Visible smoke detection device, program, visible smoke detection system, and visible smoke detection method

Abstract

To determine the color of visible smoke in addition to the determination as to whether or not the visible smoke is generated from a facility to be monitored by image analysis.SOLUTION: A visible smoke determination device includes: a visible smoke generation determination unit for determining whether visible smoke is generated in a visible smoke determination area on the basis of the image information of each pixel in the visible smoke determination area set in a picked-up image obtained by imaging a direction of a facility monitored for visible smoke generation; a visible smoke color index value calculation unit for calculating a visible smoke color index value to be an index for color of the visible smoke on the basis of the pixel information of each pixel in the viable smoke determination area about the visible smoke determination area determined that the visible smoke is generated; and a visible smoke color determination unit for determining the color of the visible smoke generated in the visible smoke determination area on the basis of the visible smoke color index value.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a visible smoke determination device, a program, a visible smoke determination system, and a visible smoke determination method.

Background Art

[0002] In steelworks, as part of conservation measures for the atmospheric environment, exhaust gas discharged from facilities such as coke ovens and sintering machines is treated so as to satisfy emission standard values and compliance values before being discharged. Furthermore, in order to meet the perspective of harmony with nature and the demands of local residents, operations are carried out to suppress the generation of visible smoke. However, for example, if poor combustion of coke occurs in a coke oven for some reason, black smoke may be generated during coke extrusion. Therefore, it is important to immediately confirm such an event and take prompt measures to prevent its recurrence.

[0003] Accordingly, efforts are being made to automatically perform image analysis on a captured image obtained by imaging a facility to be monitored as a subject to determine the occurrence of visible smoke. As a method of detecting smoke by applying image analysis technology to surveillance video, for example, Patent Document 1 discloses that a fluctuating image that changes due to sunlight, rainfall, etc. is subjected to pixel decomposition, a standard image obtained by respectively moving-averaging the pixels of several images is used as an original image, a real-time fluctuating image is subjected to difference calculation for each pixel to remove the invariant image portion constituting the background part, and a smoke or dust emission detection device including means for issuing an alarm when the area and luminance difference of the dust and smoke emission image composed of the fluctuating image portion exceed a certain set value is disclosed.

[0004] Further, Patent Document 2 discloses that the transition of the luminance of each pixel obtained by moving-averaging an image over time is time-differentiated, and when the first-order differential coefficient obtained by the time differentiation produces a peak, and the ratio of the number of pixels whose peak value exceeds a certain value exceeds a certain value, a smoke or dust emission detection device including means for estimating that the image is a dust and smoke emission image is disclosed.

[0005] Patent Document 3 discloses a smoke or dust detection device that, when estimating a dust or smoke image using the same means as in Patent Document 2, compares the rate of change of the first derivative of the area under analysis and the area outside that area with respect to the steady state value, and estimates that it is a dust or smoke image if the ratio between the two rates of change is 2 or more.

[0006] Patent Document 4 discloses a visible smoke determination device that determines captured smoke to be visible smoke when the difference in brightness for each hue between the background area of ​​an image and the visible smoke determination area is greater than or equal to a preset threshold for at least one hue. [Prior art documents] [Patent Documents]

[0007] [Patent Document 1] Japanese Patent Application Publication No. 4-352077 [Patent Document 2] Japanese Patent Application Publication No. 4-358285 [Patent Document 3] Japanese Patent Application Publication No. 5-10738 [Patent Document 4] Japanese Patent Publication No. 2015-169618 [Overview of the project] [Problems that the invention aims to solve]

[0008] As mentioned above, visible smoke can be generated from multiple pieces of equipment, such as coke ovens and sintering machines, and the color of the visible smoke tends to differ depending on the equipment. For example, coke ovens often produce black visible smoke from coal and coke, while sintering machines often produce reddish-brown visible smoke from iron ore.

[0009] However, the visible smoke detection methods incorporated into the devices described in Patent Documents 1 to 4 all involve setting a threshold for a detection index obtained from an captured image, and determining that visible smoke is present when the threshold is exceeded. None of these methods determine what color the visible smoke is. Therefore, even if visible smoke is generated for some reason and identified as such, it may not be immediately clear what equipment generated the smoke, potentially delaying measures to prevent recurrence.

[0010] Therefore, the present invention has been made in view of the above problems, and the object of the present invention is to provide a visible smoke determination device, program, visible smoke determination system, and visible smoke determination method that can determine whether or not visible smoke is being emitted from equipment under monitoring by image analysis, as well as determine what color the visible smoke is. [Means for solving the problem]

[0011] To solve the above problems, according to one aspect of the present invention, a visible smoke determination device is provided, comprising: a visible smoke generation determination unit that determines whether or not visible smoke is generated in a visible smoke determination area based on the pixel information of each pixel in a visible smoke determination area set in an image obtained by imaging the direction of equipment that is the target of monitoring for visible smoke generation; a visible smoke color index value calculation unit that calculates a visible smoke color index value, which is an indicator of the color of visible smoke, based on the pixel information of each pixel in the visible smoke determination area for a visible smoke determination area in which visible smoke has been determined to be generated; and a visible smoke color determination unit that determines the color of the visible smoke generated in the visible smoke determination area based on the visible smoke color index value.

[0012] The visible smoke color index value calculation unit calculates a reference color index value corresponding to a reference color of visible smoke that serves as a criterion for determining the color of visible smoke, and at least one monitoring color index value corresponding to at least one monitoring color of visible smoke whose occurrence is to be monitored. The visible smoke color determination unit may then determine the color of the visible smoke based on the reference color index value and the monitoring color index value.

[0013] The standard color for visible smoke may be the color of the most frequently occurring visible smoke. Alternatively, the monitoring color for visible smoke may include at least one of the following: the color of the second most frequently occurring visible smoke, or the color of the visible smoke for which recurrence prevention measures have a high priority.

[0014] The visible smoke color determination unit calculates an evaluation value for each monitored color based on the difference between the monitored color index value and the reference color index value. If all evaluation values ​​are smaller than the threshold set for determining the reference color of visible smoke, the unit may determine that the color of the visible smoke is the reference color.

[0015] The visible smoke color determination unit may determine that the color of the visible smoke is the monitoring color corresponding to the monitoring color index value with the highest evaluation value when at least one evaluation value is greater than or equal to a threshold value.

[0016] The visible smoke detection device may include a threshold setting unit for setting a threshold. The threshold setting unit can set a threshold by using multiple captured images taken within a predetermined period in the past, and by setting Ratio 1, which is determined by the ratio of the number of visible smokes that a person visually confirms as a standard color and that the visible smoke color detection unit has determined to be a standard color, to the number of visible smokes that a person visually confirms as a standard color, to be greater than or equal to a predetermined ratio; setting Ratio 2, which is determined by the ratio of the number of visible smokes that a person visually confirms as a standard color and that the visible smoke color detection unit has determined to be a standard color, to be greater than or equal to a predetermined ratio; or setting the harmonic mean of Ratio 1 and Ratio 2 to the maximum value.

[0017] Multiple visible smoke detection regions may be set within the captured image.

[0018] When the captured image is a 256-level RGB color system image, the visible smoke color index value calculation unit may calculate the pixel information of each pixel using a function represented by the red, green, and blue components of the pixel.

