Fish counting system, fish counting method, and program

Abstract

To provide a fish counting system, fish counting method, and program that can easily correct erroneous counting.SOLUTION: A fish counting system includes an image acquisition unit that acquires an image including fish, a counting unit that counts the number of fish on the basis of the image, and a disturbance detection unit that detects disturbances on the basis of the image. The fish counting method includes acquiring an image including fish, counting the number of fish on the basis of the image, and detecting disturbances on the basis of the image. A program disclosed herein is a program for causing one or more processors to execute the fish counting method.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present disclosure relates to a fish counting system, a fish counting method, and a program. [Background technology]

[0002] In the aquaculture of tuna and other fish, it is desirable to know the exact number of fish in order to reduce feed costs and plan production. Conventionally, fish are counted by moving them from the first cage to the second cage and filming them as they move. The number of fish was counted visually while playing back the filmed video in slow motion, which increased the labor costs and lacked accuracy.

[0003] Patent Document 1 discloses a system for counting fish passing through a fishway in a river or the like by using a plurality of cameras. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2005-202674 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the accuracy of counting by camera can vary depending on changes in the imaging environment such as the direction of the sun, the turbidity of the water, etc. Also, when a large number of fish move at the same time, there can be cases where the fish overlap and miscounts occur.

[0006] Therefore, since there may be cases of erroneous counting, it is preferable to be able to manually correct the counting results. However, it is troublesome to visually check whether there has been an erroneous count by watching all of the video footage taken over a long period of time, and this increases the number of steps.

[0007] The present disclosure provides a fish counting system, a fish counting method, and a program that can easily correct erroneous counting. [Means for solving the problem]

[0008] The fish counting system of the present disclosure includes an image acquisition unit that acquires images including fish, a counting unit that counts the number of fish based on the images, and a disturbance detection unit that detects disturbances based on the images.

[0009] The fish counting method of the present disclosure includes obtaining an image including fish, counting the number of fish based on the image, and detecting a disturbance based on the image.

[0010] The program of the present disclosure is a program for causing one or more processors to execute the above-mentioned fish counting method. Effect of the Invention

[0011] Counting errors can be easily corrected. [Brief description of the drawings]

[0012] [Figure 1] 1 is a block diagram showing a fish counting system according to an embodiment of the present invention. [Diagram 2] FIG. [Diagram 3] FIG. 13 is a diagram showing a screen including a count result display and a change in the number of fish. [Figure 4] 11 is a flowchart illustrating an example of a process executed by the system. [Diagram 5] FIG. 13 shows a screen including an image with manual correction marks added thereto. [Figure 6] FIG. 13 is a diagram showing a schematic diagram of another configuration of the fish counting system. [Figure 7] FIG. 13 is a diagram showing another example of a screen including a count result display and a change in the number of fish. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0014] As shown in FIG. 1, the fish counting system 3 is configured to count the number of fish based on a plurality of images, provide a display of the counting result to a destination such as a display 4, and accept a correction operation via an operation unit 5 to correct the number of fish. The plurality of images are obtained by photographing an area where a fluid containing fish 1 flows over time with a camera 2. FIG. 1 is an example, in which a first cage and a second cage are directly connected to move fish such as tuna from the first cage to the second cage. By placing a camera near the entrance of the second cage, the fish moved to the second cage are counted and the total number of fish is grasped. The installation direction of the camera is not limited to the example shown in FIG. 1. For example, the camera may be installed at the exit of the first cage.

[0015] In this embodiment, the fish counting system 3 is realized by a computer to which the display 4 and the operation unit 5 (devices such as a touch panel or a mouse) are connected, but is not limited to this. For example, the fish counting system 3 may be realized by a server or cloud, and the display 4 and operation unit 5 of a computer capable of communicating with the server or cloud may be used.

