JP2526237B2 - Image monitoring device for living groups - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial field of application] The present invention provides, as test water, a plurality of organisms bred using influent and treated water of a water treatment plant or a sewage treatment plant, river water, and the like. The present invention relates to a device that recognizes an image and detects the presence or absence of poisonous substances in test water. Further, the present invention can be generally applied to a device for studying the behavior of a living group by image recognition.

[Conventional technology]

At water purification plants, etc., in order to determine whether or not toxic substances are mixed in the raw water, a portion of the raw water or the purified water is guided to an aquarium, where fish such as crucian carp, carp, dace, tanago, oikawa and goldfish are raised. ing. Similarly, fish may be bred to monitor the treated water, effluent water, river water, and lakes of sewage treatment plants for the presence of toxic substances in the water. When a poisonous substance is mixed in water, the fish behave abnormally or die, so this is visually monitored. However, since it relies on visual inspection and cannot be detected when a person is not monitoring it, automatic monitoring has been desired.

Japanese Patent Application Laid-Open No. 61-46294 discloses a method of monitoring the behavior pattern of a plurality of organisms in order to monitor the water quality.
The disclosed technology describes that temperature and water quality are measured by a water quality sensor and whether the behavior pattern is normal or abnormal is determined with reference to the measured values. It is described that the action pattern also includes speed and position. However, even if the behavior pattern is simply analyzed by using image technology, such an idea is conventionally known, and how to specifically detect or evaluate the speed and position of a plurality of organisms? Is not disclosed, so it is difficult to implement.

[Problems to be solved by the invention]

The inventors of the present invention have conducted extensive research to put into practical use a method for monitoring the behavior of living things, particularly aquatic animals such as fish, using images, and have invented a device for effectively recognizing a group of living things.

The problems of the prior art will be described below taking the case of fish as an example. When there is one fish, if the fish can be image-recognized, its position and movement can be easily measured and evaluated. However, when analyzing the movements of multiple fish, how to track each fish becomes a problem. Figure 2 2 fish of fish shown in the F ₁ and F ₂ in (a) is, and as a result, it becomes as shown in (b) after a certain time. In this case, it is extremely difficult to identify which is F ₁ and which is F ₂ in (b).
This identification becomes increasingly difficult as the number of fish increases.
It goes without saying that the position and speed of the fish cannot be calculated unless the image of each fish can be recognized. In other words, it is difficult to understand the behavior patterns of multiple fish schools.

As described above, the conventional method has a problem that it is not possible to grasp the behavioral pattern of a group of organisms such as a fish school, and further, a problem that the inflow of poisonous substances cannot be detected with high accuracy.

An object of the present invention is to provide a device that can effectively detect a behavior pattern as a group of a plurality of living things.

[Means for solving problems]

The present invention, the group of organisms to be kept in a constant breeding space, particularly the position of aquatic animals such as fish, is detected depending on where the image of the entire organism was located, and the velocity of the organisms at different times. It is detected by the difference processing of the two organism group images in. By detecting the position and velocity of these organism groups, the behavior pattern of the organism groups can be evaluated.

That is, the aquatic animal image monitoring device of the present invention, an image pickup device installed on the side surface of the aquarium that converts the image information of a plurality of aquatic animals raised in the aquarium into electric signals at regular time intervals, and the aquatic animal. An illuminating device for illuminating the image, a first image storing means for storing the image captured by the image capturing device, and a second image storing means for storing the image at a time different from that, Position distribution calculation means for calculating the position distribution in the water depth direction of the animal, position distribution addition means for adding the position distribution, and position distribution comparison means for comparing the added position distribution and the normal position distribution. A first image monitoring means, an image difference means for obtaining a difference image between the first image storage means and the second image storage means, a difference area calculation means for calculating an area of the difference image, and the difference At least one image monitoring means of the area distribution calculation means for calculating the frequency distribution of the products and the second image monitoring means having the difference area comparison means for comparing the frequency distribution with the frequency distribution in the normal state Comprises the first
The behavior of the aquatic animal is determined based on one or both of the image monitoring means and the second image monitoring means.

[Work]

In the present invention, the position of a group of organisms such as a group of multiple fish is detected by the position of the image of the component group, and the velocity of the group of organisms is detected by the image difference processing. Can be evaluated.

