. The output unit 140 displays various information according to the control of the control unit 150. When a touch panel is adopted in the information processing apparatus 100, the input unit 130 and the output unit 140 are integrated. Also, in the following description, the output unit 140 may be described as a screen.

[0026] (Control unit 150) The control unit 150 is a controller, which is realized, for example, by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc., when various programs (corresponding to an example of an information processing program) stored in the storage device inside the information processing apparatus 100 are executed with the RAM as a work area. Further, the control unit 150 is a controller and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0027] The control unit 150 has an acquisition unit 151, a generation unit 152, an estimation unit 153, and an output control unit 154 as functional units, and may realize or execute the operations of information processing described below. Note that the internal configuration of the control unit 150 is not limited to the configuration shown in FIG. 2, and other configurations may be used as long as they can perform the information processing described later. Further, each functional unit represents the function of the control unit 150 and does not necessarily have to be physically distinguished.

[0028] (Acquisition Unit 151) The acquisition unit 151 acquires the value of an internal parameter related to the biological characteristics of a fish, the value of an external parameter related to the characteristics of the environment around the fish, and the value of a school parameter related to the characteristics of the group behavior, which is the behavior of the fish towards other fish. Specifically, the acquisition unit 151 acquires the value of the internal parameter, the value of the external parameter, and the value of the school parameter input by the user via the input unit 130.

[0029] More specifically, the acquisition unit 151 acquires the value of the internal parameter set for each fish belonging to the fish school included in the simulation image. For example, when the number of fish in the fish school included in the simulation image is N (N is a natural number), the acquisition unit 151 acquires the values of N internal parameters set for each of the N individual fish.

[0030] In addition, the acquisition unit 151 acquires the value of the group parameter set for the school of fish included in the simulation image. The value of the group parameter is set to a value common to each fish for each school of fish. For example, when the number of fish in the school of fish included in the simulation image is N (N is a natural number), the acquisition unit 151 acquires the value of the group parameter common to all N individual fish.

[0031] In addition, the acquisition unit 151 acquires the value of the external parameter set for the environment around the school of fish included in the simulation image. For example, the acquisition unit 151 acquires the value of the external parameter set for each fish tank in which the school of fish included in the simulation image is located. For example, the acquisition unit 151 acquires the value of the external parameter whose value varies according to the water depth of the fish tank in which the school of fish included in the simulation image is located.

[0032] (Generation unit 152) The generation unit 152 generates a simulation image by controlling the behavior of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the group parameter acquired by the acquisition unit 151. Hereinafter, with reference to FIGS. 3 to 8, the case where the generation unit 152 controls the behavior of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the group parameter will be described in detail.

[0033] FIG. 3 is a diagram for explaining the relationship between the water temperature and the behavior of fish. As a biological characteristic of fish, it is known that each fish has a preferred water temperature, and each individual fish moves toward the region of its preferred water temperature. In the example shown in the upper part of FIG. 3, since the water temperature around the fish is higher than the water temperature preferred by the fish, the generation unit 152 controls the behavior of the fish so that the fish moves toward the region of its preferred water temperature. Also, in the example shown in the lower part of FIG. 3, since the water temperature around the fish is lower than the water temperature preferred by the fish, the generation unit 152 controls the behavior of the fish so that the fish moves toward the region of its preferred water temperature. For example, the generation unit 152 controls the moving direction of the fish so that the moving direction of the fish is toward the region of its preferred water temperature. In this way, based on the water temperature preferred by each fish belonging to the fish school as the value of the internal parameter, the generation unit 152 controls the behavior of each fish so that each fish moves toward the region of its preferred water temperature.

[0034] Also, it is known that the distribution of water temperature in the fishpond varies according to the season (or seasonal tidal current) and water depth. In the example shown in the upper part of FIG. 3, the season is summer, and the Kuroshio Current flows into the fishpond where the fish are located, so the water temperature in the fishpond is high. Also, it is known that in the summer fishpond, the water temperature is higher closer to the water surface of the fishpond and lower closer to the bottom of the fishpond. Therefore, as the value of the external parameter, the generation unit 152 changes the distribution of the water temperature in the fishpond according to the water depth so that the water temperature is higher closer to the water surface of the fishpond and lower closer to the bottom of the fishpond. Also, in the example shown in the lower part of FIG. 3, the season is winter, and the Oyashio Current flows into the fishpond where the fish are located, so the water temperature in the fishpond is low. Also, it is known that in the winter fishpond, the water temperature is lower closer to the water surface of the fishpond and higher closer to the bottom of the fishpond. Therefore, as the value of the external parameter, the generation unit 152 changes the distribution of the water temperature in the fishpond according to the water depth so that the water temperature is lower closer to the water surface of the fishpond and higher closer to the bottom of the fishpond. In this way, based on the distribution of the water temperature in the fishpond where each fish belonging to the fish school is located as the value of the external parameter, the generation unit 152 controls the behavior of each fish so that each fish moves toward the region of its preferred water temperature.

[0035] In addition, as a biological characteristic of fish, it is known that the higher the water temperature around the fish, the higher the movement speed of the fish, and the lower the water temperature around the fish, the lower the movement speed of the fish. Therefore, the generation unit 152 controls the behavior of each fish belonging to the fish school so that the higher the water temperature around each fish, the greater the movement speed of each fish, based on the water temperature distribution in the fish cage where each fish belonging to the fish school is located, as the value of the internal parameter.

