WO2013100069A1 - 炉内撮像方法、炉内撮像システムおよびガラス物品の製造方法 - Google Patents
炉内撮像方法、炉内撮像システムおよびガラス物品の製造方法 Download PDFInfo
- Publication number
- WO2013100069A1 WO2013100069A1 PCT/JP2012/083917 JP2012083917W WO2013100069A1 WO 2013100069 A1 WO2013100069 A1 WO 2013100069A1 JP 2012083917 W JP2012083917 W JP 2012083917W WO 2013100069 A1 WO2013100069 A1 WO 2013100069A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- value
- luminance
- correction
- statistic
- Prior art date
Links
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C03—GLASS; MINERAL OR SLAG WOOL
- C03B—MANUFACTURE, SHAPING, OR SUPPLEMENTARY PROCESSES
- C03B5/00—Melting in furnaces; Furnaces so far as specially adapted for glass manufacture
- C03B5/16—Special features of the melting process; Auxiliary means specially adapted for glass-melting furnaces
-
- C—CHEMISTRY; METALLURGY
- C03—GLASS; MINERAL OR SLAG WOOL
- C03B—MANUFACTURE, SHAPING, OR SUPPLEMENTARY PROCESSES
- C03B5/00—Melting in furnaces; Furnaces so far as specially adapted for glass manufacture
- C03B5/16—Special features of the melting process; Auxiliary means specially adapted for glass-melting furnaces
- C03B5/225—Refining
- C03B5/2252—Refining under reduced pressure, e.g. with vacuum refiners
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0007—Image acquisition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/555—Constructional details for picking-up images in sites, inaccessible due to their dimensions or hazardous conditions, e.g. endoscopes or borescopes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/71—Circuitry for evaluating the brightness variation
Definitions
- the present invention relates to an in-furnace imaging method, an in-furnace imaging system, and a glass article manufacturing method to which the in-furnace imaging method is applied.
- Patent Document 1 describes a high-temperature furnace wall surface observation device for observing the wall surface state in a high-temperature furnace such as a coke oven or a blast furnace from the outside of the furnace (line 19 on the lower right of page 2 of Patent Document 1). (Refer to the second line in the upper left column on page 3 to page 3).
- the apparatus described in Patent Document 1 includes a TV camera that captures an image of the furnace wall and supplies the captured image to the outside of the furnace wall, and a light amount adjustment element that adjusts the amount of light in the furnace that passes through the TV camera in accordance with the applied voltage. And are provided.
- the operator adjusts the amount of light transmitted to the TV camera by changing the voltage applied to the light amount adjustment element by remote control while observing the image captured by the TV camera.
- Patent Document 2 describes an in-furnace observation device that images a furnace wall in order to detect a depression or crack in the furnace wall (see paragraph 0041 of Patent Document 2).
- the furnace wall is irradiated with laser light from the outside of the furnace, and the furnace wall is imaged by the reflected light of the laser from the furnace wall and the emitted light of the furnace wall.
- the apparatus described in Patent Document 2 shortens the shutter speed so that the received light intensity of the reflected laser light is larger than the received light intensity of the radiated light.
- the furnace wall itself is an observation target, and a parameter at the time of image capturing (specifically, the amount of light transmitted to the TV camera) is changed based on the image of the observation target.
- a clear image can be obtained by capturing an image of an observation target and changing parameters at the time of imaging based on the image of the observation target itself.
- the furnace wall itself is an observation target, and the parameters (shutter speed) at the time of imaging the furnace wall based on the state of the furnace wall (the intensity of light received from the furnace wall) To change.
- molten glass When manufacturing glass articles such as glass plates, molten glass may be observed.
- bubbles are present in the initial state.
- the bubbles are generated in a melting tank for melting a raw material that is a glass melting furnace, a clarification tank for removing (that is, clarifying) the bubbles from the molten glass, and the like.
- a case where the molten glass inside the clarification tank is observed will be described as an example. It is assumed that the molten glass to be observed is imaged, and the parameters used for obtaining the image are changed based on the molten glass image.
- the brightness of light emitted from the object increases, so the parameters used when obtaining an image of the object to be observed are changed according to the brightness. It is considered that a good image can be obtained.
- the brightness changes due to a factor other than the temperature of the molten glass. For example, if a bubble passes or a bubble layer formed by aggregating or laminating bubbles on the liquid surface portion is generated, the brightness becomes brighter.
- the evaluation position changes at the point fixed on the image and the brightness changes, and if it is a point fixed on the molten glass surface, the reflection destination changes. Changes the brightness. It is not easy to remove the influence of these brightness changes and extract only the influence of temperature. For this reason, it is difficult to obtain an image with good contrast even if the parameters used for obtaining the image are changed based on the image of the surface of the molten glass.
- the present invention provides an in-furnace imaging method, an in-furnace imaging system, and an in-furnace imaging system capable of obtaining an image with good contrast when imaging molten glass using a molten glass in a high-temperature furnace as an observation target. It aims at providing the manufacturing method of the glass article to which the imaging method is applied.
- An in-furnace imaging method is an in-furnace imaging method for imaging a molten glass in a furnace to be observed, an imaging step for imaging the molten glass together with a structure in the furnace, and generating an image.
- An image correction step for correcting the image generated in the step using predetermined parameters, and a luminance value data group of a predetermined area predetermined as an area corresponding to a structure in the image before correction.
- a luminance statistic specifying step for specifying a calculated statistic; a parameter value calculating step for calculating a value of a predetermined parameter based on the statistic of the luminance value of the predetermined area specified in the luminance statistic specifying step; A parameter value update step for updating the value of the predetermined parameter used in the image correction step with the value calculated in the parameter value calculation step.
- the image correction step the image is corrected using an offset, which is a parameter representing a difference between a statistic of a luminance value of a predetermined area in the image before correction and a predetermined value as a predetermined parameter, and the parameter value calculation
- the offset value may be calculated based on the statistic of the luminance value of the predetermined area in the image before correction.
- a structure in which the relationship between the brightness value of the region corresponding to the structure in the image obtained by imaging and the temperature of the structure is known is provided in the furnace, and the region corresponding to the structure in the image is predetermined. It may be determined as a region.
- Pre-correction luminance value calculation step for calculating the luminance value of the pixel in the predetermined region in the image before correction by performing reverse calculation of the correction processing in the image correction step on the pixel in the predetermined region in the image after correction obtained in the image correction step
- the statistic of the luminance value of the predetermined area in the image before correction may be specified from the luminance value calculated in the luminance value calculating step before correction.
- the luminance statistic specifying step a statistic of a luminance value of a predetermined area in the image after correction obtained in the image correcting step is specified, and the back calculation of the correction processing in the image correcting step is performed on the statistic of the luminance value.
- the statistic of the luminance value of the predetermined area in the image before correction may be specified.
- a statistic of a brightness value of a predetermined area in the image generated in the imaging step may be specified.
- a contrast processing step for selecting an image may be included.
- an average value of luminance values in a predetermined area may be specified as a statistic of luminance values.
- An in-furnace imaging system is an in-furnace imaging system that images a molten glass in a furnace that is an observation target, and an imaging unit that images the molten glass together with a structure in the furnace and generates an image.
- An image correction unit that corrects an image generated by the imaging unit using a predetermined parameter; and a data group of luminance values of a predetermined region that is predetermined as a region corresponding to a structure in the image before the correction
- a brightness statistic specifying means for specifying a statistic calculated from the above
- a parameter value calculating means for calculating a value of a predetermined parameter based on a statistic of a brightness value of a predetermined area specified by the brightness statistic specifying means
- Parameter value updating means for updating the value of a predetermined parameter used by the image correction means with the value calculated by the parameter value calculating means.