[0019] Further, the visible smoke determination apparatus may include a visible smoke generation facility determination unit that determines, based on the color of visible smoke determined by the visible smoke color determination unit, one or a plurality of facilities associated with the color of the visible smoke as a visible smoke generation facility.

[0020] The visible smoke determination apparatus may include a notification instruction unit that instructs a notification apparatus to issue a notification of visible smoke generation. The notification instruction unit outputs, to the notification apparatus, the visible smoke determination region for which the visible smoke generation determination unit has determined that visible smoke is being generated, and the color of the visible smoke determined by the visible smoke color determination unit.

[0021] The facility to be monitored may be at least one of a coke oven or a sintering machine.

[0022] Further, in order to solve the above problem, according to another aspect of the present invention, there is provided a program that causes a computer to function as a visible smoke determination apparatus comprising: a visible smoke generation determination unit that determines whether or not visible smoke is generated in a visible smoke determination region, based on pixel information of each pixel in the visible smoke determination region set in a captured image obtained by imaging the direction of a facility that is a monitoring target of visible smoke generation; a visible smoke color index value calculation unit that calculates a visible smoke color index value serving as an index of the color of the visible smoke, for the visible smoke determination region in which visible smoke is determined to be generated, based on the pixel information of each pixel in the visible smoke determination region; and a visible smoke color determination unit that determines the color of the visible smoke generated in the visible smoke determination region, based on the visible smoke color index value.

[0023] Furthermore, in order to solve the above problems, according to another aspect of the present invention, there is provided an imaging device that captures an image in the direction of equipment that is a monitoring target for visible smoke generation to obtain a captured image, and a visible smoke determination device that determines that visible smoke is generated from the monitoring target equipment based on the captured image, the visible smoke determination device comprising: a visible smoke occurrence determination unit that determines whether or not visible smoke is generated in a visible smoke determination region, based on pixel information of each pixel in the visible smoke determination region set in the captured image; a visible smoke color index value calculation unit that calculates a visible smoke color index value serving as an index of the color of the visible smoke for the visible smoke determination region in which it is determined that visible smoke is generated, based on the pixel information of each pixel in the visible smoke determination region; and a visible smoke color determination unit that determines the color of the visible smoke generated in the visible smoke determination region based on the visible smoke color index value. A visible smoke determination system is provided.

[0024] Moreover, in order to solve the above problems, according to another aspect of the present invention, a visible smoke occurrence determination step of determining whether or not visible smoke is generated in a visible smoke determination region, based on pixel information of each pixel in the visible smoke determination region set in a captured image obtained by imaging the direction of equipment that is a monitoring target for visible smoke generation; a visible smoke color index value calculation step of calculating a visible smoke color index value serving as an index of the color of the visible smoke for the visible smoke determination region in which it is determined that visible smoke is generated, based on the pixel information of each pixel in the visible smoke determination region; and a visible smoke color determination step of determining the color of the visible smoke generated in the visible smoke determination region based on the visible smoke color index value. A visible smoke determination method is provided. [Effects of the Invention]

[0025] As explained above, according to the present invention, in addition to determining whether or not visible smoke is being emitted from the monitored equipment through image analysis, it is also possible to determine the color of the visible smoke. Since the components of the visible smoke can be narrowed down from the color of the visible smoke, the equipment using those components can be narrowed down as candidates for the equipment that emitted the visible smoke (visible smoke generating equipment). Therefore, measures to prevent recurrence can be taken more quickly compared to when the color of the visible smoke is not reported. Furthermore, if the visible smoke generating equipment associated with the color of the visible smoke is also reported, it becomes possible to know which equipment emitted the visible smoke at the same time as the visible smoke is emitted, so measures to prevent recurrence can be taken even more quickly. [Brief explanation of the drawing]

[0026] [Figure 1] This is a schematic diagram showing an example of an image captured above equipment that is being monitored for visible smoke generation. [Figure 2] This is a functional block diagram showing one example configuration of a visible smoke detection system equipped with a visible smoke detection device according to one embodiment of the present invention. [Figure 3] This is a schematic diagram showing an example of setting the visible smoke detection area and the background area. [Figure 4] This is a flowchart showing a visible smoke detection method according to the same embodiment. [Figure 5] This is a block diagram showing an example of the hardware configuration of an information processing device that functions as a visible smoke detection device according to the same embodiment. [Figure 6] This graph shows the changes in each visible smoke color index value and the changes in the evaluation value for the monitored color in Case 1 of the example. [Figure 7] This graph shows the changes in each visible smoke color index value and the changes in the evaluation value for the monitored color in Case 2 of the example. [Modes for carrying out the invention]

[0027] Preferred embodiments of the present invention will be described in detail below with reference to the attached drawings. In this specification and drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant descriptions will be omitted.

[0028] [1. Overview] First, an overview of visible smoke detection by a visible smoke detection device according to one embodiment of the present invention will be explained based on Figure 1. Figure 1 is a schematic diagram showing an example of an image captured above a facility that is the target of monitoring for visible smoke generation.

[0029] The visible smoke determination device according to this embodiment determines whether or not visible smoke is generated, and also determines the color of the visible smoke that is generated, based on an image taken of the air above the equipment that is the target of monitoring for visible smoke generation.

[0030] The captured image is obtained by capturing the direction of the equipment being monitored for visible smoke generation (the equipment itself or the area above it). For example, the captured image 10 shown in Figure 1 is an image taken from a distance of a factory equipped with various monitored equipment 5, showing the monitored equipment 5 (including multiple chimneys 3) behind trees 7, and the sky above them. Although not directly visible in the captured image 10, there are also multiple monitored equipment 5 hidden by trees 7. When visible smoke is generated from the monitored equipment 5 inside the factory, visible smoke 9 is also captured in the captured image 10, as shown in Figure 1. The visible smoke 9 shown in Figure 1 is an example of smoke generated from monitored equipment 5 hidden by trees 7.

[0031] Here, the color of visible smoke tends to differ depending on the equipment generating it. For example, in a steel mill, equipment handling coal-based or coke-based materials emits dark smoke, while sintering machines emit reddish smoke. Based on this relationship between equipment and the color of the visible smoke it generates, when a visible smoke detection device detects the generation of visible smoke, it is possible to identify the equipment generating the visible smoke by determining and identifying the color of the visible smoke. As a result, as shown in Figure 1, even if the monitored equipment 5 is hidden by trees 7, the equipment 5 generating the visible smoke 9 can be immediately identified based on the detected color of the visible smoke 9.

[0032] The visible smoke detection method according to this embodiment will be described in detail below.

[0033] [2. Visible Smoke Detection System] First, a visible smoke detection system 1 equipped with the visible smoke detection device 100 according to this embodiment will be described based on Figure 2. Figure 2 is a functional block diagram showing one example configuration of the visible smoke detection system 1 equipped with the visible smoke detection device 100 according to this embodiment.

[0034] As shown in Figure 4, the visible smoke detection system 1 consists of an imaging device 50, a visible smoke detection device 100, and an alarm device 200. The visible smoke detection system 1 may also be configured so that an information processing terminal 300 can send and receive information with the visible smoke detection device 100.

