Evaluation device and evaluation method

Abstract

To evaluate the swimming state of an organism to be cultured in detail.SOLUTION: An evaluation device (5) includes: a central specification part (31) that specifies the center of the orbit of a cultured fish being an organism to be cultured from a moving image that captures at least a part of the range in which the cultured fish is swimming; a speed specification part (32) which specifies the swimming speed of the cultured fish from the moving image; a calculation part (33) that calculates a representative value of the swimming speed for each of a plurality of division areas obtained by dividing an evaluation target area where the swimming speed is within a prescribed range around the center according to a distance from the center; and an evaluation part (34) that evaluates the swimming state of the cultured fish on the basis of the representative value for each division area.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an evaluation device for evaluating the swimming state of cultured organisms in land-based aquaculture. [Background technology]

[0002] In land-based aquaculture of fish and shellfish, the cultured organisms are made to swim against a water current generated in an aquarium, and their swimming behavior is monitored to determine feeding timing, abnormal behavior, etc. For example, Patent Document 1, which differs from land-based aquaculture, describes monitoring the condition of aquatic organisms for water quality monitoring, in which water quality is determined based on the area in which photographed aquatic organisms are swimming. Aquatic organisms swim against the rotating water current, and live, calm aquatic organisms are often found in the middle area excluding the outer and central areas, while abnormal aquatic organisms are often found in the outer or central area. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2-242154 Summary of the Invention [Problem to be solved by the invention]

[0004] Even in the intermediate area, the swimming behavior, such as speed, of aquatic organisms may vary. However, the monitoring method described in Patent Document 1 cannot evaluate the swimming behavior of aquatic organisms in the intermediate area in more detail.

[0005] One aspect of the present invention aims to evaluate in detail the swimming state of cultured organisms. [Means for solving the problem]

[0006] In order to solve the above problems, an evaluation device according to one embodiment of the present invention comprises a center identification unit that identifies the center of the circular orbit in which the cultivated organism swims from a video image capturing at least a portion of the area in which the cultivated organism swims; a speed identification unit that identifies the swimming speed of the cultivated organism from the video image; a calculation unit that calculates a representative value of the swimming speed for each of a plurality of divided areas obtained by dividing the evaluation area around the center within which the swimming speed is within a predetermined range according to the distance from the center; and an evaluation unit that evaluates the swimming state of the cultivated organism for each divided area based on the representative value.

[0007] In order to solve the above problems, an evaluation method according to one embodiment of the present invention includes a center identification step of identifying the center of the circular orbit in which the cultivated organism swims from a video image capturing at least a portion of the area in which the cultivated organism swims; a speed identification step of identifying the swimming speed of the cultivated organism from the video image; a calculation step of calculating a representative value of the swimming speed for each of a plurality of divided areas obtained by dividing an evaluation area around the center within which the swimming speed is within a predetermined range according to the distance from the center; and an evaluation step of evaluating the swimming state of the cultivated organism for each of the divided areas based on the representative value. [Effects of the Invention]

[0008] According to one aspect of the present invention, the swimming state of cultured organisms can be evaluated in detail. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram showing a schematic configuration of an aquaculture facility according to one embodiment of the present invention. FIG. [Figure 2] FIG. 2 is a block diagram showing the system configuration of the aquaculture facility. [Figure 3] 10 is a flowchart showing a procedure for a process of evaluating the swimming state of fish by the evaluation device in the aquaculture facility. [Figure 4] 4 is a flowchart specifically showing a center identification process in the processing procedure shown in FIG. 3. [Figure 5]4 is a flowchart specifically illustrating a representative value calculation process in the procedure of the process shown in FIG. 3. [Figure 6] FIG. 2 is a diagram showing fish swimming in a tank in the aquaculture facility. [Figure 7] FIG. 2 is a diagram showing the fish swimming in the aquarium divided into regions. [Figure 8] FIG. 8 is a diagram showing a state in which the intermediate region shown in FIG. 7 is further divided. [Figure 9] FIG. 10 is a diagram showing another state in which the fish swimming in the aquarium are divided into regions. [Figure 10] 10 is a graph showing changes in swimming speed in one segment of an evaluation target area that is the target of evaluation of swimming conditions by the evaluation device. [Figure 11] 10 is a graph showing changes in swimming speed in other divided areas in the evaluation target area that is the target for evaluation of swimming conditions by the evaluation device. [Figure 12] 10 is a graph showing changes in swimming speed in still another divided area in the evaluation target area that is the target for evaluation of swimming conditions by the evaluation device. [Figure 13] FIG. 2 is a block diagram showing a configuration of the evaluation device according to a first modified example of the embodiment. [Figure 14] FIG. 10 is a block diagram showing the configuration of the evaluation device according to a second modified example of the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] [Configuration of aquaculture facilities] The configuration of an aquaculture facility according to one embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a diagram showing the schematic configuration of the aquaculture facility.