- the image correction means corrects the image using an offset, which is a parameter indicating a difference between a statistic of a luminance value of a predetermined area in the image before correction and a predetermined value as a predetermined parameter, and calculates the parameter value
- the means may be configured to calculate an offset value based on a statistic of a luminance value of a predetermined area in the image before correction.
- a pre-correction luminance value calculating unit that calculates a luminance value of a pixel in the predetermined region in the image before correction by performing reverse calculation of the correction processing performed by the image correction unit on the pixel in the predetermined region in the image corrected by the image correction unit;
- the luminance statistic specifying unit may be configured to specify a statistic of a luminance value of a predetermined area in the image before correction from the luminance value calculated by the luminance value calculating unit before correction.
- the luminance statistic specifying unit specifies a statistic of a luminance value of a predetermined area in the image after the correction process performed by the image correction unit, and performs a back calculation of the correction process on the statistic of the luminance value before correction.
- the configuration may be such that the statistic of the luminance value of the predetermined area in the image is specified.
- the luminance statistic specifying unit may specify a statistic of a luminance value of a predetermined area in the image generated by the imaging unit.
- Contrast processing means may be provided for calculating an amount representing the contrast of light and dark in a predetermined area in an image captured by the image capturing unit at a predetermined cycle, and selecting an image satisfying a predetermined condition regarding the amount representing the contrast.
- the luminance statistic specifying unit may specify an average value of luminance values in a predetermined area as a statistical value of luminance values.
- the glass article manufacturing method includes a glass melting step for manufacturing molten glass in a melting tank, a clarification step for removing bubbles of the molten glass in a clarification tank, and bubbles are removed in the clarification step. And a slow cooling step for slowly cooling the molded molten glass, and the molten glass in the clarification tank is used as an observation target, and the molten glass is used together with the structure in the clarification tank.
- the glass article manufacturing method includes a glass melting step for manufacturing molten glass in a melting tank, a clarification step for removing bubbles of the molten glass in a clarification tank, and bubbles are removed in the clarification step.
- An imaging step for capturing an image and generating an image; an image correction step for correcting the image generated in the imaging step using predetermined parameters; and an area corresponding to a structure in the image before correction
- a luminance statistic specifying step for specifying a statistic calculated from a luminance value data group of a predetermined area, and a location specified by the luminance statistic specifying step.
- an image with good contrast can be obtained when the molten glass is imaged with the molten glass in a high-temperature furnace as an observation target.
- FIG. 1 is a block diagram illustrating a configuration example of an in-core imaging system according to a first embodiment of the present invention.
- FIG. 4 is a schematic diagram illustrating an example of an image generated by an image generation unit 11.
- the flowchart which shows the example of the process progress of 1st Embodiment.
- the scatter diagram which shows the relationship between the temperature of a structure, and the average brightness
- the schematic diagram which shows the example of the image obtained by imaging the inside of a furnace.
- Drawing 1 is a mimetic diagram showing the situation where the molten glass in a clarification tank is imaged.
- the clarification tank 30 is a kind of furnace, and the inside becomes a high temperature and maintains the molten state of the glass.
- An inflow port 33 and an outflow port 34 are provided in the lower part of the clarification tank 30, and the molten glass 31 flows in from the inflow port 33 and flows out of the outflow port 34.
- the clarification tank include a reduced pressure type clarification tank in which the inside of the tank is depressurized to remove bubbles, and a high temperature type clarification tank in which the interior of the tank is removed at a high temperature.
- the clarification tank 30 shown in FIG. 1 is a reduced pressure type clarification tank
- the clarification tank 30 is not limited to a reduced pressure type clarification tank, and other types of clarification tanks. It may be.
- the high-temperature furnace to which the present invention is applied is not limited to a clarification tank, and may be a dissolution tank in which bubbles are generated.
- the molten glass 31 flowing into the clarification tank 30 contains bubbles, and when the bubbles rise to the surface of the molten glass 31, a bubble layer 32 is generated on the surface of the molten glass 31.
- the bubbles are broken and the bubbles are removed. Accordingly, although bubbles are present on the upstream side in the clarification tank 30, the bubbles are removed toward the downstream side, and the molten glass 31 flows out from the outlet 34 in a state where the bubbles are removed.
- the molten glass 31 inside such a furnace (clarification tank 30) is imaged by the camera 1 provided in the in-furnace imaging system, and an image of the molten glass 31 is obtained.
- the camera 1 images the molten glass 31 and the structure of the furnace other than the molten glass 31 (in this example, the wall surface inside the clarification tank 30). Therefore, an image including the molten glass 31 and the structure (furnace wall) is obtained.
- the bubble layer 32 may be reflected in the image.
- the camera 1 is arranged facing the inside of the furnace (clarification tank 30) and images the inside of the clarification tank 30. At this time, the angle is adjusted so that the molten glass 31 and the wall surface are imaged together.
- illustration of the window of the clarification tank 30 is omitted in FIG. 1, the camera 1 images the molten glass 31 and the wall surface through the window of the clarification tank 30.
- FIG. 1 illustrates the case where the camera 1 is arranged so as to image the upstream side from the downstream side, but the camera 1 may be arranged so as to image the downstream side from the upstream side. Good.
- FIG. 2 is a block diagram illustrating a configuration example of the in-core imaging system according to the first embodiment of the present invention.
- the in-furnace imaging system according to the first embodiment of the present invention includes a camera 1 and a correction parameter value update device 2.
- the camera 1 includes an image generation unit 11, an image correction unit 12, and a first correction parameter value storage unit 13.
- the correction parameter value update device 2 includes a pre-correction luminance statistic deriving unit 21, a correction parameter value updating unit 22, and a second correction parameter value storage unit 23.
- the first correction parameter value storage unit 13 is simply referred to as a correction parameter value storage unit 13
- the second correction parameter value storage unit 23 is simply referred to as a correction parameter value storage unit 23.
- the image generation unit 11 captures the molten glass 31 and the wall surface inside the clarification tank 30 and generates an image thereof.
- the shutter speed when the image generation unit 11 images the inside of the clarification tank 30 is determined in advance as a fixed value. However, the structure which can operate the camera 1 and can change the value of shutter speed may be sufficient.
- the image correction unit 12 corrects the image generated by the image generation unit 11. At this time, the image correction unit 12 corrects the image using the correction parameters stored in the correction parameter value storage unit 13.
- the correction parameter value storage unit 13 is a storage device (for example, a memory) that stores values of correction parameters.
- FIG. 3 is an example of a histogram of luminance values in the entire image.
- FIG. 3A shows an example of a histogram of luminance values of the entire image (that is, the image before correction) generated by the image generation unit 11.
- FIG. 3B shows an example of a histogram of luminance values of the entire image after correction by the image correction unit 12.
- the “average luminance value in a predetermined area” shown in FIGS. 3A and 3B is an average value of luminance values in a predetermined area in the image. Note that the average value of the luminance values of the predetermined area is an example of a statistic of the luminance value of the predetermined area.
- FIG. 4 is a schematic diagram illustrating an example of an image generated by the image generation unit 11. As shown in FIG. 4, the surface portion 45 of the molten glass and the furnace wall portion 42 are shown in the image. In addition, in FIG. 4, the case where the window 41 provided in the furnace wall is also illustrated.
- an area 43 in the image illustrated in FIG. 4 may be determined as a predetermined area.
- the entire furnace wall portion 42 in the image may be determined as the predetermined area, as shown in FIG. 4, a part of the area 43 may be determined as the predetermined area.
- a part of the region 43 in the furnace wall portion 42 in the image is a predetermined region will be described as an example.
- the area 43 illustrated in FIG. 4 is an example of the predetermined area, and the position and size of the predetermined area in the image are not limited to the example illustrated in FIG.
