JP2007187575A - Device and method of monitoring water quality - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a device for monitoring water quality capable of accurately judging the abnormality of water quality without causing the determination mistake of the abnormality of water quality even if specific conditions other than the abnormality of water quality occur, and to provide a method of monitoring water quality. <P>SOLUTION: The device is constituted so as to capture and analyze the image of the fish housed in a water tank 1 to monitor the water quality in the water tank 1 and composed of an advance direction operating means for calculating the advancement direction of the fish from a plurality of captured images a direction change quantity operating means for calculating the change quantity in the advance direction of the fish on the basis of the advance direction calculated by the direction change quantity operating means, a change quantity averaging means for calculating the time average value of the change quantity in the advancement direction calculated by the direction change quantity operating means and a water quality determination means for determining water quality on the basis of the time average value of the change quantity in the advancement direction calculated by the change quantity averaging means. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a water quality monitoring apparatus and a water quality monitoring method. More specifically, small fish (eg, medaka) that are sensitive to toxic substances as living organisms are placed in multiple tailwater tanks, and the captured small fish images are processed by a computer to automatically track the behavior of each small fish in real time. The present invention relates to a device for detecting an abnormality in water quality.

In recent years, there has been a growing interest in protecting safe water from environmental degradation caused by terrorism and illegal dumping.
When inspecting the water quality of rivers and ponds, an unspecified number of toxic substances cannot be detected by a water quality inspection device using an industrial instrument. In addition, depending on the type of toxic substance, it takes time for pretreatment and component analysis, making it difficult to respond quickly.
Therefore, water-related facilities such as water purification plants often detect abnormalities in water quality using not only industrial instruments but also organisms such as fish. In recent years, the behavior of fish is photographed and the images are processed. Techniques have been developed to determine water quality abnormalities based on abnormal behavior of fish recognized by doing so.
Abnormal behavior of fish when poisonous substances are mixed in, nose-lifting behavior, repeated rapid movement / stop, frequent direction change, sinking behavior (behavior that repeats rapid rise and fall), gathers at a specific location in the aquarium It is known that the above behavior is detected and the water quality is judged using various parameters.

In order to grasp the repetition of rapid movement / stop of a fish, a technique using the acceleration of the fish has been developed (conventional example 1: Patent Document 1).
The technique of Conventional Example 1 forms a fish acceleration frequency distribution graph within a predetermined time, and when the frequency of acceleration abnormality is higher than a predetermined number, the rapid movement / stop of the fish is repeated. It is judged that an abnormality has occurred.

Moreover, the technique which judges water quality abnormality by grasping | ascertaining the frequent direction change of a fish is also developed (conventional example 2: patent document 2).
In the technique of Conventional Example 2, since the fish has an elongated shape, the longitudinal direction is defined as the direction of the fish, the number of times the direction is reversed is counted, and if the number of times is greater than normal, water quality abnormality occurs. It is to be judged.

  However, in the patent of Conventional Example 1, since only the acceleration frequency distribution is formed, even if some fish have an abnormal behavior due to illness or the like, an abnormality caused by the abnormal behavior is caused. Acceleration is also included in the frequency distribution. Then, since it is not possible to distinguish between special circumstances other than water quality abnormalities and real water quality abnormalities, there is a high possibility that an error in determining water quality abnormalities will occur.

  Similarly, in the case of the conventional example 2, since only the number of inversions of the fish is counted, it is not possible to distinguish between the special circumstances other than the water quality abnormality and the real water quality abnormality, and an error in judging the water quality abnormality occurs. Is likely to occur. Moreover, the conventional example 2 only considers the reversal of the fish, that is, the case where the fish changes its direction by 180 °. Therefore, when the fish swims zigzag, the direction is changed frequently. May not be reflected in the number of inversions. Then, even if a water quality abnormality occurs, the abnormality may not be detected.