[0036] FIG. 4 is a diagram for explaining the relationship between illuminance and fish behavior. As a biological characteristic of fish, it is known that each fish has a preferred illuminance, and each fish moves toward the region of the preferred illuminance. In the example shown in the upper part of FIG. 4, since the illuminance around the fish is lower than the illuminance preferred by the fish, the generation unit 152 controls the behavior of the fish so that the fish moves toward the region of the preferred illuminance. Also, in the example shown in the lower part of FIG. 4, since the illuminance around the fish is higher than the illuminance preferred by the fish, the generation unit 152 controls the behavior of the fish so that the fish moves toward the region of the preferred illuminance. For example, the generation unit 152 controls the movement direction of the fish so that the movement direction of the fish is toward the region of the preferred illuminance. In this way, the generation unit 152 controls the behavior of each fish so that each fish moves toward the region of the preferred illuminance, based on the illuminance preferred by each fish belonging to the fish school, as the value of the internal parameter.

[0037] Also, it is known that the illuminance distribution in the fish tank varies depending on season, time, weather, and water depth. In the example shown in the upper part of FIG. 4, the season is winter (or the time is morning or night, etc.), and the illuminance in the fish tank is low. Also, in the example shown in the lower part of FIG. 4, the season is summer (or the time is noon, etc.), and the illuminance in the fish tank is high. Also, generally, it is known that the illuminance in the fish tank is higher closer to the water surface of the fish tank and lower closer to the bottom surface of the fish tank. Therefore, the generation unit 152 changes the illuminance distribution in the fish tank according to the water depth so that the illuminance is higher closer to the water surface of the fish tank and lower closer to the bottom surface of the fish tank as the value of the external parameter. In this way, the generation unit 152 controls the behavior of each fish so that each fish belonging to the fish school moves toward the region of the illuminance that the fish prefers, based on the illuminance distribution in the fish tank where each fish is located.

[0038] FIG. 5 is a diagram for explaining the relationship between the net of the fish tank and the behavior of the fish. As a biological characteristic of the fish, it is known that when the fish approaches an obstacle such as the net of the fish tank or the water surface of the fish tank, the fish takes an avoidance behavior of avoiding the obstacle. The inventors of the present invention obtained an experimental result that when the distance between the fish and the obstacle becomes 4 times or less the body length of the fish, the fish detects the obstacle and takes an avoidance behavior of avoiding the obstacle. Therefore, the generation unit 152 controls the behavior of each fish so that each fish takes an avoidance behavior of avoiding the obstacle when the distance between each fish belonging to the fish school and the obstacle is equal to or less than a predetermined threshold value (for example, a length that is a predetermined multiple of the body length of each fish).

[0039] Also, as shown in FIG. 5, as a biological characteristic of fish, it is known that the closer (farther) the distance between the fish and the net of the fish trap is, the faster (slower) the fish takes collision avoidance action. Therefore, the generation unit 152 controls the behavior of each fish based on a greater repulsive force as the distance between each fish belonging to the fish school and the obstacle is smaller. Here, the repulsive force refers to the force with which the fish tries to move away from the obstacle in order to avoid a collision with the obstacle. For example, when the distance between the fish and the obstacle is equal to or less than a predetermined threshold value, the generation unit 152 controls the behavior of the fish based on a repulsive force having a magnitude proportional to the distance between the fish and the obstacle. For example, the generation unit 152 controls the behavior of the fish so that the fish avoids the obstacle (the net of the fish trap in FIG. 5) by applying a repulsive force in a direction opposite to the moving direction of the fish (in FIG. 5, the direction in which the fish is heading toward the net of the fish trap) to the fish. In this way, when the distance between each fish belonging to the fish school and the obstacle is equal to or less than a predetermined threshold value, the generation unit 152 controls the behavior of each fish based on the repulsive force acting on each fish as a value of the internal parameter.

[0040] FIG. 6 is a diagram for explaining the range in which fish take group behavior with respect to other fish. As a biological characteristic of fish, it is known that fish take group behavior with respect to other fish located around themselves. The inventors of the present invention obtained an experimental result that fish detect other fish located within a range of three times their body length and take group behavior with respect to the other fish located within a range of three times their body length. Therefore, as a value of the group parameter, when other fish are located within a predetermined range (for example, within a range of a predetermined multiple of the body length of each fish) from the position of each fish belonging to the fish school, the generation unit 152 controls the behavior of each fish so that each fish takes group behavior.

[0041] Here, the schooling behavior of fish with respect to other fish refers to behavior that follows three rules: cohesion, separation, and alignment. "Cohesion" refers to the force that individuals try to approach each other so as not to disperse (hereinafter also referred to as the cohesive force), "separation" refers to the force that individuals try to move apart to avoid collisions (hereinafter also referred to as the separation force), and "alignment" refers to the force that tries to align the direction of movement as a group (hereinafter also referred to as the alignment force). The behavior of fish is determined by the sum of these three forces. Hereinafter, the three forces of the cohesive force, the separation force, and the alignment force are collectively referred to as "schooling parameters". The three forces are each determined by the value of a parameter indicating the magnitude of the force, the direction of the force, and the range to which the force extends. For example, the schooling parameters are determined by the size of the space where the school is located (e.g., an aquarium), the size of the fish, and the density of the fish school. In this way, the generation unit 152 controls the behavior of each fish based on, as the value of the schooling parameter, the cohesive force which is the force that each fish belonging to the fish school tries to approach each other so as not to disperse, the separation force which is the force that each fish belonging to the fish school tries to move apart to avoid collisions, and the alignment force which is the force that each fish belonging to the fish school tries to align the direction of movement as a group.