- the minimum luminance value of each image before and after correction is zero.
- L the maximum luminance value.
- L 2 n ⁇ 1.
- the image correcting unit 12 converts the entire image generated by the image generating unit 11 so as to widen the spread of the luminance distribution in the entire image by a predetermined factor.
- the spread of the luminance distribution in the entire image is a value obtained by subtracting the minimum luminance value from the maximum luminance value in the entire image.
- a correction parameter indicating how many times the spread of the luminance distribution is to be increased is hereinafter referred to as gain, and the gain value is represented by G.
- the image correction unit 12 performs correction so that the average value of the luminance values of the predetermined area 43 in the image before correction approaches a predetermined value (C).
- C is a central value in the range of 0 to L that can be expressed as a luminance value.
- the correction parameter indicating how much the average value of the luminance value of the predetermined area 43 in the image before correction is changed is referred to as an offset.
- the offset value is represented by B.
- the offset value B is a value obtained by multiplying the average value of the luminance values of the predetermined area 43 before correction by ⁇ 1 and adding C / G.
- the offset value B can be expressed by the following equation (1).
- b in the equation (1) is an average value of luminance values of the predetermined area 43 in the image before correction.
- the correction parameter value update device 2 calculates the average value of the luminance values of the predetermined area 43 in the image before correction using the image after correction, and calculates the moving average of the average value. .
- the case where the calculation result is used as b will be described as an example.
- the offset is a parameter representing a value corresponding to a difference between an average luminance value of each pixel in a predetermined region in the image before correction and a desired average luminance value C for each pixel in the predetermined region in the image after correction. be able to.
- the correction parameter value storage unit 13 stores the gain value G and the offset value B.
- the gain value G is determined in advance as a fixed value.
- the structure which can operate the camera 1 and can change the gain value G may be sufficient.
- the initial value of the offset value B is stored in the correction parameter value storage unit 13. Thereafter, the offset value B is updated by the correction parameter value updating unit 22.
- the image correction unit 12 uses the G and B stored in the correction parameter value storage unit 13 to calculate the luminance value by calculating the following equation (2) for each pixel in the image generated by the image generation unit 11. The image is corrected by the conversion.
- I (x) is expressed by the following formula (3).
- Equation (3) Shown in Equation (3) is a Gaussian symbol, and [x] is the maximum integer that does not exceed x.
- g 0 is a luminance value in the image before correction.
- G c is the luminance value in the corrected image. That is, the image correction unit 12 adds the offset value B to the luminance value g 0 of the image before correction, and multiplies the addition result by G to obtain the luminance value of the image after correction. However, if the multiplication result is less than 0, the luminance value of the corrected image is set to 0. If the multiplication result exceeds L (255 in this example), the luminance value of the corrected image is set to L.
- the image correction unit 12 inputs the corrected image to the pre-correction luminance statistic deriving unit 21 of the correction parameter value update device 2.
- the image captured by the camera 1 is corrected, and the corrected image is input to the correction parameter value update device 2.
- the pre-correction luminance statistic deriving unit 21 calculates an average value of luminance values in a predetermined region 43 (see FIG. 4) in the image before correction based on the corrected image input from the image correction unit 12. Specifically, the pre-correction luminance statistic deriving unit 21 performs the calculation of the following equation (4) for each individual pixel in the predetermined region 43 in the corrected image input from the image correction unit 12. Then, the luminance value before correction is calculated backward.
- g 0 ′ is a luminance value in the image before correction obtained by back calculation.
- the pre-correction luminance statistic deriving unit 21 obtains a pre-correction luminance value g 0 ′ for each pixel in the predetermined region 43 and calculates an average value of the pre-correction luminance values in the predetermined region 43.
- This average value is denoted as g 0 ′ ave .
- the average value of the luminance values of the predetermined area is an example of a statistic of the luminance value of the predetermined area. In each embodiment, a case where an average value of luminance values in a predetermined area is used will be described as an example. However, other statistics such as an intermediate value may be used instead of the average value.
- the pre-correction brightness statistic deriving unit 21 calculates g 0 ′ ave every time a corrected image is input from the image correction unit 12, and uses g 0 ′ ave obtained in the past to obtain g 0 ′ ave. Find the moving average of.
- the correction parameter value storage unit 23 is a storage device (for example, a memory) that stores correction parameter values. Specifically, the correction parameter value storage unit 23 stores the gain value G and the offset value B. The correction parameter value storage unit 23 stores the same values as G and B stored in the correction parameter value storage unit 12 of the camera 1 as G and B.
- the pre-correction luminance statistic deriving unit 21 may use G and B stored in the correction parameter value storage unit 23 when obtaining g 0 ′ by calculation of Expression (4). Note that the correction parameter value update device 2 does not include the correction parameter value storage unit 23, but the pre-correction brightness statistic deriving unit 21 accesses the correction parameter value storage unit 13 of the camera 1 and stores the correction parameter value storage unit 13 in the correction parameter value storage unit 13. The stored G and B may be read to perform the calculation of Expression (4).
- the correction parameter value updating unit 22 recalculates the offset value B by calculating Equation (1), where b is the moving average of g 0 ′ ave calculated by the pre-correction luminance statistic deriving unit 21.
- the correction parameter value update unit 22 updates B stored in the correction parameter value storage units 13 and 23 with the offset value B obtained by the calculation of Expression (1).
- FIG. 5 is a flowchart illustrating an example of processing progress of the first embodiment.
- the image generation unit 11 of the camera 1 images the surface of the molten glass and the furnace wall in the furnace (in the clarification tank), and generates the image (step S1).
- the image correction unit 12 reads G and B stored in the correction parameter value storage unit 13 of the camera 1. Then, the image correction unit 12 corrects the image generated in step S1 by calculating the formula (2) for each pixel of the image generated in step S1 and converting the luminance value (step S2). . The image correction unit 12 inputs the corrected image to the pre-correction brightness statistic deriving unit 21 of the correction parameter value update device 2.
- the pre-correction luminance statistic deriving unit 21 reads G and B stored in the correction parameter value storage unit 23 of the correction parameter value update device 2. Then, the pre-correction luminance statistic deriving unit 21 performs the calculation of Expression (4) for each pixel in the predetermined area 43 (see FIG. 4) in the input image after correction, and the predetermined area in the image before correction The luminance value g 0 ′ of 43 pixels is calculated backward (step S3).
- the pre-correction luminance statistic deriving unit 21 calculates an average value g 0 ′ ave of the luminance values of the pixels in the predetermined area 43 in the image before correction (that is, the luminance values g 0 ′ calculated in step S3). Calculate (step S4). In step S4, the pre-correction luminance statistic deriving unit 21 stores the calculated g 0 ′ ave .
- the pre-correction luminance statistic deriving unit 21 calculates g 0 ′ ave by performing the processes of steps S3 and S4 each time a corrected image is input from the image correcting unit 12.
- the pre-correction luminance statistic deriving unit 21 stores g 0 ′ ave for the most recent predetermined number of images. For example, m g 0 ′ ave corresponding to the most recently input m images are stored. For example, if g 0 ′ ave newly calculated in step S4 is stored, the oldest g 0 ′ ave may be deleted.
- the pre-correction luminance statistic deriving unit 21 calculates a moving average of g 0 ′ ave by calculating an average value of g 0 ′ ave corresponding to the most recent predetermined number of images ( Step S5).
- the correction parameter value update unit 22 reads G stored in the correction parameter value storage unit 23. Then, the correction parameter value updating unit 22 calculates the offset value B by calculating Equation (1) using the moving average of g 0 ′ ave calculated in Step S5 (Step S6).
- the moving average of g 0 ′ ave calculated in step S5 is b in the equation (1).
