JP2017072433A - Measurement apparatus, measurement method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a measurement apparatus, a measurement method and a program which measure a grain size and a temperature of agglomerate discharged from a reduction furnace at the same time.SOLUTION: There is provided a measurement apparatus that includes an imaging apparatus 100 which generates a picked-up image formed by imaging agglomerate discharged from a reduction furnace, and an arithmetic processing apparatus 200 which calculates a grain size and a temperature of the agglomerate based on the generated picked-up image, where the arithmetic processing apparatus 200 has a filter processing image generation section which generates a filter processing image by acting each of a plurality of normalization LoG filters having different standard deviations to the picked-up image, a threshold determination section which determines a binarization threshold that binarizes the filter processing image, a binarization image generation section which binarizes the filter processing image utilizing the determined binarized threshold, a composite image generation section which combines the generated binarized images, a grain size calculation section which calculates a grain size of the agglomerate utilizing the generated composite image, and a temperature calculation section which calculates a temperature of the agglomerate utilizing the generated composite image.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a measuring apparatus, a measuring method, and a program.

  As one of the processes for producing reduced iron, powdered iron ore and powdered coal or coke are mixed into agglomerates such as pellets and briquettes. There is a method of obtaining solid metallic iron by reducing iron oxide in iron ore by charging the chemical compound into a reduction furnace such as a rotary hearth furnace and heating it to a high temperature. Generally, a burner is used to heat a reduction furnace such as a rotary hearth furnace. The agglomerated material, which is a raw material of reduced iron, is transferred from the outside by radiant heat from the furnace wall of the burner and the reduction furnace. Heated. Thereafter, the agglomerated material is discharged out of the furnace and sent to the melting step.

  It has been confirmed that there is a correlation between the agglomerate temperature and the metallization rate, and it is important to control the agglomerate temperature appropriately. There is a possibility that operation and quality can be controlled by measuring the temperature of the agglomerated material. Therefore, Patent Document 1 below discloses that when reducing iron is produced using a rotary hearth furnace, the temperature of the hearth surface is measured by a radiation thermometer installed above the floor surface. .

  In addition, if the agglomerated material is crushed and becomes a particle with a diameter of several millimeters or less, it is removed by a dust collector or the like in the next process, resulting in a decrease in yield, so a technique for accurately measuring the particle size distribution of the agglomerated material is required. ing.

  As a technique for measuring the particle size distribution of the agglomerate as described above, for example, in Patent Document 2 below, a sample is photographed with an optical system means, and a Laplacing Gaussian function is applied to the obtained captured image. Wavelet transform to create a wavelet image, apply a threshold value set in advance to the obtained wavelet image, perform binarization processing, using the obtained binarized image, A technique for calculating granular material information including at least the size and shape of the granular material is described.

JP 2001-181720 A JP 2011-106923 A

  However, when the radiation thermometer is installed in, for example, a measurement hole installed outside the furnace using the technique disclosed in Patent Document 1, only the average temperature of the agglomerated material can be measured. The temperature distribution cannot be known. Therefore, even if such a technique is used, the temperature control of the agglomerated material is insufficient. Moreover, since a radiation thermometer cannot take an image, the particle size distribution of the agglomerated material cannot be measured.

  In the technique disclosed in Patent Document 2, a Laplacian Gaussian filter is used for particle detection. The function form of the Laplacian Gaussian filter is a form represented by the following Expression 1, and In the examples in the literature, σ = 2 is applied as the standard deviation σ included in Equation 1.

  In the function form like the above formula 1, the response of the Laplacian Gaussian filter decreases when the value of the standard deviation σ is increased. Therefore, when a large value (for example, σ = 5) is set, the response decreases and particle detection Becomes difficult. Here, when an agglomerated material having a large particle size distribution, a high temperature close to 1000 ° C., and a temperature distribution is used as a measurement target, luminance variation increases because self-luminescence is measured. Accordingly, the particle size distribution of the agglomerated material as described above cannot be measured only by applying a Laplacian Gaussian filter defined by a single standard deviation σ.

  Further, as is clear from the above Patent Document 1 and Patent Document 2, in a reduction furnace such as a rotary hearth furnace, a technique for simultaneously measuring the particle size and temperature distribution of the agglomerated material has not been proposed. There is a need for a technique that can simultaneously measure the particle size and temperature distribution of agglomerated materials in order to manage the production process of reduced iron used and the quality of the produced reduced iron.

  Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to provide a measuring device capable of simultaneously measuring the particle size and temperature of the agglomerated material discharged from the reduction furnace. It is to provide a measuring method and a program.

  In order to solve the above-described problem, according to an aspect of the present invention, there is provided a measuring device for measuring the particle size and temperature of an agglomerate discharged from a reduction furnace, and imaging an image of the discharged agglomerate. An imaging device that generates an image; and an arithmetic processing device that calculates a particle size and a temperature of the agglomerated material based on the generated captured image, the arithmetic processing device being a standard for the captured image A plurality of normalized Laplacian Gaussian filters having different values of deviation are allowed to act to generate a plurality of filtered images, and at least a part of the plurality of filtered images is used. A threshold value determining unit that determines a binarization threshold value when binarizing the filter processing image, and binarizing each of the plurality of filter processing images using the determined binarization threshold value A binarized image generating unit that generates a plurality of binarized images, a composite image generating unit that generates a composite image by synthesizing the plurality of generated binarized images, and the generated composite image A measurement apparatus is provided that includes a particle size calculation unit that calculates the particle size of the agglomerated material, and a temperature calculation unit that calculates the temperature of the agglomerated material using the generated composite image. The

  The filtered image generation unit generates a first filtered image group by causing each of the first normalized Laplacian Gaussian filter groups to be used to detect the agglomerates having a diameter equal to or smaller than the first diameter. And a second normalized Laplacian Gaussian filter group used to detect the agglomerate having a diameter equal to or greater than the second diameter is generated to generate a second filtered image group, and the threshold value determination The unit multiplies the binarization threshold for detecting an agglomerate having a diameter equal to or smaller than the first diameter by multiplying an average luminance value of each of the first filtered image groups by a predetermined fixed value. A first threshold value, and the binarization threshold value for detecting an agglomerate having a diameter equal to or larger than the second diameter is set as a flat value for each predetermined first filtered image group. A linear function representing the relationship between the average luminance values of the luminance value and the second filtered image group, it is preferable to calculate by using the average luminance value of each of the first filtered image group.

The measurement apparatus further includes a linear function calculation unit that calculates a linear function representing a correspondence relationship between the average luminance value of each of the first filtered image group and the average luminance value of the second filtered image group, Each of the first normalized Laplacian Gaussian filter group and the second normalized Laplacian Gaussian filter group includes N normalized Laplacian Gaussian filters, and the linear function calculation unit includes the first filter processing. each image group in average luminance value and X _n, the combination of an average luminance value of each of the second filter processing image group when the Y _{n (n} = 1~N), were generated (Xn, Yn) plotted on the XY plane, child calculate a linear function obtained by linear approximation set of lower limit value of Y _n at each X position It is preferred.