[0042] FIG. 7 is a diagram for explaining the relationship between the body length of fish and the speed of fish. As a biological characteristic of fish, it is known that the larger (smaller) the body length of fish, the larger (smaller) the moving speed of fish. Therefore, the generation unit 152 controls the behavior of each fish based on, as the value of the internal parameter, the body length of each fish belonging to the fish school so that the larger the body length, the larger the moving speed of each fish. Also, as a biological characteristic of fish, it is known that the larger (smaller) the amplitude of the caudal fin of fish, the larger (smaller) the moving speed of fish. Therefore, the generation unit 152 may control the behavior of each fish based on, as the value of the internal parameter, the magnitude of the amplitude of the caudal fin of each fish belonging to the fish school so that the larger the magnitude of the amplitude, the larger the moving speed of each fish.

[0043] FIG. 8 is a diagram for explaining the relationship between the reaction rate of the fish's Mauthner cells, the length of time required for the fish's decision-making, and the time interval. As a biological characteristic of fish, it is known that the time required for a fish to make a decision to take each action is determined by the reaction rate of the fish's Mauthner cells (a type of nerve cell). Here, the decision-making for a fish to take each action refers to the decision-making for a fish to instantaneously determine "where to swim" and "how to swim". In the example shown in FIG. 8, the time required for a fish to make a decision to take each action is about 200 milliseconds, and the time interval between decisions is several hundred milliseconds. Therefore, the generation unit 152 controls the actions of each fish based on the length of time required for each fish belonging to the fish group to make a decision to take each action and the time interval as the value of the internal parameter. Specifically, the generation unit 152 sets the update time of the simulation image to the time required for a fish to make a decision to take each action (for example, several hundred milliseconds). For example, the generation unit 152 controls the length of time for a fish to be in a predetermined state (for example, the "Slow Swim" state shown in FIG. 11 described later) to the time required for a fish to make a decision to take each action (for example, several hundred milliseconds). Subsequently, the generation unit 152 controls the time interval for a fish to transition from a predetermined state (for example, the "Slow Swim" state shown in FIG. 11 described later) to another state (for example, the "C-start Left" state shown in FIG. 11 described later) to the time interval between decisions (for example, several hundred milliseconds). Subsequently, the generation unit 152 controls the length of time for a fish to be in another state (for example, the "C-start Left" state shown in FIG. 11 described later) to the time required for a fish to make a decision to take each action (for example, several hundred milliseconds).

[0044] Also, as a biological characteristic of fish, it is known that the lower (higher) the water temperature around the fish (or the body temperature of the fish), the slower (faster) the reaction rate of the fish's Mauthner cells. Therefore, the generation unit 152 may control the actions of each fish based on the length of time required for a longer decision-making and the time interval as the value of the internal parameter, where the lower the water temperature around the fish is.

[0045] FIG. 9 is a diagram showing a 3D CG image of a fish and a 3D bounding box. The fish shown in FIG. 9 is a 3D CG image of a fish generated based on the body side data measured for each fish species (hereinafter also referred to as the actual data of the fish cage). The generation unit 152 generates a simulation image using a realistic 3D CG image of a fish generated based on the actual data of the fish cage. Note that the generation unit 152 may generate a simulation image using a 3D CG image of a fish that is not based on the actual data of the fish cage. For example, the generation unit 152 may generate a simulation image using a 3D CG image of a fish having body side data different from the actual data of the fish cage based on values around the actual data of the fish cage (for example, values within a predetermined range from the representative value of the measured data). Further, the generation unit 152 may vary the body length, movement speed, initial position, initial state, weight, etc. of each fish belonging to the fish group included in the simulation image.

[0046] Also, the frame surrounding the fish shown in FIG. 9 is a 3D bounding box for specifying the position information and size of the fish. The generation unit 152 generates the position information of each fish. For example, the generation unit 152 includes the central position of fish OB and the position information indicating the existence range of fish OB. The position information of the fish is generated using, for example, 3D coordinate information. In the example of FIG. 9, as an example of the position information of fish OB, the generation unit 152 generates information regarding the coordinates (b x 、b y 、b z )(not shown) of the center of fish OB, and the depth b d 、width b w 、and height b h of the rectangular parallelepiped (3D bounding box) of the minimum size that encloses fish OB.

[0047] FIG. 10 is a diagram showing a 3D CG image of a fish cage. FIG. 10 is a 3D CG image of a fish cage generated based on the latitude and longitude, water temperature, illuminance, underwater image data, etc. of an actual fish cage (hereinafter also referred to as the actual data of the fish cage). The generation unit 152 generates a simulation image using a realistic 3D CG image of a fish cage generated based on the actual data of the fish cage. Note that the generation unit 152 may generate a simulation image using a 3D CG image of a fish cage that is not based on the actual data of the fish cage. For example, the generation unit 152 may generate a simulation image using a 3D CG image of a fish cage having data different from the actual data of the fish cage (for example, the size, depth, water temperature, illuminance, etc. of the fish cage are within a predetermined range from the representative value of the measured data) based on values around the actual data of the fish cage (for example, values within a predetermined range from the representative value of the measured data). Further, the generation unit 152 may generate a simulation image using a 3D CG image of a fish cage having data different from the actual data of the fish cage based on values that do not exist in the actual data (for example, data for a time period when there is no measured data).