- the correction parameter value update unit 22 determines whether it is the update timing of the offset value B stored in the correction parameter value storage units 13 and 23 (step S7).
- the correction parameter value update unit 22 is, for example, the update timing of the offset value B if a predetermined period has elapsed since the last time the offset value B stored in the correction parameter value storage units 13 and 23 was updated. If the predetermined period has not elapsed, it may be determined that it is not the update timing of the offset value B.
- the correction parameter value update unit 22 calculates the offset value B stored in the correction parameter value storage units 13 and 23 in the immediately preceding step S6.
- the updated offset value is updated (step S8).
- the offset value B stored in the correction parameter value storage units 13 and 23 is periodically updated.
- the image generation part 11 also images the inside of a furnace regularly and produces
- the update cycle of the offset value B is set to be longer between the image generation cycle by the image generation unit 11 and the update cycle of the offset value B by the correction parameter value update unit 22.
- step S7 If it is determined in step S7 that it is not the update timing of the offset value B (No in step S7), the process proceeds to step S1 after step S8. Alternatively, after step S8 for updating the offset value B, the process proceeds to step S1. When a certain period has elapsed from the previous image generation time, the image generation unit 11 again captures the molten glass and the furnace wall in the furnace (in the clarification tank), and generates the image (step S1). The operations after step S1 are the same as those already described.
- the correction parameter value update device 2 may store an image input from the image correction unit 12 of the camera 1 in a storage device (not shown). Alternatively, the correction parameter value update device 2 may display the image input from the image correction unit 12 on a display device (not shown).
- the predetermined region 43 includes a plurality of pixels has been described as an example.
- the predetermined area 43 may be an area composed of one pixel.
- the pre-correction luminance statistic deriving unit 21 back-calculates the luminance value g 0 ′ in the image before correction for one pixel corresponding to the predetermined region 43 in the input image after correction. That's fine.
- the pre-correction luminance statistic deriving unit 21 calculates the moving average of g 0 ′ ave
- the correction parameter value updating unit 22 uses the moving average of g 0 ′ ave.
- the offset value B may be calculated from g 0 ′ ave . That is, the process of step S5 may not be executed.
- the pre-correction luminance statistic deriving unit 21 performs the calculation of Expression (4) on the pixels of the predetermined area 43 in the image after correction, whereby the predetermined area 43 in the image before correction is performed. 'back to find, g 0' of the luminance values g 0 of the pixel has been described a case of calculating the average value g 0 'ave (see step S3, S4).
- the pre-correction brightness statistic deriving unit 21 obtains the average brightness value of the pixels in the predetermined region 43 in the image after correction, and performs the back calculation of the correction process in step S2 on the average brightness value, thereby performing the pre-correction image. You may calculate the average value of the luminance value of the predetermined area
- the pre-correction luminance statistic deriving unit 21 may obtain the average luminance value of the pixels in the predetermined area 43 in the corrected image. Then, the pre-correction luminance statistic deriving unit 21 substitutes the average luminance value for g c in the equation (4) and calculates the result of the calculation in the equation (4) for the predetermined region 43 in the image before the correction.
- the average value g 0 ′ ave of the luminance values of the pixels may be used. This process may be performed instead of steps S3 and S4 and the process may proceed to step S5.
- a predetermined region 43 (see FIG. 4) corresponding to a structure (in this example, a furnace wall) other than the surface portion 45 of the molten glass to be observed is determined in advance. Then, the average luminance of each pixel in the predetermined area 43 in the image before correction is obtained, and the offset value B is recalculated based on the average luminance.
- the image correction unit 12 (see FIG. 2) calculates the formula (2) for each pixel of the image generated by the image generation unit 11 using the offset value B and the gain value G determined as a fixed value. To correct the image.
- the state of the reflected light at the liquid surface part of the molten glass changes with time, and even if the parameters are changed based on the image of the surface of the molten glass, it is possible to obtain an image with good contrast. difficult.
- a region in the image corresponding to a structure other than the surface portion 45 of the molten glass to be observed is defined as the predetermined region 43. Then, as described above, the offset value B is calculated based on the average luminance of each pixel in the predetermined area 43, and the image is corrected by the calculation of Expression (2).
- the temperature of the molten glass or the structure in the furnace becomes high, and the luminance value of each pixel is biased to a high value in the image before correction, or the temperature of the molten glass or structure becomes low, and Even if the luminance value of each pixel is biased to a low value in the image, the average luminance is C (for example, (L + 1) / 2) in the corrected image. In addition, the spread of the luminance distribution is widened. Therefore, even when the luminance value is biased as described above, an image with good contrast can be obtained by the correction.
- FIG. 6 is a scatter diagram showing the relationship between the temperature of the structure (in this example, the furnace wall) and the average brightness of the furnace wall portion in the image.
- the horizontal axis represents the temperature of the structure (furnace wall), and the vertical axis represents the average brightness of the furnace wall portion.
- FIG. 7 is an example of a luminance histogram in the entire image of the molten glass 31 and the wall surface captured by the camera 1. It is assumed that when the furnace wall temperature changes, the brightness histogram of the entire image translates. The designer sets an upper limit and a lower limit of the luminance value in the histogram illustrated in FIG. In this case, for example, the upper limit value and the lower limit value of the range of the luminance value of the pixel corresponding to the bubble layer in the molten glass to be observed and the luminance value of the pixel corresponding to the structure not to be observed may be determined.
- an upper limit value and a lower limit value of luminance in a region other than the liquid surface of the molten glass that is in a mirror surface state may be determined.
- the upper limit value of the luminance values designer defined thus as L 1 the lower limit value be L 2.
- the average value of the luminance in the region corresponding to the furnace wall is L ave . Then, the difference between the L ave and L 1 and delta 1, the difference between L ave and L 2 and delta 2.
- the change in the value obtained by adding the delta 1 the luminance value indicated by the linear regression equation shown in two-dot chain line shows the change of a value obtained by subtracting the delta 2 from the luminance value indicated by the linear regression equation by the one-dot broken line . Since the histogram illustrated in FIG. 7 is assumed to move in parallel with the temperature change, these changes are represented by straight lines (see FIG. 6).
- the lower limit of the furnace wall temperature at which a good contrast image is obtained is shown as t min .
- the temperature value obtained by adding the delta 1 the luminance value indicated by the linear regression equation is 255, which is the upper limit of the temperature of the furnace wall image of good contrast.
- the upper limit of the temperature of the furnace wall at which a good contrast image is obtained is shown as t max .
- a region corresponding to the furnace wall in the image is defined as a predetermined region, and the predetermined region is a calculation target of a moving average of average values g 0 ′ ave and g 0 ′ ave of luminance values before correction.
- the case where the area is used has been described as an example.
- An area corresponding to a structure other than the furnace wall in the image may be defined as the predetermined area.
- a measuring instrument such as a thermocouple or a ground meter is arranged in the furnace. Of the areas in the image, an area corresponding to a measuring instrument arranged in the furnace may be determined as a predetermined area.
- the ground meter is a furnace internal structure for visually checking the ground level.
- a new structure (eg, a brick block) is placed in the furnace to define the predetermined area in the image. You may arrange. Then, an area corresponding to the structure may be determined as a predetermined area in an image obtained by imaging the inside of the furnace by the camera 1 (see FIGS. 1 and 2). In this case, the relationship between the average luminance value of the region corresponding to the structure in the image and the temperature of the structure is examined, and the structure having such a relationship is placed in the furnace. Is preferred.
- the relationship between the average luminance value of the region corresponding to the structure in the image and the temperature of the structure in the furnace is known, the relationship is represented by a regression equation, as described with reference to FIGS. Furthermore, the upper limit and the lower limit of the temperature of the structure from which a good contrast image can be obtained can be obtained.