  The particle size calculation unit uses the generated composite image, and at least any of the number, area, circumference, roundness, equivalent diameter, major axis length, minor axis length of the agglomerated material. It is good also as particle size information regarding the particle size of the said agglomerated material.

  The temperature calculating unit calculates a temperature of the agglomerated material using a luminance value of the generated composite image and a temperature calibration formula indicating a relationship between the luminance value and the temperature, and the agglomerated material It is good also as temperature information regarding the temperature of this.

  The particle size calculation unit may calculate a time transition of the particle size of the agglomerated product, and the temperature calculation unit may calculate a time transition of the temperature of the agglomerated product.

  The first diameter may be 3 mm, and the second diameter may be 8 mm.

  The arithmetic processing apparatus further includes a pre-processing unit that performs image pre-processing for reducing the captured image to a predetermined image size, and the filter-processed image generation unit performs filter processing on the reduced captured image. You may implement.

  In order to solve the above problem, according to another aspect of the present invention, there is provided a measuring method for measuring the particle size and temperature of the agglomerate discharged from the reduction furnace, which is discharged using an imaging device. An imaging step of imaging the agglomerated material and generating a captured image, and a plurality of normalized Laplacian Gaussian filters having different standard deviation values on the generated captured image, respectively. A filtered image generation step for generating a processed image; a threshold value determining step for determining a binarization threshold value when binarizing the filtered image using at least a part of the plurality of filtered images; A binarized image generating step of binarizing each of the plurality of filtered images using the determined binarization threshold and generating a plurality of binarized images; A composite image generation step of generating a composite image by combining a plurality of the binarized images, and a particle size calculation step of calculating a particle size of the agglomerated product using the generated composite image And a temperature calculating step of calculating a temperature of the agglomerated material using the synthesized image.

  In order to solve the above-described problem, according to still another aspect of the present invention, a computer capable of communicating with an imaging device that captures an agglomerate discharged from a reduction furnace and generates a captured image is reduced. A program for causing a computer to function as a measuring device for measuring the particle size and temperature of agglomerates discharged from a furnace, wherein the computer has a plurality of normalized Laplacian Gaussians having different standard deviation values with respect to the captured image. A binarization when binarizing the filtered image using a filtered image generating function for generating a plurality of filtered images by using each filter and at least a part of the filtered images A threshold determination function for determining a binarization threshold, and binarizing each of the plurality of filtered images using the determined binarization threshold. A binarized image generation function to be generated, a composite image generation function for generating a composite image by combining a plurality of the generated binary images, and the agglomeration using the generated composite image There is provided a program for realizing a particle size calculation function for calculating the particle size of a compound and a temperature calculation function for calculating the temperature of the agglomerate using the generated composite image.

  As described above, according to the present invention, it is possible to simultaneously measure the particle size and temperature of the agglomerate discharged from the reduction furnace.

It is explanatory drawing which showed typically the whole structure of the measuring apparatus which concerns on embodiment of this invention. It is explanatory drawing for demonstrating the imaging device with which the measuring apparatus which concerns on the same embodiment is provided. It is explanatory drawing which showed an example of the captured image produced | generated with the imaging device which concerns on the embodiment. It is explanatory drawing for demonstrating the relationship between a captured image and a binarization threshold value. It is explanatory drawing for demonstrating an example of the binarization process of a captured image. It is the block diagram which showed an example of the structure of the image process part in the arithmetic processing apparatus with which the measuring apparatus which concerns on the same embodiment is provided. It is explanatory drawing for demonstrating the linear function used with the image process part which concerns on the same embodiment. It is explanatory drawing for demonstrating the determination process of the binarization threshold value implemented by the image process part which concerns on the embodiment. It is explanatory drawing which showed an example of the binarization process implemented with the image process part which concerns on the same embodiment. It is explanatory drawing which showed an example of the binarization process implemented with the image process part which concerns on the same embodiment. It is the flowchart which showed an example of the flow of the measuring method which concerns on the embodiment. It is the block diagram which showed an example of the hardware constitutions of the arithmetic processing unit which concerns on the same embodiment. It is explanatory drawing for demonstrating an Example. It is explanatory drawing for demonstrating an Example. It is explanatory drawing for demonstrating an Example. It is explanatory drawing for demonstrating an Example. It is explanatory drawing for demonstrating an Example.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

(About the overall configuration of the measuring device)
First, an overall configuration of the measuring apparatus 10 according to the first embodiment of the present invention will be described with reference to FIG. FIG. 1 is an explanatory diagram schematically showing the overall configuration of a measuring apparatus 10 according to the present embodiment.

  The measuring device 10 according to the present embodiment is a measuring device that measures the particle size and temperature of the agglomerate discharged from the reduction furnace.

  Here, the reduction furnace in which the measuring apparatus 10 is installed is formed by mixing powdered iron ore (iron oxide) and carbonaceous material (that is, reducing agent) such as powdered coal or coke. An agglomerate such as pellets or briquettes is charged, and the agglomerate is heated to a high temperature to reduce iron oxide in iron ore to produce solid metallic iron (ie reduced iron) It is. One such reduction furnace is a reduction furnace called a rotary hearth furnace. In the following, a rotary hearth furnace will be taken up as an example of a reduction furnace and described.

  As schematically shown in FIG. 1, the measurement apparatus 10 according to the present embodiment mainly includes an imaging device 100 and an arithmetic processing device 200.

  The imaging device 100 is installed in the vicinity of the out-of-furnace discharge port of the rotary hearth furnace, images the agglomerate discharged from the out-of-furnace discharge port, and the agglomerated material discharged from the out-of-furnace discharge port. It is an apparatus that generates a captured image.

  The imaging apparatus 100 includes various optical elements such as a lens and an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). Here, the imaging apparatus 100 according to the present embodiment may be capable of generating a still image or may be capable of generating a moving image. Further, the imaging apparatus 100 according to the present embodiment may be capable of capturing a monochrome image or may be capable of capturing a color image. Note that when an imaging device capable of capturing a color image is used, a one-channel image may be generated. That is, as the image generation means, only one of R, G, and B components among the RGB components may be used, or conversion from the RGB color space to the YCbCr color space is performed, and only the Y component is used. You may do it.

  The imaging device 100 is controlled by an arithmetic processing device 200 described later, and a trigger signal for imaging is output from the arithmetic processing device 200 at every predetermined frame rate. The imaging device 100 captures the thermal radiation of the agglomerates at the out-of-core discharge port of the rotary hearth furnace according to the trigger signal output from the arithmetic processing device 200, and outputs the generated image to the arithmetic processing device 200. .