[0048] FIG. 11 is a diagram showing a finite state machine for determining the state of a fish. As a biological characteristic of a fish, it is known that the swimming style (also referred to as swimming method) of each fish species can be classified into specific patterns. Note that in FIG. 11, the case where the fish species is salmon is described, but the swimming pattern may be different for each fish species. The generation unit 152 generates 12 types of animations showing the swimming states of 12 types of fish as shown in FIG. 11. Further, the generation unit 152 determines the swimming state of each fish by a finite state machine (FSM) from among the 12 types of animations, thereby transitioning the swimming state of each fish.

[0049] For example, the generation unit 152 transitions the swimming of the fish from the "Slow Swim" state to the "C-start Left" state. Subsequently, the generation unit 152 transitions the swimming of the fish from the "C-start Left" state to the "Fast Swim" state. Subsequently, the generation unit 152 transitions the swimming of the fish from the "Fast Swim" state to the "Semi Fast Swim" state. Subsequently, the generation unit 152 transitions the swimming of the fish from the "Semi Fast Swim" state to the "Slow Swim" state. Subsequently, the generation unit 152 transitions the swimming of the fish from the "Slow Swim" state to the "Rest Swim" state. Also, when performing the state transition, the generation unit 152 can realize smooth animation by complementing the state before the transition and the state after the transition.

[0050] FIG. 12 is a diagram showing an example of a simulation image according to the embodiment. Although the simulation image generated by the generation unit 152 is a video, FIG. 12 shows a part of the video as a still image. FIG. 12 is a diagram showing an example of a simulation image generated by the generation unit 152. The generation unit 152 controls, within the 3D CG image of the fish tank (see FIG. 10), the 3D CG images of a plurality of fish (see FIG. 9) to swim based on the values of the internal parameters, external parameters, and flock parameters acquired by the acquisition unit 151, thereby generating a simulation image of a school of fish as shown in FIG. 12. Note that the simulation image shown in FIG. 12 reproduces an image taken from a virtual camera installed at a position 4 meters (or 6 meters) deep in the water of the 3D CG image of the fish tank shown in FIG. 10.

[0051] FIG. 13 is a diagram showing an example of training data in which a 3D bounding box is added to each fish included in the simulation image according to the embodiment. When generating the simulation image, the generation unit 152 generates training data with a 3D bounding box added that indicates the position information of each fish included in the generated simulation image. Note that the generation unit 152 can easily generate the training data with the 3D bounding box added by using the position information of each fish used when generating the simulation image.

[0052] FIG. 14 is a diagram showing an example of training data in which a 2D bounding box is added to each fish included in the simulation image according to the embodiment. When generating the simulation image, the generation unit 152 generates training data with a 2D bounding box added that indicates the position information of each fish included in the generated simulation image. Note that the generation unit 152 can easily generate the training data with the 2D bounding box added by using the position information of each fish used when generating the simulation image.

[0053] FIG. 15 is a diagram showing an example of training data in which each fish included in the simulation image according to the embodiment is replaced with a silhouette. When generating the simulation image, the generation unit 152 generates training data in which each fish included in the generated simulation image is replaced with a silhouette. The example in FIG. 15 is an example in which a plurality of fish are color-coded. The color-coding in FIG. 15 corresponds to the assignment of color elements. When there are a plurality of fish, the colors for color-coding each fish may be different, or the colors may be different according to the classification information of the fish.

[0054] FIG. 16 is a diagram showing an example of a machine learning model according to an embodiment. The machine learning model shown in FIG. 16 includes a neural network of YOLO (You Only Look Once). The generation unit 152 trains the machine learning model so that when a simulation image is input to the machine learning model, it outputs individual identification information of each fish included in the simulation image and information corresponding to the individual identification information of each fish (for example, the number of tails). Note that the generation unit 152 is not limited to YOLO, and any known neural network used for object detection may be applied to the machine learning model. For example, in addition to YOLO, the generation unit 152 can apply Faster R-CNN or SSD (Single Shot MultiBox Detector) developed for object detection to the machine learning model.

[0055] For example, when the generation unit 152 inputs the generated simulation image to the machine learning model M1, it trains the machine learning model M1 so that it outputs a simulation image with a 3D bounding box indicating the position information of each individually identified fish and the number of tails of the individually identified fish (the number of tails of the fish group).

[0056] Also, when the generation unit 152 inputs the generated simulation image to the machine learning model M2, it trains the machine learning model M2 so that it outputs a simulation image with a 2D bounding box indicating the size of each individually identified fish and the number of tails of the individually identified fish (the number of tails of the fish group).

[0057] Also, when the generation unit 152 inputs the generated simulation image to the machine learning model M3, it trains the machine learning model M3 so that it outputs a simulation image in which each individually identified fish is replaced with a silhouette and the number of tails of the individually identified fish (the number of tails of the fish group).