[0035] [2-1. Imaging device] The imaging device 50 captures an image of the direction of the equipment being monitored for visible smoke generation. The imaging range of the imaging device 50 does not necessarily have to include the equipment being monitored; it is sufficient that it includes the area where visible smoke appears when it is generated from the equipment (for example, above the equipment). In other words, the captured image does not need to show the equipment being monitored in a way that allows for visual confirmation; it is sufficient that the visible smoke generated from the equipment is captured. The imaging range of the imaging device 50 may include only one piece of equipment being monitored, or it may include multiple pieces of equipment being monitored.

[0036] The imaging device 50 continuously captures images of the imaging area and acquires captured images. The imaging device 50 may, for example, capture the imaging area as a video. In this case, each frame of the video becomes an captured image that is processed by the visible smoke detection device 100. Alternatively, the imaging device 50 may continuously capture images of the imaging area at predetermined intervals. For example, the imaging device 50 may acquire one still image every 3 seconds. The imaging device 50 is a color camera that acquires color images. The captured images from the imaging device 50 are output to the visible smoke detection device 100.

[0037] [2-2.Visible smoke determination device] The visible smoke detection device 100 processes the image captured by the imaging device 50 to determine whether or not visible smoke is being emitted from the equipment being monitored. The visible smoke detection device 100 includes a region setting unit 110, a visible smoke generation determination unit 120, a visible smoke color index calculation unit 130, a visible smoke color determination unit 140, a threshold setting unit 150, a notification instruction unit 160, a visible smoke generating equipment determination unit 170, and a storage unit 180.

[0038] (Area setting section) The region setting unit 110 sets visible smoke determination regions within the captured image. The visible smoke determination region is a region defined in the captured image that determines whether or not visible smoke is being emitted from the equipment being monitored. The region setting unit 110 sets at least one visible smoke determination region in the captured image. For example, the region setting unit 110 may set a visible smoke determination region for each piece of equipment being monitored, between pieces of equipment, or above the equipment, or it may set the entire captured image as the visible smoke determination region. For example, as shown in Figure 3, the region setting unit 110 may set visible smoke determination regions A to M between and above the equipment 5 (including the chimney 3) being monitored in the captured image 10. When the equipment 5 being monitored is a coke oven, the visible smoke determination region is set, for example, above the coke oven equipment. In Figure 3, the visible smoke determination region is a rectangular region, but the present invention is not limited to this example and may have other shapes. Also, when setting multiple visible smoke determination regions, the shape and size of each visible smoke determination region may be the same or different.

[0039] Furthermore, the region setting unit 110 may further set a background region X within the captured image. The background region X is an area that will not be completely covered by visible smoke even if visible smoke is generated from the equipment being monitored. In order to improve the accuracy of the visible smoke detection device 100's detection of visible smoke generation, it is desirable that the background region X is wider than the visible smoke detection region. For example, as shown in Figure 3, the region setting unit 110 may set the background region X above the visible smoke detection regions A to M in the captured image 10.

[0040] The shape, size, position, and number of visible smoke determination areas A to M and background area X are empirically set based on the locations where visible smoke appeared in previously acquired images. For example, the area setting unit 110 does not necessarily need to set the visible smoke determination areas above the equipment 5 (including the chimney 3). Based on multiple images taken within a predetermined period in the past, it may set areas where visible smoke generated from the monitored equipment has been captured as visible smoke determination areas, and areas that were not completely covered by visible smoke as background areas.

[0041] When the region setting unit 110 sets a visible smoke determination region within the captured image, it outputs information about the region set within the captured image (positional information of each region within the captured image) to the visible smoke generation determination unit 120 and the visible smoke color index value calculation unit 140.

[0042] (Visible smoke generation detection unit) The visible smoke generation determination unit 120 determines whether or not visible smoke is being generated based on the pixel information of each pixel within the visible smoke determination area. The pixel information is, for example, information representing brightness or lightness. The visible smoke generation determination unit 120 can determine the generation of visible smoke using a well-known visible smoke determination method. For example, the visible smoke generation determination unit 120 may use an index value represented by spatial brightness, lightness, or their temporal changes as an indicator of visible smoke generation, and determine the generation of visible smoke when the index value exceeds a reference value. The visible smoke generation determination unit 120 determines whether or not visible smoke is being generated for each visible smoke determination area, and outputs the visible smoke determination areas in which visible smoke is being generated to the visible smoke color determination unit 140 and the notification instruction unit 160.

[0043] (Visible smoke color index value calculation unit) The visible smoke color index calculation unit 130 calculates a visible smoke color index value, which serves as an indicator of the color of visible smoke, for each visible smoke determination area based on the pixel information of each pixel within the visible smoke determination area. The visible smoke color index calculation unit 130 only needs to calculate the visible smoke color index value for at least the visible smoke determination areas where visible smoke is determined to be present, but it may also calculate the visible smoke color index value for all set visible smoke determination areas regardless of whether visible smoke is present or not.

[0044] The pixel information used to calculate the visible smoke color index value is, for example, information representing luminance or brightness. Whether to use luminance values ​​or brightness values ​​as pixel information should be determined according to the characteristics of the smoke color to be detected. For example, the visible smoke color index calculation unit 130 may calculate the visible smoke color index value based on the ratio of red, blue, and green component values ​​obtained as RGB pixel information. Specifically, for example, the visible smoke color index value may be obtained by multiplying the red, blue, and green component values ​​by different ratios (coefficients) for at least two or more colors of visible smoke and summing them up.

[0045] In this embodiment, since the image captured by the imaging device 50 is a color image, the visible smoke color index calculation unit 130 calculates pixel information for each pixel using a function represented by the red, green, and blue components of the pixel. Based on the calculated pixel information, the visible smoke color index calculation unit 130 then calculates a reference color index value corresponding to the reference color of visible smoke, and at least one monitoring color index value corresponding to at least one monitoring color, as visible smoke color index values.

[0046] Here, the reference color and at least one monitoring color are colors set to distinguish visible smoke by color. The reference color is set as the color used as the criterion for determining the color of visible smoke. The monitoring color is the color of visible smoke whose occurrence we want to monitor. The monitoring color is a different color from the reference color and is a color that we want to distinguish from the reference color. The reference color is preferably the color of the visible smoke that occurs most frequently. The monitoring color is preferably the color of the second most frequently occurring color, or a color of visible smoke that, even if it occurs less frequently, has a higher priority for recurrence prevention measures compared to other colors of visible smoke, etc.

[0047] The visible smoke color index calculation unit 130 first calculates a reference color index value based on the pixel information of each pixel within a set area in the captured image. The reference color index value is calculated as an index representing the degree of the color of the reference color. The monitoring color is a color that is highly related to the equipment that generates visible smoke and can identify the equipment that is the source of the visible smoke. For example, when monitoring visible smoke generated in a steel mill, black, which is highly related to coke ovens, can be used as the reference color. In this case, the reference color index value is calculated from the pixel information represented by grayscale conversion of the pixels within the area. For example, when the captured image is a 256-level RGB color system image, the luminance value and lightness value of each pixel can be represented as follows using a function that is represented by the red, green, and blue components of the pixel, as grayscale conversion of the pixel information.

