Information processing device and its contamination detection method, water treatment system, and contamination detection program

Abstract

To reduce an influence of noise on contamination detection.SOLUTION: An information processing device (1) includes: an image acquisition unit (101) that acquires sludge images taken of a floc by a photographing device through an inspection window provided in a flocculation tank for forming the floc; and a sludge image detection unit (103) that calculates statistics of shading values for each micro-region by using multiple sludge images divided into a plurality of micro-regions and detects sludge of the inspection window based on the calculated statistical value.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and the like that detects dirt on a window between a liquid to be treated containing solid suspended matter and an imaging device.

Background Art

[0002] Conventionally, a technique has been used in which a chemical such as a flocculant is added to a liquid to be treated such as sewage sludge and stirred to aggregate solid suspended matter to form flocs, and the aggregated sludge, which is an aggregate of these flocs, is dehydrated to obtain dehydrated sludge. In order to stably perform sludge dehydration, it is necessary to form flocs of an appropriate size. Therefore, in the process of forming flocs, it is desirable to perform control at any time to maintain the size of the flocs at an appropriate size while grasping the state of the flocs being formed.

[0003] Among the techniques for grasping the state of flocs, there is a technique that uses an image of the flocs taken by an imaging device. In this case, if the window between the flocs and the imaging device is dirty, it is difficult to appropriately grasp the state of the flocs. Therefore, it is desirable to detect the dirt on the window and quickly remove the detected dirt.

[0004] As documents disclosing techniques for detecting dirt on the window between the flocs and the imaging device, for example, the following Patent Documents 1 and 2 can be cited. The floc image recognition device described in Patent Document 1 includes image processing means for performing image processing by classifying the image taken by the imaging device into flocs and the background for each pixel. The image processing means always determines that the number of pixels indicating flocs from the start of image processing is the same as the number of such pixels in the previous image, and when this coincidence occurs twice in a row, determines that the window is dirty. Further, the dirt detection device for the imaging device described in Patent Document 2 extracts the difference in density values of a plurality of images taken by the imaging device, integrates the extracted differences in density values, and determines that the dirt exists in a region where the integrated difference in density values is equal to or less than a predetermined value.

Prior Art Documents

Patent Documents

[0005] [Patent Document 1] Japanese Patent Laid-Open No. 62-85843 [Patent Document 2] Japanese Patent Laid-Open No. 2003-259358 [Summary of the Invention] [Problems to be Solved by the Invention]

[0006] The devices described in Patent Documents 1 and 2 are susceptible to the influence of noise on the detection of dirt. For example, in the case of Patent Document 1, if a pixel corresponding to window dirt is misjudged as the background even once due to noise, it becomes difficult to detect the above-mentioned dirt. Also, in the case of Patent Document 2, if the difference in grayscale values in the area containing dirt becomes a large value even once due to noise, it becomes difficult to detect the above-mentioned dirt.

[0007] One aspect of the present invention aims to reduce the influence of noise on the detection of dirt. [Means for Solving the Problems]

[0008] To solve the above problems, an information processing apparatus according to one aspect of the present invention includes an acquisition unit that acquires an image of the flock captured by an imaging device through a window provided in a tank for forming the flock, and a detection unit that calculates a statistical value of grayscale values for each of the micro regions using a plurality of the images divided into a plurality of micro regions and detects dirt on the window based on the statistical value.

[0009] Also, a control method for an information processing apparatus according to another aspect of the present invention includes an acquisition step of acquiring an image of the flock captured by an imaging device through a window provided in a tank for forming the flock, and a detection step of calculating a statistical value of grayscale values for each of the micro regions using a plurality of the images divided into a plurality of micro regions and detecting dirt on the window based on the statistical value. [Effects of the Invention]

[0010] According to one aspect of the present invention, it is possible to reduce the influence on the detection of dirt due to noise.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present invention will be described in detail. For convenience of explanation, members having the same functions as those shown in each embodiment are denoted by the same reference numerals, and the description thereof will be omitted as appropriate.

[0013] [Embodiment 1] An embodiment of the present invention will be described with reference to FIGS. 1 to 10.

[0014] (Water treatment system) The outline of the water treatment system 100 according to this embodiment will be described with reference to FIG. 2. FIG. 2 is a diagram showing a configuration example of the water treatment system 100. The water treatment system 100 is a system for separating a liquid to be treated into solid suspended matter and a liquid component. As shown in the figure, it includes an information processing device 1, a control device 3, a flocculator 5, an addition device 6, and a dehydrator 9. Hereinafter, an example in which the liquid to be treated is sludge generated by biological treatment such as sewage will be described. Sludge is a liquid containing solid suspended matter and can also be called slurry.

[0015] The flocculator 5 is a device that aggregates solid suspended matter in sludge to form flocs and obtains aggregated sludge. The flocculator 5 in FIG. 2 includes an aggregation tank (also called a stirring tank) 51 (tank), a stirring blade 52, a motor 53, and an inspection window 54 (window). Since the sludge in the aggregation tank 51 is stirred by rotating the stirring blade 52 by the motor 53, the flocculator 5 can also be said to be a stirring device. In addition, the flocculator 5 is provided with a sludge inlet 55, a chemical inlet 56, and an outlet 57.

[0016] Furthermore, a photographing device 72 and a lighting device 71 for photographing are attached to the inspection window 54. The photographing device 72 may be any device that can at least take still images. During the operation of the water treatment system 100, it is preferable that the flocculation tank 51 is made of a material that is not light-transmissive so that the way light hits the flocs does not change. Also, as in the illustrated example, the photographing device 72 and the lighting device 71 are housed in a light-shielding dark box with an opening on the inspection window 54 side, and it is preferable to shield at least the remaining part of the inspection window 54 from light during photographing. Note that the photographing device 72 may take a photograph from above the liquid surface. Also, the photographing device 72 may be submerged in water for photographing.