[0016] FIG. 2 is a diagram showing a captured image. The camera 2 is set in a predetermined direction. As shown in FIG. 2, the predetermined direction is such that a part of the edge of the image is set as the first area Ar1, and the other edges are set as the second area Ar2, with the first area Ar1 being close to the first cage. By setting the camera 2 in such a predetermined direction, fish moving from the first cage to the second cage always pass through the first area Ar1 before reaching the second area Ar2. In FIG. 2, one of the four sides is set as the first area Ar1, and the remaining three sides are set as the second area Ar2, but this is not limited thereto.

[0017] In addition, since fish often pass through the center of the image, the photographing area has a third area Ar3 between the first area Ar1 and the second area Ar2. The third area Ar3 is arranged in the center of the image. By arranging in this manner, the fish 1 that leaves the first area Ar1 does not immediately reach the second area Ar2, and the fish is captured in the third area Ar3 in multiple images, so that it is possible to improve the recognition accuracy. It is also possible to omit the third area Ar3. As shown in FIG. 1, the area setting data D1 relating to the first area Ar1, the second area Ar2, and the third area Ar3 is stored in the storage unit 39 in the system 3. The area setting data D1 may be set to an initial value, or may be changed by a separate user operation. In this embodiment, the area setting data D1 is one file, and one area setting data D1 (one file) is stored corresponding to one video D2.

[0018] 1, the fish counting system 3 has an image acquisition unit 30, a counting unit 34, a result providing unit 36, a correction unit 37, a fish number change display providing unit 38, and a memory unit 39. Each of these units 30 to 38 is realized by hardware and software working together as a predetermined program is executed by one or more processors on a computer. The memory unit 39 is a memory, a storage, or the like.

[0019] The image acquisition unit 30 shown in Fig. 1 acquires multiple images captured over time of a shooting area where a fluid containing fish 1 flows. The camera 2 captures video at, for example, 30 fps (Flames Per Second), and the video D2 is stored in the memory unit 39 of the system 3. The image acquisition unit 30 acquires multiple images from the video D2. The multiple images are arranged in chronological order. In this specification, one image may be referred to as one frame.

[0020] The counting unit 34 shown in FIG. 1 counts the number of fish based on a plurality of images. The counting unit 34 is configured to count (add) the number of fish 1 when the fish 1 in the first area Ar1 moves to the second area Ar2. Specifically, the counting unit 34 extracts fish from each of a plurality of images arranged in time series by image processing, assigns an individual identification label to the extracted fish for identifying the individual based on the position of the fish in the past image, and counts the fish in the image (frame) at that time when a fish with the same label as the label assigned to the fish 1 in the first area Ar1 reaches the second area Ar2. This process is one example, and various algorithms can be adopted as long as they can count the number of fish.

[0021] As shown in FIG. 1, the counting unit 34 stores automatic count data D3 indicating the counting result in the storage unit 39. In this embodiment, the automatic count data D3 is one file, and one automatic count data D3 (one file) is stored corresponding to one video D2. In this embodiment, the automatic count data D3 has the number of fish counted (added) for each frame (each image). In the example shown in FIG. 1, the automatic count data D3 indicates that the number of fish counted in the jth frame is +3, the number of fish counted in the j+1th frame is +2, the number of fish counted in the j+2th frame is +1, and the number of fish counted in the j+3th frame is +4. j is a natural number, but is used for convenience of explanation.

[0022] The counting unit 34 also stores in the memory unit 39 mark data D4 (see FIG. 1) indicating the position of the counted mark 61 (see FIG. 3) for each frame, which indicates that the fish have been counted. The mark data D4 is used to display the counted mark 61 (see FIG. 3) for each frame, which indicates that the fish have been counted. In this embodiment, the mark is a Region of Interest (ROI) display, and a rectangular frame is displayed superimposed on the image of the fish, but this is not limited to this, and marks of various shapes or colors can be used. Note that fish that have passed through the first area Ar1 but have not yet reached the second area Ar2 and are to be counted are represented by a count target mark 68. The counted mark 61 and the count target mark 68 are different colors.