[0048] Brightness value = Red component × 0.21 + Green component × 0.72 + Blue component × 0.07 Brightness value ={(max(red component, green component, blue component))+(min(red component, green component, blue component))} / 2

[0049] The visible smoke color index calculation unit 130 may use the grayscaled pixel information described above to generate representative pixel information that represents the grayscaled pixel information of each region set in the captured image, as a reference color index value. The representative pixel information is representative pixel information that represents the characteristics of the pixel information of each pixel within the region. When the luminance value is the pixel information, the representative pixel information may be, for example, the value obtained by dividing the sum of the luminance values ​​of each pixel within the region by the number of pixels in that region (i.e., the average luminance value). Also, when the brightness is the pixel information, the representative pixel information may be, for example, the value obtained by dividing the sum of the brightness values ​​of each pixel within the region by the number of pixels in that region (i.e., the average brightness value).

[0050] Furthermore, the visible smoke color index calculation unit 130 calculates a monitoring color index value based on the pixel information of each pixel within a set area in the captured image. The monitoring color index value is calculated as an index representing the degree of the color of the monitoring color. The monitoring color is a color that is highly related to the equipment that generates visible smoke and can identify the equipment that is the source of the visible smoke. For example, when monitoring visible smoke generated in a steel mill, a color such as red, which is highly related to sintering machines, should be used as the monitoring color. One or more monitoring colors can be set.

[0051] For example, if the reference color is black and the monitoring color is red, the visible smoke color index calculation unit 130 calculates image information (hereinafter also referred to as "red pixel information") that represents the degree of red relative to black, using the red component of the pixels for each region set in the captured image. That is, for example, when the luminance value is the pixel information, the red image information can be expressed as follows using a function represented by the red component of the pixels.

[0052] Red pixel information (luminance) = Red component × 1.00 + Green component × 0.00 + Blue component × 0.00

[0053] The visible smoke color index calculation unit 130 uses red pixel information to generate representative red pixel information that represents the red pixel information of a region set within that region, based on the red pixel information of each pixel within that region. For example, the visible smoke color index calculation unit 130 obtains the representative red pixel information by dividing the sum of the red pixel information of each pixel within the region by the number of pixels in that region (i.e., the average value). The visible smoke color index calculation unit 130 may also use the representative red pixel information as the color index value of red visible smoke (hereinafter also referred to as "monitoring color index value A").

[0054] Furthermore, for example, if the reference color is black and yellow is the monitoring color, the visible smoke color index calculation unit 130 calculates image information (hereinafter also referred to as "yellow pixel information") that represents the degree of yellow relative to black, using the red and green components of the pixels for each region set in the captured image. That is, for example, when the luminance value is the pixel information, the yellow image information can be expressed as follows using a function represented by the red and green components of the pixels.

[0055] Yellow pixel information (luminance) = Red component × 0.50 + Green component × 0.50 + Blue component × 0.00

[0056] The visible smoke color index calculation unit 130 uses yellow pixel information to generate representative yellow pixel information that represents the yellow pixel information of a region set within that region, based on the yellow pixel information of each pixel in that region. For example, the visible smoke color index calculation unit 130 obtains the representative yellow pixel information by dividing the sum of the yellow pixel information of each pixel in the region by the number of pixels in that region (i.e., the average value). The visible smoke color index calculation unit 130 may also use the representative yellow pixel information as the yellow visible smoke color index value (hereinafter also referred to as "monitoring color index value B").

[0057] The visible smoke color index calculation unit 130 outputs the calculated reference color index value and monitoring color index value to the visible smoke color determination unit 140.

[0058] (Visible smoke color determination section) The visible smoke color determination unit 140 determines the color of the visible smoke generated in the visible smoke determination area based on the visible smoke color index value. First, the visible smoke color determination unit 140 calculates an evaluation value for each monitored color based on the difference between the monitored color index value and the reference color index value. For example, the visible smoke color determination unit 140 may calculate the evaluation value as the absolute value of the difference between each monitored color index value and the reference color index value. For example, when red and yellow are set as monitored colors, the visible smoke color determination unit 140 calculates the evaluation value A for red as the absolute value of the difference between the monitored color index value A for red and the reference color index value, and calculates the evaluation value B for yellow as the absolute value of the difference between the monitored color index value B for yellow and the reference color index value. That is, the visible smoke color determination unit 140 calculates the evaluation value i for a monitored color i based on the following formula (1). Herein, i represents the type of monitored color, i = A, B, C, ... For example, A corresponds to red, B corresponds to yellow.

[0059] Evaluation value i = |Reference color index value - Monitoring color index value i| ... (1) (i=A,B,C,···)

[0060] Furthermore, for example, the visible smoke color determination unit 140 may calculate the difference between the monitored color index value and the reference color index value as the evaluation value for each monitored color. For example, when red and yellow are set as monitored colors, the visible smoke color determination unit 140 calculates the difference between the monitored color index value A for red and the reference color index value as the evaluation value A for red, and the difference between the monitored color index value B for yellow and the reference color index value as the evaluation value B for yellow. That is, the visible smoke color determination unit 140 calculates the evaluation value i for a monitored color i based on the following formula. Herein, i represents the type of monitored color, and i = A, B, C, ... For example, A corresponds to red, and B corresponds to yellow.

[0061] Evaluation value i = Monitoring color index value - Reference color index value i ... (2) (i=A,B,C,···)

[0062] The visible smoke color determination unit 140 calculates evaluation values ​​for all monitored colors and then compares all of these evaluation values ​​with a threshold value set to determine the reference color of the visible smoke. The threshold value is a value related to the reference color index value set by the threshold setting unit 150, which will be described later. The visible smoke color determination unit 140 then determines that the color of the visible smoke is the reference color if all evaluation values ​​are less than the threshold value. On the other hand, the visible smoke color determination unit 140 determines that the color of the visible smoke is the monitored color corresponding to the monitored color index value with the largest evaluation value if at least one evaluation value is greater than or equal to the threshold value.

[0063] In this manner, the visible smoke color determination unit 140 determines whether the visible smoke is of a standard color or not. If the visible smoke is not of a standard color, it determines that visible smoke of a monitoring color corresponding to the monitoring color index value that deviates most from the standard color index value is being generated. The visible smoke color determination unit 140 outputs the color of the visible smoke generated in the visible smoke determination area to the notification instruction unit 160.

[0064] (Threshold setting section) The threshold setting unit 150 sets a threshold for determining the reference color of visible smoke based on past determination results. Specifically, the threshold setting unit 150 can set a threshold value using past determination results of reference color of visible smoke recorded in the storage unit 180. The storage unit 180 stores time-series data of the reference color index values ​​of each visible smoke determination area determined by the visible smoke determination device 100 for multiple captured images taken within a predetermined period in the past. The storage unit 180 also records the visible smoke determination area and the time of occurrence of the reference color of visible smoke, as confirmed by a monitor visually inspecting these captured images.

[0065] For example, the threshold setting unit 150 may set a threshold such that the ratio 1, which is determined by the ratio of the number of visible smokes that a person visually confirms as the standard color and that the visible smoke color determination unit 140 also determines to be the standard color, is equal to or greater than a predetermined ratio. The ratio 1 is a value set based on the number of visible smokes that a person visually confirms as the standard color, and represents the recall rate.