[0017] The dehydrator 9 is disposed downstream of the flocculator 5 and is a device that dehydrates the flocculated sludge discharged from the flocculator 5. The dehydrator 9 shown in FIG. 2 is a screw press type dehydrator including an outer cylinder screen 91 and a screw 92. The dehydrator 9 is also provided with a sludge inlet 93, a filtrate outlet 94, and a dehydrated cake outlet 95. Of course, the dehydrator 9 may be any device that can dehydrate the flocculated sludge and is not limited to the screw press type. For example, a centrifugal dehydrator, a filter press type dehydrator, a belt press dehydrator, or the like can also be applied.

[0018] In the water treatment system 100, the sludge to be treated is continuously or intermittently supplied from a sludge inlet 55 into the flocculation tank 51 of the flocculator 5 by a supply device (not shown). The supply rate of the sludge may be automatically controlled by the supply device or its control device according to the treatment rate of the sludge by the flocculator 5 and the dehydrator 9.

[0019] Then, based on the control of the control device 3, the adding device 6 injects a chemical (including at least a flocculant) for aggregating sludge into the flocculation tank 51 from the chemical injection port 56. In this state, the motor 53 is driven to rotate the stirring blade 52, stirring the sludge and the chemical in the flocculation tank 51 to form flocs. Then, the aggregated sludge, which is a mixture of the formed flocs and the water contained in the sludge, is discharged from the discharge port 57. Note that the chemical may be injected in advance into the sludge before it is introduced into the flocculator 5 from the sludge inlet 55.

[0020] During the process of forming these flocs, the imaging device 72 captures an image. Since the sludge is shown in this image, the image is hereinafter referred to as a sludge image. In the sludge image, a plurality of flocs overlap, making it difficult to calculate the number of flocs and the area of each individual floc. Therefore, the information processing device 1 detects and analyzes the background area rather than the flocs from the sludge image, and calculates an index value indicating the formation state of the flocs.

[0021] Subsequently, this aggregated sludge is supplied from the sludge inlet 93 of the dehydrator 9 into the outer cylinder screen 91. Inside the dehydrator 9, the above-mentioned aggregated sludge is dehydrated under pressure by the screw 92, the filtrate is discharged from the filtrate discharge port 94, and the dehydrated cake, which is a solid mass of the dehydrated aggregated sludge, is discharged from the dehydrated cake discharge port 95.

[0022] The control device 3 controls at least one of the chemical addition amount by the adding device 6 and the stirring speed in the flocculator 5 so that the size of the flocs becomes an appropriate size according to the index value indicating the formation state of the flocs calculated by the information processing device 1. The details of this control will be described later. Also, the control device 3 may control other devices in the water treatment system 100. Also, the above-mentioned stirring speed can also be referred to as stirring intensity.

[0023] As described above, the water treatment system 100 includes an adding device 6 that adds a chemical for aggregating solid suspended matter to the sludge in the aggregation tank 51, a flocculator 5 that stirs the sludge in the aggregation tank 51, a photographing device 72 that photographs the flocs in the aggregation tank 51 through the inspection window 54, an information processing device 1 that calculates an index value indicating the formation state of the flocs from the image photographed by the photographing device 72, and a control device 3 that controls at least one of the chemical addition amount and the stirring speed by the adding device 6 according to the calculated index value.

[0024] As described above, the information processing device 1 detects and analyzes the background area rather than the flocs from the sludge image to calculate an index value indicating the formation state of the flocs. Therefore, an index value accurately indicating the formation state of the flocs can be calculated from a sludge image in which a plurality of flocs overlap and appear. And the control of the chemical addition amount and the control of the stirring speed are both effective for changing the size of the flocs. Thus, according to the water treatment system 100, while treating the sludge, the formation state of the flocs can be automatically improved, and flocs of an appropriate size can be stably generated.

[0025] (Information Processing Device) A more detailed configuration of the information processing device 1 will be described with reference to FIG. 1. FIG. 1 is a block diagram showing an example of the main part configuration of the information processing device 1. As shown in FIG. 1, the information processing device 1 includes a control unit 10 that comprehensively controls each part of the information processing device 1, and a storage unit 11 that stores various data used by the information processing device 1. Further, the information processing device 1 includes a communication unit 12 for the information processing device 1 to communicate with other devices (for example, the control device 3), an input unit 13 that receives an input to the information processing device 1, and an output unit 14 for the information processing device 1 to output information.

[0026] The control unit 10 also includes an image acquisition unit 101 (acquisition unit), an image analysis unit 102 (processing unit), a stain detection unit 103 (detection unit), and an instruction unit 104. The storage unit 11 stores a sludge image 111 and a binarized image 112, and also includes an index value storage unit 113. Further, the storage unit 11 includes minute region information 114. Note that the stain detection unit 103 and the minute region information 114 will be described later.

[0027] The image acquisition unit 101 sequentially acquires the sludge image 111 from the imaging device 72 via the communication unit 12. The image acquisition unit 101 stores the acquired sludge image 111 in the storage unit 11. Accordingly, a plurality of sludge images 111 are stored in the storage unit 11.

[0028] The image analysis unit 102 (processing unit) performs image processing for detecting the formation state of flocs for each sludge image 111 stored in the storage unit 11. The image analysis unit 102 includes a binarization processing unit 1021, a background detection unit 1022, and an index value calculation unit 1023.

[0029] The binarization processing unit 1021 binarizes the sludge image 111 stored in the storage unit 11 to generate a binarized image 112 that is divided into a floc region and a background region. Then, the binarization processing unit 1021 stores the generated binarized image 112 in the storage unit 11. The sludge image 111 and the binarized image 112 will be described later with reference to FIG. 3.

[0030] The background detection unit 1022 detects the background region of the flocs from an image in which a plurality of flocs overlap. Specifically, the background detection unit 1022 acquires the binarized image 112 stored in the storage unit 11 and detects the background region in the binarized image 112. The background detection unit 1022 outputs the detection result of the background region to the index value calculation unit 1023. Although details will be described later, the background region is composed of a plurality of small regions.

[0031] The index value calculation unit 1023 analyzes a plurality of small regions that make up the background region detected by the background detection unit 1022, and calculates an index value indicating the formation state of the flock. Further, the index value calculation unit 1023 stores the calculated index value in the index value storage unit 113 of the storage unit 11. The calculation of the index value will be described later.