〔Example〕

The present invention can be generally applied to the monitoring of the behavior pattern of a living body, but in the present embodiment, an embodiment in which the behavior of a school of fish is image-monitored will be described. Examples will be described below with reference to the drawings.

The configuration and operation of the embodiment will be briefly described with reference to FIG. Water to be measured is supplied to the environmental control tank 1 by a water distribution pipe 2A and a pump 2B. Excess water is drained by drain pipe 2C. The stirrer 3 stirs the test water with the stirring blade 3A. A thermometer 4 such as a thermistor detects the temperature of the test water. The detected temperature is input to the temperature adjusting device 5 and the radiator output device 6 is adjusted to control the amount of heat radiated from the radiator 6A to control the temperature to be constant. As the temperature adjusting method, known techniques such as an on / off adjusting method and a PID adjusting method can be easily used. The target value of the temperature to be adjusted is set to a temperature suitable for the activity of the fish raised in the aquarium 10. The air pump 7 is an air diffuser
Air bubbles are supplied from 7A to adjust the dissolved oxygen concentration. The air pump 7 supplies air. If the dissolved oxygen in the test water is supersaturated, the dissolved oxygen concentration is lowered by supplying air.

The test water whose temperature and dissolved oxygen concentration have become suitable for raising fish is supplied to a water tank 10 by a water supply pipe 11 and a water supply pump 12. The water introduced into the water tank 10 is drained by the drain pipe 13. Partition plates 18A and 1 such as wire mesh and perforated plate in the water tank 10.
There is a breeding space 19 divided by 8B, where fish 14A, 14
Bring B and 14C. In the present embodiment, the case where there are three fish will be described, but the principle is exactly the same for a larger number of fish. The lighting devices 15A, 15B, 15C illuminate the fish 14 in the aquarium 10. A semi-transparent plate 16 made of a semi-transparent substance having a property of scattering frosted glass, paper or the like is provided between the lighting devices 15A, 15B, 15C and the water tank 10. The semitransparent plate 16 scatters the light upon receiving the light from the lighting devices 15A, 15B, 15C, and the light emitted from the entire semitransparent plate 16 illuminates the aquarium 10. Lighting device 15A, 15B, 16
An industrial TV camera (ITV) on the opposite side of the aquarium 10 as seen from C
The image pickup device 20 is arranged. That is, the imaging device 20 images the light emitted from the illumination devices 15A, 15B, 15C and passing through the semitransparent plate 16. Here, the imaging device 20 images the breeding space 19.

The signal of the imaging device 20 is guided to the image monitoring device 30. A detailed description of the configuration and operation of the image monitoring device 30 will be given later. The function of the image monitoring device 30 will be briefly described.
Then, first, the imaging device is loaded at every preset time interval h to image and recognize the fish body, and the center of gravity and speed of the fish body are calculated. The center of gravity and velocity of the fish are sequentially calculated for each time interval h, and the result is stored in a memory. Based on this memory information, a statistical pattern of the position (center of gravity) and velocity of the fish at the preset measurement time T is calculated. The behavior of the fish 14 is calculated and monitored, and an alarm is issued in the case of an abnormality based on the monitoring result.

The monitor TV 50 displays the captured image. The image monitor 60 receives the signal from the image monitoring device 30 and displays the image recognition result and the monitoring result such as the fish position distribution and velocity distribution. The keyboard 70 is for monitoring conditions of the image monitoring device 30 and CR.
Enter the information that controls the display of the T80.

Next, the configuration of the image monitoring device 30 will be described in detail. The timer 31S outputs a trigger signal to the A / D converter 32 at every initialized time interval h. The A / D converter 32 receives the image signal output from the imaging device 20 in synchronization with this trigger signal,
This is converted from an analog value to a digital value and stored in the multi-valued image memory 32M. The luminance frequency distribution calculation circuit 33 receives the signal of the multi-valued image memory 32M and calculates the luminance frequency distribution (histogram) of the multi-valued image. Here, the luminance frequency distribution represents the frequency of each value (luminance) of the multivalued image. The threshold value determining circuit 34 receives the calculation result of the luminance frequency distribution, while receiving the signal of the fish area setting circuit 34S, and determines the threshold value for binarization based on both signals. The binarization circuit 35 is a multi-valued image memory 32.
Receiving the M signal and the signal of the threshold value determining circuit 34, the multi-valued image is
This binary image is binarized and stored in the binary memory 31M1. However, the storage in the binary memory 35M1 is performed only for the first time when the measurement is started, and thereafter, it is stored in the binary memory 35M2. First, time h
After that, the binary image obtained in the same manner is stored in the binary memory 35M2. After that, the binary image is stored in the binary memory at every time interval h.
Store in 35M2. The binarization circuit 35 extracts the images of the fish 14A, 14B, 14C. In the following, the group of fish 14A, 14B, 14C will be referred to as the group of fish 14 when it is expressed. The type of fish may be different. The binary image of the school of fish 14 stored in the binary memory 35M1 and the binary memory 35M2 is displayed on the image monitor 60.