JP-A-63-175766 JP-A-63-133060

  SUMMARY OF THE INVENTION In view of the above circumstances, an object of the present invention is to provide a water quality monitoring device and a water quality monitoring method capable of accurately determining a water quality abnormality without causing a water quality abnormality determination error even if a special situation other than the water quality abnormality occurs. And

A water quality monitoring device according to a first aspect of the present invention is a monitoring device that monitors and analyzes the quality of water in a water tank by photographing and analyzing an image of fish contained in the water tank, and is a predetermined time calculated from a plurality of photographed images. It is characterized by comprising water quality judging means for judging the water quality based on the amount of change in the direction of travel of the fish.
A water quality monitoring device according to a second aspect of the present invention is a monitoring device that monitors and analyzes the quality of water in a water tank by photographing and analyzing images of fish contained in the water tank, and calculates the traveling direction of the fish from the plurality of photographed images. Based on the advancing direction calculated by the advancing direction calculating means, the directional change amount calculating means for calculating the amount of change in the advancing direction of the fish, and the change in the advancing direction calculated by the directional change amount calculating means And a change amount averaging means for calculating a time average value of the amount.
A water quality monitoring device according to a third aspect of the present invention is a monitoring device for photographing and analyzing an image of a fish housed in the aquarium to monitor the water quality in the aquarium, and calculating the traveling direction of the fish from the plurality of photographed images. Based on the advancing direction calculated by the advancing direction calculating means, the directional change amount calculating means for calculating the amount of change in the advancing direction of the fish, and the change in the advancing direction calculated by the directional change amount calculating means A change amount averaging means for calculating a time average value of the amount, and a water quality determination means for determining the water quality based on the time average value of the change amount in the traveling direction calculated by the change amount average means. To do.
A water quality monitoring method according to a fourth aspect of the present invention is a monitoring method for monitoring the water quality in a water tank by photographing and analyzing an image of a fish housed in the water tank, and a predetermined time calculated from a plurality of photographed images. The water quality is judged based on the amount of change in the traveling direction of the fish in the water.
A water quality monitoring device according to a fifth aspect of the present invention is a monitoring method for monitoring the water quality in a water tank by photographing and analyzing an image of a fish housed in the water tank, and calculating the traveling direction of the fish from the plurality of photographed images. Based on the advancing direction calculation step, the direction change amount calculating step for calculating the amount of change in the advancing direction of the fish based on the advancing direction calculated in the advancing direction calculating step, and the advancing direction calculated in the direction change amount calculating step The change amount averaging step for calculating the time average value of the change amount is sequentially performed.
A water quality monitoring device according to a sixth aspect of the present invention is a monitoring method for monitoring the water quality in a water tank by photographing and analyzing an image of a fish housed in the water tank, and calculating the traveling direction of the fish from the plurality of photographed images. Based on the advancing direction calculation step, the direction change amount calculating step for calculating the amount of change in the advancing direction of the fish based on the advancing direction calculated in the advancing direction calculating step, and the advancing direction calculated in the direction change amount calculating step The change amount averaging step for calculating the time average value of the change amount and the water quality determination step for determining the water quality based on the time average value of the change amount in the traveling direction calculated in the change amount average step are sequentially performed. Features.
A water quality monitoring device according to a seventh aspect of the present invention is a monitoring device that monitors and analyzes the quality of water in the aquarium by photographing and analyzing images of a plurality of fish contained in the aquarium, and calculates the acceleration of each fish from the captured images. The average of the acceleration of a plurality of fish photographed at the same time, the average acceleration calculation means for calculating the average fish acceleration, and the average fish average acceleration calculated at each time by the fish average acceleration calculation means The time average acceleration calculating means for calculating the time average acceleration within the time period and the water quality determining means for determining the water quality based on the time average acceleration calculated by the time average acceleration calculating means.
The water quality monitoring device according to an eighth aspect of the present invention is the water quality monitoring device according to the seventh aspect, wherein the fish average acceleration calculating means excludes an average acceleration that is abnormally large or abnormally small compared to other average accelerations among the average accelerations of each fish. Then, the average fish acceleration is calculated.
The water quality monitoring device according to a ninth aspect of the present invention is the water quality monitoring device according to the seventh aspect, wherein the time average acceleration calculating means has an abnormally large fish average acceleration and abnormality compared to the fish average acceleration at other times among the fish average acceleration at each time. The time average acceleration is calculated by excluding the small fish average acceleration.