[0066] Furthermore, the threshold setting unit 150 may set a threshold such that the ratio 2, which is determined by the ratio of the number of visible smokes that the visible smoke color determination unit 140 has determined to be a standard color and that a person has visually confirmed to be a standard color and that the visible smoke color determination unit 140 has determined to be a standard color, is equal to or greater than a predetermined ratio. The ratio 2 is a value set based on the number of visible smokes that the visible smoke color determination unit 140 has confirmed to be a standard color, and represents the conformance rate.

[0067] Alternatively, the threshold setting unit 150 may set the threshold by maximizing the harmonic mean of ratio 1 and ratio 2. In other words, the threshold setting unit 150 sets the threshold by maximizing the F-value, which is the harmonic mean of recall and precision. Since recall and precision have a trade-off relationship, if you want to set a baseline value that is in the middle between them, you can set the threshold in this way.

[0068] Thus, there are multiple methods for setting the threshold value of the reference color index, and the appropriate method should be used depending on the purpose. Note that the threshold value of the reference color index may be set to a different value for each visible smoke determination area, or the reference value may be the same for all visible smoke determination areas. The threshold setting unit 150 outputs to the visible smoke color determination unit 140 when a threshold value for the reference color index has been set. The threshold setting unit 150 may also record the threshold value of the reference color index in the storage unit 180.

[0069] (Visible smoke generating equipment detection unit) The visible smoke generating equipment determination unit 170 may determine one or more pieces of equipment associated with a visible smoke color as equipment generating visible smoke (hereinafter also referred to as "visible smoke generating equipment") based on the visible smoke color determined by the visible smoke color determination unit 140. The association between visible smoke color and equipment is set in advance by the monitor and recorded, for example, in the storage unit 180. The storage unit 180 stores a visible smoke color-equipment table that associates visible smoke color with equipment, for example, black (standard color) with coke ovens, red with sintering machines, etc. When the visible smoke generating equipment determination unit 170 determines the color of visible smoke generated in the visible smoke determination area, it can refer to the visible smoke color-equipment table in the storage unit 180 and determine the equipment corresponding to that visible smoke color. When the visible smoke generating equipment determination unit 170 determines equipment corresponding to a visible smoke color generated in the visible smoke determination area, it may output it to the notification instruction unit 160 as visible smoke generating equipment.

[0070] (Hochi Instruction Department) The notification instruction unit 160 instructs the alarm device 200 to notify the system of visible smoke generation. The notification instruction unit 160 outputs to the alarm device 200 the visible smoke determination area determined by the visible smoke generation determination unit 120, and the color of the visible smoke determined by the visible smoke color determination unit 140. In addition, if the visible smoke generation equipment determination unit 170 determines the equipment corresponding to the color of the visible smoke generated in the visible smoke determination area, the system may output to the alarm device 200 the visible smoke generation equipment along with the visible smoke generation and the color of the generated visible smoke.

[0071] (Storage part) The memory unit 180 is a memory unit that stores various information used by the visible smoke detection device 100. For example, the memory unit 180 records time-series data of visible smoke color index values ​​for each visible smoke detection area determined by the visible smoke detection device 100 for multiple images taken in the past, as well as the visible smoke detection area and time of occurrence of visible smoke as confirmed by the monitor visually for these images. The memory unit 180 also records a visible smoke color-equipment table that associates the color of visible smoke with equipment. Furthermore, the memory unit 180 may also record threshold values ​​for the reference color index values ​​set by the threshold setting unit 150.

[0072] [2-3. Alarm device] Upon receiving notification from the visible smoke detection device 100, the alarm device 200 notifies the equipment monitor and relevant personnel at the factory, etc., of the generation of visible smoke from the monitored equipment and the color of the generated visible smoke. In addition, if the visible smoke detection device 100 notifies the alarm device 200 of the visible smoke generating equipment along with the generation of visible smoke and the color of the generated visible smoke.

[0073] The alarm device 200 is, for example, an information processing terminal such as a computer, tablet terminal, or mobile communication terminal, and includes a display unit such as a display for displaying information. The alarm device 200 may also include an audio output unit such as a speaker for outputting sound. Upon receiving notification from the visible smoke detection device 100, the alarm device 200 may notify the monitor of the occurrence of visible smoke by displaying a message on its display unit, or it may notify relevant persons at the factory, etc., by email. In this case, an image of the smoke determined to be visible smoke may be displayed on the display unit or attached to the email.

[0074] [2-4. Information Processing Terminals] The information processing terminal 300 is a terminal capable of sending and receiving information with the visible smoke detection device 100. For example, it is used when a monitor or the like associates the color of visible smoke with equipment for the visible smoke detection device 100. The information processing terminal 300 may also be used in conjunction with, for example, the alarm device 200.

[0075] The configuration of the visible smoke detection system 1 according to this embodiment has been described above. Although the functional units of the visible smoke detection device 100 have been described as being provided in a single device, the present invention is not limited to this example. The functional units of the visible smoke detection device 100 may be composed of multiple devices. It is also possible to create a program to realize each function of the visible smoke detection device 100 and implement it on a computer or the like. Furthermore, a computer-readable recording medium on which such a program is stored can also be provided. Examples of recording media include magnetic disks, optical disks, magneto-optical disks, flash memory, etc. In addition, the above program may be distributed, for example, via a network, without using a recording medium.

[0076] [3. Visible smoke determination method] Next, the visible smoke detection method according to this embodiment will be described based on Figure 4. Figure 4 is a flowchart of the visible smoke detection method according to this embodiment.

[0077] As shown in Figure 4, first, the imaging device 50 takes an image of the equipment that is the subject of monitoring for visible smoke generation and acquires an image (S100). The imaging device 50 takes images continuously and outputs the image to the visible smoke determination device 100 each time an image is acquired.

[0078] When an image is input from the imaging device 50, the visible smoke determination device 100 processes the image from the imaging device 50 to determine whether or not visible smoke is being emitted from the equipment being monitored. To this end, the region setting unit 110 sets visible smoke determination regions within the image (S110). For example, as shown in Figure 3, the region setting unit 110 sets visible smoke determination regions A to M above the equipment being monitored in the image 10. The shape, size, position, and number of visible smoke determination regions set for the image are appropriately set, for example, based on the position where visible smoke appeared in previously acquired images. At this time, the region setting unit 110 may further set a background region within the image. For example, as shown in Figure 3, the region setting unit 110 may set a background region X above the visible smoke determination regions A to M in the image 10.

[0079] When the region setting unit 110 sets a visible smoke determination region within the captured image, it outputs information about the region set within the captured image (positional information of each region within the captured image) to the visible smoke generation determination unit 120 and the visible smoke color index calculation unit 130.

[0080] When a visible smoke detection area is set in the captured image, the visible smoke color index calculation unit 130 calculates a visible smoke color index value for the visible smoke detection area based on the pixel information of each pixel within the visible smoke detection area (S120). The visible smoke color index calculation unit 130 only needs to calculate the visible smoke color index value for at least the visible smoke detection area where visible smoke is determined to be present, but in this example, it calculates the visible smoke color index value for all set visible smoke detection areas. If the visible smoke color index value is to be calculated only for the visible smoke detection area where visible smoke is determined to be present, the process in step S120 may be performed after step S130, which will be described later.