The position distribution calculation circuit 36 receives the signal from the binary memory 35M2 and calculates the position distribution of the school of fish 14 in the depth direction. The position distribution addition circuit 37 receives the result of the position distribution calculation circuit 36 and adds the position distributions. Based on the command from the timer 31S, the series of processes up to this point are repeated a fixed number of times at a fixed time interval. The position distribution comparing circuit 38 compares the position distribution in the normal state input from the normal distribution setting circuit 38S with the position distribution input from the position distribution calculating circuit 37. If it is determined to be abnormal, an alarm signal is input to the alarm device 38A.

The difference calculation circuit 40 includes a binary memory 35M1 and a binary memory 35.
The binary image of the school of fish 14 stored in M2 is received, the differential image of the binary image is calculated and stored in the differential image memory 40M. The difference area calculation circuit 41 calculates the area of the difference image. The difference image is subtracted from the image. If the moving speed of the image is high, the area of the difference image is large, and conversely, if the moving speed is small, the area is small. Therefore, information about the moving speed of the school of fish can be obtained. I can. The difference area distribution adding circuit 42 receives the result of the difference area calculating circuit 41 and adds the area distribution,
The added result is input to the difference area distribution comparison circuit 43. The normal distribution is input from the normal distribution setting circuit 43S to the differential area distribution comparison circuit 43, and this normal distribution is compared with the distribution input from the differential area distribution calculation circuit 42. If it is determined to be abnormal, an alarm signal is input to the alarm device 43A. The alarm device 44A further outputs an alarm signal if the signals of the alarm devices 38A and 43A are ON (determined to be abnormal). In addition, from the keyboard 70, the timer 31S fish body area setting circuit 34S,
The set values are input to the normal distribution setting circuit 38S and the normal distribution setting circuit 43S.

Next, the operation of the image monitoring device 30 will be described in detail. The timer 30S outputs an A / D conversion trigger signal to the A / D converter 31 at every time interval h that is input by the keyboard 70 and initialized. This h is about 0.1 second to 2 seconds, and the following image processing is executed at this time interval. Also the timer
In 31S, one image processing time h and the number of repetitions n of this image processing are set, and a measurement time T (when one image processing time is h, repeating image processing n times results in T = nh). ) Is set so that statistical behavior patterns of the school of fish during this period can be calculated. The measuring time T is about 10 seconds to 1 hour. The A / D converter 32 converts the multi-valued image signal from the analog image device 20 into a digital value in synchronization with the trigger signal output from the timer 30S, and converts the digital multi-valued image signal into a multi-valued image memory 32M. Remember. Multi-valued image memory 3
The 2M has 256 vertical and 256 horizontal storage locations, and the luminance signal of the pixel corresponding to each storage location is stored as a digital value. I row and j column of this storage location (i = 1 to 256, j = 1
The signal (luminance) of the (256th) th pixel is represented as G (i, j). If the A / D converter 32 converts an analog value into a 7-bit digital value, G (i, j) has a digital value of 128 steps. An example of a multi-valued image stored in the multi-valued image memory 32M is shown in FIG. FIG. 3 shows an image having multi-valued luminance. The luminance frequency distribution calculation circuit 33 calculates the luminance frequency distribution of the multi-valued image. The luminance frequency distribution of FIG. 3 is shown in FIG.
The threshold value determining circuit 34 determines the threshold value I based on the calculation result of the luminance frequency distribution. Next, a method of setting the threshold I will be described.