[0032] The instruction unit 104 gives various instructions to the control device 3 via the communication unit 12. Based on the above various instructions, the control device 3 controls various devices. Note that the instruction unit 104 may control various devices via the communication unit 12. In this case, the control device 3 can be omitted.

[0033] In the present embodiment, the instruction unit 104 instructs the control device 3 to appropriately maintain the size of the flock based on the index value stored in the index value storage unit 113. The control device 3 controls, for example, at least one of the chemical addition amount by the addition device 6 and the rotation speed of the motor 53 in the water treatment system 100 based on the instruction from the instruction unit 104.

[0034] (Regarding the sludge image and the binary image) FIG. 3 and FIG. 4 are diagrams showing examples of sludge images A1 to A5 in which flocks of different sizes are captured and binary images a1 to a5 obtained by binarizing each sludge image. The sludge image A1 shown in FIG. 3 is an image that is generally black, and the flock region is a color closer to white than its background region.

[0035] In the binarization process of the sludge image A1, the binarization processing unit 1021 determines for each pixel constituting the sludge image A1 whether the pixel value of the pixel is equal to or greater than a predetermined threshold value. Then, the binarization processing unit 1021 sets the pixels determined to be equal to or greater than the threshold value in the sludge image A1 to white and the pixels determined to be less than the threshold value to black.

[0036] As a result, a binarized image a1 shown in FIG. 3 is generated. The binarized image a1 is an image in which the flock region 301 is represented in white and its background region 300 is represented in black. Thus, in the binarized image a1, the boundary between the flock region and the background region, which was unclear in the sludge image A1, can be clearly recognized. For example, from the binarized image a1, it is possible to clearly recognize that the gaps between the flocks and the steps in the depth direction are the background region 300, and the outlines, unevenness, etc. of the flocks are also clearly recognized as the background region 300.

[0037] In the sludge images A1 to A5 shown in FIGS. 3 and 4, the visual classification of the flock sizes is "extremely large", "large", "medium", "small", and "extremely small", respectively. As shown in FIGS. 3 and 4, as the flock size approaches from "extremely large" to "extremely small", the background region 300 is subdivided, that is, it can be seen that the area of each of the plurality of small regions constituting the background region 300 becomes smaller and the number becomes larger. Therefore, the index value calculation unit 1023 can calculate an index value indicating the formation state of the flock by analyzing the plurality of small regions constituting the background region.

[0038] For example, the index value calculation unit 1023 may calculate the average area of the small regions as the index value. In this case, the index value calculation unit 1023 first counts the number of small regions by regarding a continuous region composed of adjacent pixels among the pixels included in the background region detected by the background detection unit 1022 as one small region. Then, the index value calculation unit 1023 calculates, as the index value, the value obtained by dividing the total area of the background region by the number of small regions, that is, the average area of the small regions.

[0039] The number of small regions in the binarized images a1 to a5 shown in FIGS. 3 and 4 is 36, 49, 57, 71, and 69, respectively, and the average area, that is, the index value, is 980, 933, 546, 392, and 231 pixels, respectively. Thus, the average area becomes smaller as the flock size becomes smaller. Therefore, the average area of the small regions is appropriate as an index value.

[0040] Note that the analysis of the small area only needs to be such that an index value indicating the formation state of the flock can be obtained, and it is not limited to the above example. For example, the index value calculation unit 1023 may obtain, for each small area, the area, the length of the long side, the length of the short side, the radius or diameter of the circumscribed circle, the radius or diameter of the inscribed circle, or the perimeter by analyzing the small area. Then, the index value calculation unit 1023 may calculate, as the above index value, the average value obtained by averaging the obtained values for all the small areas. Note that the length of the long side and the length of the short side are the lengths of the long side and the short side when the small area is approximated by an ellipse. Also, the radius or diameter of the circumscribed circle is the radius or diameter of the smallest circumscribed circle surrounding the small area. And the radius or diameter of the inscribed circle is the radius or diameter of the largest inscribed circle surrounding the small area.

[0041] (Instructions according to the index value) Based on the index value calculated as described above, the instruction unit 104 instructs the control device 3 to appropriately maintain the size of the flock. For example, when the index value is outside a predetermined appropriate range, the instruction unit 104 may instruct the control device 3 to perform control to return the index value to the appropriate range.

[0042] When the index value is less than the above appropriate range, that is, when the size of the flock corresponds to "extremely small", the instruction unit 104 may instruct the control device 3 to perform control to increase the size of the formed flock. For example, when the amount of the coagulant input is sufficient, generally, if the stirring speed of the flocculator 5 is decreased, the size of the formed flock will increase. Therefore, the instruction unit 104 may instruct the control device 3 to perform control to decrease the rotation speed of the motor 53. Also, when the amount of the coagulant input is insufficient, generally, even if the chemical injection rate of the coagulant is increased, the size of the formed flock will increase. Therefore, the instruction unit 104 may instruct the control device 3 to perform control to increase the addition amount of the coagulant to the adding device 6. These instructions may be performed simultaneously or at different timings. In the latter case, for example, the instruction unit 104 may first instruct the control device 3 to control the motor 53, and if the index value does not enter the appropriate range even after a predetermined time has elapsed after the control, the instruction unit 104 may instruct the control device 3 to control the adding device 6.

[0043] Similarly, when the index value exceeds the above-mentioned appropriate range, that is, when the size of the flock corresponds to "extremely large" to "medium", the instruction unit 104 may instruct the control device 3 to perform control to reduce the size of the formed flock. For example, the instruction unit 104 may instruct the control device 3 to control to increase the rotation speed of the motor 53, or may instruct the control device 3 to control to reduce the addition amount of the flocculant to the addition device 6.