  FIG. 2 is an explanatory diagram for explaining an installation state of the imaging apparatus 100 according to the present embodiment, and FIG. 3 is an explanatory diagram illustrating an example of an image according to the present embodiment. As shown in FIG. 2, the imaging apparatus 100 according to the present embodiment is installed in the vicinity of an observation window provided for observing the state of the out-of-furnace outlet. Inside this out-of-furnace discharge port, agglomerates discharged from the rotary hearth furnace are falling at any time. The imaging device 100 is installed, for example, at a position about 2 m away from the observation window, and the agglomerates falling through the observation window through the outside of the furnace outlet (the temperature of the agglomerates at the outside furnace outlet is , About 800 ° C. to 1000 ° C.), and a captured image (thermal radiation image) obtained by imaging the thermal radiation of the agglomerate as shown in FIG. 3 is generated.

  At this time, the imaging apparatus 100 is subjected to temperature calibration processing using a black body furnace in advance, and the brightness value of the generated captured image and the temperature of the thermal radiator are appropriately associated with each other. .

  As shown in FIG. 3, the thermal radiation image obtained in this way is an agglomeration that falls inside the out-of-furnace outlet inside the field of view corresponding to the observation window (substantially circular field of view in FIG. 3). The monster is reflected. In such a thermal radiation image, an agglomerate having a higher temperature appears white in the thermal radiation image, and an agglomerate having a lower temperature appears black in the thermal radiation image.

  The arithmetic processing device 200 controls the imaging processing by the imaging device 100, uses the captured image generated by the imaging device 100, and performs image processing on the captured image to thereby obtain the particle size and temperature of the agglomerated material. Is a device for calculating.

  The detailed configuration of the arithmetic processing device 200 will be described in detail later.

(Image processing for captured images)
Hereinafter, prior to the detailed description of the arithmetic processing apparatus 200 according to the present embodiment, the content of the examination performed by the present inventor regarding the image processing on the captured image generated by the imaging apparatus 100 will be described with reference to FIGS. 4 and 5. While briefly explaining.
FIG. 4 is an explanatory diagram for explaining the relationship between the captured image and the binarization threshold, and FIG. 5 is an explanatory diagram for explaining an example of the binarization processing of the captured image.

  In order to measure the particle size and temperature of the agglomerate using the thermal radiation image as shown in FIG. 3, the portion corresponding to the agglomerate is specified from the thermal radiation image as shown in FIG. Is required. However, it is considered difficult to specify only the part corresponding to the agglomerate from the thermal radiation image for the following reasons.

  FIG. 4 shows a luminance histogram relating to the luminance value of each pixel constituting the thermal radiation image of the thermal radiation image shown in FIG. As is clear from FIG. 4, since the luminance distribution also exists in the background, it is difficult to specify a luminance threshold value that clearly distinguishes the agglomerate from the background. For example, the binarized image A shown in FIG. 4 is a binarized image that has been binarized by setting the luminance threshold to 120, and the binarized image B has been binarized by setting the luminance threshold to 210. The binarized image is a binarized image C. The binarized image C is a binarized image that has been binarized with a luminance threshold of 400. In the case of the binarized image A shown in FIG. 4, the agglomerated particles are not detected, and the binarized image has a large mass of agglomerated materials as a whole. In the case of the binarized image B shown in FIG. 4, the agglomerates are not separated. In the case of the binarized image C shown in FIG. 4, the number of detected agglomerates. There is little state. Therefore, it can be seen that it is difficult to extract only the agglomerated material from the thermal radiation image by a simple binarization process using a certain fixed threshold value.

  Therefore, the present inventor has further studied and has come up with the idea of applying a Laplacian Gaussian filter (hereinafter abbreviated as “LoG filter”) to a thermal radiation image. The LoG filter is a filter having a function form as shown in Equation 1 above. In such a LoG filter, it is possible to set a detectable particle diameter by changing the standard deviation σ. That is, when detecting an agglomerate having a small particle size, the standard deviation σ, which is a parameter, is set small, and when detecting an agglomerate having a large particle size, the standard deviation σ may be set large. . In Equation 1, x is the horizontal position coordinate in the captured image, and y is the vertical position coordinate in the captured image.

However, in the thermal radiation image as shown in FIG. 3, the agglomerate has a particle size of 10 pixels or less, or a particle size of 50 pixels or more. It is not possible to detect all agglomerates simply by setting σ. Therefore, the inventor prepares a plurality of LoG filters having different values of the standard deviation σ, and generates a plurality of filtered images by causing each of the plurality of LoG filters to act on the thermal radiation image. The inventors have conceived to solve the above-mentioned problems by creating a new image by combining and combining the obtained images. At this time, since the response of the LoG filter decreases when the value of the standard deviation σ increases, a normalized Laplacian Gaussian filter obtained by multiplying Equation 1 by σ ² (hereinafter abbreviated as “normalized LoG filter”). It was decided to use. The function form of the normalized LoG filter is as shown in the following (Formula 3).

  In such filter processing, the coordinates of the center are set to (0, 0), and the weight of a pixel separated by (i, j) pixels from the center is a value obtained by substituting (x, y) = (i, j) into Equation 3. A filter process is performed by creating a filter and multiplying the thermal radiation image by the filter.

  That is, in this filter processing, the thermal radiation image expressed in luminance is set to f (x, y), f (x, y) at the position of the coordinate (x, y) is multiplied by φ (0, 0), and the coordinate ( It is defined as the sum of parameters i and j related to a value obtained by multiplying f (x + i, y + j) at the position of x + i, y + i) by φ (i, j). Therefore, by calculating g (x, y) represented by the following Expression 5, a thermal radiation image with a normalized LoG filter applied can be obtained.

  When carrying out such processing, a normalized LoG filter of σ = 1/3, 2/3, 1, 2,..., 6 is prepared, and the calculated luminance value becomes negative. The luminance value was set to 0. In the example shown in FIG. 5, a composite image of an image (normalized LoG filter image) that has been subjected to a normalized LoG filter with σ = 3 to 6 is used as a medium to large particle size detection image, and σ = 1/3 to 1 The composite image was used as a small particle size detection image to perform image synthesis. At this time, even in the image for small particle size detection, the agglomerate having a large particle size has a large luminance value, and the outer portion of the agglomerate has a luminance value even after filtering, A composite image obtained by subtracting a composite image for medium to large particle size detection from a composite image for small particle size detection was defined as a composite image for small particle size detection.

  By generating a composite image by the above processing and binarizing it, a composite binary image as shown on the right side of FIG. 5 can be obtained. In the rotary hearth furnace focused on in this study, the agglomerates discharged outside the furnace had a size of about 16 mm in diameter at the maximum, so the number of particles having a diameter of 8 mm or more was set as a medium to large particle size. I counted. Moreover, since it was thought that the powder particle | grains whose diameter is 3 mm or less will become a yield by the dust collection in the next process, 3 mm or less diameter was counted as powder.

  When the image processing as described above is performed on the actually obtained captured image, the small particle size (3 mm or less) with high brightness is connected and handled, and the medium particle size or more (8 mm or more) is assumed. The overdetection which detects, and the undetected in which the agglomerate with a low brightness | luminance is not detected generate | occur | produced. Therefore, as a result of studying the cause of such overdetection and non-detection, the present inventor fixed the binarization threshold value to a certain value when binarizing the image obtained by the filter processing. As a result, the inventors have thought that overdetection and non-detection as described above may occur. Therefore, the present inventor has come up with an image processing method that does not cause overdetection or undetection as described in detail below by conducting further studies based on such knowledge.