[0011] As shown in Figure 1, the aquaculture facility 100 is a facility for conducting closed-circulation land-based aquaculture. Closed-circulation land-based aquaculture is a farming method that uses a filtration system to purify the rearing water while circulating it. The aquaculture facility 100 is applicable to the rearing of aquatic organisms, particularly seafood other than shellfish. Examples of species that can be reared in the aquaculture facility 100 include mackerel and salmon, which are migratory fish that swim against the water current.

[0012] The aquaculture facility 100 may be configured as a free-flowing land-based aquaculture facility that continuously draws in seawater or the like from the natural environment and uses it as rearing water. In such a configuration, the water treatment device 4 described below is omitted.

[0013] The aquaculture facility 100 includes an aquarium 1, a camera 2, a feeding device 3, a water treatment device 4, an evaluation device 5, a control device 6, and a terminal device 7.

[0014] The aquarium 1 can store water (freshwater, seawater, brackish water, etc.) suitable for the fish F (cultured organisms) to be cultured. The culture environment in the aquarium 1 is set according to the type of fish F, the growth stage of the fish F, etc. The aquarium 1 may be installed either indoors or outdoors. The aquarium 1 shown in FIG. 1 has a cylindrical shape, but its shape and size are not particularly limited.

[0015] The camera 2 captures images of the aquarium 1 from above and transmits the captured video (video data) to the evaluation device 5. The video shows a planar view of the water surface of the aquarium 1 and captures at least a portion of the area in which the fish F swims. Specifically, the capture range R captured by the camera 2 may be part or the entire swimming range of the fish F, as shown in FIG. 1. When capturing a portion of the swimming range, the camera 2 may have a fixed capture position, or may be configured to track the center of the orbital path of the fish F using an operating mechanism. The cameras 2 may be installed or set so that the center of the orbital path is always captured in the video captured by one or more cameras 2. The cameras 2 may also be configured to capture an area in the aquarium 1 that is different from the capture range R.

[0016] The camera 2 may be a device capable of capturing images of an object in both the visible light region and the infrared light region. In the aquaculture facility 100, the lights may be turned off at night. Therefore, the camera 2 may capture visible images during the day and infrared images at night. Image processing (described later) in the evaluation device 5 may be performed without distinguishing between visible images and infrared images.

[0017] Feeding device 3 is installed above aquarium 1 and supplies food to aquarium 1. Feeding device 3 normally starts and stops feeding a fixed amount of food at a preset time without being controlled by control device 6. However, when feeding device 3 receives a command from control device 6, it will start and stop feeding and / or adjust the amount of food based on that command, giving priority over normal feeding operations.

[0018] Water treatment device 4 is a device that performs filtration, denitrification, sterilization, and other processes to purify the water in aquarium 1. Water treatment device 4 purifies the water discharged from the drain outlet of aquarium 1, and then supplies the water to aquarium 1 through the water inlet of aquarium 1. The water inlet is located on the outer peripheral wall of aquarium 1 at a position that allows water to be supplied into aquarium 1 in a tangential direction to the circular outer peripheral wall. The drain outlet is located on the opposite side of the outer peripheral wall from the water inlet, at a position that allows water to be discharged from aquarium 1 in a tangential direction to the outer peripheral wall. This generates a rotating water current in aquarium 1.

[0019] The evaluation device 5 is a device that evaluates the swimming state of the fish F based on the moving images captured by the camera 2. The evaluation device 5 will be described in detail later.

[0020] The control device 6 controls the operation of the feeding device 3, and also acquires data from various sensors placed in the aquarium 1 to control the operation of the water treatment device 4 so as to maintain the aquaculture environment. The control device 6 will be described in detail later.

[0021] The terminal device 7 acquires the evaluation data accumulated by the evaluation device 5 and displays it so that it can be viewed. Furthermore, the terminal device 7 performs processes such as creating graphs and statistical data based on the evaluation data.