According to the first aspect of the invention, if the fish swims while changing its direction frequently, the amount of change in the traveling direction becomes larger than that in the normal state, so it is possible to detect that an abnormality has occurred in the water quality. In addition, when the fish exhibits abnormal behavior, the direction is often changed greatly, so that the amount of change in the traveling direction is larger than when the direction is changed the same number of times. Therefore, it is possible to detect an abnormality in the water quality quickly and accurately as compared with the case of simply counting the number of direction changes.
According to the second invention, if the fish frequently changes its direction and swims, the time average value of the amount of change in the traveling direction becomes larger than that in the normal state, so it is possible to detect that an abnormality has occurred in the water quality. In addition, when the fish exhibits an abnormal behavior, the direction is greatly changed, so that the time average value is larger than that when the fish is changed the same number of times. Therefore, it is possible to detect an abnormality in the water quality quickly and accurately as compared with the case of simply counting the number of direction changes.
According to the third aspect of the invention, if the fish swims while changing its direction frequently, the time average value of the amount of change in the traveling direction becomes larger than that in the normal state, so that the water quality judging means detects that an abnormality has occurred in the water quality. be able to. In addition, when the fish exhibits an abnormal behavior, the direction is greatly changed, so that the time average value is larger than that when the fish is changed the same number of times. Therefore, it is possible to detect an abnormality in the water quality quickly and accurately as compared with the case of simply counting the number of direction changes.
According to the fourth aspect of the invention, if the fish frequently changes its direction and swims, the amount of change in the traveling direction becomes larger than that in the normal state, so that it is possible to detect that an abnormality has occurred in the water quality. In addition, when the fish exhibits abnormal behavior, the direction is often changed greatly, so that the amount of change in the traveling direction is larger than when the direction is changed the same number of times. Therefore, it is possible to detect an abnormality in the water quality quickly and accurately as compared with the case of simply counting the number of direction changes.
According to the fifth aspect of the invention, if the fish swims while changing its direction frequently, the time average value of the amount of change in the traveling direction becomes larger than that in the normal state, so that it is possible to detect that an abnormality has occurred in the water quality. In addition, when the fish exhibits an abnormal behavior, the direction is greatly changed, so that the time average value is larger than that when the fish is changed the same number of times. Therefore, it is possible to detect an abnormality in the water quality quickly and accurately as compared with the case of simply counting the number of direction changes.
According to the sixth aspect of the present invention, if the fish swims while changing its direction frequently, the time average value of the amount of change in the traveling direction becomes larger than that in the normal state, so it is possible to detect that an abnormality has occurred in the water quality. In addition, when the fish exhibits an abnormal behavior, the direction is greatly changed, so that the time average value is larger than that when the fish is changed the same number of times. Therefore, it is possible to detect an abnormality in the water quality quickly and accurately as compared with the case of simply counting the number of direction changes.
According to the seventh invention, if the movement of the fish becomes faster, the time average acceleration becomes larger than that at the normal time, so that it is possible to detect that an abnormality has occurred in the water quality by the water quality judging means. Moreover, since the average fish acceleration is obtained from the acceleration of a plurality of fish, and the average time acceleration is obtained by averaging the average fish average time, the probability that the time average acceleration shows an abnormal value can be lowered. It is possible to reduce the possibility of occurrence of an erroneous determination of water quality abnormality.
According to the eighth aspect of the invention, special circumstances other than water quality abnormality can be removed, so that the possibility of occurrence of a water quality abnormality determination error can be reduced.
According to the ninth aspect, special circumstances other than the water quality abnormality can be removed, so that the possibility of occurrence of a water quality abnormality determination error can be reduced.

Next, an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 shows a water quality monitoring apparatus according to an embodiment of the present invention, in which 1 is a water tank, 2 is a camera, and 3 is a computer. The water quality monitoring apparatus of the present embodiment can be configured by the water tank 1, the camera 2, and the computer 3, and is characterized by a simple configuration that is completed when various programs for executing water quality monitoring are incorporated into the computer 3.

In the present embodiment, the water tank 1 and the computer 3 can be installed in different places, respectively, and can be monitored from a remote place. It is also possible to transfer collective monitoring and alarms of a plurality of water tanks 1 to a mobile phone or the like.
FIG. 2 shows an example of remote monitoring. Arbitrary communication means such as video cable, wireless LAN or wired LAN, wireless or wired dedicated line, public line can be used between the camera 2 and the computer 3, and the distance between the water tanks 1A to 1D and the computer 3 is as follows. From a few meters to a few tens of kilometers is practical, but remote monitoring is possible with existing technology even at distances beyond that.