(About the configuration of the arithmetic processing unit)
Returning to FIG. 1 again, the configuration of the arithmetic processing apparatus according to the present embodiment will be described.
As illustrated in FIG. 1, the arithmetic processing device 200 according to the present embodiment mainly includes an imaging control unit 201, an image processing unit 203, a display control unit 205, and a storage unit 207.

  The imaging control unit 201 is realized by a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a communication device, and the like. The imaging control unit 201 performs imaging control of the out-of-furnace outlet of the rotary hearth furnace by the imaging device 100 according to the present embodiment. More specifically, the imaging control unit 201 transmits a control signal for starting imaging to the imaging device 100 when imaging of the out-of-core discharge port of the rotary hearth furnace is started. In addition, the imaging control unit 201 transmits a trigger signal for performing imaging at every predetermined frame rate after transmitting a control signal for starting imaging.

The image processing unit 203 is realized by, for example, a CPU, a ROM, a RAM, a communication device, and the like. The image processing unit 203 performs image processing as described below on the imaging data of the captured image acquired from the imaging device 100 to calculate the particle size and temperature of the agglomerated material.
The image processing unit 203 will be described in detail later.

  The display control unit 205 is realized by, for example, a CPU, a ROM, a RAM, an output device, and the like. The display control unit 205 includes an output device such as a display provided in the arithmetic processing unit 200 or an arithmetic processing unit, which has information on the agglomerate and temperature of the agglomerates at the out-furnace outlet of the rotary hearth furnace transmitted from the image processing unit 203. Display control is performed when displaying on an output device or the like provided outside 200. Thereby, the user of the measuring apparatus 10 can grasp information on the particle size and temperature of the agglomerates at the out-of-core discharge port of the rotary hearth furnace on the spot.

  The storage unit 207 is realized by, for example, a RAM or a storage device included in the arithmetic processing device 200 according to the present embodiment. The storage unit 207 stores various parameters, intermediate progress of processing, and various databases and programs that need to be saved when the arithmetic processing apparatus 200 according to the present embodiment performs some processing, as appropriate. To be recorded. The storage unit 207 can be freely read / written by the imaging control unit 201, the image processing unit 203, the display control unit 205, and the like.

<Configuration of image processing unit>
Next, the configuration of the image processing unit 203 included in the arithmetic processing apparatus 200 according to the present embodiment will be described in detail with reference to FIGS.
FIG. 6 is a block diagram illustrating an example of the configuration of the image processing unit in the arithmetic processing device included in the measurement apparatus according to the embodiment. FIG. 7 is an explanatory diagram for describing a linear function used in the image processing unit according to the present embodiment, and FIG. 8 is a binarization threshold value determination process performed by the image processing unit according to the present embodiment. It is explanatory drawing for demonstrating. 9 and 10 are explanatory diagrams illustrating an example of the binarization process performed by the image processing unit according to the present embodiment.

  In the image processing unit 203 according to the present embodiment, the binarization threshold value when binarizing the image for medium-large particle size detection is not set to a fixed value based on the examination result as described above, but a small value. Vary according to the image for particle size detection. Thereby, in the image processing unit 203 according to the present embodiment, it is possible to detect the agglomerate contained in the captured image without causing overdetection or undetection, and the particle size and temperature of the agglomerate are determined. It becomes possible to measure more accurately.

  As illustrated in FIG. 6, the image processing unit 203 that performs such processing includes a preprocessing unit 211, a filter processing image generation unit 213, a linear function calculation unit 215, a threshold value determination unit 217, and a binarized image. A generation unit 219, a composite image generation unit 221, a labeling unit 223, a particle size calculation unit 225, a temperature calculation unit 227, and a result output unit 229 are included.

  The preprocessing unit 211 is realized by, for example, a CPU, a ROM, a RAM, and the like. The pre-processing unit 211 is a processing unit that performs various types of pre-processing on the captured image (thermal radiation image) output from the imaging device 100 and captured of the agglomerates at the out-of-furnace outlet. . As such preprocessing, for example, image reduction processing for reducing a captured image to a predetermined image size can be mentioned. The extent to which the captured image is reduced is not particularly limited as long as the size is such that the powdery agglomerates exist as at least one pixel in the reduced captured image. The pre-processing unit 211 can arbitrarily set the reduction ratio of the captured image. For example, the pre-processing unit 211 can perform image reduction processing that reduces the captured image to 1/3 both vertically and horizontally. By performing such image reduction processing, it is possible to further reduce the calculation time of image processing as described in detail below.

  The captured image that has been subjected to the preprocessing as described above is output to the filtered image generation unit 213 as necessary.

  The filter processing image generation unit 213 is realized by, for example, a CPU, a ROM, a RAM, and the like. The filter processing image generation unit 213 holds in advance a plurality of normalized LoG filter groups having different values of the standard deviation σ, and these normalized LoG filter groups for the captured image output from the preprocessing unit 211. To generate a plurality of filtered images.

  Here, the filtered image generation unit 213 according to the present embodiment uses, as the normalized LoG filter group, a first normalized LoG filter group (that is, a first normalized LoG filter group used for detecting an agglomerate having a diameter equal to or smaller than the first diameter). , A normalized LoG filter group for detecting small particle size agglomerates) and a second normalized LoG filter group used for detecting agglomerates having a diameter greater than or equal to the second diameter (ie, medium To a normalized LoG filter group for detecting an agglomerate having a large particle size). The specific values of the first diameter and the second diameter can be appropriately set by analyzing the particle size distribution of the agglomerate generated in the rotary hearth furnace of interest by a known measurement method in advance. Good.

  The first normalized LoG filter group is used to generate a filtered image for detecting agglomerates having a small particle size as described above. For example, when the first diameter is 3 mm, the first normalized LoG filter group includes, for example, four types of normalized LoG filters in which values of σ = 1/3, 2/3, 1 and 2 are set. Can be used.

  The second normalized LoG filter group is used to generate a filtered image for detecting an agglomerate having a medium to large particle size as described above. For example, when the second diameter is 8 mm, for example, four types of normalized LoG filters in which values of σ = 3, 4,..., 6 are used are used as the second normalized LoG filter group. Can do.

  The filter-processed image generation unit 213 causes the first normalized LoG filter group and the second normalized LoG filter group as described above to act on the captured image output from the pre-processing unit 211, so that the above formula 5 A plurality of filtered images are generated by the calculation as described above. Hereinafter, the filtered image group generated by applying the first normalized LoG filter group will be referred to as the first filtered image group, and generated by applying the second normalized LoG filter group. The filtered image group will be referred to as a second filtered image group.

  When the filter-processed image generation unit 213 generates a plurality of filter-processed images as described above, the obtained filter-processed images are converted into a linear function calculation unit 215, a threshold value determination unit 217, and a binarized image generation unit 219. Output to.