- an offset value may be calculated for each predetermined area by defining a plurality of predetermined areas in the image, which are moving average calculation target areas of the average luminance values g 0 ′ ave and g 0 ′ ave .
- the area in the image to be corrected using the offset value is determined in correspondence with each predetermined area. Then, the same processing as in the first embodiment may be performed for each region in the image corresponding to each predetermined region, and then the corrected image obtained for each region may be synthesized. Specific examples are shown below.
- FIG. 8 is a schematic diagram showing an example of an image obtained by imaging the inside of the furnace.
- the case where the downstream side is imaged from the upstream side in a furnace is illustrated. Therefore, the arrow direction shown in FIG. 8 is the direction of the flow of the molten glass.
- a tunnel is provided in the furnace, and the molten glass enters the tunnel from the entrance of the tunnel, passes through the tunnel, and flows downstream.
- FIG. 8 is an image obtained by imaging the vicinity of the entrance of the tunnel from the upstream side in the furnace.
- a portion corresponding to the furnace wall 50 inside the tunnel, the furnace wall 52 above the tunnel entrance, and the furnace walls 51 on both sides of the tunnel entrance Is also included.
- FIG. 8 is a schematic diagram of an image, and does not express the difference in luminance due to the difference in area.
- FIG. 9 is a schematic diagram in which a region corresponding to the downstream side at a low temperature in the image shown in FIG. 8 is extracted.
- the image illustrated in FIG. 8 is divided into a region corresponding to the downstream side at low temperature (see FIG. 9) and other regions, and average luminance values g 0 ′ ave and g 0 ′ ave for each region. What is necessary is just to define the predetermined area
- a predetermined region 43b is defined in a portion corresponding to the furnace wall 50 inside the tunnel in a region corresponding to the downstream side.
- the in-furnace imaging system may derive the offset value B using the predetermined region 43b for the region corresponding to the downstream side (see FIG. 9), and correct the image using the offset value.
- a predetermined range 43a is defined in a portion corresponding to the furnace wall 52 at the upper entrance of the tunnel.
- the offset value B is calculated using the predetermined region 43 a, and the image using the offset value is used. May be corrected. Then, it is only necessary to derive one image by combining the corrected images respectively obtained for the region corresponding to the downstream side and the region corresponding to the upstream side.
- the camera 1 (see FIG. 2) images the inside of the furnace to generate an image, corrects the image, and inputs the corrected image to the correction parameter value update device 2. . Therefore, in the first embodiment, the pre-correction brightness statistic deriving unit 21 of the correction parameter value updating device 2 determines the predetermined area in the image before correction from the luminance value of the predetermined area 43 (see FIG. 4) in the image after correction. The luminance value of 43 is calculated backward. In contrast, in the second embodiment, the camera inputs an image obtained by imaging the inside of the furnace to the correction parameter value update device without correction.
- the first embodiment is suitable.
- the second embodiment is suitable.
- FIG. 10 is a block diagram illustrating a configuration example of the second exemplary embodiment of the present invention.
- the in-furnace imaging system according to the second embodiment of the present invention includes a camera 60 and a correction parameter value update device 70.
- the camera 60 includes an image generation unit 61.
- the correction parameter value update device 70 includes an image correction unit 71, a correction parameter value storage unit 72, a pre-correction luminance statistic derivation unit 73, and a correction parameter value update unit 74.
- the camera 60 is arrange
- generation part 61 images the molten glass 31 and wall surface inside the clarification tank 30 together, and produces
- the image generation unit 61 inputs the image to the correction parameter value update device 70.
- the shutter speed at the time of imaging is determined as a fixed value in advance. However, the shutter speed value may be changed by operating the camera 60.
- the correction parameter value storage unit 72 is a storage device (for example, a memory) that stores the value of the correction parameter, and specifically stores the gain value G and the offset value B.
- the gain value G is determined in advance as a fixed value. The configuration may be such that the gain value G can be changed by operating the camera 60. Further, the initial value of the correction parameter value storage unit 72 is stored. Thereafter, the offset value B is updated by the correction parameter value update unit 74.
- the image correction unit 71 corrects the image input from the image generation unit 61 of the camera 60. This correction processing is the same as the correction processing by the image correction unit 12 in the first embodiment. That is, the image correction unit 71 uses the G and B stored in the correction parameter value storage unit 72 to calculate the above-described equation (2) for each pixel in the image input from the image generation unit 61. The image is corrected by converting the luminance value.
- the pre-correction luminance statistic deriving unit 73 calculates the average value of the luminance values of a predetermined area in the image input from the image generation unit 61 (in other words, the image before correction).
- this average value is denoted as g 0ave .
- the predetermined region is a region corresponding to a structure (in this example, a furnace wall) other than the surface portion 45 (see FIG. 4) corresponding to the molten glass to be observed, as in the first embodiment. is there.
- an area 43 in the image illustrated in FIG. 4 may be determined as a predetermined area.
- the case where the area 43 shown in FIG. 4 is determined as the predetermined area will be described as an example.
- the pre-correction luminance statistic deriving unit 73 calculates an average value g 0ave of luminance values in a predetermined region in the predetermined region 43 every time an image is input from the image generation unit 61, and uses g 0ave obtained in the past. To obtain a moving average of g 0ave .
- the pre-correction luminance statistic deriving unit 73 directly uses the image generated by the image generating unit 61 to calculate the average luminance value g 0ave of the predetermined region 43. Therefore, the pre-correction luminance statistic deriving unit 73 does not have to reversely calculate the luminance value of the predetermined area 43 from the image corrected by the image correcting unit 71.
- the correction parameter value update unit 74 is the same as the correction parameter value update unit 22 in the first embodiment.
- the correction parameter value updating unit 74 recalculates the offset value B by calculating Equation (1), where b is the moving average of g 0ave calculated by the pre-correction luminance statistic deriving unit 73. .
- the correction parameter value update unit 74 updates B stored in the correction parameter value storage unit 72 with the offset value B obtained by the calculation of Expression (1).
- FIG. 11 is a flowchart illustrating an example of processing progress of the second embodiment.
- the image generation unit 61 images the molten glass and the furnace wall in the furnace (in the clarification tank), and generates the image (step S11).
- the image generation unit 61 inputs the generated image to the correction parameter value update device 70.
- the image correction unit 71 When an image is input from the image generation unit 61 to the correction parameter value update device 70, the image correction unit 71 reads G and B stored in the correction parameter value storage unit 72. Then, the image correction unit 71 corrects the generated image by calculating the formula (2) for each pixel of the image input from the camera 60 (image generation unit 61) and converting the luminance value ( Step S12).
- the image correcting unit 71 may store the corrected image generated in step S12 in a storage device (not shown). Alternatively, the image correction unit 71 may display the corrected image on a display device (not shown).
- the pre-correction luminance statistic deriving unit 73 calculates the luminance value of each pixel in the predetermined region 43 in the image (the image before correction). An average value g 0ave is calculated (step S13). In step S13, the pre-correction luminance statistic deriving unit 73 stores the calculated g 0ave .
- the pre-correction brightness statistic deriving unit 73 performs the process of step S13 each time an image is input from the image generation unit 61 to the correction parameter value update device 70 to calculate g 0 ave .
- the pre-correction luminance statistic deriving unit 73 stores m pieces of g 0ave corresponding to the most recently inputted m pieces of images.
- the pre-correction luminance statistic deriving unit 73 calculates the moving average of g 0ave by calculating the average value of g 0ave corresponding to the most recent predetermined number of images (step S14).