The water tank 1 may be of an appropriate size, but it is preferable that the monitoring area 12 is narrowly limited by inserting a partition 11 or the like. The fish to be placed in the aquarium 1 is preferably a small fish that is easy to handle and highly sensitive to harmful substances, but medaka which is particularly easily available is suitable. Medaka has characteristics such as nose-lifting behavior, repeated rapid movement / stopping, frequent direction change, subsidence behavior, and gathering at specific locations in the aquarium when harmful substances are mixed in. Highly reliable judgment results have been obtained for about 200 cases of poisons such as “Arsenic”.
In addition, it is preferable to place about 10 medaka f in the monitoring area 12 in the water tank 1 because the individual medaka f can be specified or the monitoring accuracy can be improved and the image processing is not complicated more than necessary. Although a water tank of a size corresponding to the monitoring area 12 may be used, the water tank 1 having a large non-monitoring area 13 as shown is more convenient for practical work such as replacing the medaka f. is there.
The water tank 1 is supplied with water for water quality inspection through a filter, and drains the water tank after running water.

  An illuminating lamp 4 for irradiating light is provided above the water tank 1. When the illumination lamp 4 is irradiated, the fish appears as a bright spot, and this bright spot is used for recognition of the fish image.

The camera 2 is not particularly limited as long as it can shoot fish images, but any camera can be used, but a camera that can stably shoot for a long period of time is preferable.
Shooting with the camera 2 is preferably performed continuously at regular intervals. It is preferable that the time interval of image processing is shorter because the behavior of the medaka f can be traced more finely. However, if the time interval is too short, image processing cannot catch up and monitoring accuracy cannot be improved much. The preferred range is about 0.033 to 0.5 seconds, but in the present invention, the intervals are 0.1 seconds.
Therefore, the camera 2 continuously shoots the water tank 1 at intervals of 0.1 seconds and sends image data to the computer 3. The computer 3 measures the movement of the medaka f about every 0.1 seconds and performs high-speed calculation processing as image data. For this reason, water quality can be determined in real time.
Further, the number of medaka f serving as sensors is about 10 as described above and is measured every about 0.1 second, so that a fine movement can be detected and a water quality abnormality can be determined with high accuracy.

  The computer 3 is installed with a program for recognizing the image of the fish (medaka f) and judging the water quality based on the image taken from the camera 2, and the fish image recognition means for recognizing the image of the fish by this program. A fish behavior analyzing means for analyzing the behavior of the fish from the recognized fish image and a water quality judging means for judging the water quality from the analyzed fish behavior are configured.

Next, a water quality judgment method executed by the water quality monitoring device will be described.
This water quality judgment method is roughly divided into (1) an image recognition step, (2) a fish behavior analysis step, and (3) a water quality judgment step, and each step is a fish installed in the computer 3 as described above. It is executed by image recognition means (program), fish behavior analysis means (program), and water quality judgment means (program).

  First, the image recognition step S1 is a process of obtaining a fish image from which noise has been removed by processing an image taken by the camera 2 by the fish image recognition means. The fish image recognition means performs, for example, a process of obtaining a fish image by performing a difference process on a background image obtained from a plurality of images and a target image (latest image) of a fish to be monitored. The processing method is not particularly limited as long as the processing method can recognize the fish and track the destination of the fish.

Next, the fish behavior analysis step will be described.
The fish behavior analysis step is a step in which fish behavior analysis means analyzes fish behavior based on the fish image obtained in the image recognition step S1. And the fish behavior analysis means of this embodiment detects frequent direction change which is one of the abnormal behavior of fish when harmful substances are mixed.
Below, the fish direction change detection process by a fish behavior analysis means is demonstrated.
First, as shown in FIG. 3 and FIG. 4 (A), images continuously photographed at regular intervals are converted into fish images F1 to F3 in the image recognition step S1. Then, the moving direction calculation means calculates a movement vector V composed of the moving direction and the moving speed of the fish from the converted fish images F1 to F3 (traveling direction calculating step S2).
In FIG. 4A, F4 indicates an image in which fish images F1 and F2 are overlapped, F5 indicates an image in which fish images F2 and F3 are overlapped, and as indicated by F4 and F5, movement vectors V1 and V2 are It can be obtained from the shooting interval between two consecutive fish images and the coordinates of the barycentric position of the fish in each fish image. The method for calculating the movement vector from the two fish images is not particularly limited, and any method may be used.