[0081] In step S120, the visible smoke color index calculation unit 130 calculates a reference color index value corresponding to a reference color of visible smoke, and at least one monitoring color index value corresponding to at least one monitoring color, as visible smoke color index values.

[0082] First, the visible smoke color index calculation unit 130 calculates a reference color index value based on pixel information represented by converting the pixels within the region to grayscale. The visible smoke color index calculation unit 130 also calculates pixel information representing the degree of the monitored color relative to the reference color for each monitored color, and calculates a monitored color index value based on this pixel information. For example, when red and yellow are monitored colors, the visible smoke color index calculation unit 130 calculates a visible smoke color index value for red (monitoring color index value A) based on image information representing the degree of red relative to black (red pixel information), and calculates a visible smoke color index value for yellow (monitoring color index value B) based on image information representing the degree of yellow relative to black (yellow pixel information). The visible smoke color index calculation unit 130 outputs the calculated reference color index value and monitoring color index value to the visible smoke color determination unit 140.

[0083] Once the visible smoke color index value is calculated, the visible smoke generation determination unit 120 determines whether or not visible smoke is being generated based on the pixel information of each pixel within the visible smoke determination area (S130). The visible smoke generation determination unit 120 can determine the generation of visible smoke using a well-known visible smoke determination method. For example, the visible smoke generation determination unit 120 uses an index value expressed by spatial luminance, brightness, or their temporal changes as an index of visible smoke generation, and determines the generation of visible smoke when the index value exceeds a reference value. The visible smoke generation determination unit 120 determines whether or not visible smoke is being generated for each visible smoke determination area, and if it determines that no visible smoke is being generated (S130: NO), processing for that captured image is terminated, and processing from step S100 is performed for the next captured image.

[0084] On the other hand, if it is determined in step S130 that visible smoke has been generated (S130: YES), the visible smoke generation determination unit 120 outputs the visible smoke determination area in which it has been determined that visible smoke has been generated to the visible smoke color determination unit 140 and the notification instruction unit 160.

[0085] The visible smoke color determination unit 140 determines the color of the visible smoke in the visible smoke determination area where visible smoke has been determined to be present. To this end, the visible smoke color determination unit 140 first calculates an evaluation value for each monitored color based on the difference between the monitored color index value and the reference color index value (S140). For example, the visible smoke color determination unit 140 calculates the evaluation value as the absolute value of the difference between the monitored color index value and the reference color index value for each monitored color. In this case, for example, when red and yellow are set as monitored colors, the visible smoke color determination unit 140 calculates the evaluation value A for red as the absolute value of the difference between the monitored color index value A and the reference color index value for red, and calculates the evaluation value B for yellow as the absolute value of the difference between the monitored color index value B and the reference color index value for yellow.

[0086] The visible smoke color determination unit 140 calculates evaluation values ​​for all monitored colors and compares all of these evaluation values ​​with a threshold set to determine the reference color of visible smoke (S150). When all evaluation values ​​are less than the threshold (S150: YES), the visible smoke color determination unit 140 determines that the color of the visible smoke is the reference color, and the notification instruction unit 160 notifies the notification device 200 that visible smoke of the reference color is being generated (S160). On the other hand, when at least one evaluation value is greater than or equal to the threshold (S150: NO), the visible smoke color determination unit 140 determines that the color of the visible smoke is the monitored color corresponding to the monitored color index value with the largest evaluation value, and the notification instruction unit 160 notifies the notification device 200 that visible smoke of that monitored color is being generated (S170). For example, when calculating evaluation values ​​A for red and B for yellow, if evaluation value A is greater than evaluation value B, the visible smoke color determination unit 140 determines that red visible smoke is being generated.

[0087] In steps S160 and S170, the visible smoke generating equipment determination unit 170 may determine one or more pieces of equipment associated with the visible smoke color as visible smoke generating equipment based on the visible smoke color determination unit 140, and output this to the notification instruction unit 160. The notification instruction unit 160 notifies the notification device 200 of the visible smoke generating equipment determined by the visible smoke generating equipment determination unit 170.

[0088] Upon receiving notification from the visible smoke detection device 100, the alarm device 200 notifies the equipment monitor and other relevant personnel at the factory, etc., of the visible smoke generated from the monitored equipment and the color of the generated visible smoke (S180). In addition, if the visible smoke detection device 100 notifies the alarm device 200 of the visible smoke generating equipment, it may also notify the equipment along with the visible smoke generated and the color of the generated visible smoke.

[0089] The visible smoke detection method according to this embodiment has been described above. According to the visible smoke detection method according to this embodiment, it is possible to determine whether or not visible smoke is generated and to determine the color of the generated visible smoke. When the generation of visible smoke is detected by the visible smoke detection device, it is possible to identify the equipment that is generating visible smoke by determining and identifying the color of the visible smoke. As a result, measures to prevent recurrence can be promptly taken for the equipment that is generating visible smoke.

[0090] [4. Hardware Configuration] Based on Figure 5, the hardware configuration of the visible smoke detection device 100 according to this embodiment will be described. Figure 5 is a block diagram showing an example of the hardware configuration of the information processing device 900 that functions as the visible smoke detection device 100 according to this embodiment.

[0091] The information processing device 900 includes a processor (CPU 901 in Figure 5), a ROM 903, and a RAM 905. The information processing device 900 also includes a bus 907, an input interface 909, an output interface 911, a storage device 913, a drive 915, a connection port 917, and a communication device 919.

[0092] The CPU 901 functions as both an arithmetic processing unit and a control unit. The CPU 901 controls the overall operation or a part of it within the information processing unit 900 according to various programs recorded in the ROM 903, RAM 905, storage device 913, or removable recording medium 925. The ROM 903 stores programs or arithmetic parameters used by the CPU 901. The RAM 905 temporarily stores programs used by the CPU 901, or parameters that change as appropriate during program execution. These are interconnected by a bus 907, which is composed of an internal bus such as the CPU bus.

[0093] Bus 907 is connected to an external bus, such as the PCI (Peripheral Component Interconnect / Interface) bus, via a bridge.

[0094] The input interface 909 is an interface that receives input from an input device 921, which is a means of operation operated by the user, such as a mouse, keyboard, touch panel, button, switch, and lever. The input interface 909 is configured, for example, as an input control circuit that generates an input signal based on information entered by the user using the input device 921 and outputs it to the CPU 901. The input device 921 may be, for example, a remote control device using infrared or other radio waves, or an external device 927 such as a PDA that is compatible with the operation of the information processing device 900. The user of the information processing device 900 can operate the input device 921 to input various data to the information processing device 900 or instruct it to perform processing operations.

[0095] The output I / F 911 is an interface that outputs the input information to an output device 923 that can visually or audibly notify the user. The output device 923 may be, for example, a display device such as a CRT display, liquid crystal display, plasma display, EL display, or lamp. Alternatively, the output device 923 may be an audio output device such as a speaker or headphones, or a printer, mobile communication terminal, or facsimile. The output I / F 911 instructs the output device 923 to output, for example, the processing results obtained from various processes performed by the information processing device 900. Specifically, the output I / F 911 instructs the display device to display the processing results from the information processing device 900 as text or an image. The output I / F 911 also instructs the audio output device to convert an audio signal, such as audio data that has been instructed to be played, into an analog signal and output it.