[0023] FIG. 3 shows an example of a screen including a counting result display 60. As shown in FIG. 3, the result providing unit 36 ​​shown in FIG. 1 provides the counting result display 60 including an image 62 with a counting mark 61 indicating that the fish have been counted. The counting mark 61 is a rectangular frame displayed over the image of the fish shown by the dashed line in FIG. 3, but is not limited to this. Various changes can be made as long as the ROI (Region of Interest) is displayed. The counting result display 60 shown in FIG. 3 includes a count value 63 for the entire video (12,345 fish in the figure), a correction value 64 for the entire video (+18 fish in the figure), an addition instruction display 65 and a subtraction instruction display 66 for inputting a correction operation, and a correction value 67 for the number of fish for the current frame. The count value 63 for the entire video is obtained by aggregating the automatic count data D3 shown in FIG. 1. On this screen, it is possible to play and pause a video (multiple images), advance the screen frame by frame, rewind the screen frame by frame, display a frame by specifying a time, and change the playback point by specifying a time.

[0024] The correction unit 37 shown in FIG. 1 accepts a correction operation and corrects the number of fish. In this embodiment, the correction unit 37 corrects the number of fish in response to an operation on the addition instruction display 65 or the subtraction instruction display 66. Specifically, when the addition instruction display 65 is operated, the correction value 67 of the number of fish for the currently displayed image 62 (frame) is increased by +1. The correction value 67 corresponds to the number of times the addition instruction display 65 is operated. For example, if the addition instruction display 65 is pressed p times, the correction value 67 becomes +p. p is a natural number equal to or greater than 1. Similarly, when the subtraction instruction display 66 is operated, the correction value 67 of the number of fish for the currently displayed image (frame) is decreased by -1. The correction value 67 corresponds to the number of times the subtraction instruction display 66 is operated. For example, if the subtraction instruction display 66 is pressed p times, the correction value 67 becomes -p. p is a natural number, but is used for convenience of explanation.

[0025] The correction result (correction value 67) by the correction unit 37 is stored in the storage unit 39 as the manual correction data D5 shown in FIG. 1. In this embodiment, the manual correction data D5 is one file, and one manual correction data D5 (one file) is stored corresponding to one video D2. In this embodiment, the manual correction data D5 has a correction value for each frame (each image). In the example shown in FIG. 1, the manual correction data D5 indicates that the manual correction value operated in the (j+10)th frame is +10, the correction value in the (j+100)th frame is +10, and the correction value in the (j+320)th frame is −2. The correction value 64 for the entire video displayed on the screen shown in FIG. 3 is obtained by tallying up the manual correction data D5.

[0026] 1, the automatic count data D3 represents the number of fish counted by the counting unit 34. The manual correction data D5 represents the number of fish corrected by the correction unit 37. The manual correction data D5 and the automatic count data D3 are different data. The correction unit 37 changes the manual correction data D5 without changing the automatic count data D3.

[0027] The fish number change display providing unit 38 shown in FIG. 1 provides a fish number change display 70 shown in FIG. 3. The change display 70 has a display 71 corresponding to the number of fish counted per unit time, and the display 71 is arranged in a chronological order. In this embodiment, as shown in FIG. 3, the fish number change display 70 has a graph display 71. In the graph display 71, the first axis Ax1 extending vertically corresponds to the number of fish counted per unit time, and the second axis Ax2 perpendicular to the first axis Ax1 corresponds to the passage of time. In the example of FIG. 3, the left side along the second axis Ax2 represents the past, and the right side represents the future. The number of fish counted per unit time increases as you move from bottom to top along the first axis Ax1. If the shooting time of the video D2 is long and does not fit on one screen, a slider bar 72 is displayed, and any time point can be displayed by sliding the slider bar 72. In addition, if you operate the time point you want to view in the change display 70, the frame at the time point specified by the operation is displayed. In this embodiment, the first axis Ax1 is vertical, but it may be horizontal. In this embodiment, the count value is managed for each frame, so the unit time is the time corresponding to one frame. For 30 fps, it is 1 / 30 seconds. Of course, this is merely an example, and a time corresponding to multiple frames may be treated as the unit time.