As shown in FIG. 3 and FIG. 4A, the amount of change in the direction of travel of the fish is calculated by the direction change amount calculation means from the movement vectors V1 and V2 obtained by the direction of movement calculation means (direction change amount calculation). Step S3). The movement vectors V1 and V2 include information on the traveling direction of the fish and its moving speed. Since the change in the traveling direction of the fish is a change in the inclination between the movement vectors V1 and V2, the movement vectors V1 and V2 Is calculated as the amount of change in the direction of travel of the fish.
In addition, when a fish changes direction, it may change direction clockwise or counterclockwise, but since it does not have any special relationship with the detection of water quality abnormality, it will change direction. What is necessary is just to let the absolute value of the angle which movement vector V1, V2 makes be the variation | change_quantity of the advancing direction of a fish.
Furthermore, although the fish changes direction three-dimensionally, if the depth of the monitoring area 12 is set to such an extent that the fish cannot swim in the depth direction, specifically, the length of the fish, the fish Since only a two-dimensional direction change is possible, the detection accuracy of the amount of change in the direction of travel of the fish can be increased.

As shown in FIGS. 3 and 4A, the time average value of the change amount in the traveling direction is calculated by the change amount averaging means from the change amount in the traveling direction of the fish obtained by the direction change amount calculating means (change). Amount average step S4). The change amount averaging means integrates and averages all the change amounts in the traveling direction calculated within a predetermined time, for example, 100 seconds, and calculates a time average value.
Instead of calculating the amount of change in the traveling direction calculated within a predetermined time, a preliminary average value is obtained as an average value of the amount of change in the traveling direction within a shorter time within the predetermined time, and the predetermined time The preliminary average values calculated within the total may be integrated and averaged to calculate the time average value. In this case, if the preliminary average value at a certain time is abnormally high compared with the preliminary average value at other times, or is abnormally low compared with other preliminary average values, the preliminary average value is removed. Thus, the time average value can be calculated. Then, it is possible to eliminate the influence of special circumstances other than water quality abnormalities on time average values such as fish behaving abnormally regardless of water quality for a certain moment, so it is possible that misjudgment of water quality abnormality may occur Can be lowered.

As shown in FIG. 3, when the time average value is calculated in the fish behavior analysis step, the water quality is determined by the water quality determination means based on the time average value (water quality determination step S5). This water quality judgment is judged by comparing the allowable value calculated from the normal average value and the time average value. The normal average value is a time average value of the amount of change in the traveling direction within a predetermined time when there is no abnormality in the water quality, and has a certain width.
When the fish frequently changes direction, the number of direction changes and the angle thereof increase, so that the time average value of the amount of change in the traveling direction also becomes larger than the average value at normal time. Also, even if the number of direction changes is the same as when there is no water quality abnormality, the direction of change in the direction of travel is still large in this case because the fish often changes direction when it shows abnormal behavior. The average value is larger than the normal average value.
Therefore, if it is determined that the water quality abnormality has occurred when the time average value is larger than the allowable value, the water quality can be monitored based on the frequent turn of the fish. The allowable value is set to about 1.5 to 3 times the upper limit of the normal average value, but how much response time and false alarm are required until an abnormality is detected after the water quality required for the device deteriorates. An appropriate value may be set based on the environment in which the apparatus is used, such as whether it is allowed, and the standard for setting the allowable value is not particularly limited.

If the water quality abnormality occurs, fish activity may stop, so if the time average value becomes smaller than the allowable value, it can be determined that the water quality abnormality has occurred. Water quality monitoring based on outages is also possible. The allowable value in this case is set to about 0.3 to 0.7 times the lower limit value in the normal average value, but an appropriate value may be set based on the environment in which the apparatus is used.
Furthermore, instead of the change amount averaging means, an integration means for simply integrating the amount of change in the direction of travel of the fish obtained by the direction change amount calculation means within a predetermined time is provided, and the water quality determination means using the integrated value May determine the water quality. In this case, the water quality may be determined by comparing the integrated value with an allowable value calculated from the normal integrated value. The normal integrated value is an integrated value in the traveling direction within a predetermined time when there is no abnormality in water quality, and it goes without saying that it has a certain range.

  Furthermore, the water quality determination method executed by the water quality monitoring device may be configured only by (1) an image recognition step and (2) a fish behavior analysis step without providing the (3) water quality determination step. In this case, (2) the time average value obtained in the fish behavior analysis step may be displayed on a monitor or the like as it is, or may be displayed as a time variation graph, and the person may judge the numerical value or graph.