- the correction parameter value update unit 74 reads the gain value G stored in the correction parameter value storage unit 72. Then, the correction parameter value updating unit 74 calculates the offset value B by calculating Equation (1) using the moving average of g 0ave calculated in Step S14 (Step S15). In this example, the moving average of g 0ave calculated in step S14 is b in the equation (1).
- the correction parameter value update unit 74 determines whether it is the update timing of the offset value B stored in the correction parameter value storage unit 72 (step S16).
- the determination process in step S16 is the same as the determination process in step S7 in the first embodiment.
- the correction parameter value update unit 74 calculates the offset value B stored in the correction parameter value storage unit 72 as the offset calculated in the immediately preceding step S15. Update with a value (step S17).
- the offset value B stored in the correction parameter value storage unit 72 is periodically updated as in the first embodiment. Also in the second embodiment, the image generation unit 61 periodically images the inside of the furnace and generates an image. The update cycle of the offset value B is set longer between the image generation cycle by the image generation unit 61 and the update cycle of the offset value B by the correction parameter value update unit 74.
- step S16 If it is determined in step S16 that it is not the update timing of the offset value B (No in step S16), or after step S17, the process proceeds to step S11.
- the image generation unit 11 When a certain period has elapsed from the previous image generation time, the image generation unit 11 again captures the molten glass and the furnace wall in the furnace (in the clarification tank), and generates the image (step S11).
- the operations after step S11 are the same as those already described.
- the predetermined region 43 includes a plurality of pixels has been described as an example.
- the predetermined area 43 may be an area composed of one pixel.
- the pre-correction luminance statistic deriving unit 73 may set the luminance value of the one pixel to g 0ave in step S13.
- the pre-correction luminance statistic deriving unit 73 calculates the moving average of g 0ave is illustrated, but the correction parameter value updating unit 74 does not use the moving average of g 0ave ,
- the offset value B may be calculated from 0 ave .
- each modification described in the first embodiment may be applied to the second embodiment.
- the images (corrected images) obtained in the first and second embodiments are used for observing the state of the molten glass in the furnace, for example.
- the correction parameter value update device 2 or other information processing device May output a warning that there is a possibility of bumping of the molten glass.
- bumping is a phenomenon in which the bubbles that have emerged on the surface of the molten glass by clarification are layered, and the thickness of the foam layer increases as the amount of the bubbles rapidly increases.
- the inside of a clarification tank is imaged with the imaging system in a furnace of this invention and the molten glass in a clarification tank is observed is illustrated, this invention is applied.
- the furnace is not limited to a clarification tank.
- the inside of the melting tank provided in the previous stage of the clarification tank and melting the glass raw material may be imaged by the in-furnace imaging system of the present invention, and the molten glass in the melting tank may be observed.
- the raw material powder or the like may flow in the space above the molten glass in the melting tank or clarification tank, the internal space may become cloudy, and the contrast of the image may decrease.
- a contrast processing step for calculating an amount representing the contrast between light and dark in a predetermined area and selecting an image to be used for quantitative evaluation.
- this contrast processing step an image that satisfies a predetermined condition with respect to an amount representing the contrast of light and dark in a predetermined area is selected, and the processing after step S2 in the first embodiment or the second is performed using the selected image. You may perform the process after step S12 in this embodiment.
- the amount representing the contrast of light and dark in the predetermined region in the image is more constant than the amount representing the contrast in the predetermined region in the previous image.
- an image is not selected from the time of occurrence of an event that decreases by more than a certain value until the lapse of a certain time.
- a quantity representing contrast for example, a standard deviation of luminance values in a predetermined area can be used.
- FIG. 12 is a schematic diagram illustrating an example of a glass article production line used in the method for producing a glass article of the present embodiment.
- the camera 1 in the first embodiment is illustrated, but the illustration of the correction parameter value update device 2 (see FIG. 2) is omitted.
- a dissolution tank 36 and a clarification tank 30 are provided in the glass article production line.
- the type of the clarification tank 30 is not limited, and the clarification tank 30 may be, for example, the above-described reduced pressure type clarification tank or the above-described high-temperature type clarification tank.
- the melting tank 36 melts a glass raw material (not shown) and changes it to a molten glass 31.
- the clarification tank 30 removes bubbles generated in the molten glass 31.
- the molten glass from which the bubbles have been removed moves to a molding process and a slow cooling process.
- FIG. 13 is a flowchart showing an example of a method for manufacturing a glass article according to this embodiment.
- a glass raw material is charged into the melting tank 36.
- the dissolution tank 36 is provided with heating means (not shown) such as a burner, and maintains the inside of the dissolution tank 36 at a high temperature.
- the molten glass 31 is manufactured by heating the raw material of glass (step S31, glass melting process).
- the molten glass 31 manufactured in step S31 is caused to flow into the clarification tank 30. Bubbles are present in the molten glass 31, and a bubble layer 32 (see FIG. 1) is generated on the surface of the molten glass 31. Inside the clarification tank 30, bubbles generated in the molten glass 31 are removed (step S32, clarification step).
- step S32 the camera 1 of the in-furnace imaging system images the inside of the furnace (in the clarification tank 30), and the in-furnace imaging system performs processing similar to that in the first embodiment (step S1) for the resulting image.
- step S8 see FIG.
- an image obtained by correcting the image generated by the image generation unit 11 (see FIG. 2) is obtained.
- the molten glass 31 in the clarification tank 30 is observed.
- the corrected image can realize a good contrast.
- a countermeasure corresponding to the event is taken. For example, when it is confirmed from the image that the surface of the foam layer is high, the correction parameter value update device 2 (or other information processing device) outputs a warning that there is a possibility of bumping do it.
- molten glass from which bubbles have been removed is molded (step S33, molding process).
- molten glass may be formed by a float process. Specifically, the molten glass 31 from which bubbles have been removed is floated on molten tin (not shown) and is advanced in the conveying direction to form a continuous plate-like glass ribbon. At this time, in order to form a glass ribbon having a predetermined plate thickness, a rotating roll is pressed against both side portions of the glass ribbon, and the glass ribbon is stretched outward in the width direction (direction perpendicular to the conveying direction).
- step S34 slow cooling step
- the glass ribbon formed in step S33 is gradually cooled (step S34, slow cooling step).
- the glass ribbon is drawn out from the molten tin, and the glass ribbon is gradually cooled inside a slow cooling furnace (not shown). Even after being transported outside the slow cooling furnace, the glass ribbon is gradually cooled to near room temperature.
- step S35 processing step.
- processing step S35 include cutting and polishing.
- the present invention is not limited to cutting and polishing, and other processing may be performed.
- the molten glass 31 in the furnace in the above example, the clarification tank 30
- the molten glass 31 in the furnace can be observed with a good contrast image. Therefore, an event (for example, an increase in the height of the bubble layer) occurring in the molten glass 31 can be accurately determined, and the event can be quickly dealt with.
- step S31 the inside of the melting tank 36 may be imaged by the in-furnace imaging system, and the molten glass 31 in the melting tank 36 may be observed.
- the in-furnace imaging system may perform processing similar to that in the first embodiment (steps S1 to S8, see FIG. 5).
- the in-furnace imaging system (see FIG. 10) of the second embodiment may be used as an in-furnace imaging system that images inside the clarification tank 30, the dissolution tank 36, and the like and corrects an image obtained by the imaging. Good.
- the in-furnace imaging system may perform the same processing as in the second embodiment (steps S11 to S17, see FIG. 11).
- the present invention can be suitably applied to observation of molten glass in a furnace.
- the entire contents of the specification, claims, drawings, and abstract of Japanese Patent Application No. 2011-286189 filed on Dec. 27, 2011 are incorporated herein as the disclosure of the present invention. .