[0044] Further, the instruction unit 104 may instruct the control device 3 to change the control target and the control amount according to the degree of deviation from the appropriate range. For example, the instruction unit 104 may instruct the control device 3 to increase the control amount of the rotation speed of the motor 53 according to the degree of deviation of the index value from the appropriate range (the difference between the index value and the upper limit value of the appropriate range / the difference between the lower limit value of the appropriate range and the index value). Also, for example, when the size of the flock corresponds to "extremely large" or "large", the instruction unit 104 may instruct the control device 3 to control both the motor 53 and the addition device 6, and when it corresponds to "medium" or "extremely small", only the motor 53 may be controlled.

[0045] Note that the appropriate size of the flock may vary depending on the type of sludge and the type of dehydrator. Therefore, the above-mentioned appropriate range may be determined in advance according to the type of sludge, the type of dehydrator, etc. Also, the control for adjusting the size of the flock is not limited to the above example, and the instruction unit 104 may instruct the control device 3 to perform any control that affects the size of the flock on any device that affects the size of the flock.

[0046] Also, if automatic control is not required, the instruction unit 104 may omit the instruction to the control device 3 according to the index value calculated by the index value calculation unit 1023. In this case, the instruction unit 104 may output the above index value to the output unit 14 to make the user recognize it, and based on the input from the user via the input unit 13, instruct the control device 3 to perform manual control to adjust the flock size. In this case, the index value calculation unit 1023 may classify the size of the flock using the calculated index value. Then, the index value calculation unit 1023 may output to the output unit 14 a classification such as "maximum" together with a numerical value such as the average area of the small region, or instead of the numerical value. Thereby, the user can easily recognize the size of the flock.

[0047] (Index value calculation process) The flow of the index value calculation process (index value calculation method) executed by the information processing device 1 will be described based on FIG. 5. FIG. 5 is a flowchart showing an example of the index value calculation process executed by the information processing device 1. The processes of S1 to S6 described below are continuously performed during the operation of the water treatment system 100. Also, during the operation of the water treatment system 100, the imaging device 72 performs imaging at predetermined intervals, and the captured image is stored in the storage unit 11 of the information processing device 1 as the sludge image 111.

[0048] In S1, the binarization processing unit 1021 acquires the sludge image 111 from the storage unit 11. If a plurality of sludge images 111 are stored, the binarization processing unit 1021 acquires the latest sludge image 111. Then, in S2, the binarization processing unit 1021 binarizes the sludge image 111 acquired in S1 to generate a binarized image, and stores this as the binarized image 112 in the storage unit 11.

[0049] In S3, the background detection unit 1022 acquires the binarized image 112 generated in S2 and stored in the storage unit 11. As described above, a plurality of flocks are overlapping in the binarized image 112 (see, for example, FIGS. 3 and 4). Then, the background detection unit 1022 detects the background region of the flock from the acquired binarized image 112.

[0050] In S4, the index value calculation unit 1023 analyzes a plurality of small regions that make up the background region detected in S3, and calculates an index value indicating the formation state of the flock. For example, the index value calculation unit 1023 may count the number of a plurality of small regions that make up the background region, calculate the total area of the background region, and calculate, as the index value, a value obtained by dividing the calculated total area by the number of small regions, that is, the average area of the small regions.

[0051] In S5, the instruction unit 104 determines whether it is necessary for the control device 3 to control the device based on the index value calculated by the index value calculation unit 1023. In FIG. 5, an example in which the device to be controlled is the motor 53, that is, an example in which the flock size is adjusted by adjusting the stirring speed, will be described. Of course, the instruction unit 104 may instruct the control device 3 to adjust the flock size by controlling the addition device 6 or other devices.

[0052] If it is determined in S5 that control is not required (No in S5), the process in FIG. 5 ends. On the other hand, if it is determined that control is required (Yes in S5), the process proceeds to S6. Note that the criterion for determining whether control is required may be determined in advance. For example, the instruction unit 104 may determine that control is required when the index value is outside a predetermined appropriate range.

[0053] In S6, the instruction unit 104 instructs the control device 3 to change the number of stirring times per unit time of the flock. Specifically, the instruction unit 104 changes the number of stirring times by instructing the control device 3 to change the rotation speed of the motor 53, and thereby the process in FIG. 5 ends. Note that since the method of changing the rotation speed has already been described, the description will not be repeated here.

[0054] (Outline of the dirt detection unit) Next, the dirt detection unit 103 will be described with reference to FIGS. 6 to 9. In the present embodiment, the dirt detection unit 103 detects the transmissive dirt adhering to the inspection window 54.

[0055] For example, ferric polysulfate is a reddish-brown liquid also known as polyiron and is used as a flocculant. When using ferric polysulfate as a flocculant, permeable stains may adhere to a partial area of the inspection window 54.

[0056] And the above-mentioned sludge image 111 is an image taken by the imaging device 72 through the inspection window 54 of the flocs in the flocculation tank 51. Therefore, when permeable stains adhere to a partial area of the inspection window 54, the area of the sludge image corresponding to the above area of the inspection window 54 becomes darker than other areas of the above sludge image, so there is a possibility of being misdetected as the background area of the flocs by the background detection unit 1022. That is, if permeable stains adhere to a partial area of the inspection window 54, there is a possibility that the above index value cannot be calculated appropriately.

[0057] FIG. 6 is a diagram showing examples of sludge images B1 to B4 taken every few days. No visually detectable permeable stains were confirmed in the first sludge image B1 shown in FIG. 6.

[0058] Slightly visually detectable permeable stains were confirmed in the second sludge image B2 shown in FIG. 6. Specifically, in the second sludge image B2, the central part on the left side was slightly darkened. However, the above central part on the left side was not misdetected as the background area of the flocs by the background detection unit 1022. Therefore, the second sludge image B2 did not affect the calculation of the index value by the index value calculation unit 1023.

[0059] Visually detectable permeable stains were clearly confirmed in the third sludge image B3 shown in FIG. 6. Specifically, in the third sludge image B3, the central part was clearly darkened. And the above central part was misdetected as the background area of the flocs by the background detection unit 1022. Therefore, the third sludge image B3 affected the calculation of the index value by the index value calculation unit 1023.