[0028] In the example shown in Fig. 3, the number of fish counted per unit time is shown as a line graph, but this is only one example and can be modified in various ways. For example, various graphs such as bar graphs may be used. Also, numbers representing the count values ​​may be arranged in chronological order.

[0029] In this way, since the displays 71 corresponding to the numbers of counted fish are arranged in chronological order, the time points when erroneous counts are likely to occur (time points when the count values ​​are high) can be grasped by looking at the display 71 without having to view the images for all times. Also, with the graph display 71, the peaks of the graph and their surroundings indicate the time points when the count values ​​are high, so it is easy to grasp the time points when the count values ​​are high.

[0030] 3 has a current display 73 that indicates the time of the currently displayed image 62 (frame). The fish number change display 70 also has a correction time display 74 that indicates the time corrected by the addition instruction display 65 or the subtraction instruction display 66. The correction time display 74 indicates not only the time but also the content of the correction value (whether it is addition or subtraction).

[0031] <Operation flow> The process executed by the system 3 will be described with reference to FIG. 4. A video D2 is stored in the storage unit 39. When a predetermined analysis start condition is met, such as when a predetermined screen is opened, an analysis instruction operation is performed, or a new video D2 is stored in the storage unit 39, in step ST1 shown in FIG. 4, the image acquisition unit 30 acquires a plurality of images of a fluid containing fish over time based on the video D2. In step ST2, the counting unit 34 counts the number of fish based on the plurality of images. The counting result is stored in the storage unit 39 as the automatic counting data D3 and the mark data D4 shown in FIG. 1. When the fish counting and analysis screen shown in FIG. 3 is opened, in the next step ST3, the fish number change display providing unit 38 provides a fish number change display 70 in which displays 71 corresponding to the number of fish counted per unit time are arranged in a time series based on the automatic counting data D3 and the mark data D4 shown in FIG. 1 (see FIG. 3). Furthermore, in step ST4, the result providing unit 36 ​​provides a count result display 60 including an image 62 with a counted mark 61 indicating that fish have been counted, as shown in Fig. 3. Step ST4 may be repeatedly executed in response to playback of the video D2 or designation of a time point in the fish number change display 70. When the addition instruction display 65 or subtraction instruction display 66 shown in Fig. 3 is operated, in step ST5 the correction unit 37 accepts the correction operation and corrects the number of fish. The correction unit 37 stores the correction result in the memory unit 39 as manual correction data D5.

[0032] [Variation 1] In the embodiment shown in FIG. 3, the number of fish is corrected for the image 62 (frame) being displayed simply by operating the addition instruction display 65 or the subtraction instruction display 66, but this is not limited thereto. As a correction method that is time-consuming but has high accuracy, the position of the miscounted fish or the fish that should be counted in the image 62 may be specified and the correction operation of the addition correction or subtraction correction may be performed. Methods for specifying the position of the fish include a method of specifying the position by surrounding it with a rectangular frame and a method of specifying the coordinates in the image 62. It is preferable that the result providing unit 36 ​​provides an image to which a manual correction mark indicating the corrected fish specified by the correction operation is added together with the counted mark 61. In this way, the reason for the correction is displayed together with the image 62 by the manual correction mark, so that appropriate fish number management is possible. FIG. 5 shows an example of a screen including the image 62 to which the manual correction mark M is added.

[0033] [Variation 2] Fig. 6 is a schematic diagram showing another configuration of the fish counting system 3 of the present embodiment. In addition to the configuration shown in Fig. 1, the fish counting system 3 may further include a disturbance detection unit 31. Like the image acquisition unit 30 and the like, the disturbance detection unit 31 is also realized by hardware and software working together as a predetermined program is executed by one or more processors on a computer.