[0022] [Details of evaluation device and control device] The evaluation device 5 and the control device 6 will be described in more detail below. FIG. 2 is a block diagram showing the system configuration of the aquaculture facility 100.

[0023] As shown in FIG. 2, the evaluation device 5 includes a center specifying unit 51, a speed specifying unit 52, a calculation unit 53, an evaluation unit 54, a storage unit 55, and an output unit 56.

[0024] The center identifying unit 51 identifies the center of the orbit in which the fish F swims from a moving image captured by the camera 2, with at least a part of the area in which the fish F swims as the imaging range R. If the center of the orbit is included in the imaging range R, the center identifying unit 51 identifies the center by image recognition.

[0025] Here, the migratory fish F has the property of swimming against the water current. Therefore, the fish F swims in an orbit in the aquarium 1 in the opposite direction to the water current. Furthermore, the fish F does not always swim in a fixed orbit, but may swim in a fluctuating orbit, for example, when feeding. When the camera 2 captures a part of the swimming range of the fish F as the capture range R, even if the orbit fluctuates and the center is not included in the moving image captured by the camera 2, the center identification unit 51 can estimate and identify the center.

[0026] The center identifying unit 51 sets a predetermined coordinate system in a plan view of the aquarium 1 that defines the swimming range of the fish F, and determines and outputs the coordinates of the identified center in the coordinate system.

[0027] The speed identification unit 52 identifies the swimming speed of the fish F from the above-mentioned moving image captured by the camera 2. The speed identification unit 52 identifies the swimming speed using, for example, optical flow. Specifically, the speed identification unit 52 determines the amount of movement for a specific pixel of the fish F from the above-mentioned two-dimensional vector, and identifies the swimming speed by dividing the amount of movement by the time between two frames. The speed identification unit 52 may also determine the amount of movement of the fish F and identify the swimming speed using a known technique other than optical flow, such as a moving object detection method such as an inter-frame difference method.

[0028] The calculation unit 53 calculates a representative value of the swimming speed for each of a plurality of divided regions obtained by dividing the evaluation target region around the center identified by the center identification unit 51, in which the swimming speed identified by the speed identification unit 52 is within a predetermined range, according to the distance from the center. As the representative value of the swimming speed, a moving average, a median, or the like is used.

[0029] The swimming speed of the fish F tends to be distributed differently among a central region near the center of the orbit, an outer peripheral region farthest from the center, and an intermediate region between the central region and the outer peripheral region. Since the fish F generally swims most actively in the intermediate region, the calculation unit 53 calculates a representative value of the swimming speed by using the intermediate region as the evaluation target region. The division regions of the evaluation target region will be explained in detail later.

[0030] The evaluation unit 54 evaluates the swimming state of the fish F for each of the above-mentioned divided areas based on the representative value of the swimming speed calculated by the calculation unit 53. Specifically, the evaluation unit 54 performs the evaluation based on the magnitude relationship between the threshold value of the representative value set for each divided area and the calculated representative value. The evaluation unit 54 outputs the evaluation result as evaluation data.

[0031] The storage unit 55 stores the evaluation data output from the evaluation unit 34 in an accumulated manner.

[0032] The output unit 56 outputs the evaluation data stored in the storage unit 55 in a format that can be viewed by the terminal device 7 in response to a request from the terminal device 7. The output unit 56 may also output the evaluation data output from the evaluation unit 54 in a format that can be viewed by the terminal device 7 immediately.

[0033] The control device 6 has a feeding control unit 61 and a water treatment control unit 62.

[0034] If the representative value calculated by the calculation unit 53 is less than the threshold value for each divided area, the feeding control unit 61 controls the feeding device 3 to reduce the amount of feed fed to the fish F from the current amount.

[0035] The water treatment control unit 62 controls the water treatment device 4 by using the evaluation data from the evaluation unit 54 as a reference index as needed. For example, if the evaluation indicates that the swimming condition is extremely poor, deterioration of the water quality is suspected. In this case, the water treatment control unit 62 controls the water treatment device 4 by referring to the evaluation.

[0036] [Evaluation of swimming speed using evaluation device] A method for evaluating swimming speed using the evaluation device 5 will be described in detail. Fig. 3 is a flowchart showing the processing steps for evaluating the swimming state of fish F using the evaluation device 5. Fig. 4 is a flowchart specifically showing the center identification processing in the processing steps shown in Fig. 3. Fig. 5 is a flowchart specifically showing the representative value calculation processing in the processing steps shown in Fig. 3.