[0058] In this way, when the generation unit 152 inputs the generated simulation image into the machine learning model, it trains the machine learning model to output correct data generated based on the parameter information used for generating the simulation image or information corresponding to the correct data.

[0059] (Estimation unit 153) The estimation unit 153 uses the trained machine learning model generated by the generation unit 152 to estimate information about the school of fish included in the captured image from the captured image of the school of fish. For example, the estimation unit 153 inputs the captured image into the trained machine learning model M2 generated by the generation unit 152. Then, the estimation unit 153 uses, as the estimation result, the captured image with the 2D bounding box added and the number of fish (the number of fish in the school of fish) for which individual identification has been performed, output from the machine learning model M2.

[0060] (Output control unit 154) The output control unit 154 controls to display the estimation result estimated by the estimation unit 153 on the screen. FIG. 17 is a diagram showing an example of a screen that outputs the estimation result of the captured image. In the example shown in FIG. 17, the output control unit 154 causes the screen to display, as the estimation result estimated by the estimation unit 153, the captured image with the 2D bounding box added and "251", which is the number of fish (the number of fish in the school of fish) for which individual identification has been performed.

[0061] [3. Effects] As described above, the information processing apparatus 100 according to the embodiment includes an acquisition unit 151 and a generation unit 152. The acquisition unit 151 acquires the value of the internal parameter related to the biological characteristics of the fish, the value of the external parameter related to the characteristics of the environment around the fish, and the value of the school parameter related to the characteristics of the group behavior, which is the behavior of the fish with respect to other fish. The generation unit 152 generates a simulation image including the behavior of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter acquired by the acquisition unit 151.

[0062] In this way, the information processing apparatus 100 can accurately reproduce the behavior of the fish school located in the actual fish cage in order to generate a simulation image including the behavior of the fish school based on the information regarding the biological characteristics of the fish, the information regarding the environment around the fish, and the information regarding the characteristics of the fish school behavior. Further, the information processing apparatus 100 can generate a large number of simulation images covering various patterns easily by changing the values of a plurality of parameters used for generating the simulation image. Further, since the information processing apparatus 100 can utilize the values of the parameters used for generating the simulation image as correct answer data, it can generate a large amount of high-quality training data easily as compared with the case where the correct answer data is given manually.

[0063] Thereby, the information processing apparatus 100 enables, for example, a machine learning model that estimates information (e.g., the number of fish) regarding the fish school from a captured image to learn a large amount of high-quality training data. That is, by having the machine learning model that estimates information (e.g., the number of fish) regarding the fish school from a captured image learn a large amount of high-quality training data, the information processing apparatus 100 can improve the estimation accuracy of the machine learning model. Therefore, the information processing apparatus 100 can accurately estimate the information regarding the fish school.

[0064] Further, the generation unit 152 generates a simulation image by controlling the behavior of each fish belonging to the fish school based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter.

[0065] As a result, the information processing apparatus 100 can accurately reproduce the behavior of each fish belonging to the fish school in the actual fish tank in order to control the behavior of each fish based on information regarding the biological characteristics of the fish, information regarding the environment around the fish, and information regarding the characteristics of the group behavior of the fish. Thereby, the information processing apparatus 100 enables, for example, a large amount of high-quality training data to be learned by a machine learning model that estimates information (e.g., the number of fish) regarding the fish school from a captured image.

[0066] Further, the generation unit 152 controls the behavior of each fish based on, as values of internal parameters, the length of time and the time interval required for each fish belonging to the fish school to make a decision to take each action.

[0067] As a result, the information processing apparatus 100 can accurately reproduce the behavior of each fish in order to control the behavior of each fish based on the length of time and the time interval required for an actual fish to make a decision to take each action.

[0068] Further, the generation unit 152 controls the behavior of each fish so that each fish heads toward a region of the water temperature that each fish prefers, based on, as a value of an internal parameter, the water temperature preferred by each fish belonging to the fish school.

[0069] As a result, the information processing apparatus 100 can accurately reproduce the behavior of each fish in the actual fish tank in order to control the behavior of each fish so as to exhibit behavior that reflects the actual ecology or habits of the fish.

[0070] Further, the generation unit 152 controls the behavior of each fish so that each fish heads toward a region of the water temperature that each fish prefers, based on, as a value of an external parameter, the distribution of the water temperature in the fish tank where each fish belonging to the fish school is located.

[0071] As a result, the information processing apparatus 100 can accurately reproduce the behavior of each fish in the actual fish tank in order to control the behavior of each fish so as to exhibit behavior that reflects the environment in the actual fish tank.

[0072] Further, the generation unit 152 controls the behavior of each fish belonging to the fish school so that the higher the water temperature around each fish belonging to the fish school is based on the distribution of the water temperature in the fish tank where each fish belonging to the fish school is located as the value of the internal parameter, the greater the movement speed of each fish becomes.

[0073] Thereby, since the information processing apparatus 100 controls the behavior of each fish so as to take actions reflecting the actual ecology or habits of the fish, it can accurately reproduce the behavior of each fish in the actual fish tank.

[0074] Further, the generation unit 152 controls the behavior of each fish so that each fish heads toward the region of the illuminance it prefers based on the illuminance preferred by each fish belonging to the fish school as the value of the internal parameter.

[0075] Thereby, since the information processing apparatus 100 controls the behavior of each fish so as to take actions reflecting the actual ecology or habits of the fish, it can accurately reproduce the behavior of each fish in the actual fish tank.