[0034] The disturbance detection unit 31 detects a disturbance based on the image acquired by the image acquisition unit 30. Then, the disturbance detection unit 31 provides a marking display 75 (see FIG. 7) at the time when the disturbance is detected in the fish number change display 70 arranged in a chronological order. At this time, the disturbance detection unit 31 may provide, in addition to the marking display 75, a disturbance content display 76 (see FIG. 7) that indicates the content of the detected disturbance.

[0035] Here, the disturbance detection unit 31 detects the disturbance for each type of disturbance (evaluation item) by the following method.

[0036] When detecting "reflection of direct sunlight" as a disturbance (when the evaluation item is "reflection of direct sunlight"), the disturbance detection unit 31 divides the image acquired by the image acquisition unit 30 into blocks. More specifically, the image acquired by the image acquisition unit 30 is divided into 23 x 23 blocks by shifting small areas that are 1 / 12 the size of the screen vertically and horizontally by 1 / 24 of the screen length and width at a time. When there is a block where the average brightness is equal to or greater than a certain value, the average hue is equal to or less than a certain value, and the average values ​​of R (red), G (green), and B (blue) are equal to or greater than a threshold, the disturbance detection unit 31 determines that there is reflection of direct sunlight (detects the presence of a disturbance).

[0037] When detecting "reflection of an obstacle such as a net or structure" as a disturbance (when the evaluation item is "reflection of an obstacle"), the disturbance detection unit 31 divides the image acquired by the image acquisition unit 30 into 4 x 4 blocks at equal intervals. Then, first, blocks whose average brightness is equal to or less than a certain value are determined as obstacle candidate areas. Next, blocks adjacent to the obstacle candidate areas and other than the obstacle candidate areas are determined as "boundary with the sea surface" candidates. Then, when more than half of the blocks adjacent to the obstacle candidate area are "boundary with the sea surface" candidates whose brightness variance is equal to or more than a certain value, the disturbance detection unit 31 determines that a boundary between an obstacle and the sea surface exists and that an obstacle is reflected (detects the presence of a disturbance).

[0038] When detecting "reflection of floating objects or the like" as a disturbance (when the evaluation item is "reflection of floating objects or the like"), the disturbance detection unit 31 converts the image acquired by the image acquisition unit 30 into a grayscale image over the entire screen, then binarizes each pixel to extract contours, and calculates the area of ​​each region surrounded by the contours. When the number of regions whose areas fall within a certain range exceeds a certain value, the disturbance detection unit 31 determines that a floating object or the like has been reflected (detects the presence of a disturbance).

[0039] When detecting "overall brightness and darkness of an image" as a disturbance (when the evaluation item is "overall brightness and darkness"), if the brightness of the entire screen of the image acquired by the image acquisition unit 30 is equal to or greater than a certain value, the disturbance detection unit 31 determines that the entire image is too bright (detects the presence of a disturbance). Conversely, if the brightness of the entire screen of the image acquired by the image acquisition unit 30 is less than the certain value, the disturbance detection unit 31 determines that the entire image is too dark (detects the presence of a disturbance).

[0040] 7 shows another example of a screen including the count result display 60 and the fish number change display 70. In the figure, the fish number change display 70 shows a state in which a marking display 75 is added at the time when the disturbance detection unit 31 detects a disturbance. If there is a disturbance such as reflection of direct sunlight, the counting unit 34 may not be able to correctly count the number of fish based on the image. In the fish number change display 70 displayed in chronological order, by adding the marking display 75 at the time when the disturbance detection unit 31 detects a disturbance, it becomes possible to correct erroneous counts caused by disturbances by performing a correction operation based on the marking display 75.