[0096] The storage device 913 is one of the storage units of the information processing device 900 and is a device for storing data. The storage device 913 is composed of, for example, a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device such as an SSD (Solid State Drive), an optical storage device, or a magneto-optical storage device. The storage device 913 stores programs executed by the CPU 901, various data generated by the execution of programs, and various data acquired from external sources.

[0097] The drive 915 is a reader / writer for recording media and is either built into or external to the information processing device 900. The drive 915 reads information recorded on the installed removable recording media 925 and outputs it to the RAM 905. The drive 915 can also write information to the installed removable recording media 925. The removable recording media 925 is, for example, a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory. Specifically, the removable recording media 925 may be CD media, DVD media, Blu-ray® media, CompactFlash® (CF), flash memory, SD memory card (Secure Digital memory card), etc. Alternatively, the removable recording media 925 may be, for example, an IC card (Integrated Circuit card) equipped with a contactless IC chip or an electronic device.

[0098] Connection port 917 is a port for directly connecting devices to the information processing device 900. Connection port 917 can be, for example, a USB (Universal Serial Bus) port, an IEEE1394 port, a SCSI (Small Computer System Interface) port, or an RS-232C port. The information processing device 900 can directly acquire various data from or provide various data to external devices 927 connected to connection port 917.

[0099] The communication device 919 is a communication interface composed of, for example, a communication device for connecting to the communication network 929. The communication device 919 is, for example, a communication card for wired or wireless LAN (Local Area Network), Bluetooth (registered trademark), or WUSB (Wireless USB). Alternatively, the communication device 919 may be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various types of communication. The communication device 919 can, for example, send and receive signals to and from the Internet or other communication devices in accordance with a predetermined protocol such as TCP / IP. The communication network 929 connected to the communication device 919 is composed of a network connected by wire or wireless means. For example, the communication network 929 is the Internet, a home LAN, infrared communication, radio wave communication, or satellite communication.

[0100] The above describes an example of the hardware configuration of the information processing device 900. Each of the above-mentioned components may be made using general-purpose materials, or each component may be made using hardware specialized for its function. The hardware configuration of the information processing device 900 can be appropriately changed depending on the level of technology at the time of implementing this embodiment. [Examples]

[0101] To verify the effectiveness of the present invention, a coke oven and a sintering machine were used as monitored equipment, and images captured by an imaging device were processed to determine which equipment generated visible smoke. The experiment was conducted for one day, with monitoring time limited to the morning (8:00 AM to 10:00 AM). The captured images were in the RGB color system, and visible smoke determination regions A to M were set in the captured images as shown in Figure 3. Pixel information was obtained from the captured images using the red component value, green component value, blue component value of the pixels and the values ​​of the functions represented by these components. The sum of the values ​​of each pixel within the region divided by the number of pixels in that region (i.e., the average value) was used as the representative pixel information.

[0102] In this verification, the reference color was black, monitoring color A was red, and monitoring color B was yellow. Visible smoke color index values ​​were expressed in terms of luminance values. The red monitoring color index value A was the red component value of the RGB values, and when the visible smoke had a reddish tint, the value was higher than the reference color index value. The yellow monitoring color index value B was the value obtained by dividing the sum of the red component value and the green component value of the RGB values ​​by 2, and when the visible smoke had a yellowish tint, the value was higher than the reference color index value.

[0103] Furthermore, we associated some visible smoke colors with the equipment. In this verification, when visible smoke was generated from the coke oven, black visible smoke appeared in the captured image, so we associated the standard color black with the coke oven. When visible smoke was generated from the sintering machine, reddish-brown visible smoke appeared in the captured image, so we associated the monitoring color A (red) with the sintering machine. Since visible smoke with monitoring color B is generated from equipment other than the coke oven and sintering machine, we associated monitoring color B with the other equipment.

[0104] Under these conditions, visible smoke detection was performed based on the flowchart shown in Figure 3 above. As a result, visible smoke was detected twice in the visible smoke detection area G during the monitoring time. The first visible smoke detection at time T1 is designated as Case 1, and the second visible smoke detection at time T2 is designated as Case 2. Figure 6 shows the changes in each visible smoke color index value and the evaluation value for the monitored color (absolute difference between the monitored color index value and the reference color index value) in Case 1. Figure 7 shows the changes in each visible smoke color index value and the evaluation value for the monitored color (absolute difference between the monitored color index value and the reference color index value) in Case 2.

[0105] In Case 1, the first instance of visible smoke detection, as shown in Figure 6, only evaluation value A exceeded the threshold around time T1. Since evaluation value A is greater than evaluation value B, it was determined that visible smoke of monitoring color A was being generated. Upon examining the image captured at time T1, it was visually confirmed that reddish-brown visible smoke was being generated. It was also confirmed that the visible smoke originated from the sintering machine. Because the visible smoke generated in Case 1 was reddish-brown, while each RGB component decreased, the decrease in the RGB red component was relatively smaller. Therefore, as can be seen from Figure 6, the difference between the reference color index value and the monitoring color index value A widened.

[0106] In Case 2, the second instance of visible smoke detection, as shown in Figure 7, at around time T2, neither the evaluation value of any of the monitored colors (evaluation values ​​A and B) exceeded the threshold, leading to the determination that black visible smoke, the reference color, was present. Visual confirmation of the captured image at time T2 confirmed the presence of black visible smoke. It was also confirmed that the smoke originated from a coke oven. Because the visible smoke in Case 2 was black, there was not much bias in the decrease of each RGB component. Therefore, as can be seen from Figure 7, there was almost no difference between any of the monitored color index values ​​and the reference color index values.

[0107] As a result, in Case 1, it was possible to determine the generation of visible smoke of monitoring color A and identify it as visible smoke from the sintering machine, and in Case 2, it was possible to determine the generation of visible smoke of the standard color and identify it as visible smoke from the coke oven.