[0037] 3, first, the center identifying unit 51 identifies the center of the orbit from a video image captured by the camera 2, capturing at least a part of the area in which the fish F is swimming (step S1, center identifying step). Next, the speed identifying unit 52 identifies the swimming speed of the fish F from the video image captured by the camera 2 (step S2, speed identifying step).

[0038] Note that the process of step S2 is not limited to being performed after the process of step S1, and the processes of steps S1 and S2 may be performed simultaneously, or the process of step S2 may be performed before the process of step S1.

[0039] Once the center and swimming speed are identified, the calculation unit 53 calculates a representative value of the swimming speed for each of a plurality of divided regions around the center, which are obtained by dividing the evaluation target region according to the distance from the center (step S3, calculation step). Furthermore, the evaluation unit 54 evaluates the swimming state of the fish F based on the calculated representative value for each divided region (step S4, evaluation step).

[0040] Next, the center identification process of step S1 will be described in detail. As shown in Fig. 4, center identification unit 51 determines whether or not the moving image from camera 2 includes the center of the orbit (step S11). If center identification unit 51 determines in step S11 that the moving image includes the center of the orbit (YES), it identifies the center of the orbit based on the moving image (step S12), and returns the process to the main routine shown in Fig. 3.

[0041] In identifying the center based on the video, the center identification unit 51 uses object detection processing utilizing deep learning or the like to detect the center of the school of fish from the video of the fish F migrating in concentric orbits, thereby identifying the inside of the smallest orbit as the center. Here, well-known technologies for object detection processing include YOLO (Your Only Look Once) and SSD (Single Shot Multibox Detector).

[0042] If the center identification unit 51 determines in step S11 that the video does not include the center of the orbit (NO), it creates a vector of the fish F from the video (step S13). The center identification unit 51 uses an optical flow method to create the vector of the fish F. Specifically, the center identification unit 51 focuses on a specific pixel of the fish F in the video, estimates the optical flow between two consecutive frames for that pixel, and represents the movement of the fish between the two frames as a two-dimensional vector.

[0043] Next, the center identifying unit 51 identifies the center of the orbit based on the vector (step S14), and returns the process to the main routine shown in Fig. 3. In identifying the center, the center identifying unit 51 finds the center of the orbit from the radius of curvature of a circle or arc connecting the multiple vectors according to the elapsed time found in the process of step S13.

[0044] Next, the representative value calculation process of step S3 will be described in detail. As shown in Fig. 5, calculation unit 53 determines whether the swimming speed (representative value) identified by speed identification unit 52 is higher than a first threshold value (step S41). If calculation unit 53 determines in step S41 that the swimming speed is higher than the first threshold value (YES), it further determines whether the swimming speed is lower than a second threshold value (step S42). Here, the first threshold value is lower than the second threshold value.

[0045] If it is determined in step S42 that the swimming speed is lower than the second threshold (YES), calculation unit 53 divides the swimming speed into the above-mentioned intermediate regions (step S43) and identifies the intermediate regions as regions to be evaluated for swimming speed (step S44). Then, calculation unit 53 calculates a representative value of the swimming speed for each of the above-mentioned divided regions for the regions to be evaluated (step S45), and returns the process to the main routine shown in FIG.

[0046] Furthermore, when it is determined in step S41 that the swimming speed is not higher than the first threshold (NO), calculation unit 53 classifies the swimming speed into the central region described above (step S46). Then, calculation unit 53 specifies the central region as an area outside the scope of swimming speed evaluation (step S47), and returns the process to the main routine shown in FIG. 3 without calculating a representative value of swimming speed for the area outside the scope of evaluation.

[0047] Furthermore, when it is determined in step S42 that the swimming speed is not lower than the second threshold (NO), calculation unit 53 divides the swimming speed into the outer circumferential regions described above (step S48), and proceeds to the process of step S47.

[0048] [Examples of swimming speed classifications] Specific examples of classification of swimming speed by the evaluation device 5 will be described in detail. Fig. 6 is a diagram showing a state in which a fish F swims in the aquarium 1. Fig. 7 is a diagram showing a state in which the fish F swimming in the aquarium 1 is classified into each region. Fig. 8 is a diagram showing a state in which the intermediate region A3 shown in Fig. 7 is further classified. Fig. 9 is a diagram showing another state in which the fish F swimming in the aquarium 1 is classified into each region.