[0041] 7, in addition to the above-mentioned marking display 75, a disturbance content display 76 showing the content of the disturbance detected by the above-mentioned detection method is added to the fish number change display 70. The presence of the disturbance content display 76 makes it possible to make corrections according to the content of the disturbance when correcting erroneous counting caused by a disturbance (it becomes possible to vary the degree of correction according to the content of the disturbance), and it becomes possible to accurately correct erroneous counting according to the disturbance.

[0042] As described above, the fish counting system 3 of this embodiment comprises an image acquisition unit 30 that acquires multiple images of a fluid containing fish over time, a counting unit 34 that counts the number of fish based on the multiple images, a fish number change display providing unit 38 that provides a fish number change display 70 in which displays 71 corresponding to the number of fish counted per unit time are arranged in chronological order, a result providing unit 36 ​​that provides a counting result display 60 including an image 62 with a counted mark 61 indicating fish that have been counted, and a correction unit 37 that accepts a correction operation and corrects the number of fish.

[0043] The fish counting method of this embodiment includes obtaining multiple images of a fluid containing fish taken over time, counting the number of fish based on the multiple images, providing a fish number change display in which displays corresponding to the number of fish counted per unit time are arranged in chronological order, providing a counting result display including images with counted marks indicating fish that have been counted, and accepting a correction operation to correct the number of fish.

[0044] Miscounting is likely to occur when many fish pass by at the same time, and many fish are counted per unit time. This configuration provides a fish number change display 70 in which displays 71 corresponding to the number of fish counted per unit time are arranged in chronological order. This makes it possible to grasp the time points when miscounting is likely to occur, when many fish pass by at the same time, without having to visually check the images for all times. Then, by visually checking and confirming the count result display 60, which includes an image with a counted mark 61 indicating that the fish have been counted, correction can be made through a correction operation. Therefore, miscounting can be easily corrected.

[0045] As in this embodiment, it is preferable that the fish number change display 70 has a graph display 71 in which a first axis Ax1 extending horizontally or vertically corresponds to the number of fish counted per unit time, and a second axis Ax2 perpendicular to the first axis Ax1 corresponds to the passage of time.

[0046] By looking at the graph display 71, it is possible to easily grasp the points at which miscounting is likely to occur, and correction can be easily performed by looking at the changes in the graph display 71. Points at which miscounting is likely to occur include, for example, peaks and sudden rises.

[0047] As in this embodiment, the result providing unit 36 ​​provides an addition instruction display 65 and a subtraction instruction display 66 to instruct the correction of the number of fish, together with an image 62 with a counted mark 61 indicating that the fish have been counted, and it is preferable that the correction unit 37 corrects the number of fish in response to an operation on the addition instruction display 65 or the subtraction instruction display 66.

[0048] According to this configuration, when an image 62 bearing a counted mark 61 is visually inspected and a missed count where the counted mark 61 is not attached or an erroneous count where the counted mark 61 is mistakenly attached is recognized, the addition instruction display 65 or subtraction instruction display 66 can be operated, thereby improving the efficiency of the correction work.

[0049] As in variant example 1 of this embodiment, the correction unit 37 accepts a correction operation involving specification of the position of the corrected fish within the image 62 and corrects the number of fish, and the result providing unit 36 ​​provides an image 62 with a manual correction mark M added to indicate the corrected fish specified in the correction operation.

[0050] In this way, the basis for the correction is displayed together with the image 62 by the manual correction mark M, making it possible to appropriately manage the number of fish.

[0051] As in this embodiment, the fish number change display 70 preferably has a correction time point display 74 that indicates the time point when the fish number was corrected.

[0052] According to this configuration, since the correction time point display 74 is displayed together with the display 71 corresponding to the number of fish counted per unit time, it is possible to easily grasp whether corrections have already been made for the points at which erroneous counting is likely to occur, improving convenience. At the same time, when multiple people are to correct erroneous counting, the person who made the correction first can easily grasp the part that has been corrected, enabling efficient checking and correction work by multiple people.