[0076] Further, the generation unit 152 controls the behavior of each fish so that each fish heads toward the region of the illuminance it prefers based on the distribution of the illuminance in the fish tank where each fish belonging to the fish school is located as the value of the external parameter.

[0077] Thereby, since the information processing apparatus 100 controls the behavior of each fish so as to take actions reflecting the environment in the actual fish tank, it can accurately reproduce the behavior of each fish in the actual fish tank.

[0078] Further, when the distance between each fish belonging to the fish school and an obstacle is equal to or less than a predetermined threshold value as the value of the internal parameter, the generation unit 152 controls the behavior of each fish so that each fish takes an avoidance action to avoid the obstacle.

[0079] Thereby, since the information processing apparatus 100 controls the behavior of each fish so as to take actions reflecting the actual ecology or habits of the fish, it can accurately reproduce the behavior of each fish in the actual fish tank.

[0080] Further, when the distance between each fish belonging to the fish school and an obstacle is equal to or less than a predetermined threshold value as the value of the internal parameter, the generation unit 152 controls the behavior of each fish based on the repulsive force acting on each fish.

[0081] Thereby, since the information processing apparatus 100 controls the behavior of each fish so as to take an action reflecting the actual ecology or habit of the fish, the behavior of each fish in the actual fish tank can be accurately reproduced.

[0082] Further, the generation unit 152 controls the behavior of each fish based on a repulsive force that is greater as the distance between each fish belonging to the fish school and an obstacle is smaller.

[0083] Thereby, since the information processing apparatus 100 controls the behavior of each fish so as to take an action reflecting the actual ecology or habit of the fish, the behavior of each fish in the actual fish tank can be accurately reproduced.

[0084] Further, as the value of the internal parameter, the generation unit 152 controls the behavior of each fish so that the moving speed of each fish increases as the body length of each fish belonging to the fish school increases.

[0085] Thereby, since the information processing apparatus 100 controls the behavior of each fish so as to take an action reflecting the actual ecology or habit of the fish, the behavior of each fish in the actual fish tank can be accurately reproduced.

[0086] Further, as the value of the school parameter, when another fish is located within a predetermined range from the position of each fish belonging to the fish school, the generation unit 152 controls the behavior of each fish so that each fish exhibits schooling behavior.

[0087] Thereby, since the information processing apparatus 100 controls the behavior of each fish so as to take an action reflecting the characteristics of the actual schooling behavior of the fish, the behavior of each fish in the actual fish tank can be accurately reproduced.

[0088] In addition, the generation unit 152 controls the behavior of each fish based on the cohesive force, which is the force that each fish belonging to the fish school tries to approach so as not to disperse, as the value of the school parameter.

[0089] As a result, the information processing apparatus 100 can accurately reproduce the behavior of each fish in an actual fish tank because it controls the behavior of each fish so as to take actions that reflect the characteristics of the actual fish school behavior.

[0090] In addition, the generation unit 152 controls the behavior of each fish based on the separation force, which is the force that each fish belonging to the fish school tries to move away to avoid collision, as the value of the school parameter.

[0091] As a result, the information processing apparatus 100 can accurately reproduce the behavior of each fish in an actual fish tank because it controls the behavior of each fish so as to take actions that reflect the characteristics of the actual fish school behavior.

[0092] In addition, the generation unit 152 controls the behavior of each fish based on the alignment force, which is the force that each fish belonging to the fish school tries to align the direction of movement as a school, as the value of the school parameter.

[0093] As a result, the information processing apparatus 100 can accurately reproduce the behavior of each fish in an actual fish tank because it controls the behavior of each fish so as to take actions that reflect the characteristics of the actual fish school behavior.

[0094] In addition, when the simulation image is input to the machine learning model, the generation unit 152 trains the machine learning model to output the correct data generated based on the parameter information used for generating the simulation image or the information corresponding to the correct data.

[0095] As a result, the information processing apparatus 100 can, for example, cause a machine learning model that estimates information (e.g., the number of fish) related to a school of fish from a captured image to learn a large amount of high-quality training data. That is, the information processing apparatus 100 can improve the estimation accuracy of a machine learning model that estimates information (e.g., the number of fish) related to a school of fish from a captured image by causing the model to learn a large amount of high-quality training data.

[0096] Further, the information processing apparatus 100 further includes an estimation unit 153. The estimation unit 153 estimates information related to the school of fish included in the captured image from the captured image of the school of fish using the learned machine learning model generated by the generation unit 152.

[0097] As a result, the information processing apparatus 100 can improve the estimation accuracy of a machine learning model that estimates information (e.g., the number of fish) related to a school of fish from a captured image by causing the model to learn a large amount of high-quality training data. Therefore, the information processing apparatus 100 can accurately estimate information related to a school of fish by using the learned machine learning model. In addition, since the information processing apparatus 100 can accurately estimate information related to a school of fish without directly touching the fish (non-contact) by using image recognition, the burden on the fish can be reduced. Further, the information processing apparatus 100 can obtain a highly accurate estimation result in a short time compared to the case where a person scoops up fish with a net by using image recognition.

[0098] [4. Hardware Configuration] Further, the information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. 18. FIG. 18 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing apparatus 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0099] The CPU 1100 operates based on programs stored in the ROM 1300 or the HDD 1400 and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs dependent on the hardware of the computer 1000, and the like.