[0060] The fourth sludge image B4 shown in FIG. 6 is an image taken on the day following the day on which the inspection window 54 was cleaned. Similar to the first sludge image B1, no visually-perceptible transmissive stain was confirmed in the fourth sludge image B4. From the above, it is desirable to be able to detect transmissive stains that affect the calculation of the above index value.

[0061] In order to detect the above transmissive stain, the stain detection unit 103 calculates a statistical value of the shade value for each of the above micro-regions using a plurality of sludge images 111 divided into a plurality of micro-regions, and detects the stain on the inspection window 54 based on the above statistical value. According to the above configuration, even if the shade value calculated for each micro-region varies greatly due to noise, the stain detection unit 103 detects the stain on the above window based on the statistical value of the shade value, so that the influence of the above noise on the above detection can be reduced.

[0062] (Details of the stain detection unit) As shown in FIG. 1, the stain detection unit 103 includes a grayscale conversion unit 1031, a shade value calculation unit 1032, an average value calculation unit 1033, a variance value calculation unit 1034, and a stain determination unit 1035.

[0063] The grayscale conversion unit 1031 acquires the sludge image 111, which is a color image (R, G, B), from the storage unit 11, and converts it into a grayscale image (Y) using the following formula (1). Y = 0.299R + 0.587G + 0.114B ···(1). Note that the color image may be converted into a grayscale image using any formula other than the above formula (1). The grayscale conversion unit 1031 sends the grayscale image (Y) to the shade value calculation unit 1032.

[0064] Next, the shade value calculation unit 1032 calculates the shade value for each of the above micro-regions using the grayscale image (Y) from the grayscale conversion unit 1031 and the micro-region information 114 in the storage unit 11. The shade value calculation unit 1032 sends the calculated shade value for each micro-region to the average value calculation unit 1033.

[0065] FIG. 7 is a diagram showing an overview of a plurality of minute regions into which the sludge image 111 is divided. The minute region information in the storage unit 11 includes the number and position information of the minute regions for each minute region. In the example of FIG. 7, the sludge image 111 has a size of 640 pixels × 478 pixels.

[0066] The sludge image 111 includes an edge portion 1111 having a width of about 20 pixels. The edge portion 1111 is easily affected by the illumination from the illumination device 71. For this reason, the edge portion 1111 is not used for calculating the above index value. Therefore, since the edge portion 1111 does not need to be used for detecting the stain, the above minute region is not assigned.

[0067] Among the sludge image 111, a target region 1112 excluding the edge portion 1111 is divided into a plurality of minute regions MA. In the example of FIG. 7, the minute region MA has a size of 32 pixels × 32 pixels and is arranged in 13 rows × 18 columns. Therefore, the number of minute regions MA is 234. The minute regions MA are numbered from 0 to 233 from the upper left to the lower right.

[0068] As shown in FIG. 7, since the lower end portion and the right end portion of the target region 1112 have a width of less than 32 pixels, the minute region MA cannot be assigned. For this reason, the above lower end portion and the above right end portion are not used for detecting the stain. Also, when the size of the sludge image 111 is 640 pixels × 480 pixels, the size of the minute region MA is 32 pixels × 32 pixels, and the entire region in the sludge image 111 is the target region 1112, the number of minute regions MA is 300. Also, the size of the minute region MA is not limited to 32 pixels × 32 pixels.

[0069] The shading value calculation unit 1032 uses the average value of the shading values of the plurality of pixels included in the minute region MA as the shading value of the minute region MA. Thereby, the shading values of 234 minute regions are obtained from one sludge image 111. Note that the shading value calculation unit 1032 may use any statistical value such as the median value, the mode value, the maximum value, and the minimum value of the shading values of the plurality of pixels as the shading value of the minute region MA.

[0070] The average value calculation unit 1033 acquires the grayscale values of each micro-region MA from the grayscale value calculation unit 1032 using a plurality of recent sludge images 111, and calculates the average value of the grayscale values for each micro-region MA. The average value calculation unit 1033 sends the calculated average value of the grayscale values of each micro-region MA to the variance value calculation unit 1034.

[0071] FIG. 8 is a graph showing the average value of the grayscale values in each micro-region MA calculated using a plurality of recent sludge images 111. In FIG. 8, graphs G1, G2, G3, and G4 are graphs when using 1, 5, 10, and 20 sludge images 111, respectively. Note that the sludge images 111 used in FIG. 8 are images taken immediately after cleaning the inspection window 54 (corresponding to the sludge image B4 in FIG. 6), that is, images taken when there is no dirt on the inspection window 54.

[0072] Referring to FIG. 8, it can be understood that as the number of sludge images 111 used increases, the variation in the average value of the grayscale values is suppressed. On the other hand, as the number of sludge images 111 used increases, the processing time in the grayscale conversion unit 1031, the grayscale value calculation unit 1032, and the average value calculation unit 1033 becomes longer. Therefore, the number of sludge images 111 to be used is preferably 5 to 20, more preferably 8 to 15, and even more preferably 10. For example, if the imaging device 72 takes an image once every 6 minutes, the 10 recent sludge images 111 can be acquired in 1 hour.

[0073] FIG. 9 is a graph showing the average value of the grayscale values in each micro-region MA calculated using 10 sludge images 111. The graphs G11 to G14 shown in FIG. 9 correspond to the sludge images B1 to B4 shown in FIG. 6, respectively.

[0074] Referring to FIG. 9, it can be understood that the variation in the average value of the shading values is greater in the second graph G12 than in the first graph G11, and greater in the third graph G13 than in the second graph G12. That is, it can be understood that as the transmissive stain in the inspection window 54 deteriorates, the variation in the average value of the shading values increases. Then, referring to the fourth graph G14 in FIG. 9, it can be understood that by cleaning the inspection window 54, the variation in the average value of the shading values becomes as small as that of the first graph G11 in FIG. 9.

[0075] Therefore, the variance value calculation unit 1034 calculates the variance value of the above average values in a plurality of minute regions MA using the average value of the shading values of each minute region MA from the average value calculation unit 1033. The variance value calculation unit 1034 sends the calculated variance value to the stain determination unit 1035.