FIG. 4 shows the luminance frequency distribution. In the illumination method of the present invention, the school of fish 14 can always be imaged as a dark object. Therefore, as shown in FIG. 4, only the area of the school of fish 14 (hatched, where f is the area) of the school of fish 14 has a low luminance. Set a _first threshold I ₁ . Since the area f differs depending on the state, the minimum area is set. This threshold setting method is particularly effective when the water becomes cloudy. However, it is better to use the second threshold if the water is not cloudy. In FIG. 4, the peak Pf represents the fish body, the peak Pb represents the background, and the part represented by Pe represents the gills and outline of the fish. To extract only the fish
A second threshold I ₂ is set at the boundary between Pf and Pe. As shown in FIG. 4, a threshold value is set to at least the brightness I ₁ in advance, and while searching for each frequency in the direction in which the brightness increases,
If there is a boundary (minimum value) between Pf and Pe, I ₂ is selected for this brightness.

Next, the binarization circuit 35 receives the signal of the multi-valued image memory 32M and the signal I (I ₁ or I ₂ ) of the threshold value determination circuit 34, binarizes the multi-valued image and stores it in the binary memory 35M1. . However, 2
The value is stored in the value memory 35M1 only for the first time when the measurement is started, and thereafter, it is stored in the binary memory 35M2. First, after the time h, the binary image obtained in the same manner is stored in the binary memory 35M2. However, the binary image of the binary memory 35M1 and the binary memory 35
When the binary image of M2 is output to the difference calculation circuit 40 and the difference calculation is performed, the binary image of M1 is stored in the binary memory 35.
Replaced with a 35M2 binary image. After that, a new binary image is stored in the binary memory 35M2 at every time interval h. Next, a specific operation of the binarization circuit 35 will be described. The binarization circuit 35 receives the bright G (i, j) of the multi-valued image memory 32M and sets all the pixels brighter than the threshold to the “0” level, and conversely sets all the pixels darker than the threshold to the “1” level. , This signal is stored in the binary memory 35M2 without exception for the first time.
The binarization calculation with this set of binarized signals as B (i, j) is expressed by the following equation.

If G (i, j) ≧ I, B (i, j) = 0 (1) If G (i, j) <I, B (i, j) = 1 (2) (1) (2) By calculating the formula for each pixel at all, the background can be at the "0" level and the school of fish 14 at the "1" level. The result of binarizing FIG. 3 is shown in FIG. The "1" part is hatched. The image of FIG. 5 is stored in the binary memory 35M1 for the first measurement, and is stored in the binary memory 35M2 for the second and subsequent measurements.

The position distribution calculation circuit 35 receives the signal from the binary memory 35M2 and calculates the position distribution of the school of fish 14. The position distribution of FIG.
As shown in the figure, the image of FIG. 5 is defined by the distribution projected in the horizontal direction. That is, the position distribution in FIG. 6 represents at which water depth the fish school was in the water depth direction. That is, the obtained position distribution is a distribution that represents the position of the school of fish. The position distribution adding circuit 37 receives the result of the position distribution calculating circuit 36 and adds the position distributions measured every time h so that an average position distribution can be calculated. This repeat timer
Based on the 31S command, the series of processes described above is performed a predetermined number of times n. The position distribution thus obtained has a peak at the bottom of the water tank under normal conditions as shown in FIG. 7 (a). The position distribution at the time of abnormality has a peak near the water surface as shown in FIG. 7 (b). This distribution represents so-called nose lift behavior.

The position distribution at normal time obtained in advance in the position distribution comparison circuit 38 is input to the normal distribution setting circuit 38S and compared with the position distribution input from the position distribution addition circuit 37. If it is determined to be abnormal, an alarm signal is input to the alarm device 38A.

The position distribution comparison method in the position distribution comparison circuit 38 will be described below. In order to evaluate the frequency of fish near the water surface, the ratio Ls / Lt of the area Ls near the water surface (shown by hatching) to the total area Lt of the distribution is calculated in FIG. In the position distribution comparison circuit 38, when the ratio Ls / Lt becomes larger than a predetermined value, it indicates that the fish 14 is taking a nose-raising action near the surface of the water, and therefore it is determined that the action is abnormal. That is, it is determined that the water quality is abnormal. For example, if Ls / Lt is 0.2 or more, it is regarded as abnormal. When it is judged to be abnormal, a signal is sent to the alarm device.
Input to 38A.