[0049] As shown in Fig. 6, the fish F is swimming in the direction indicated by the arrow. In this state, the center O of the orbit of the fish F is included in the shooting range R, which is a rectangle indicated by a two-dot chain line in Fig. 6. This allows the center identifying unit 51 to identify the center O of the orbit of the fish F from the moving image. The speed identifying unit 52 identifies the swimming speeds of all fish F that can be distinguished from the moving image.

[0050] As shown in FIG. 7, the calculation unit 53 divides the swimming speed of the identified fish F into a central region A1, an outer peripheral region A2, and an intermediate region A3 by the above-described steps S41 to S43, S46, and S48, and identifies the intermediate region A3 as an evaluation target region. Here, the central region A1 is a circular region including the center O. The outer peripheral region A2 is an annular region near the inner peripheral wall of the water tank 1 that is farthest from the center O. The intermediate region A3 is an annular region sandwiched between the central region A1 and the outer peripheral region A2. The central region A1, the outer peripheral region A2, and the intermediate region A3 form a substantially circular shape.

[0051] As shown in FIG. 8, the calculation unit 53 divides the intermediate region A3 into three divided regions A31 to A33 according to the distance from the center O. The divided region A31 is an annular region having a width between the position of the outer periphery of the central region A1 on the innermost peripheral side in the intermediate region A3 and the position separated from the center O by a distance D1. The divided region A32 is an annular region having a width between the position separated from the center O by a distance D1 and the position separated from the center O by a distance D2 in the middle of the intermediate region A3. The divided region A33 is an annular region having a width between the position separated from the center O by a distance D2 and the position separated from the center O by a distance D3 on the outer peripheral side in the intermediate region A3. Here, the distances D1, D2, and D3 have a relationship of D1 < D2 < D3.

[0052] Incidentally, when feeding is performed by the feeding device 3 in the feeding region FD indicated by the dashed-dotted line in FIG. 9, the fish F swims so as to approach the feeding region FD. For this reason, the center O also approaches the feeding region FD, so that the circular orbit is deformed into an elliptical shape. Along with the deformation of the circular orbit, the central region A1, the outer peripheral region A2, and the intermediate region A3 are also deformed into an elliptical shape. In this case, the respective areas of the central region A1, the outer peripheral region A2, and the intermediate region A3 do not change significantly compared to the respective areas of the circular central region A1, the outer peripheral region A2, and the intermediate region A3 shown in FIG. 8.

[0053] In the case shown in Fig. 9, the calculation unit 53 divides the intermediate region A3 into divided regions A31 to A33 in the same manner as in the case shown in Fig. 8. However, in the case shown in Fig. 9, the distances D1 to D3 are different from those in the case shown in Fig. 8, and therefore, based on the widest width of the intermediate region A3, the distances D1 to D3 are determined in the part having that width.

[0054] 8 and 9, the intermediate region A3 is divided into annular divided regions A31 to A33, but the present invention is not limited to this example. For example, the intermediate region A3 may be divided to the left and right of the center O, or may be divided into a grid pattern regardless of the distance from the center O.

[0055] [Specific example of evaluation of swimming speed] A specific example of evaluation of swimming speed by the evaluation device 5 will be described in detail. Fig. 10 is a graph showing changes in swimming speed in one segment in the evaluation target area that is the subject of evaluation of swimming status by the evaluation device 5. Fig. 11 is a graph showing changes in swimming speed in another segment in the evaluation target area. Fig. 12 is a graph showing changes in swimming speed in yet another segment in the evaluation target area.

[0056] 10, the evaluation unit 54 compares the moving average (average speed) of the swimming speed in the segmented area A31 with a predetermined threshold Th1 set for the segmented area A31. Then, the evaluation unit 54 evaluates the swimming state of the fish F swimming in the segmented area A31 based on the magnitude relationship between the moving average value in the segmented area A31 and the threshold Th1.

[0057] Specifically, the evaluation unit 54 evaluates the swimming condition as good when the moving average is equal to or greater than the threshold value Th1, and evaluates the swimming condition as poor when the moving average is less than the threshold value Th1. Alternatively, depending on the setting of the threshold value Th1, the evaluation unit 54 may evaluate the swimming condition as poor when the moving average is equal to or greater than the threshold value Th1, and evaluate the swimming condition as good when the moving average is less than the threshold value Th1.