[0053] As in this embodiment, the fish counting system 3 is equipped with a memory unit 39, which stores automatic counting data D3 representing the number of fish counted by the counting unit 34 and manual correction data D5 which is data different from the automatic counting data D3 and represents the number of fish corrected by the correction unit 37, and it is preferable that the correction unit 37 changes the manual correction data D5 without changing the automatic counting data D3.

[0054] With this configuration, the automatic count data D3 is not affected by the correction, so that even if the correction is made erroneously, it can be easily restored.

[0055] As in the second modification of this embodiment, it is preferable that the fish counting system 3 further includes a disturbance detection unit 31 that detects a disturbance based on the image acquired by the image acquisition unit 30, and the fish number change display 70 has a marking display 75 that indicates the time point when the disturbance detection unit 31 detected the disturbance. In this case, it is possible to correct erroneous counting caused by disturbances by performing a correction operation based on the marking display 75.

[0056] Furthermore, it is preferable that the fish number change display 70 has a disturbance content display 76 that shows the detected disturbance content. In this case, correction according to the disturbance content can be performed according to the correction operation based on the disturbance content display 76. This makes it possible to accurately correct erroneous counts caused by disturbances.

[0057] The program according to the present embodiment is a program for causing one or more processors to execute the above-mentioned method. Also, a computer-readable temporary recording medium according to the present embodiment stores the above-mentioned program.

[0058] Each of the units 30 to 38 shown in FIG. 1 is realized by executing a predetermined program on one or a processor, but each unit may be configured with a dedicated memory or a dedicated circuit.

[0059] In the system 3 of the above embodiment, each of the units 30 to 38 is realized by a computer processor, but each of the units 30 to 38 may be distributed and implemented in multiple computers or in the cloud. In other words, the above method may be executed by one or multiple processors.

[0060] Although the embodiments of the present disclosure have been described above based on the drawings, the specific configurations should not be considered to be limited to these embodiments. The scope of the present disclosure is indicated not only by the description of the above-mentioned embodiments but also by the claims, and further includes all modifications within the meaning and scope equivalent to the claims. [Industrial Applicability]

[0061] The present invention can be used in a fish counting system. [Explanation of symbols]

[0062] 1 fish 3. Fish Counting System 30 Image acquisition unit 34 Counting Department 36 Results Provision Department 37 Correction section 38 Fish population change display section 39 Memory section 61 Counted Mark 65 Addition Indicator 66 Subtraction Indicator 70 Fish number change display 71 Graph display 74 Correction time display Ax1 1st axis Ax2 2nd axis D3 Automatic counting data D5 Manual correction data

Claims

1. an image acquisition unit for acquiring an image including a fish; A counting unit that counts the number of fish based on the image; A fish counting system comprising: a disturbance detection unit that detects a disturbance based on the image.

2. 2. The fish counting system of claim 1, further comprising a fish count change display providing unit that provides a fish count change display in which displays corresponding to the numbers of fish counted per unit time are arranged in a time series.

3. The fish counting system according to claim 2 , wherein the disturbance detection unit provides a predetermined display in the fish count change display when the disturbance is detected.

4. The fish counting system according to claim 3 , wherein the predetermined display includes a marking display of a time point at which the disturbance is detected, or a disturbance content display showing the content of the detected disturbance.

5. A fish counting system as described in any one of claims 2 to 4, wherein the fish number change display has a graph display in which a first axis extending horizontally or vertically corresponds to the number of fish counted per unit time, and a second axis perpendicular to the first axis corresponds to the passage of time.

6. 6. The fish counting system according to claim 1, wherein the disturbance includes at least one of reflections of direct sunlight, reflections of obstacles, reflections of floating objects, and overall brightness and darkness of the image.

7. The fish counting system according to claim 1 , further comprising a correction unit that receives a correction operation to correct the number of fish.

8. Obtaining an image including a fish; counting the number of fish based on the images; and detecting a disturbance based on the image.

9. A program that causes one or more processors to execute the fish counting method according to claim 8.

Images