  The linear function calculation unit 215 is realized by a CPU, a ROM, a RAM, and the like, for example. The straight line function calculation unit 215 calculates a straight line function used for determining a binarization threshold value when the filter processing image is binarized in the threshold value determination unit 217 described later. This linear function is a linear function that represents the correspondence relationship between the average luminance value of each of the first filtered image group and the average luminance value of each of the second filtered image group generated by the filtered image generation unit 213.

  In order to explain the linear function calculated by the linear function calculating unit 215, first, referring to FIG. 7, first, the luminance value of the agglomerated material having a small particle size and the agglomerated material having a medium to large particle size will be described. The relationship with the luminance value will be described.

  When the inventor is examining the filtered image generated by applying the normalized LoG filter, the average luminance value of each of the first filtered image group is set to X, and the second filtered image group. The generated combinations of (X, Y) were plotted on the XY plane with each average luminance value being Y, and the distribution status of the combinations of (X, Y) was confirmed. Then, the combination of (X, Y) has a distribution as shown in FIG. 7, and it has been found that the boundary that defines the lower limit of the average luminance Y distribution having a medium particle size or more can be approximated by a straight line (Y = AX + B). The reason why the lower limit of the average luminance Y distribution over the medium grain size can be approximated by a straight line is not certain, but it is due to cooling within a few seconds when the agglomerates discharged from the rotary hearth furnace fall into the observation window This is considered to be the effect of temperature change.

  By using such a linear relationship (Y = AX + B), the average luminance X of the agglomerated material having a small particle diameter is calculated using the first filtered image group, and corresponds to the calculated average luminance X. It is possible to calculate the lower limit value of the average luminance Y of the agglomerates having a medium to large particle size. Since the luminance value of the agglomerate having a medium to large particle size has a value larger than the lower limit, by using such a method, the undetected and overdetected agglomerates can be suppressed. Is possible.

Such a linear function (Y = AX + B) can be obtained as follows.
First, a sample image consisting of a plurality of images in a rotary hearth furnace of interest is prepared, and a first filtered LoG filter group is made to act by the filter processing image generation unit 213 using the sample image. A processed image group and a second filtered image group in which the second normalized LoG filter group is applied are generated. Then, an average luminance value X of each filter processed image constituting the first filter processed image group and an average luminance value Y of each filter processed image constituting the second filter processed image group are respectively calculated, XY Plot on a plane. Thereby, a plot as shown in FIG. 7 can be obtained.

  Next, the linear function calculation unit 215 extracts the lower limit value of Y at each X position in the plot as shown in FIG. Such a lower limit sampling method is not particularly defined. However, as shown in FIG. 7, it is considered that data is dense from about X = 25 to about X = 60. The minimum value of Y can be extracted for all X coordinates by the following method.

That is, when the minimum value (X, Y _min ) is extracted from the plot group included in the range of p ≦ X <p + q in FIG. 7, the linear function calculation unit 215 has the data as shown in FIG. In consideration of crowding, in the range of 0 ≦ X <25, q = 1 is set, and Y _min in the range of p ≦ X <p + 1 is extracted. In other words, the linear function calculation unit 215, when extracting _{Y min} at X = 0, when extracting _{Y min} at 0 ≦ X <1, and extracts the _{Y min} at X = 1 is 1 ≦ X <Y _min in <2 is extracted. Further, the linear function calculation unit 215 sets q = 0.5 in the range of 25 ≦ X <60 in which data is dense, and extracts Ymin in the range of p ≦ X <p + 0.5. Similarly, the linear function calculation unit 215 sets q = 1 in the range of 60 ≦ X <75, and sets q = 5 in the range of 75 ≦ X <100 where the data distribution is sparse, Y _min is extracted. By performing such processing, the linear function calculation unit 215 can more accurately extract the lower limit value of Y in consideration of the degree of data density.

  In this way, after specifying a set of lower limit values of Y at each X position, the linear function calculation unit 215 converts the obtained set of lower limit values by a known linear approximation method such as a least square method, for example. Approximate straight line. Thereby, the straight line function calculation unit 215 can calculate a straight line function used in a threshold value determination unit 217 described later.

  When the linear function calculation unit 215 calculates the linear function as shown in FIG. 7 as described above, the linear function calculation unit 215 outputs information on the linear function to the threshold value determination unit 217 described later. The linear function calculation unit 215 may store the linear function calculated as described above in the storage unit 207 so that other processing units can refer to it as needed.

  The straight line function calculation processing as described above may be performed at least once as long as the imaging environment of the agglomerates by the imaging device 100 does not change, and every time a captured image is generated by the imaging device 100. It is not necessary to carry out.

  The threshold value determination unit 217 is realized by, for example, a CPU, a ROM, a RAM, and the like. The threshold value determination unit 217 is a processing unit that determines a binarization threshold value when binarizing the filter processing image using at least a part of the plurality of filter processing images.

  More specifically, the threshold value determination unit 217 uses the linear function calculated by the linear function calculation unit 215 to binarize the first filtered image group and the second filtered image. The binarization threshold value for binarizing the group is determined as follows.

That is, the threshold value determination unit 217 multiplies the average luminance value of the first filtered image by a predetermined fixed value by the binarization threshold value for detecting an agglomerate having a diameter equal to or smaller than the first diameter. The first threshold is assumed. More specifically, the threshold value determination unit 217, to the average luminance value X _r of the first filtered image, so that the luminance in consideration of brightness variations in the agglomerate can also be detected following agglomerate X _r Is multiplied by a certain value (for example, 0.5 or the like) included in the range of 0.4 to 0.6 to obtain the first threshold value.

The reason why the first threshold value is obtained by multiplying the obtained average value _Xr by a certain fixed value is that the agglomerate having a small particle size contained in the first filtered image has less temperature unevenness, This is because binarization is also considered easy.

Further, the threshold value determination unit 217 calculates a binarization threshold value for detecting an agglomerate having a diameter equal to or larger than the second diameter as a linear function (Y = AX + B) calculated by the linear function calculation unit 215. The calculated average value _Xr is used to calculate as shown in FIG. That is, the threshold determination unit 217, the linear function calculated by the linear function calculating section 215 substitutes the calculated average value X _r, the obtained value Y _r, when binarizing the second filtering-processed image Of the second threshold. As described above, in the image processing unit 203 according to the present embodiment, the second threshold value for binarizing the second filtered image group is not a fixed value, but according to the average luminance value of the first filtered image. It is a variable value that fluctuates. Thereby, it becomes possible to set the binarization threshold value for detecting an agglomerate of medium to large particle diameter, which is more important as temperature information, to a value at which no detection or overdetection occurs.

  The threshold value determination unit 217 determines the first threshold value for binarizing the first filtered image and the second threshold value for binarizing the second filtered image as described above. The obtained threshold values are output to the binarized image generation unit 219.