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Materials Engineering (AREA)
- Organic Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Waste-Gas Treatment And Other Accessory Devices For Furnaces (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
Description
図2は、本発明の第1の実施形態の炉内撮像システムの構成例を示すブロック図である。本発明の第1の実施形態の炉内撮像システムは、カメラ1と、補正パラメータ値更新装置2とを備える。そして、カメラ1は、画像生成部11と、画像補正部12と、第1の補正パラメータ値記憶部13とを備える。補正パラメータ値更新装置2は、補正前輝度統計量導出部21と、補正パラメータ値更新部22と、第2の補正パラメータ値記憶部23と、を備える。以下、第1の補正パラメータ値記憶部13を単に補正パラメータ値記憶部13と記し、第2の補正パラメータ値記憶部23を単に補正パラメータ値記憶部23と記す。
前述の第1の実施形態では、カメラ1(図2参照)が炉内を撮像して画像を生成した後、その画像に対する補正を行い、補正後の画像を補正パラメータ値更新装置2に入力する。そのため、第1の実施形態では、補正パラメータ値更新装置2の補正前輝度統計量導出部21が補正後の画像における所定領域43(図4参照)の輝度値から、補正前の画像における所定領域43の輝度値を逆算する。これに対して、第2の実施形態では、カメラは、炉内を撮像して得た画像を、補正せずに補正パラメータ値更新装置に入力する。
次に、本発明の第3の実施形態として、ガラス物品の製造方法について説明する。本発明のガラス物品の製造方法には、第1の実施形態または第2の実施形態で説明した炉内撮像方法が適用される。以下の説明では、第1の実施形態を適用したガラス物品の製造方法について説明する。図12は、本実施形態のガラス物品の製造方法で用いるガラス物品の製造ラインの一例を示す模式図である。なお、図12では、第1の実施形態におけるカメラ1を図示しているが、補正パラメータ値更新装置2(図2参照)の図示を省略している。ガラス物品の製造ラインには、溶解槽36と、清澄槽30とが設けられる。なお、清澄槽30の種類は限定されず、清澄槽30は、例えば、前述した減圧タイプの清澄槽であっても、あるいは、前述した高温タイプの清澄槽であってもよい。
なお、2011年12月27日に出願された日本特許出願2011-286189号の明細書、特許請求の範囲、図面および要約書の全内容をここに引用し、本発明の開示として取り入れるものである。
2,70 補正パラメータ値更新装置
11,61 画像生成部
12,71 画像補正部
13 第1の補正パラメータ値記憶部
21,73 補正前輝度統計量導出部
22,74 補正パラメータ値更新部
23 第2の補正パラメータ値記憶部
72 補正パラメータ値記憶部
Claims (17)
- 観察対象である炉内の溶融ガラスを撮像する炉内撮像方法であって、
前記溶融ガラスを炉内の構造物とともに撮像し、画像を生成する撮像ステップと、
前記撮像ステップで生成された画像を、所定のパラメータを用いて補正する画像補正ステップと、
補正前の画像における、画像内で構造物に該当する領域として予め定められた所定領域の輝度値のデータ群から算出される統計量を特定する輝度統計量特定ステップと、
前記輝度統計量特定ステップで特定された前記所定領域の輝度値の統計量に基づいて、前記所定のパラメータの値を算出するパラメータ値算出ステップと、
前記画像補正ステップで用いる前記所定のパラメータの値を、前記パラメータ値算出ステップで算出された値で更新するパラメータ値更新ステップと、
を含むことを特徴とする炉内撮像方法。 - 前記画像補正ステップで、補正前の画像における所定領域の輝度値の統計量と予め定められた値との差を表すパラメータであるオフセットを所定のパラメータとして用いて画像を補正し、
前記パラメータ値算出ステップで、補正前の画像における所定領域の輝度値の統計量に基づいて、前記オフセットの値を算出する、
請求項1に記載の炉内撮像方法。 - 撮像して得られる画像内で構造物に該当する領域の輝度値と構造物の温度との関係が既知である構造物を炉内に設け、画像内で前記構造物に該当する領域を予め所定領域として定める、
請求項1または2に記載の炉内撮像方法。 - 画像補正ステップで得られる補正後の画像における所定領域の画素に、前記画像補正ステップにおける補正処理の逆算を行うことによって補正前の画像における前記所定領域の画素の輝度値を算出する補正前輝度値算出ステップを含み、
輝度統計量特定ステップで、前記補正前輝度値算出ステップで算出された輝度値から、補正前の画像における所定領域の輝度値の統計量を特定する、
請求項1から3のうちのいずれか一項に記載の炉内撮像方法。 - 前記輝度統計量特定ステップで、画像補正ステップで得られる補正後の画像における所定領域の輝度値の統計量を特定し、当該輝度値の統計量に、画像補正ステップにおける補正処理の逆算を行うことによって、補正前の画像における所定領域の輝度値の統計量を特定する、
請求項1から3のうちのいずれか一項に記載の炉内撮像方法。 - 前記輝度統計量特定ステップで、撮像ステップで生成された画像における所定領域の輝度値の統計量を特定する、
請求項1から3のうちのいずれか一項に記載の炉内撮像方法。 - 撮像ステップで所定の周期で撮像し、画像補正ステップの前または後に行なうステップであって、画像内の所定領域の明暗のコントラストを表す量を算出し前記コントラストを表す量に関して予め定められた条件を満たす画像を選択するコントラスト処理ステップを含む、
請求項1から6のうちのいずれか一項に記載の炉内撮像方法。 - 前記輝度統計量特定ステップで、輝度値の統計量として、所定領域の輝度値の平均値を特定する、
請求項1から7のうちのいずれか一項に記載の炉内撮像方法。 - 観察対象である炉内の溶融ガラスを撮像する炉内撮像システムであって、
前記溶融ガラスを炉内の構造物とともに撮像し、画像を生成する撮像手段と、
撮像手段が生成した画像を、所定のパラメータを用いて補正する画像補正手段と、
補正前の画像における、画像内で構造物に該当する領域として予め定められた所定領域の輝度値のデータ群から算出される統計量を特定する輝度統計量特定手段と、
前記輝度統計量特定手段が特定した前記所定領域の輝度値の統計量に基づいて、前記所定のパラメータの値を算出するパラメータ値算出手段と、
前記画像補正手段が用いる前記所定のパラメータの値を、前記パラメータ値算出手段が算出した値で更新するパラメータ値更新手段と、
を備えることを特徴とする炉内撮像システム。 - 前記画像補正手段は、補正前の画像における所定領域の輝度値の統計量と予め定められた値との差を表すパラメータであるオフセットを所定のパラメータとして用いて画像を補正し、
前記パラメータ値算出手段は、補正前の画像における所定領域の輝度値の統計量に基づいて、前記オフセットの値を算出する、
請求項9に記載の炉内撮像システム。 - 画像補正手段による補正後の画像における所定領域の画素に、前記画像補正手段が行う補正処理の逆算を行うことによって補正前の画像における前記所定領域の画素の輝度値を算出する補正前輝度値算出手段を備え、
前記輝度統計量特定手段は、前記補正前輝度値算出手段が算出した輝度値から、補正前の画像における所定領域の輝度値の統計量を特定する、
請求項9または10に記載の炉内撮像システム。 - 前記輝度統計量特定手段は、画像補正手段が行う補正処理後の画像における所定領域の輝度値の統計量を特定し、当該輝度値の統計量に、前記補正処理の逆算を行うことによって、補正前の画像における所定領域の輝度値の統計量を特定する、
請求項9または10に記載の炉内撮像システム。 - 前記輝度統計量特定手段は、撮像手段が生成した画像における所定領域の輝度値の統計量を特定する、
請求項9または10に記載の炉内撮像システム。 - 撮像手段が所定の周期で撮像した画像内の所定領域の明暗のコントラストを表す量を算出し、前記コントラストを表す量に関して予め定められた条件を満たす画像を選択するコントラスト処理手段を備える、
請求項9から13のうちのいずれか一項に記載の炉内撮像システム。 - 前記輝度統計量特定手段は、輝度値の統計量として、所定領域の輝度値の平均値を特定する、
請求項9から14のうちのいずれか一項に記載の炉内撮像システム。 - 溶解槽内で溶融ガラスを製造するガラス溶融ステップと、
清澄槽内で前記溶融ガラスの泡を除去する清澄ステップと、
前記清澄ステップにて泡が除去された溶融ガラスを成形する成形ステップと、
成形された溶融ガラスを徐冷する徐冷ステップと、を含むとともに、
前記清澄槽内の溶融ガラスを観察対象として、当該溶融ガラスを前記清澄槽内の構造物とともに撮像し、画像を生成する撮像ステップと、
前記撮像ステップで生成された画像を、所定のパラメータを用いて補正する画像補正ステップと、
補正前の画像における、画像内で構造物に該当する領域として予め定められた所定領域の輝度値のデータ群から算出される統計量を特定する輝度統計量特定ステップと、
前記輝度統計量特定ステップで特定された前記所定領域の輝度値の統計量に基づいて、前記所定のパラメータの値を算出するパラメータ値算出ステップと、