[0076] Referring to FIG. 9, there are minute regions MA numbered 0 and 17 where the average value of the shading values deviates significantly compared to others. Such a deviation in the average value of the minute region MA is considered to be caused by a cause other than the transmissive stain, such as the influence of illumination by the lighting device 71. For this reason, the minute region MA is considered to have an adverse effect on the calculation of the variance value.

[0077] Therefore, when arranging the average values of the shading values in all the minute regions MA, it is desirable for the variance value calculation unit 1034 to calculate the variance value of the average values after excluding a predetermined number of average values from the maximum average value and a predetermined number of average values from the minimum average value. In this case, since the average values considered to have an adverse effect on the calculation of the variance value are excluded from the variance value calculation process, the transmissive stain of the inspection window 54 can be detected with higher accuracy.

[0078] Note that the predetermined number may be selected from 4 to 6, or may be selected from 1 to 3% of the total number (234) of the minute regions MA. As a result of the above calculation, the variance values for the sludge images B1 to B4 were 47, 59, 120, and 46, respectively.

[0079] Based on the variance value of the above average value from the variance value calculation unit 1034, the stain determination unit 1035 determines whether or not a transmissive stain has been detected. When the stain determination unit 1035 determines that the stain has been detected, it notifies the instruction unit 104 of the detection of the stain.

[0080] Since the variance value corresponding to the sludge image B3 in FIG. 6 that affected the calculation of the above index value is 120, when the variance value is 100 or more, the stain determination unit 1035 may determine that a transmissive stain that affects the calculation of the above index value has been detected.

[0081] By the way, in the case of a plurality of sludge images 111 taken by the imaging device 72 through the inspection window 54 to which two types of flocks having different average sizes are mixed in the flocculation tank 51 and no transmissive stain is attached, the variance value of the average value of the above light and shade values was at most 68. Therefore, the stain determination unit 1035 may determine that a transmissive stain has been detected when the variance value is 80 or more.

[0082] When the instruction unit 104 is notified of the detection of the stain from the stain detection unit 103, it instructs the output unit 14 to issue an alarm. Thereby, the user can be alerted to the above stain. In addition, the instruction unit 104 changes the instruction to the control device 3 from an automatic instruction according to the above index value calculated by the image processing in the image analysis unit 102 to a manual instruction according to the user's input in the input unit 13. Thereby, it is possible to prevent an inappropriate instruction to the control device 3 based on an inappropriate index value calculated due to the stain on the inspection window 54.

[0083] Based on the above alert, the user may stop the water treatment system 100 and clean the inspection window 54. Alternatively, based on the above alert, the user may stop the information processing device 1, visually observe the liquid to be treated in the flocculation tank 51 through the inspection window 54, judge the floc formation state, and operate the control device 3 based on the result of the above judgment to adjust the addition device 6, the stirring device 5, etc. In this case, the operation of the water treatment system 100 can be continued.

[0084] As described above, the stain detection unit 103 calculates the average value of the density values for each of the micro regions using a plurality of sludge images 111 stored in the storage unit 11, calculates the variance value of the average values in the plurality of micro regions, and detects the transmissive stain on the inspection window 54 based on the variance value.

[0085] According to the above configuration, the average value of the density values of each micro region MA converges to a certain value as the number of sludge images 111 increases. At this time, in the micro region MA including the transmissive stain, the converging value is lower than that in the micro region MA not including the stain. Therefore, in the inspection window 54 where there is a transmissive stain in a partial region, the variance value is larger than that in the inspection window 54 where there is no stain. Also, as the transmittance of the stain decreases, the variance value increases. On the other hand, when the transmittance of the stain is high, the image processing for detecting the formation state of the flock, that is, the influence on the calculation of the index value is small. Therefore, it is possible to detect the transmissive stain on the inspection window 54 that affects the image processing based on the variance value.

[0086] Further, the information processing apparatus 1 executes the detection of the formation state of the flock by the image analysis unit 102 and the detection of the stain on the inspection window 54 by the stain detection unit 103 on one device. Thereby, it is not necessary to install two devices having an image processing function, and an inexpensive device configuration can be achieved. Also, by separating the execution timing of the detection of the flock formation state and the execution timing of the detection of the stain on the inspection window 54, the processing load on the information processing apparatus 1 can be reduced.

[0087] (Stain Detection Process) FIG. 10 is a flowchart showing an example of the stain detection process. The processes of S11 to S17 described below can be performed at an arbitrary frequency from several seconds to several days.

[0088] In S11, the grayscale conversion unit 1031 converts each of the plurality of sludge images 111, which are color images and stored in the storage unit 11, into a plurality of grayscale sludge images 111 using the above formula (1). If the plurality of sludge images 111 stored in the storage unit 11 are grayscale images, S11 is omitted.

[0089] Next, in S12, the shading value calculation unit 1032 calculates the shading value for each sludge image 111 and each minute area MA using the plurality of grayscale sludge images 111 and the minute area information 114 of the storage unit 11. Next, in S13, the average value calculation unit 1033 calculates the average value of the shading values for each minute area MA in the plurality of sludge images 111.

[0090] Next, in S14, when arranging the average values of the shading values in all the minute areas MA, the variance value calculation unit 1034 excludes a predetermined number of average values from the maximum average value and a predetermined number of average values from the minimum average value. Next, in S15, the variance value calculation unit 1034 calculates the variance value of the remaining plurality of average values.

[0091] Next, in S16, the stain determination unit 1035 determines whether or not the variance value is equal to or greater than a threshold value (for example, 100). If it is determined in S16 that the variance value is less than the threshold value (No in S16), the stain determination unit 1035 ends the stain detection process on the assumption that no transmissive stain in the inspection window 54 that affects the calculation of the index value has been detected. On the other hand, if it is determined in S16 that the variance value is equal to or greater than the threshold value (Yes in S16), the process proceeds to the process of S17.

[0092] Assuming that the stain determination unit 1035 has detected the transmissive stain in S17, the instruction unit 104 instructs the output unit 14 to issue an alarm and changes the instruction to the control device 3 from the automatic instruction according to the index value calculated in S4 of FIG. 5 to the manual instruction according to the user input in the input unit 13. Then, the stain detection process ends.