In the above example, the case of one fish is described, but a plurality of fish are photographed simultaneously, the amount of change in the direction of travel for each fish is calculated, and finally the time from the amount of change in the direction of travel of all fish An average value may be calculated, and the water quality may be determined based on the average value. In this case, the error of water quality judgment can be reduced compared to using the average value of one fish.
In particular, within a predetermined time, first, the average value of the amount of change in the direction of travel for each fish (fish average change amount) is calculated, and the average value of all fish average change amounts is averaged to obtain the time average value. If there is a fish that has an abnormally high average fish change compared to other fish, or a fish that has an abnormally low average fish change compared to other fish, The time average value can be calculated by removing the fish average change amount of the fish. Then, it is possible to eliminate the influence of special circumstances other than water quality abnormalities, such as some fish suffering from illness and other abnormal behavior, on the time average value, which may cause misjudgment of water quality abnormalities Can be lowered.

Further, as described above, the angle formed by the movement vectors V1 and V2 may be used as the amount of change in the direction of travel of the fish, but in this case, when the fish repeatedly changes direction with a large amount of change and changes direction with a small amount of change, There is a possibility that the time average value of the amount of change in the traveling direction becomes relatively small and an error occurs in the water quality judgment.
When calculating the time average value, the above problem can also be solved by excluding the amount of change below the threshold, but without using the angle formed by the movement vectors V1 and V2 as the amount of change in the direction of travel, it proceeds as follows. If the direction change amount is determined, it is possible to prevent an error from occurring in the water quality judgment due to the direction change with a small change amount, and the water quality judgment can be facilitated.

As shown in FIG. 4B, when the base points of the movement vectors V1 and V2 are described on the xy coordinates in accordance with the origin, the movement vector V2 is a quadrant in which the movement vector V1 exists (FIG. B) may exist in the first quadrant) or may exist in a quadrant different from the movement vector V1 (second, third or fourth quadrant in FIG. 4B). Further, even when the quadrant exists in a quadrant different from the movement vector V1, the quadrant adjacent to the quadrant in which the movement vector V1 exists (second quadrant in FIG. 4B) or the movement vector V1. In some cases, there is a quadrant that is not adjacent to the quadrant in which there is (a third quadrant in FIG. 4B).
Here, when the movement vector V2 exists in the same quadrant as the movement vector V1, the amount of change in the direction of travel of the fish is small, and each component of the movement vector V2 has the same sign as each component of the movement vector V1. Yes. That is, it can be considered that the moving direction of the fish has not changed in either the x-axis direction or the y-axis direction.
On the other hand, when the movement vector V2 exists in a quadrant different from the movement vector V1, each component of the movement vector V2 has an x component, a y component, or both have a different sign from each component of the movement vector V1. ing. That is, at least one of the x-axis direction and the y-axis direction can be regarded as the fish moving direction changing.

  Therefore, when the movement vector V2 exists in the same quadrant as the movement vector V1, the amount of change in the traveling direction is 0, and when the movement vector V2 exists in a quadrant different from the movement vector V1, the amount of change in the traveling direction is 1. In this case, the number of changes in the moving direction of the fish in at least one of the x-axis direction and the y-axis direction is an integrated value of the amount of change in the traveling direction within a predetermined time. Then, if the time average value obtained by averaging the integrated values becomes larger than the allowable value calculated from the normal average value, it can be determined that a water quality abnormality has occurred. Water quality monitoring based on frequent turning can be performed. In this case, the permissible value is set to about 1.5 to 3 times the upper limit of the average value during normal operation. What is the response time from when the water quality required for the device deteriorates until the abnormality is detected, and what is the false alarm? An appropriate value may be set based on the environment in which the apparatus is used, such as whether it is allowed, and the criteria for setting the allowable value are not particularly limited.

If the water quality abnormality occurs, fish activity may stop, so if the time average value becomes smaller than the allowable value, it can be determined that the water quality abnormality has occurred. Water quality monitoring based on outages is also possible. The allowable value in this case is set to about 0.3 to 0.7 times the lower limit value in the normal average value, but an appropriate value may be set based on the environment in which the apparatus is used.
Furthermore, the water quality determination means may determine the water quality using the integrated value without averaging the integrated value of the amount of change in the traveling direction to obtain the time average value. In this case, the water quality may be determined by comparing the integrated value with an allowable value calculated from the normal integrated value. The normal integrated value is an integrated value of the amount of change in the traveling direction within a predetermined time when there is no abnormality in the water quality, and it goes without saying that it has a certain range.