[0058] 11, the evaluation unit 54 compares the moving average (average speed) of the swimming speed in the segmented area A32 with a predetermined threshold Th2 set for the segmented area A32. Then, the evaluation unit 54 evaluates the swimming state of the fish F swimming in the segmented area A32 based on the magnitude relationship between the moving average value in the segmented area A32 and the threshold Th2.

[0059] Specifically, the evaluation unit 54 evaluates the swimming condition as good when the moving average is equal to or greater than the threshold value Th2, and evaluates the swimming condition as poor when the moving average is less than the threshold value Th2. Alternatively, depending on the setting of the threshold value Th2, the evaluation unit 54 may evaluate the swimming condition as poor when the moving average is equal to or greater than the threshold value Th2, and evaluate the swimming condition as good when the moving average is less than the threshold value Th2.

[0060] 12, the evaluation unit 54 compares the moving average (average speed) of the swimming speed in the segmented area A33 with a predetermined threshold Th3 set for the segmented area A33. Then, the evaluation unit 54 evaluates the swimming state of the fish F swimming in the segmented area A33 based on the magnitude relationship between the moving average value in the segmented area A33 and the threshold Th3.

[0061] Specifically, the evaluation unit 54 evaluates the swimming condition as good when the moving average is equal to or greater than the threshold value Th3, and evaluates the swimming condition as poor when the moving average is less than the threshold value Th3. Alternatively, depending on the setting of the threshold value Th3, the evaluation unit 54 may evaluate the swimming condition as poor when the moving average is equal to or greater than the threshold value Th3, and evaluate the swimming condition as good when the moving average is less than the threshold value Th3.

[0062] In the intermediate region A3, since swimming speeds may differ among the segmented regions A31 to A33, it is preferable to set threshold values ​​Th1 to Th3 independently for each of the segmented regions A31 to A33. For example, threshold value Th1 may be set higher in segmented region A31, and threshold value Th2 may be set lower in segmented region A32.

[0063] Incidentally, from a long-term perspective, such as one year, it is necessary to evaluate whether there are any problems with growth or water quality. Aquarium 1 tends to be densely populated, containing tens of thousands of fish F. For this reason, depending on the feeding method, the CO2 concentration in Aquarium 1 may rise, causing the growth of fish F to stagnate. Signs of this growth stagnation can be detected by evaluating the swimming behavior.

[0064] In aquaculture, fish F are raised from fry for several months before being shipped. Since it is important that fish F be raised to a large, consistent size at the time of shipping, stunted growth is a problem. Therefore, evaluation of swimming behavior can be used to detect growth stagnation and abnormalities early on, which is expected to help solve the problem.

[0065] [Feeding control based on evaluation] Fish F tend to have a slower swimming speed when they are full. Therefore, if any one of the moving averages in the divided areas A31 to A33 is less than the corresponding threshold value Th1 to Th3, the feeding control unit 61 of the control device 6 issues a command to the feeding device 3 to reduce the amount of feed from normal.

[0066] In this way, overfeeding can be prevented by reducing the amount of feed in accordance with the slowing of the swimming speed of the fish F. This makes it possible to reduce feeding costs.

[0067] [Variation 1] Next, a first modification of this embodiment will be described. Fig. 13 is a block diagram showing the configuration of an evaluation device 5 according to the first modification of this embodiment.

[0068] 13, the evaluation device 5 according to the first modification is configured by further including a determination unit 57 in addition to the components of the evaluation device 5 shown in FIG. The determination unit 57 determines whether or not there is an abnormality in the fish F based on the amount of change per unit period in the representative value of the swimming speed for each of the divided areas A31 to A33, which is acquired from the calculation unit 53.

[0069] When the culture environment, such as the circulation of water in the aquarium 1, is not appropriate, the fish F may exhibit abnormal behavior, such as a sudden change in swimming speed. For this reason, the evaluation unit 54 can evaluate the swimming state based on the determination result by the determination unit 57, for example, depending on whether or not there is an abnormality in the moving average (average speed) for each unit period shown in Figures 10 to 12.

[0070] [Variation 2] Next, a second modification of this embodiment will be described below. Fig. 14 is a block diagram showing the configuration of an evaluation device 5 according to the second modification of this embodiment.

[0071] As shown in Fig. 14, the evaluation device 5 according to the second modification is configured by further adding a generation unit 58 and a determination unit 59 to the evaluation device 5 shown in Fig. 2. The generation unit 58 generates vectors indicating the swimming direction of the fish F from the video image captured by the camera 2 using the optical flow described above or the like. The determination unit 59 determines whether or not there is an abnormality in the fish F depending on the number of vectors that do not follow the circular orbit among the generated vectors.