前記画像補正ステップで用いる前記所定のパラメータの値を、前記パラメータ値算出ステップで算出された値で更新するパラメータ値更新ステップと、
を含むことを特徴とするガラス物品の製造方法。 - 溶解槽内で溶融ガラスを製造するガラス溶融ステップと、
清澄槽内で前記溶融ガラスの泡を除去する清澄ステップと、
前記清澄ステップにて泡が除去された溶融ガラスを成形する成形ステップと、
成形された溶融ガラスを徐冷する徐冷ステップと、を含むとともに、
前記溶解槽内の溶融ガラスを観察対象として、当該溶融ガラスを前記溶解槽内の構造物とともに撮像し、画像を生成する撮像ステップと、
前記撮像ステップで生成された画像を、所定のパラメータを用いて補正する画像補正ステップと、
補正前の画像における、画像内で構造物に該当する領域として予め定められた所定領域の輝度値のデータ群から算出される統計量を特定する輝度統計量特定ステップと、
前記輝度統計量特定ステップで特定された前記所定領域の輝度値の統計量に基づいて、前記所定のパラメータの値を算出するパラメータ値算出ステップと、
前記画像補正ステップで用いる前記所定のパラメータの値を、前記パラメータ値算出ステップで算出された値で更新するパラメータ値更新ステップと、
を含むことを特徴とするガラス物品の製造方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011-286189 | 2011-12-27 | ||
JP2011286189 | 2011-12-27 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013100069A1 true WO2013100069A1 (ja) | 2013-07-04 |
Family
ID=48697548
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2012/083917 WO2013100069A1 (ja) | 2011-12-27 | 2012-12-27 | 炉内撮像方法、炉内撮像システムおよびガラス物品の製造方法 |
Country Status (2)
Country | Link |
---|---|
JP (1) | JPWO2013100069A1 (ja) |
WO (1) | WO2013100069A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2019119668A (ja) * | 2017-12-27 | 2019-07-22 | AvanStrate株式会社 | ガラス基板の製造方法、及びガラス基板製造装置 |
JP2020042468A (ja) * | 2018-09-10 | 2020-03-19 | 三菱重工業株式会社 | 画像特徴抽出方法、および、画像特徴抽出装置 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS61292528A (ja) * | 1985-06-20 | 1986-12-23 | Kawasaki Steel Corp | 炉内鋼材測温の補正方法 |
JPH06123656A (ja) * | 1992-10-12 | 1994-05-06 | Tokai Carbon Co Ltd | トンネル炉の非接触測温方法 |
JP2000295502A (ja) * | 1999-04-06 | 2000-10-20 | Asahi Glass Co Ltd | 炉内観察装置 |
-
2012
- 2012-12-27 WO PCT/JP2012/083917 patent/WO2013100069A1/ja active Application Filing
- 2012-12-27 JP JP2013551801A patent/JPWO2013100069A1/ja active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS61292528A (ja) * | 1985-06-20 | 1986-12-23 | Kawasaki Steel Corp | 炉内鋼材測温の補正方法 |
JPH06123656A (ja) * | 1992-10-12 | 1994-05-06 | Tokai Carbon Co Ltd | トンネル炉の非接触測温方法 |
JP2000295502A (ja) * | 1999-04-06 | 2000-10-20 | Asahi Glass Co Ltd | 炉内観察装置 |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2019119668A (ja) * | 2017-12-27 | 2019-07-22 | AvanStrate株式会社 | ガラス基板の製造方法、及びガラス基板製造装置 |
JP2020042468A (ja) * | 2018-09-10 | 2020-03-19 | 三菱重工業株式会社 | 画像特徴抽出方法、および、画像特徴抽出装置 |
JP7154537B2 (ja) | 2018-09-10 | 2022-10-18 | 三菱重工業株式会社 | 画像特徴抽出方法、および、画像特徴抽出装置 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2013100069A1 (ja) | 2015-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105555444B (zh) | 通过图像分析监控激光束的能量密度的方法和相应装置 | |
KR102118613B1 (ko) | Mura 현상 보상방법 | |
CN106531049B (zh) | 一种显示面板的亮度调节方法及系统 | |
CN105590605A (zh) | 曲面液晶面板的Mura现象补偿方法 | |
CN107749284B (zh) | 一种曲面面板的补偿数据获取方法及液晶显示器 | |
CN106782430A (zh) | 一种显示面板亮度调节方法及系统 | |
WO2013133033A1 (ja) | 輝度測定装置 | |
JP5928451B2 (ja) | ガラス溶融炉内監視方法、ガラス溶融炉操作方法、ガラス溶融炉内監視システム | |
CN102448661B (zh) | 在升高温度下的玻璃的激光刻痕 | |
CN112504163B (zh) | 热轧带钢横段面的轮廓曲线获取方法、装置及电子设备 | |
WO2013100069A1 (ja) | 炉内撮像方法、炉内撮像システムおよびガラス物品の製造方法 | |
TW201627232A (zh) | 控制玻璃帶中厚度楔形物的方法 | |
JPWO2009063756A1 (ja) | ガラス板の製造方法およびガラス物品の残留応力測定方法 | |
CN106148674A (zh) | 连退机组以热瓢曲与跑偏控制为目标的张力调节方法 | |
US20130307938A1 (en) | Stereo vision apparatus and control method thereof | |
JP2020063898A (ja) | 溶滓量測定装置および溶滓量測定方法 | |
WO2012081398A1 (ja) | ガラス板、ガラス板の検査方法、およびガラス板の製造方法 | |
JP2013252531A (ja) | 加熱炉の操業支援システム | |
JP5327533B2 (ja) | ガラスリボンのエッジ位置管理装置及びその方法 | |
KR102098770B1 (ko) | 전기로에서 탕면의 높이를 측정하기 위한 영상 처리 장치 및 방법 | |
CN104028561B (zh) | 保证钢板终冷温度精度的方法 | |
JP6105907B2 (ja) | 表示装置 | |
WO2016125096A1 (fr) | Dispositif et procédé de détermination de la perte au feu d'au moins une partie d'un produit sidérurgique | |
JP2013087039A (ja) | 単結晶インゴット直径制御方法 | |
Liu et al. | The MIVD method of optimal seeding state detection using image processing technology for sapphire crystal growth via the Kyropoulos method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12862275 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2013551801 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 12862275 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 12862275 Country of ref document: EP Kind code of ref document: A1 |