  The binarized image generation unit 219 is realized by a CPU, a ROM, a RAM, and the like, for example. The binarized image generation unit 219 binarizes each of the filtered images output from the filtered image generation unit 213 using the two types of binarized threshold values determined by the threshold value determination unit 217. Generate a digitized image.

  More specifically, the binarized image generation unit 219 uses the first threshold output from the threshold determination unit 217 to binarize each image included in the first filtered image, and the threshold determination unit Using the second threshold value output from 217, each image included in the second filtered image is binarized.

  When the binarized image generation unit 219 binarizes each filter processing image in this way to generate a binarized image, the binarized image generation unit 219 outputs the generated binarized image to the composite image generation unit 221.

  The composite image generation unit 221 is realized by, for example, a CPU, a ROM, a RAM, and the like. The composite image generation unit 221 combines a plurality of binarized images generated by the binarized image generation unit 219 to generate a composite binarized image.

  In addition, in the binarized image obtained from the 1st filter processing image, the case where the external shape of the agglomerate of medium-large particle diameter remains is also considered. In this case, the composite image generation unit 221 first separately synthesizes the binarized image obtained from the first filter processed image and the binarized image obtained from the second filter processed image. An image obtained by subtracting the synthesized image obtained from the second filtered image from the synthesized image obtained from the processed image (difference image) is used as a synthesized image of the first filtered image used for the final synthesized image. May be. By using such a difference image, it becomes possible to more accurately detect agglomerates having a small particle diameter.

  FIG. 9 shows a binarized image obtained by binarizing a captured image obtained by capturing an agglomerate having low luminance. FIG. 9 shows a binarized image based on a variation threshold as described above and a binarized image based on a general fixed threshold studied in the process of conceiving the present invention. Comparing the binarized image based on the fixed threshold and the binarized image based on the variation threshold, as can be seen from FIG. 9, there are many undetected agglomerates in the binarized image based on the fixed threshold. I understand that.

  Similarly, FIG. 10 shows a binarized image obtained by binarizing a captured image obtained by capturing an agglomerate with high luminance. Comparing the binarized image based on the fixed threshold and the binarized image based on the variation threshold, as is clear from FIG. 10, in the binarized image based on the fixed threshold, there is an excess in the upper left part and the lower right part of the image. It can be seen that detection has occurred.

  Thus, it can be seen that undetected and overdetection can be appropriately suppressed by using the binarized image based on the variation threshold as described above.

  When the composite image generation unit 221 generates a composite image (combined binary image) in this way, the generated image is output to the labeling unit 223.

  The labeling unit 223 is realized by a CPU, a ROM, a RAM, and the like, for example. The labeling unit 223 refers to the composite binarized image generated by the composite image generation unit 221 and performs a labeling process on a portion having a luminance value of 1, thereby generating an agglomerate included in the binarized image. To detect. In addition, the labeling process which the labeling part 223 implements is not specifically limited, It is possible to apply a well-known labeling process.

  When the labeling unit 223 performs a labeling process on the synthetic binarized image of interest, the labeling unit 223 includes information related to the labeling result of the agglomerated product and the composite binarized image, a particle size calculating unit 225 and a temperature calculation described later. Output to the unit 227.

  The particle size calculation unit 225 is realized by a CPU, a ROM, a RAM, and the like, for example. The particle size calculation unit 225 calculates the particle size of the agglomerated material included in the focused composite binarized image using information on the labeling result of the agglomerated material and the composite binarized image.

Examples of the characteristic amount related to the particle size of the agglomerated material calculated by the particle size calculating unit 225 include the number of agglomerated materials, the area S, the perimeter (length along the outer shape of the agglomerated material) L, and the roundness ( L ² / 4πS), equivalent diameter (0.5 × (S / π)), length of major axis (specifically, an equivalent ellipse of the agglomerate (the same area as the agglomerate, primary and The length of the major axis in the ellipse having the same second moment), the length of the minor axis (the length of the minor axis in the equivalent ellipse), and the like.

  When the particle size calculation unit 225 calculates at least one of the above-described feature amounts related to the particle size, the particle size calculation unit 225 outputs the obtained calculation result to the result output unit 229 as particle size information.

  In addition, the particle size calculation unit 225 can calculate the temporal transition of the feature amount related to the particle size as described above, and can output it to the result output unit 229.

  The temperature calculation unit 227 is realized by a CPU, a ROM, a RAM, and the like, for example. The temperature calculation unit 227 calculates the temperature of the agglomerated material included in the focused composite binarized image using the information related to the labeling result of the agglomerated material and the composite binarized image.

  Specifically, the temperature calculation unit 227 uses a luminance value (for example, an average luminance value) of each labeled agglomerated material to calculate a temperature calibration equation (for example, a plank) indicating a relationship between the luminance value and the temperature. The temperature of the agglomerated material is calculated based on the relational expression obtained from the radiation law of the above.

  When the temperature calculation unit 227 calculates the temperature of the agglomerated material as described above, the temperature calculation unit 227 outputs the obtained calculation result to the result output unit 229 as temperature information.

  In addition, the temperature calculation unit 227 can calculate the time transition of the temperature and output it to the result output unit 229.

  The result output unit 229 is realized by a CPU, a ROM, a RAM, a communication device, and the like, for example. The result output unit 229 outputs the particle size information calculated by the particle size calculation unit 225 and the temperature information calculated by the temperature calculation unit 227 to the display control unit 205, for example. The result output unit 229 may output the granularity information and temperature information calculated for an external device via various networks such as the Internet and a local area network. The result output unit 229 may output the calculated particle size information and temperature information as a printed matter using a printer or the like.

  In addition, the result output unit 229 may associate time information related to the date and time when the data is calculated with the data indicating the calculated granularity information and temperature information, and record the data as history information in the storage unit 207.

  Heretofore, an example of the function of the arithmetic processing apparatus 200 according to the present embodiment has been shown. Each component described above may be configured using a general-purpose member or circuit, or may be configured by hardware specialized for the function of each component. In addition, the CPU or the like may perform all functions of each component. Therefore, it is possible to appropriately change the configuration to be used according to the technical level at the time of carrying out the present embodiment.

  A computer program for realizing each function of the arithmetic processing apparatus according to the present embodiment as described above can be produced and installed in a personal computer or the like. In addition, a computer-readable recording medium storing such a computer program can be provided. The recording medium is, for example, a magnetic disk, an optical disk, a magneto-optical disk, a flash memory, or the like. Further, the above computer program may be distributed via a network, for example, without using a recording medium.

  By using the measuring apparatus 10 according to the present embodiment as described above, the agglomerate is accurately detected even when the brightness (that is, the temperature) of the agglomerate changes in the captured image. It is possible to calculate the particle size and temperature of the agglomerates with higher accuracy. In addition, it is possible to more accurately grasp changes over time in the particle size and temperature change of the agglomerate discharged outside the rotary hearth furnace, optimization of furnace heating settings, and adjustment of agglomerate additives It is possible to adjust the strength by the above, and it is possible to realize an efficient reduction treatment of the agglomerated material.