[0108] Although preferred embodiments of the present invention have been described in detail above with reference to the attached drawings, the present invention is not limited to these examples. It is clear to any person with ordinary skill in the art to which the present invention belongs that various modifications or alterations can be conceived within the scope of the technical idea described in the claims, and these are also understood to fall within the technical scope of the present invention. [Explanation of Symbols]

[0109] 1. Visible Smoke Detection System 10 Acquired images 50 Imaging device 100 Visible smoke determination device 110 Area setting unit 120 Visible smoke generation detection unit 130 Visible Smoke Color Index Value Calculation Unit 140 Visible smoke color determination section 150 Threshold setting section 160 News and Instruction Department 170 Visible smoke generation equipment determination unit 180 Storage section 200 Alarm device 300 Information Processing Terminals 900 Information Processing Equipment 901 CPU 903 ROM 905 RAM 907 Bus 909 Input I / F 911 Output I / F 913 Storage device 915 Drive 917 Connection Ports 919 Communication equipment 921 Input device 923 Output device 925 Removable recording media 927 External equipment 929 Communications Network

Claims

1. A visible smoke generation determination unit determines whether or not visible smoke is generated in a visible smoke determination area based on the pixel information of each pixel within a visible smoke determination area set in the captured image obtained by capturing the direction of the equipment that is the target of monitoring for visible smoke generation, A visible smoke color index value calculation unit calculates, based on the pixel information of each pixel within the visible smoke determination area where it has been determined that visible smoke is present, a reference color index value corresponding to a reference color of visible smoke that serves as a criterion for determining the color of visible smoke, and at least one monitoring color index value corresponding to at least one monitoring color as the color of visible smoke to be monitored, as an indicator of the color of the visible smoke. A visible smoke color determination unit that determines the color of the visible smoke occurring in the visible smoke determination area based on the visible smoke color index value, Equipped with, The visible smoke color determination unit calculates an evaluation value for each of the monitored colors based on the difference between the monitored color index value and the reference color index value, and determines that the color of the visible smoke is the reference color when all of the evaluation values ​​are smaller than the threshold set for determining the reference color of the visible smoke. Visible smoke determination device.

2. The visible smoke color determination device according to claim 1, wherein the visible smoke color determination unit determines that the color of the visible smoke is a monitoring color corresponding to the monitoring color index value with the largest evaluation value when at least one of the evaluation values ​​is equal to or greater than the threshold value.

3. The reference color of the visible smoke is the color of the visible smoke that occurs most frequently. The visible smoke determination device according to claim 1, wherein the visible smoke monitoring color includes at least one of the following: the color of the visible smoke with the second highest frequency of occurrence, or the color of the visible smoke with a high priority for recurrence prevention measures.

4. The system includes a threshold setting unit for setting the aforementioned threshold, The threshold setting unit uses a plurality of captured images taken within a predetermined period in the past, With respect to visible smoke determined by the visible smoke color determination unit to be the standard color, the ratio 1, which is determined by the ratio of the number of visible smokes that a person visually confirms as the standard color and that the visible smoke color determination unit determines to be the standard color to the number of visible smokes that a person visually confirms as the standard color, is set to be equal to or greater than a predetermined ratio. With respect to visible smoke that the visible smoke color determination unit has determined to be the standard color, the ratio 2, which is determined by the ratio of the number of visible smokes that a person visually confirms to be the standard color and that the visible smoke color determination unit has determined to be the standard color to the number of visible smokes that the visible smoke color determination unit has determined to be the standard color, is set to be equal to or greater than a predetermined ratio, or The harmonic mean of ratio 1 and ratio 2 is maximized. The visible smoke determination device according to claim 1, wherein the threshold is set by any of the following.

5. The visible smoke detection device according to any one of claims 1 to 4, wherein a plurality of visible smoke detection regions are set within the captured image.

6. The captured image is an RGB color system image with 256 levels of grayscale. The visible smoke determination device according to any one of claims 1 to 4, wherein the visible smoke color index value calculation unit calculates pixel information for each pixel using a function represented by the red component, green component, and blue component of the pixel.

7. A visible smoke determination device according to any one of claims 1 to 4, further comprising a visible smoke generating equipment determination unit that determines one or more pieces of equipment associated with the color of the visible smoke as visible smoke generating equipment based on the color of the visible smoke determined by the visible smoke color determination unit.

8. It is equipped with a notification instruction unit that instructs the alarm device to notify of the generation of visible smoke, The visible smoke determination device according to any one of claims 1 to 4, wherein the notification instruction unit outputs to the alarm device the visible smoke determination area in which visible smoke is determined to be generated by the visible smoke generation determination unit, and the color of the visible smoke determined by the visible smoke color determination unit.

9. The visible smoke determination device according to any one of claims 1 to 4, wherein the equipment to be monitored is at least one of a coke oven or a sintering machine.

10. Computers, A visible smoke generation determination unit determines whether or not visible smoke is generated in a visible smoke determination area based on the pixel information of each pixel within a visible smoke determination area set in the captured image obtained by capturing the direction of the equipment that is the target of monitoring for visible smoke generation, A visible smoke color index value calculation unit calculates, based on the pixel information of each pixel within the visible smoke determination area where it has been determined that visible smoke is present, a reference color index value corresponding to a reference color of visible smoke that serves as a criterion for determining the color of visible smoke, and at least one monitoring color index value corresponding to at least one monitoring color as the color of visible smoke to be monitored, as an indicator of the color of the visible smoke. A visible smoke color determination unit that determines the color of the visible smoke occurring in the visible smoke determination area based on the visible smoke color index value, Equipped with, The visible smoke color determination unit calculates an evaluation value for each of the monitored colors based on the difference between the monitored color index value and the reference color index value, and determines that the color of the visible smoke is the reference color when all of the evaluation values ​​are smaller than the threshold set for determining the reference color of the visible smoke. A program to function as a visible smoke detection device.

11. An imaging device that captures images of the direction of equipment that is being monitored for visible smoke generation and acquires the captured images, A visible smoke detection device that determines whether visible smoke is being emitted from the equipment being monitored based on the captured image, It has, The visible smoke detection device is A visible smoke generation determination unit determines whether or not visible smoke is generated in the visible smoke determination area based on the pixel information of each pixel within the visible smoke determination area set in the captured image, A visible smoke color index value calculation unit calculates, based on the pixel information of each pixel within the visible smoke determination area where it has been determined that visible smoke is present, a reference color index value corresponding to a reference color of visible smoke that serves as a criterion for determining the color of visible smoke, and at least one monitoring color index value corresponding to at least one monitoring color as the color of visible smoke to be monitored, as an indicator of the color of the visible smoke. A visible smoke color determination unit that determines the color of the visible smoke occurring in the visible smoke determination area based on the visible smoke color index value, Equipped with, The visible smoke color determination unit calculates an evaluation value for each of the monitored colors based on the difference between the monitored color index value and the reference color index value, and determines that the color of the visible smoke is the reference color when all of the evaluation values ​​are smaller than the threshold set for determining the reference color of the visible smoke. Visible smoke detection system.

12. A visible smoke generation determination step, which determines whether or not visible smoke is generated in a visible smoke determination area based on the pixel information of each pixel within a visible smoke determination area set in an image obtained by capturing the direction of the equipment that is the target of monitoring for visible smoke generation, A visible smoke color index value calculation step for the visible smoke determination region in which it has been determined that visible smoke is present, based on the pixel information of each pixel within the visible smoke determination region, calculates a visible smoke color index value that serves as an indicator of the color of the visible smoke, which includes a reference color index value corresponding to a reference color of visible smoke that serves as a criterion for determining the color of the visible smoke, and at least one monitoring color index value corresponding to at least one monitoring color as the color of the visible smoke whose occurrence is to be monitored. A visible smoke color determination step, which determines the color of the visible smoke occurring in the visible smoke determination area based on the visible smoke color index value, Includes, The visible smoke color determination step calculates an evaluation value for each of the monitored colors based on the difference between the monitored color index value and the reference color index value, and determines that the color of the visible smoke is the reference color when all of the evaluation values ​​are smaller than the threshold set for determining the reference color of the visible smoke. Visible smoke determination method.

Images