[0100] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, and the like. The communication interface 1500 receives data from other devices via a predetermined communication network, sends it to the CPU 1100, and sends data generated by the CPU 1100 to other devices via a predetermined communication network.

[0101] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output devices via the input / output interface 1600.

[0102] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory or the like.

[0103] For example, when computer 1000 functions as information processing apparatus 100 according to an embodiment, CPU 1100 of computer 1000 realizes the functions of control unit 150 by executing a program loaded onto RAM 1200. Although CPU 1100 of computer 1000 reads and executes these programs from recording medium 1800, as another example, these programs may be acquired from another device via a predetermined communication network.

[0104] As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the column of the disclosure of the invention.

[0105] 〔5. Others〕 Also, among the respective processes described in the above embodiments and modification examples, all or part of the processes described as being automatically performed can be manually performed, or all or part of the processes described as being manually performed can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0106] Also, each component of each device shown in the drawings is a functional concept, and does not necessarily have to be physically configured as shown in the drawings. That is, the specific form of the dispersion and integration of each device is not limited to that shown in the drawings, and all or part of it can be functionally or physically dispersed and integrated in any unit according to various loads and usage situations.

[0107] Also, the above-described embodiments and modification examples can be appropriately combined as long as the processing contents do not conflict.

[0108] In addition, the "section, module, unit" described above can be read as "means", "circuit", etc. For example, the generation section can be read as a generation means or a generation circuit.

[0109] According to the present disclosure, it is possible to accurately estimate information related to a school of fish.

[0110] Although the present invention has been described with respect to specific embodiments for the purpose of complete and clear disclosure, the appended claims are not limited thereto, and should be construed as embodying all modifications and alternative configurations that can be conceived by those skilled in the art within the appropriate scope of the basic teachings of this specification.

Claims

1. An information processing method executed by a computer, comprising: an acquisition step of acquiring a value of an internal parameter related to a biological characteristic of a fish, a value of an external parameter related to a characteristic of the environment around the fish, and a value of a school parameter related to a characteristic of a group behavior which is an action taken by the fish with respect to other fish; a generation step of generating a simulation image including the actions of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter acquired in the acquisition step; wherein the generation step includes any one of a) to d) below: a) controlling the actions of each fish based on the length of time required for each fish belonging to the school of fish to make a decision to take each action and the interval of the time as the value of the internal parameter; b) controlling the actions of each fish so that each fish heads toward a region of a water temperature preferred by each fish based on the water temperature preferred by each fish belonging to the school of fish as the value of the internal parameter; c) controlling the actions of each fish so that the higher the water temperature around each fish belonging to the school of fish, the greater the movement speed of each fish based on the distribution of water temperature in the fish tank where each fish belonging to the school of fish is located as the value of the internal parameter; d) controlling the actions of each fish so that each fish heads toward a region of an illuminance preferred by each fish based on the illuminance preferred by each fish belonging to the school of fish as the value of the internal parameter; An information processing method characterized by the above.

2. An information processing method executed by a computer, comprising: an acquisition step of acquiring a value of an internal parameter related to a biological characteristic of a fish, a value of an external parameter related to a characteristic of the environment around the fish, and a value of a school parameter related to a characteristic of a group behavior which is an action taken by the fish with respect to other fish; a generation step of generating a simulation image including the actions of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter acquired in the acquisition step; wherein the generation step includes either a) or b) below: a) controlling the actions of each fish so that each fish heads toward a region of a water temperature preferred by each fish based on the distribution of water temperature in the fish tank where each fish belonging to the school of fish is located as the value of the external parameter; b) As the value of the external parameter, based on the illuminance distribution in the fish tank where each fish belonging to the school of fish is located, controlling the behavior of each fish so as to direct it towards the area of illuminance it prefers. An information processing method characterized by the above. **Claim 3** The generation step is as follows: Based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter, generating the simulation image by controlling the behavior of each fish belonging to the school of fish. The information processing method according to claim 1 or 2. **Claim 4** The generation step is as follows: As the value of the internal parameter, when the distance between each fish belonging to the school of fish and an obstacle is equal to or less than a predetermined threshold value, controlling the behavior of each fish so that each fish takes an avoidance behavior of avoiding the obstacle. The information processing method according to claim 1 or 2. **Claim 5** The generation step is as follows: As the value of the internal parameter, when the distance between each fish belonging to the school of fish and an obstacle is equal to or less than a predetermined threshold value, controlling the behavior of each fish based on the repulsive force acting on each fish. The information processing method according to claim 1 or 2. **Claim 6** The generation step is as follows: Based on the repulsive force that is greater as the distance between each fish belonging to the school of fish and an obstacle is smaller, controlling the behavior of each fish. The information processing method according to claim 5. **Claim 7** The generation step is as follows: As the value of the internal parameter, based on the body length of each fish belonging to the school of fish, controlling the behavior of each fish so that the moving speed of each fish increases as the body length increases. The information processing method according to claim 1 or 2. **Claim 8** The generation step is as follows: As the value of the school parameter, when there are other fish within a predetermined range from the position of each fish belonging to the school of fish, controlling the behavior of each fish so that each fish takes the group behavior. The information processing method according to claim 1 or 2. **Claim 9** The generation step is as follows: As the value of the school parameter, based on the binding force, which is a force that causes each fish belonging to the school of fish to approach so as not to separate from each other, controlling the behavior of each fish. The information processing method according to claim 1 or 2. **Claim 10** The generation step is as follows: As the value of the school parameter, based on the separation force, which is a force that causes each fish belonging to the school of fish to move away from each other to avoid collision, controlling the behavior of each fish. The information processing method according to claim 1 or 2. **Claim 11** The generation step is as follows: Based on the alignment force, which is the force that each fish belonging to the school of fish attempts to align the direction of movement as a school, as the value of the school parameter, controlling the behavior of each fish. The information processing method according to claim 1 or 2.