[0093] (Modification example) Note that the shading value calculation unit 1032 may store the shading values of each micro area MA for the latest 10 sludge images 111 in the storage unit 11. In this case, the grayscale conversion unit 1031 and the shading value calculation unit 1032 only need to operate on the sludge image 111 newly acquired by the image acquisition unit 101, and do not need to operate on the 10 sludge images 111.

[0094] Also, the shading value calculation unit 1032 may discard the shading values of each micro area MA for the oldest sludge image 111 among the 10 sludge images 111 in the storage unit 11, and store the shading values of each micro area MA for the newly acquired sludge image 111 in the storage unit 11. In this case, the storage unit 11 only needs to secure resources for storing the shading values of each micro area MA for the latest 10 sludge images 111, and there is no need to increase the resources even if the number of sludge images 111 stored in the storage unit 11 increases.

[0095] 〔Embodiment 2〕 Another embodiment of the present invention will be described with reference to FIGS. 11 and 12.

[0096] FIG. 11 is a block diagram showing an example of the main configuration of the information processing apparatus 1 in the water treatment system 100 according to the present embodiment. The information processing apparatus 1 of the present embodiment is different from the information processing apparatus 1 shown in FIG. 1 in that the stain detection unit 103 detects impermeable stains attached to the inspection window 54, and the other configurations are the same.

[0097] The shading values of the areas of the sludge image 111 including the impermeable stains are substantially constant over a plurality of sludge images 111. Therefore, in the micro area MA including the impermeable stain, the dispersion value of the shading value is smaller than that in the micro area MA not including the stain. On the other hand, when the number of micro areas MA including the impermeable stain is small, the influence on the image processing for detecting the floc formation state, that is, the image processing for calculating the index value, is small.

[0098] Therefore, in the present embodiment, the stain detection unit 103 calculates the variance value of the density values for each of the micro-regions MA using a plurality of sludge images 111 divided into a plurality of micro-regions MA, and detects the opaque stain in the inspection window 54 based on the number of micro-regions MA where the variance value is equal to or less than the threshold value. Thereby, it is possible to detect the opaque stain in the inspection window 54 that affects the above image processing. Note that the number of the micro-regions MA may be set based on the influence on the above image processing. Also, the threshold value may be 10, or may be 5, or may be 0.

[0099] The stain detection unit 103 shown in FIG. 11 is different in that it includes a variance value calculation unit 1036, a stain determination unit 1037, and a display instruction unit 1038 instead of the average value calculation unit 1033, the variance value calculation unit 1034, and the stain determination unit 1035 compared to the stain detection unit 103 shown in FIG. 1, and the other configurations are the same.

[0100] The variance value calculation unit 1036 uses a plurality of most recent sludge images 111 to obtain the density values of each micro-region MA from the density value calculation unit 1032, and calculates the variance value of the density values for each micro-region MA. The variance value calculation unit 1036 sends the calculated variance value of the density values of each micro-region MA to the stain determination unit 1037.

[0101] When the number of micro-regions MA where the variance value from the variance value calculation unit 1036 is equal to or less than the threshold value is equal to or more than a predetermined number, the stain determination unit 1037 determines that the opaque stain in the inspection window 54 has been detected. When the stain determination unit 1037 determines that the stain has been detected, it notifies the instruction unit 104 of the detection of the stain. Also, when the stain determination unit 1037 determines that the stain has been detected, it sends the information of the micro-region MA where the variance value is equal to or less than the threshold value to the display instruction unit 1038.

[0102] The display instruction unit 1038 instructs the display device in the output unit 14 to display the information of the micro-region MA from the stain determination unit 1037. That is, when detecting the impermeable stain on the inspection window 54, the display instruction unit 1038 instructs the display device to display the information of the micro-region MA where the above dispersion value is below the threshold value.

[0103] According to the above configuration, by the user referring to the information of the micro-region MA where the above dispersion value is below the threshold value, the position of the impermeable stain on the inspection window 54 can be easily identified. As a result, the impermeable stain on the inspection window 54 can be efficiently removed.

[0104] FIG. 12 is a flowchart showing an example of the stain detection process. The processes of S21 to S26 described below can be performed at an arbitrary frequency from several seconds to several days. Note that since S21 and S22 are the same as S11 and S12 shown in FIG. 10, the description thereof is omitted.

[0105] In S23, the dispersion value calculation unit 1036 calculates the dispersion value of the density values for each micro-region MA in the plurality of sludge images 111. Next, in S24, the stain determination unit 1037 determines whether the number of micro-regions MA where the above dispersion value is below the threshold value is equal to or greater than a predetermined number. If the number of the micro-regions MA is less than the predetermined number in S24 (No in S24), the stain determination unit 1037 ends the above stain detection process on the assumption that no impermeable stain on the inspection window 54 that affects the calculation of the above index value has been detected. On the other hand, if the number of the micro-regions MA is equal to or greater than the predetermined number in S24 (Yes in S24), the process proceeds to S25.

[0106] In S25, assuming that the stain determination unit 1035 detects the above-mentioned impermeable stain, the instruction unit 104 instructs the output unit 14 to issue an alarm, and changes the instruction to the control device 3 from the automatic instruction according to the index value calculated in S4 of FIG. 5 to the manual instruction according to the user input at the input unit 13. Next, in S26, the display instruction unit 1038 instructs the display device of the output unit 14 to display the information of the minute area MA where the above-mentioned dispersion value is equal to or less than the threshold value. Note that S25 and S26 may be executed in any order or simultaneously. After that, the above-mentioned stain detection process is terminated.

[0107] (Modification example) When the number of minute areas MA in which the above-mentioned dispersion value from the dispersion value calculation unit 1036 is equal to or less than the threshold value, that is, the number of minute areas MA including impermeable stains is less than a predetermined number (No in S24 of FIG. 12), the stain determination unit 1037 may send the information of the minute area MA to the index value calculation unit 1023 of the image analysis unit 102. On the other hand, the index value calculation unit 1023 may analyze a plurality of small areas excluding the minute area MA among the plurality of small areas constituting the background area detected by the background detection unit 1022 by using the information of the minute area MA from the stain determination unit 1037, and calculate an index value indicating the formation state of the flock. In this case, since the index value calculation unit 1023 excludes the minute area MA including impermeable stains from the plurality of small areas to be analyzed, the above-mentioned index value can be calculated accurately.