  Here, when the movement vector V2 exists in a quadrant different from the movement vector V1 and the quadrant is not adjacent to the quadrant where the movement vector V1 exists, the movement direction of the fish is the x-axis direction and the y-axis direction. Both directions have changed. That is, in such a case, the movement direction of the fish is greatly changed compared to the case where the movement vector V2 exists in the quadrant adjacent to the movement vector V1. In this case, if the amount of change in the traveling direction is 2, even if it is the same one turn, if a large change in direction occurs, the integrated value of the amount of change in the traveling direction becomes large. The time average value also increases. In other words, it is possible to evaluate the direction change by weighting according to the moving direction, and the evaluation can be reflected in the water quality judgment. It is possible to reduce the possibility of occurrence.

In the case where a plurality of fish are photographed simultaneously, in the fish behavior analysis step, it is possible to detect the rapid movement / rest of the fish when a harmful substance is mixed.
In this case, until the movement vector V is calculated from images continuously captured at a fixed time interval, the same processing as that in the case of detecting frequent direction changes is performed as described above (FIG. 4 (A)).
As shown in FIG. 5, the acceleration of the fish is calculated by the acceleration calculation means from the movement vectors V1 and V2 obtained by the traveling direction calculation means (acceleration calculation step S2). The acceleration calculation means calculates the accelerations of a plurality of fish that are photographed simultaneously.

  As shown in FIG. 5, the average acceleration (fish average acceleration) of a plurality of fishes is calculated by the fish average acceleration calculation means from the accelerations of the plurality of fish obtained by the acceleration calculation means (fish average acceleration calculation step S4). At this time, the average fish acceleration may be calculated using the acceleration of all the fish, but there are fish whose acceleration is abnormally large compared to the acceleration of other fish and fish that are abnormally small compared to the acceleration of other fish. In this case, the fish average acceleration can be calculated by removing the acceleration of the fish. Then, it is possible to eliminate the influence of special circumstances other than water quality abnormalities such as some fish suffering from illness and other abnormal behavior on fish average acceleration, so there is a possibility of misjudgment of water quality abnormality Can be lowered.

  As shown in FIG. 5, the time average acceleration calculation means calculates the time average acceleration from the fish average acceleration obtained by the fish average acceleration calculation means (time average acceleration calculation step S4). At this time, the average time acceleration may be calculated using all the fish average acceleration, but the fish average acceleration is abnormally larger than the fish average acceleration at other times or the fish average acceleration at other times. If there is something that is abnormally small compared to, the fish average acceleration can be removed to calculate the time average acceleration. Then, it is possible to eliminate the influence of special circumstances other than water quality abnormalities, such as fish abnormal behavior regardless of water quality for a certain moment, on the time average acceleration, so it is possible that misjudgment of water quality abnormality may occur Can be lowered.

  As shown in FIG. 5, when the time average acceleration is calculated in the time average acceleration calculation step, the water quality is determined by the water quality determination means based on the time average value (water quality determination step S5). This water quality judgment is made by comparing the measured time average acceleration with an allowable value calculated from the normal average acceleration. The normal average acceleration is a time average acceleration when there is no abnormality in water quality, and it goes without saying that it has a certain width.

When the fish repeats abrupt movement / stop, the acceleration increases, so the measured time average acceleration is also larger than the normal average acceleration.
Therefore, if it is determined that a water quality abnormality has occurred when the measured time-average acceleration is greater than the allowable value, water quality monitoring based on repeated rapid movement and stationary of fish can be performed. it can. The allowable value is set to about 1.5 to 3 times the upper limit of the normal average acceleration, but how much response time and false alarm are allowed until the abnormality is detected after the water quality required for the device deteriorates. An appropriate value may be set based on the environment in which the apparatus is used, and the standard for setting the allowable value is not particularly limited.

If the water quality abnormality occurs, fish activity may stop, so if the measured time average acceleration becomes smaller than the allowable value, it can be determined that the water quality abnormality has occurred. It is also possible to monitor water quality based on the suspension of activities. The allowable value in this case is set to about 0.3 to 0.7 times the lower limit value in the normal average acceleration, but an appropriate value may be set based on the environment in which the apparatus is used.
Furthermore, the water quality determination means may determine the water quality using the integrated value of acceleration without obtaining the time average acceleration. In this case, the water quality may be determined by comparing the integrated value with an allowable value calculated from the normal integrated value. The normal integrated value is an integrated value of acceleration within a predetermined time when there is no abnormality in water quality, and it goes without saying that it has a certain range.