[0072] The evaluation unit 54 performs evaluation according to the result of the determination by the determination unit 59. Specifically, the evaluation unit 54 evaluates the swimming state of the moving average (average speed) shown in Figures 10 to 12 in combination with the presence or absence of an abnormality. For example, even if the moving average of the swimming speed of the divided area A31 shown in Figure 10 is equal to or greater than the threshold value Th1, if the determination by the determination unit 59 is abnormal, the evaluation unit 54 evaluates the swimming state as having a good speed but an abnormal movement.

[0073] When the culture environment, such as water circulation, is not appropriate, the fish F may exhibit abnormal behavior, such as swimming in a direction that does not follow the orbital path. Therefore, by determining whether or not there is an abnormality in the fish F based on the number of vectors that do not follow the orbital path, the swimming state can be evaluated based on the results.

[0074] [Contribution to SDGs] According to the configuration of the above-described embodiment, the aquaculture facility 100 is equipped with the evaluation device 5, which allows for detailed evaluation of the swimming state of the fish F, thereby improving the efficiency of aquaculture. If this results in an increase in the shipping volume of farmed fish, it can contribute to controlling overfishing of wild fish. Therefore, it can contribute to achieving Goal 14 of the Sustainable Development Goals (SDGs), "Conserve and sustainably use the oceans and seas (related to plastic-free agriculture, forestry, and fisheries)."

[0075] [Software implementation example] The functions of the evaluation device 5 (hereinafter referred to as the "device") can be realized by a program for causing a computer to function as the device. The program causes a computer to function as each block of the device (particularly, the center identification unit 51, the velocity identification unit 52, the calculation unit 53, the evaluation unit 54, the determination units 57 and 59, and the generation unit 58).

[0076] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. By executing the program using the control device and storage device, each function described in the above embodiment is realized.

[0077] The program may be non-transitory and may be recorded on one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0078] Furthermore, some or all of the functions of the control blocks can be realized by logic circuits. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of the control blocks can also be realized by, for example, a quantum computer.

[0079] Furthermore, each process described in the above embodiment may be executed by AI (Artificial Intelligence). In this case, the AI ​​may run on the control device or on another device (for example, an edge computer or a cloud server).

[0080] 〔summary〕 As described above, the evaluation device of aspect 1 of the present invention comprises a center identification unit that identifies the center of the circular orbit in which the cultured organism swims from a moving image that captures at least a portion of the area in which the cultured organism swims; a speed identification unit that identifies the swimming speed of the cultured organism from the moving image; a calculation unit that calculates a representative value of the swimming speed for each of a plurality of divided areas obtained by dividing the evaluation area around the center within which the swimming speed is within a predetermined range according to the distance from the center; and an evaluation unit that evaluates the swimming state of the cultured organism for each divided area based on the representative value.

[0081] According to the above configuration, the swimming state of the cultured organisms can be evaluated for each divided area. This allows for a more detailed evaluation of the swimming state of the cultured organisms compared to conventional evaluation methods. Based on the evaluation results, the aquaculture manager can be given an opportunity to improve the aquaculture environment.

[0082] In addition, by speeding up the evaluation cycle, aquaculture managers can maintain a stable aquaculture environment, which in turn reduces poor growth and sudden death of cultivated organisms and promotes good growth.

[0083] In the evaluation device according to aspect 2 of the present invention, in the above aspect 1, the evaluation unit may perform the evaluation based on the magnitude relationship between a threshold value of the representative value set for each divided area and the calculated representative value.

[0084] According to the above configuration, in each divided area, for example, if the representative value is equal to or greater than a threshold value, the swimming condition can be evaluated as good, and if the representative value is less than the threshold value, the swimming condition can be evaluated as poor.

[0085] The evaluation device of aspect 3 of the present invention may further include a feeding control unit that, in aspect 2 above, controls the amount of feed given to the cultivated organisms to be reduced from the current amount if the representative value is less than the threshold value.

[0086] Cultivated organisms tend to have a slower swimming speed when full. With the above configuration, the amount of feed can be reduced in response to a decrease in the swimming speed of the cultivated organisms, thereby preventing overfeeding and reducing feeding costs.