(Measurement method flow)
Next, an example of the flow of the measurement method in the measurement apparatus 10 according to the present embodiment will be briefly described with reference to FIG. FIG. 11 is a flowchart showing an example of the flow of the measuring method in the measuring apparatus 10 according to the present embodiment.

  The imaging device 100 of the measuring apparatus 10 according to the present embodiment images an agglomerate at the out-of-core outlet of the rotary hearth furnace under the control of the imaging control unit 201 in the arithmetic processing device 200 (step S101). The generated captured image is output to the arithmetic processing device 200.

  When the preprocessing unit 211 included in the arithmetic processing unit 200 of the measurement apparatus 10 acquires the captured image output from the imaging apparatus 100, the preprocessing such as reduction processing is performed on the acquired captured image as necessary. After (step S103), the captured image is output to the filtered image generation unit 213.

  The filtered image generation unit 213 applies a plurality of normalized LoG filters having different values of the standard deviation σ to the obtained captured image to generate a plurality of filtered images (step S105), and calculates a linear function. Output to the unit 215, the threshold determination unit 217, and the binarized image generation unit 219.

  Here, the linear function calculation unit 215 outputs the linear function used when the threshold value determination unit 217 calculates the second threshold value by performing the processing described above, from the filtered image generation unit 213. Calculation is performed in advance using the filtered image.

  The threshold value determination unit 217 first calculates an average luminance value of the first filter processing image group (step S107), and determines a first threshold value when binarizing the first filter processing image group. Thereafter, the threshold value determination unit 217 determines a second threshold value for binarizing the second filtered image group using the calculated average luminance value (step S109). When the threshold value determination unit 217 determines two types of threshold values, the threshold value determination unit 217 outputs information on the threshold values to the binarized image generation unit 219.

  Subsequently, the binarized image generation unit 219 binarizes each filter processing image using the determined two types of threshold values (step S111), and generates a binarized image. Thereafter, the binarized image generation unit 219 outputs the generated binarized image to the composite image generation unit 221.

  The composite image generation unit 221 combines the respective binarized images generated by the binarized image generation unit 219 to generate a composite binarized image (step S113), and the generated composite binarized image is Output to the labeling unit 223.

  The labeling unit 223 identifies the agglomerated material by labeling the portion where the luminance value = 1 in the composite binarized image (step S115), and displays the obtained labeling result together with the composite binarized image with the granularity. It outputs to the calculation part 225 and the temperature calculation part 227.

  The particle size calculation unit 225 calculates the particle size of the detected agglomerated material, and the temperature calculation unit 227 calculates the temperature of the detected agglomerated material (step S117). Thereby, the particle size and temperature of the agglomerated material are calculated together.

  The flow of the measurement method according to the present embodiment has been briefly described above with reference to FIG.

(About hardware configuration)
Next, the hardware configuration of the arithmetic processing apparatus 200 according to the embodiment of the present invention will be described in detail with reference to FIG. FIG. 12 is a block diagram for explaining a hardware configuration of the arithmetic processing device 200 according to the embodiment of the present invention.

  The arithmetic processing device 200 mainly includes a CPU 901, a ROM 903, and a RAM 905. The arithmetic processing device 200 further includes a bus 907, an input device 909, an output device 911, a storage device 913, a drive 915, a connection port 917, and a communication device 919.

  The CPU 901 functions as an arithmetic processing device and a control device, and controls all or a part of the operation in the arithmetic processing device 200 according to various programs recorded in the ROM 903, the RAM 905, the storage device 913, or the removable recording medium 921. The ROM 903 stores programs used by the CPU 901, calculation parameters, and the like. The RAM 905 primarily stores programs used by the CPU 901, parameters that change as appropriate during execution of the programs, and the like. These are connected to each other by a bus 907 constituted by an internal bus such as a CPU bus.

  The bus 907 is connected to an external bus such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge.

  The input device 909 is an operation unit operated by the user, such as a mouse, a keyboard, a touch panel, a button, a switch, and a lever. The input device 909 may be, for example, remote control means (so-called remote control) using infrared rays or other radio waves, or an external connection device 923 such as a PDA corresponding to the operation of the arithmetic processing device 200. May be. Furthermore, the input device 909 includes, for example, an input control circuit that generates an input signal based on information input by a user using the operation unit and outputs the input signal to the CPU 901. By operating the input device 909, the user can input various data or instruct processing operations to the arithmetic processing device 200.

  The output device 911 is configured by a device capable of visually or audibly notifying acquired information to the user. Such devices include display devices such as CRT display devices, liquid crystal display devices, plasma display devices, EL display devices and lamps, audio output devices such as speakers and headphones, printer devices, mobile phones, and facsimiles. The output device 911 outputs results obtained by various processes performed by the arithmetic processing device 200, for example. Specifically, the display device displays the results obtained by various processes performed by the arithmetic processing device 200 as text or images. On the other hand, the audio output device converts an audio signal composed of reproduced audio data, acoustic data, and the like into an analog signal and outputs the analog signal.

  The storage device 913 is a data storage device configured as an example of a storage unit of the arithmetic processing device 200. The storage device 913 includes, for example, a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device, an optical storage device, or a magneto-optical storage device. The storage device 913 stores programs executed by the CPU 901, various data, various data acquired from the outside, and the like.

  The drive 915 is a recording medium reader / writer, and is built in or externally attached to the arithmetic processing unit 200. The drive 915 reads information recorded on a removable recording medium 921 such as a mounted magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 905. The drive 915 can also write a record on a removable recording medium 921 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory. The removable recording medium 921 is, for example, a CD medium, a DVD medium, a Blu-ray (registered trademark) medium, or the like. Further, the removable recording medium 921 may be a compact flash (registered trademark) (CompactFlash: CF), a flash memory, an SD memory card (Secure Digital memory card), or the like. Further, the removable recording medium 921 may be, for example, an IC card (Integrated Circuit card) on which a non-contact type IC chip is mounted, an electronic device, or the like.

  The connection port 917 is a port for directly connecting a device to the arithmetic processing device 200. Examples of the connection port 917 include a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface) port, and an RS-232C port. By connecting the external connection device 923 to the connection port 917, the arithmetic processing apparatus 200 acquires various data directly from the external connection device 923 or provides various data to the external connection device 923.

  The communication device 919 is a communication interface configured with, for example, a communication device for connecting to the communication network 925. 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). The communication device 919 may be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various communication. The communication device 919 can transmit and receive signals and the like according to a predetermined protocol such as TCP / IP, for example, with the Internet and other communication devices. In addition, the communication network 925 connected to the communication device 919 is configured by a wired or wireless network, for example, the Internet, a home LAN, an in-house LAN, infrared communication, radio wave communication, satellite communication, or the like. May be.

  Heretofore, an example of the hardware configuration capable of realizing the function of the arithmetic processing device 200 according to the embodiment of the present invention has been shown. Each component described above may be configured using a general-purpose member, or may be configured by hardware specialized for the function of each component. Therefore, it is possible to change the hardware configuration to be used as appropriate according to the technical level at the time of carrying out this embodiment.