  The present invention is most suitable for facilities that require strict water quality management, such as water purification plants, sewage treatment facilities, drinking water manufacturers, and food manufacturers.

It is explanatory drawing of the water quality monitoring apparatus which concerns on one Embodiment of this invention. It is explanatory drawing of the image transmission method. It is a flowchart of the fish behavior analysis process by a fish behavior analysis means. It is explanatory drawing of the fish behavior analysis process by a fish behavior analysis means. It is a flowchart of the fish behavior analysis process by other fish behavior analysis means.

Explanation of symbols

1 Aquarium 2 Camera 3 Computer 4 Lighting

Claims (9)

A monitoring device that captures and analyzes images of fish contained in the aquarium and monitors the water quality in the aquarium,
A water quality monitoring apparatus comprising water quality judgment means for judging water quality based on a change amount of a fish traveling direction within a predetermined time calculated from a plurality of captured images. A monitoring device that captures and analyzes images of fish contained in the aquarium and monitors the water quality in the aquarium,
A traveling direction calculation means for calculating the traveling direction of the fish from a plurality of captured images;
Direction change amount calculating means for calculating the amount of change in the traveling direction of the fish based on the direction of travel calculated by the direction of travel calculating means;
A water quality monitoring device comprising: a change amount averaging means for calculating a time average value of a change amount in the traveling direction calculated by the direction change amount calculation means. A monitoring device that captures and analyzes images of fish contained in the aquarium and monitors the water quality in the aquarium,
A traveling direction calculation means for calculating the traveling direction of the fish from a plurality of captured images;
Direction change amount calculating means for calculating the amount of change in the traveling direction of the fish based on the direction of travel calculated by the direction of travel calculating means;
Change amount averaging means for calculating a time average value of the change amount in the traveling direction calculated by the direction change amount calculation means;
A water quality monitoring device comprising: a water quality judging means for judging a water quality based on a time average value of a change amount in the traveling direction calculated by the change amount averaging means. A monitoring method for photographing and analyzing images of fish contained in the aquarium to monitor the water quality in the aquarium,
A water quality monitoring method for judging a water quality based on a change amount in a traveling direction of a fish within a predetermined time calculated from a plurality of photographed images. A monitoring method for photographing and analyzing images of fish contained in the aquarium to monitor the water quality in the aquarium,
A traveling direction calculating step for calculating a traveling direction of the fish from a plurality of captured images;
Based on the traveling direction calculated in the traveling direction calculation step, a direction change amount calculating step that calculates a change amount in the traveling direction of the fish,
A water quality monitoring method comprising: sequentially performing a change amount averaging step for calculating a time average value of a change amount based on the traveling direction calculated in the direction change amount calculation step. A monitoring method for photographing and analyzing images of fish contained in the aquarium to monitor the water quality in the aquarium,
A traveling direction calculating step for calculating a traveling direction of the fish from a plurality of captured images;
Based on the traveling direction calculated in the traveling direction calculation step, a direction change amount calculating step that calculates a change amount in the traveling direction of the fish,
Based on the traveling direction calculated in the direction change amount calculation step, a change amount average step for calculating a time average value of the change amount;
A water quality monitoring method comprising: sequentially performing a water quality determination step for determining water quality based on a time average value of a change amount in the traveling direction calculated in the change amount average step. A monitoring device that captures and analyzes images of a plurality of fish stored in the aquarium and monitors the water quality in the aquarium,
Acceleration calculation means for calculating the acceleration of each fish from the captured image;
Fish average acceleration calculation means for averaging the accelerations of a plurality of fish photographed at the same time and calculating the fish average acceleration;
A time average acceleration calculation means for calculating a time average acceleration within a predetermined time from the fish average acceleration of each time calculated by the fish average acceleration calculation means;
A water quality monitoring device comprising water quality determination means for determining water quality based on the time average acceleration calculated by the time average acceleration calculation means. The fish average acceleration calculating means is
8. The water quality according to claim 7, wherein, among the average accelerations of each fish, the fish average acceleration is calculated by excluding an abnormally large average acceleration or an abnormally small average acceleration compared to other average accelerations. Monitoring device. The time average acceleration calculating means is
Of the average fish average acceleration at each time, the average average acceleration is calculated by excluding the abnormally large fish average acceleration and the abnormally small fish average acceleration compared to the fish average acceleration at other times. The water quality monitoring device according to claim 7.

Images