[0087] The evaluation device of aspect 4 of the present invention, in any of aspects 1 to 3 above, may further include a judgment unit that judges whether or not there is an abnormality in the cultivated organism based on the change in the representative value per unit period, and the evaluation unit may perform the evaluation based on the result of the judgment.

[0088] When the culture environment, such as water circulation, is not optimal, the cultured organisms may exhibit abnormal behavior, such as a sudden change in swimming speed. With the above configuration, the presence or absence of abnormalities in the cultured organisms can be determined based on the amount of change per unit period in the representative value, and the swimming state can be evaluated based on the result.

[0089] The evaluation device of aspect 5 of the present invention, in any of aspects 1 to 4 above, further comprises a generation unit that generates a vector indicating the swimming direction of the cultivated organism from the moving image, and a judgment unit that determines whether or not there is an abnormality in the cultivated organism based on the number of vectors that do not follow the circular orbit, and the evaluation unit may perform the evaluation based on the result of the judgment.

[0090] When the culture environment, such as water circulation, is not optimal, the cultured organisms may exhibit abnormal behavior, such as swimming in a direction that does not follow their orbit. With the above configuration, the presence or absence of abnormalities in the cultured organisms can be determined based on the number of vectors that do not follow their orbit, and the swimming state can be evaluated based on the results.

[0091] The evaluation method of aspect 6 of the present invention includes a center identification step of identifying the center of the circular orbit in which the cultivated organism swims from a video image capturing at least a portion of the area in which the cultivated organism swims; a speed identification step of identifying the swimming speed of the cultivated organism from the video image; a calculation step of calculating a representative value of the swimming speed for each of a plurality of divided areas obtained by dividing the evaluation area around the center into areas where the swimming speed is within a predetermined range according to the distance from the center; and an evaluation step of evaluating the swimming state of the cultivated organism for each of the divided areas based on the representative value.

[0092] The above method, like the evaluation device according to aspect 1, can provide an opportunity for the aquaculture manager to improve the aquaculture environment based on the results of a more detailed evaluation of the swimming state of the cultured organisms compared to conventional evaluation methods. Furthermore, it is possible to reduce poor growth and sudden death of the cultured organisms and promote good growth.

[0093] [Additional Notes] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Furthermore, embodiments obtained by appropriately combining the technical means disclosed in the respective embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0094] 5 Evaluation equipment 51 Center specific part 52 Speed ​​identification part 53 Calculation section 54 Evaluation Department 61 Feeding control unit A3 Intermediate area (area to be evaluated) A31~A33 segment area F Fish (cultured organisms) O center Th1~Th3 thresholds

Claims

1. a center identifying unit that identifies the center of the orbit in which the cultured organisms swim from a moving image that captures at least a portion of the area in which the cultured organisms swim; a speed identification unit that identifies the swimming speed of the cultured organisms from the moving image; a calculation unit that calculates a representative value of the swimming speed for each of a plurality of divided regions obtained by dividing an evaluation target region around the center where the swimming speed is within a predetermined range according to a distance from the center; and and an evaluation unit that evaluates the swimming state of the cultured organisms for each of the divided areas based on the representative value.

2. The evaluation device according to claim 1 , wherein the evaluation unit performs the evaluation based on a magnitude relationship between a threshold value of the representative value provided for each of the divided regions and the calculated representative value.

3. The evaluation device according to claim 2 , further comprising a feed control unit that controls the amount of feed given to the cultured organisms to be reduced from a current amount when the representative value is less than the threshold value.

4. a determination unit that determines whether or not there is an abnormality in the cultured organisms based on the amount of change per unit period of the representative value, The evaluation device according to claim 1 , wherein the evaluation unit performs the evaluation in accordance with a result of the determination.

5. a generation unit that generates a vector indicating the swimming direction of the cultured organisms from the moving image; a determination unit that determines whether or not there is an abnormality in the cultured organisms based on the number of vectors that do not follow the orbit; The evaluation device according to claim 1 , wherein the evaluation unit performs the evaluation in accordance with a result of the determination.

6. a center identifying step of identifying the center of the orbital path in which the cultured organisms swim from a video image capturing at least a portion of the area in which the cultured organisms swim; a speed determining step of determining the swimming speed of the cultured organisms from the moving image; a calculation step of calculating a representative value of the swimming speed for each of a plurality of divided regions obtained by dividing an evaluation target region around the center where the swimming speed is within a predetermined range according to a distance from the center; and an evaluation step of evaluating the swimming state of the cultured organisms for each of the divided areas based on the representative value.

Images