[0108] 〔Matters requiring special mention〕 The device configuration of the water treatment system 100 described in the above embodiment is an example, and a water treatment system having the same functions can be constructed with various device configurations. And the execution subject of each process described in the above embodiment is only an example. Each of the above-mentioned processes may be appropriately assigned to each device constituting the water treatment system.

[0109] For example, the water treatment system 100 may include a control panel that controls the addition and agitation of a flocculant, and an image processing device that performs binarization processing on sludge images. In this case, the detection of the background area and the calculation of the index value may be performed by the image processing device. And the update of the threshold value used for the binarization processing may be performed by the control panel. Thus, each process described in the above embodiment (particularly each process included in the flowchart of FIG. 5) may be executed by being shared among a plurality of information processing devices.

[0110] Further, the image analysis unit 102 and the stain detection unit 103 may be provided in separate information processing devices. In this case, the execution timings of the detection of the floc formation state and the detection of the stain can be arbitrarily set without considering the processing load of the information processing device.

[0111] 〔Example of Realization by Software〕 The functions of the information processing device 1 (hereinafter referred to as "device") can be realized by a program for causing a computer to function as the device, and by programs for causing a computer to function as each control block of the device (particularly each part included in the control unit 10).

[0112] In this case, the above device includes a computer having at least one control device (for example, a processor) and at least one storage device (for example, a memory) as hardware for executing the above program. By executing the above program with this control device and storage device, each function described in the above embodiments is realized.

[0113] The above program may be recorded on one or more computer-readable recording media, not temporarily. This recording medium may or may not be provided in the above device. In the latter case, the above program may be supplied to the above device via any wired or wireless transmission medium.

[0114] In addition, part or all of the functions of each of the above control blocks can also be realized by a logic circuit. For example, an integrated circuit in which a logic circuit functioning as each of the above control blocks is formed is also included in the scope of the present invention. In addition to this, for example, it is also possible to realize the functions of each of the above control blocks by a quantum computer.

[0115] Moreover, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI may operate in the above control device, or may operate in another device (for example, an edge computer or a cloud server, etc.).

[0116] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope indicated in the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

Explanation of Reference Numerals

[0117] 1 Information processing device 3 Control device 5 Flocculator (agitation device) 6 Adding device 9 Dehydrator 10 Control unit 11 Storage unit 12 Communication unit 13 Input unit 14 Output unit 51 Coagulation tank (tank) 52 Agitation blade 53 Motor 54 Inspection window (window) 55 Sludge inlet 56 Chemical inlet 57 Outlet 71 Lighting device 72 Imaging device 100 Water treatment system 101 Image acquisition unit (acquisition unit) 102 Image analysis unit (processing unit) 103 Contamination Detection Unit (Detection Unit) 104 Indication Unit 111 Sludge Image 112 Binary Image 113 Index Value Storage Unit 114 Micro Region Information 1021 Binarization Processing Unit 1022 Background Detection Unit 1023 Index Value Calculation Unit 1031 Grayscale Conversion Unit 1032 Shading Value Calculation Unit 1033 Average Value Calculation Unit 1034 Variance Value Calculation Unit 1035 Judgment Unit 1036 Variance Value Calculation Unit 1037 Judgment Unit 1038 Display Indication Unit

Claims

1. An acquisition unit that acquires an image of the flock taken by an imaging device through a window provided in a tank for forming the flock; An information processing apparatus comprising: a detection unit that calculates a statistical value of density values for each of the micro regions using a plurality of the images divided into a plurality of micro regions, and detects dirt on the window based on the statistical value.

2. The information processing apparatus according to claim 1, further comprising a processing unit that performs image processing for detecting a formation state of the flock for each of the images.

3. The detection unit according to claim 2, calculates an average value of density values for each of the micro regions using a plurality of the images, calculates a variance value of the average values in a plurality of the micro regions, and detects transmissive dirt on the window based on the variance value.

4. When calculating the variance value, the detection unit according to claim 3 excludes a predetermined number of average values from the maximum average value and a predetermined number of average values from the minimum average value among the average values of the density values in the plurality of micro regions.

5. The detection unit according to claim 2, calculates a variance value of density values for each of the micro regions using a plurality of the images, and detects non-transmissive dirt on the window based on the number of micro regions where the variance value is equal to or less than a threshold value.

6. The information processing apparatus according to claim 5, further comprising a display instruction unit that, when the detection unit detects non-transmissive dirt on the window, instructs a display device to display information on the micro regions where the variance value is equal to or less than the threshold value.

7. An adding device that adds a chemical for aggregating solid suspended matter to a liquid to be treated in a tank; A stirring device that stirs the liquid to be treated in the tank; An imaging device that images the flock in the tank through a window provided in the tank; The information processing apparatus according to any one of claims 2 to 6, which detects a formation state of the flock and dirt on the window from an image taken by the imaging device; A water treatment system including a control device that controls at least one of the adding device and the stirring device based on an instruction from the information processing apparatus according to the formation state of the flock and the dirt on the window.

8. When the information processing apparatus detects dirt on the window, the information processing apparatus issues an alarm and changes an instruction to the control device from an instruction according to a formation state of the flock detected by image processing of the image to an instruction according to a user input.

9. An acquisition step of acquiring an image of the flock taken by an imaging device through a window provided in a tank for forming the flock; A detection step of calculating a statistical value of density values for each of the minute regions using the plurality of images divided into a plurality of minute regions, and detecting dirt on the window based on the statistical value. A method for detecting dirt on an information processing apparatus including the steps.

10. A dirt detection program for causing a computer to function as the information processing apparatus according to claim 1, the dirt detection program for causing a computer to function as the detection unit.

Images