The difference calculation circuit 40 uses the image B ₁ (i, j) of the binary memory 35M1.
And the image B ₂ (i, j) in the binary memory 35M2 are calculated by the following formula, and the result S (i, j) is stored in the difference image memory 40M.

S (i, j) = B 1 (i, j) -B 2 (i, j) (5) This calculation is repeated for each set time interval h in timer 31S. FIG. 8 shows the outline of the binary image B ₁ (i, j) by a solid line and the outline of the binary image B ₂ (i, j) by a broken line. The difference image stored in the difference image memory 40M is as shown in FIG. In this way, only the moved part is extracted. The difference area calculation circuit 41 receives the difference images in the difference image memory 40M and calculates the sum of the areas. The sum is calculated in order to detect the movement of the entire school of fish, but the area of each may be calculated. At this time, the movement of each fish is detected, but when a plurality of fish overlap, the movement of one fish cannot always be detected. In any case, the difference area calculated by the difference area calculation circuit 41 is
When 14 moves at a high speed, this area becomes large, and conversely, when 14 moves at a slow speed, the area becomes small. This area is small under normal conditions and large under abnormal conditions. That is, it represents a frenzy.

The difference area distribution addition circuit 42 receives the result of the difference area calculation circuit 41 and calculates the difference area distribution while adding the difference areas at each time interval h. The differential area distribution is a diagram in which the horizontal axis represents the differential area and the vertical axis represents the frequency, as shown in FIG. The difference area distribution under normal conditions is shown in Fig. 11 (a).
As shown in, the distribution has a peak at a small difference area. As shown in FIG. 11 (b), the difference area distribution at the time of abnormality is a distribution in which the frequency at a large difference area is higher than that at the normal time.

The differential area distribution comparison circuit 43 receives the normal differential area distribution from the normal distribution setting circuit 43S, and the normal distribution,
The difference area distribution input from the difference area distribution addition circuit 42 is compared. The operation of the difference area distribution comparison circuit 43, that is, the comparison method will be described. In order to detect the movement of the school of fish, the ratio Vs / Vt of the total area Vt of the distribution to the area Vs near the water surface (shown by hatching) is calculated in FIGS. 11 (a) and (b). In the difference area distribution comparison circuit 43, the ratio V
If s / Vt becomes larger than a predetermined value, it indicates that the school of fish 14 is taking a frenzy action of swimming at a high speed, and therefore it is determined to be an abnormal action. That is, it is determined that the water quality is abnormal.
For example, if Vs / Vt is 0.2 or more, it is considered abnormal. If it is determined to be abnormal, the signal is input to the alarm device 43A. In addition, Ls /
The values of Lt and Vs / Vt differ depending on the type of fish.

The alarm device 44A receives signals from the alarm device 43A and the alarm device 38A, and determines that the behavior of the school of fish is abnormal when these signals are ON (abnormal). When the position distribution and the difference area distribution become abnormal at the same time, it means that the degree of water quality abnormality is large. When the alarm device 44A, the alarm device 43A, or the alarm device 38A determines that there is an abnormality, in particular, an alarm is given on the CRT 80 or a voice message is output. Also keyboard
Based on the command from 70, the image monitor 60 displays the image of the binarized memory 35M at each time h, and displays the position distribution shown in FIG. 7 and the speed difference area distribution shown in FIG. 11 at each time T. To display.

Although the embodiment of FIG. 1 has been described in detail above, the behavior of a plurality of fish schools can be detected by the position distribution and the difference area distribution in this embodiment, so that the abnormal behavior of the fish school is effectively detected. can do. In this way, the behavior of a plurality of fish can be continuously monitored by an image, and therefore abnormal behavior of fish when a poison enters the test water can be accurately detected and an alarm can be issued.

In the embodiment of FIG. 1, the difference calculation circuit 40 makes a difference between the binary images of the binary memories 35M1 and 35M2.
Since the feature is that the motion is detected by the difference between the images, it is possible to make the difference between the multi-valued images. Only the difference from the embodiment of FIG. 1 in this case will be briefly described below.

When subtracting multi-valued images, in addition to the multi-valued image memory 32M1 as in the case of the binary memory, a multi-valued image memory 32M1 for storing multi-valued images at different times is set (not shown). Then, these are subtracted. In this case, since the difference image is a multi-valued image, the obtained difference multi-valued image is binarized, and the difference area calculation circuit 41 calculates the difference area of the result. The other procedures are similar to those of the embodiment shown in FIG.