12. The generation step includes When the simulation image is input into the machine learning model, training the machine learning model to output correct data generated based on the parameter information used for generating the simulation image or information corresponding to the correct data. The information processing method according to claim 1 or 2.

13. Further comprising an estimation step of estimating information regarding the school of fish included in the captured image from the captured image of the school of fish using the trained machine learning model generated by the generation step. The information processing method according to claim 12.

14. An acquisition procedure for acquiring the value of the internal parameter regarding the biological characteristics of the fish, the value of the external parameter regarding the characteristics of the environment around the fish, and the value of the school parameter regarding the characteristics of the group behavior, which is the behavior of the fish towards other fish. A generation procedure for generating a simulation image including the behavior of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter acquired by the acquisition procedure. A non-transitory computer-readable storage medium storing an information processing program for causing a computer to execute the following: The generation procedure includes any one of the following a) to d): a) Based on the length of time required for each fish belonging to the school of fish to make a decision to take each action and the interval of the time, as the value of the internal parameter, controlling the behavior of each fish. b) Based on the water temperature preferred by each fish belonging to the school of fish, as the value of the internal parameter, controlling the behavior of each fish so that each fish heads towards the region of the preferred water temperature. c) Based on the distribution of water temperature in the fish tank where each fish belonging to the school of fish is located, as the value of the internal parameter, controlling the behavior of each fish so that the higher the water temperature around each fish belonging to the school of fish, the greater the movement speed of each fish. d) Based on the illuminance preferred by each fish belonging to the school of fish, as the value of the internal parameter, controlling the behavior of each fish so that each fish heads towards the region of the preferred illuminance. Non-transitory computer-readable storage medium.

15. An acquisition procedure for acquiring a value of an internal parameter related to a biological characteristic of a fish, a value of an external parameter related to a characteristic of the environment around the fish, and a value of a school parameter related to a characteristic of shoaling behavior, which is the behavior of the fish towards other fish; A generation procedure for generating a simulation image including the behavior of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter acquired by the acquisition procedure; A non-transitory computer-readable storage medium storing an information processing program for causing a computer to execute; The generation procedure includes either a) or b) below: a) As the value of the external parameter, based on the water temperature distribution in the fish tank where each fish belonging to the school of fish is located, controlling the behavior of each fish so that each fish moves towards the region of the water temperature it prefers; b) As the value of the external parameter, based on the illuminance distribution in the fish tank where each fish belonging to the school of fish is located, controlling the behavior of each fish so that each fish moves towards the region of the illuminance it prefers; A non-transitory computer-readable storage medium.

16. An acquisition unit for acquiring a value of an internal parameter related to a biological characteristic of a fish, a value of an external parameter related to a characteristic of the environment around the fish, and a value of a school parameter related to a characteristic of shoaling behavior, which is the behavior of the fish towards other fish; A generation unit for generating a simulation image including the behavior of each fish belonging to the school of fish based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter acquired by the acquisition unit; Comprising: The generation unit includes any one of a) to d) below: a) As the value of the internal parameter, based on the length of time required for each fish belonging to the school of fish to make a decision to take each action and the interval of the time, controlling the behavior of each fish; b) As the value of the internal parameter, based on the water temperature preferred by each fish belonging to the school of fish, controlling the behavior of each fish so that each fish moves towards the region of the water temperature it prefers; c) As the value of the internal parameter, based on the water temperature distribution in the fish tank where each fish belonging to the school of fish is located, controlling the behavior of each fish so that the higher the water temperature around each fish belonging to the school of fish, the greater the moving speed of each fish; d) Based on the illuminance preferred by each fish belonging to the fish school as the value of the internal parameter, controlling the behavior of each fish so as to move towards the region of the illuminance preferred by each fish. An information processing apparatus. According to claim 17, an acquisition unit that acquires a value of an internal parameter related to a biological characteristic of a fish, a value of an external parameter related to a characteristic of the environment around the fish, and a value of a school parameter related to a characteristic of a school behavior that is the behavior of the fish towards other fish; A generation unit that generates a simulation image including the behavior of each fish belonging to the fish school based on the value of the internal parameter, the value of the external parameter, and the value of the school parameter acquired by the acquisition unit; An information processing apparatus comprising: The generation unit includes either a) or b) below: a) Based on the water temperature distribution in the fish tank where each fish belonging to the fish school is located as the value of the external parameter, controlling the behavior of each fish so as to move towards the region of the water temperature preferred by each fish. b) Based on the illuminance distribution in the fish tank where each fish belonging to the fish school is located as the value of the external parameter, controlling the behavior of each fish so as to move towards the region of the illuminance preferred by each fish. An information processing apparatus.

Images