FIG. 12 shows an example for studying the behavior of a plurality of experimental animals such as rats and mice. Air is supplied to the air conditioner 1A through an air supply pipe 2C. In the air conditioner 1A, the temperature and humidity of air are adjusted to be constant. This air is supplied to the breeding cage 10A by the blower 12A. Rearing cage 10A
Rats 14R1, 14R2 and 14R3 are raised in. The imaging device 20 images the rearing cage 10A from the upper part and rats 14R1, 14R2, 14R
Get 3 images. The subsequent image monitoring method is similar to that of the embodiment shown in FIG. Since this embodiment is for studying the behavior of experimental animals, the data accumulated in the position distribution addition circuit 37 and the difference area distribution addition circuit 42 are analyzed in particular.
In this example, it is possible to investigate the influence of the properties and quality of food and air on experimental animals.

〔The invention's effect〕

According to the present invention, the behaviors of a plurality of organism groups can be image-monitored, so that abnormalities in the behavior patterns of organisms caused by inflow of poisonous substances and other factors can be detected accurately and highly accurately.
As shown in the example of the water treatment plant, by monitoring the behavior of the school of fish, it is possible to promptly take emergency measures such as issuing an alarm and stopping water intake in the event of an abnormality, and it is possible to secure a high level of water quality safety. effective.

[Brief description of drawings]

FIG. 1 is a diagram for explaining an embodiment of the present invention, FIGS. 2 and 3 are diagrams showing images of a plurality of fish schools, FIG. 4 is a diagram showing a luminance frequency distribution, and FIG. 5 is a binary image. FIGS. 6 and 7 are diagrams showing the position distribution of fish in the depth direction, FIGS. 8 and 9 are diagrams for explaining the difference calculation, and FIGS. 10 and 11 are diagrams showing the difference area distribution, FIG. 12 is a view showing a part of an example of raising experimental animals. 1 ... Environment control tank, 10 ... Water tank, 14 ... Fish, 20 ... Imaging device, 30 ... Image monitoring device, 32 ... A / D converter, 35 ...
Binarization circuit, 36 ... Position distribution calculation circuit, 38 ... Position distribution comparison circuit, 40 ... Difference calculation circuit, 43 ... Difference area distribution comparison circuit, 38A, 43A, 44A ... Alarm device, 50 ... Monitor TV, 60 …… Image monitor, 70 …… Keyboard, 80 ……
CRT.

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Naoki Hara 5-2-1 Omika-cho, Hitachi City Inside the Omika Plant, Hitachi Ltd. (72) Inventor Mikio Yoda 5-2-1 Omika-cho, Hitachi (56) References JP 62-80557 (JP, A) Actual development 61-19765 (JP, U) 38th water supply research presentation (Showa 62-5) P. 485-487

Claims (3)

(57) [Claims] 1. An image pickup device installed on a side surface of the aquarium for converting image information of a plurality of aquatic animals kept in the aquarium into electric signals at regular time intervals, an illumination device for illuminating the aquatic animal, and A first image storage unit that stores an image captured by the image capturing apparatus and a second image storage unit that stores the image at a time different from the first image storage unit are provided, and the position distribution of the aquatic animal in the water exploration direction in the image. First image monitoring means having position distribution calculation means for calculating the position distribution, position distribution addition means for adding the position distributions, and position distribution comparison means for comparing the added position distribution and the normal position distribution. An image difference means for obtaining a difference image between the first image storage means and the second image storage means, a difference area calculation means for calculating an area of the difference image, and a surface for calculating a frequency distribution of the difference area. At least one image monitoring unit is provided from among a second image monitoring unit having a distribution calculation unit and a difference area comparison unit that compares the frequency distribution with a normal frequency distribution, and the first image monitoring unit is provided. An image monitoring apparatus for an aquatic animal group, characterized in that the behavior of the aquatic animal is determined based on one or both of the means and the second image monitoring means. 2. The image monitoring apparatus for an aquatic animal group according to claim 1, wherein the position distribution comparison means compares the position distributions with a ratio of an area near a specific water surface to the total area of the position distributions. 3. The image monitoring apparatus for an aquatic animal group according to claim 1, wherein the difference area comparing means compares the ratio of the area of the large area to the total area of the area distribution.