  Hereinafter, the measurement apparatus and the measurement method according to the present invention will be specifically described with reference to examples. In addition, the Example shown below is only an example of the measuring apparatus and measuring method which concern on this invention, and the measuring apparatus and measuring method which concern on this invention are not limited to the following example.

  In the following, using ten captured images captured by the image capturing apparatus 100, detection results of detection thresholds having a medium particle size (8 mm) or more as a variation threshold and detection thresholds, and skilled workers The visual count by was compared.

  The first diameter was set to 3 mm, and four types of normalized LoG filters with values of σ = 1/3, 2/3, 1 and 2 were used as the first normalized LoG filter group. . In addition, four types of normalized LoG filters in which values of σ = 3, 4,..., 6 are set are used as the second normalized LoG filter group.

The obtained results are shown in FIG.
As is clear from FIG. 13, at the fluctuation threshold, the calculation result and the visual count have a strong positive correlation (correlation coefficient: 0.99).
It can be seen that the undetected and over-detected conditions are suppressed, and the visual result can be reflected almost accurately. On the other hand, at the fixed threshold value, the calculation result and the visual count do not match (correlation coefficient: 0.47), not detected (region below the straight line indicated by the dotted line in the figure) or overdetected (in the figure It can be seen that a region above the straight line shown) has occurred.

  Next, for comparison, as shown in FIG. 14, in addition to the linear function for the fluctuation threshold specified in advance, two linear functions giving a fluctuation threshold ± 5 are further prepared. Using the function, the same verification as described above was performed. The obtained results are shown in FIG.

  In the example in which the fluctuation threshold is +5, it is expected that undetected will increase, but as can be seen from FIG. 15, it can be seen that undetected increases in the calculation result (correlation coefficient: 0.94). Further, in the example in which the variation threshold value is -5, overdetection is expected to increase, but as is apparent from FIG. 15, it can be seen that the overdetection is increased in the calculation result (correlation coefficient: 0. 96). From these results, it was confirmed that the threshold value determination method according to the present invention is appropriate.

  Next, as shown in FIG. 2, the image pickup apparatus 100 is installed at the out-of-furnace outlet of the actual rotary hearth furnace, and the above-described measurement method is applied to the obtained picked-up image for a long time. Time granularity and temperature data were calculated simultaneously. The processing time was about 1 second per image, and real-time processing was possible. The obtained results are shown in FIGS. FIG. 16 shows a real-time measurement result concerning the particle size, and FIG. 17 shows a real-time measurement result concerning the temperature. In FIGS. 16 and 17, the result obtained from the captured image captured every 10 seconds is smoothed by taking a moving average of 30 points.

  As apparent from FIGS. 16 and 17, it became clear that the particle size and temperature of the agglomerated material can be measured simultaneously and in real time by using the measuring apparatus and measuring method according to the present invention.

  The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention pertains can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that these also belong to the technical scope of the present invention.

DESCRIPTION OF SYMBOLS 10 Measuring apparatus 100 Imaging apparatus 200 Arithmetic processing apparatus 201 Imaging control part 203 Image processing part 205 Display control part 207 Storage part 211 Preprocessing part 213 Filter process image generation part 215 Linear function calculation part 217 Threshold value determination part 219 Binary image generation Unit 221 synthetic image generation unit 223 labeling unit 225 particle size calculation unit 227 temperature calculation unit 229 result output unit

Claims (10)

A measuring device for measuring the particle size and temperature of the agglomerate discharged from the reduction furnace,
An imaging device for generating a captured image obtained by imaging the discharged agglomerated material;
An arithmetic processing device that calculates the particle size and temperature of the agglomerated material based on the generated captured image;
With
The arithmetic processing unit includes:
A filtered image generation unit that generates a plurality of filtered images by causing a plurality of normalized Laplacian Gaussian filters having different standard deviation values to act on the captured image, respectively.
A threshold value determination unit that determines a binarization threshold value when binarizing the filtered image using at least a part of the plurality of filtered images;
A binarized image generating unit that binarizes each of the plurality of filter processed images using the determined binarization threshold and generates a plurality of binarized images;
A composite image generating unit that generates a composite image by combining the plurality of generated binary images;
Using the generated composite image, a particle size calculation unit for calculating the particle size of the agglomerated product,
Using the generated composite image, a temperature calculation unit that calculates the temperature of the agglomerated product,
A measuring device. The filtered image generation unit
Each of the first normalized Laplacian Gaussian filter groups used to detect the agglomerates having a diameter equal to or smaller than the first diameter to generate a first filtered image group;
Each of the second normalized Laplacian Gaussian filter groups used to detect the agglomerates having a diameter equal to or greater than a second diameter to generate a second filtered image group;
The threshold determination unit
A first threshold value obtained by multiplying the binarization threshold value for detecting an agglomerate having a diameter equal to or smaller than the first diameter by a predetermined fixed value to an average luminance value of each of the first filtered image groups. age,
The binarization threshold value for detecting an agglomerate having a diameter equal to or greater than the second diameter is determined by determining an average luminance value of each of the first filtered image groups and the second filtered image group. The measurement apparatus according to claim 1, wherein calculation is performed using a linear function representing a correspondence relationship with the average luminance value of the first and the average luminance value of each of the first filtered image groups. The measurement apparatus further includes a linear function calculation unit that calculates a linear function representing a correspondence relationship between the average luminance value of each of the first filtered image group and the average luminance value of the second filtered image group,
Each of the first normalized Laplacian Gaussian filter group and the second normalized Laplacian Gaussian filter group includes N normalized Laplacian Gaussian filters,
The linear function calculation unit
Respective average luminance value of the first filtered image group and X _n, the average luminance value of each of the second filter processing image group when the Y _{n (n} = 1~N), were generated (Xn, Yn) combinations are plotted on the XY plane,
The measuring apparatus according to claim 2, wherein a linear function obtained by linearly approximating a set of lower limit values of Y _n at each X position is calculated.   The particle size calculation unit uses the generated composite image, and at least any of the number, area, circumference, roundness, equivalent diameter, major axis length, minor axis length of the agglomerated material. The measuring apparatus according to any one of claims 1 to 3, wherein the measurement information is calculated and used as particle size information related to a particle size of the agglomerated material.   The temperature calculating unit calculates a temperature of the agglomerated material using a luminance value of the generated composite image and a temperature calibration formula indicating a relationship between the luminance value and the temperature, and the agglomerated material The measuring apparatus according to claim 1, wherein the temperature information is related to the temperature of the liquid crystal. The particle size calculation unit calculates the time transition of the particle size of the agglomerated product,
The said temperature calculation part is a measuring apparatus of any one of Claims 1-5 which calculates the time transition of the temperature of the said agglomerate.   The measuring apparatus according to claim 2, wherein the first diameter is 3 mm and the second diameter is 8 mm. The arithmetic processing unit includes:
A pre-processing unit that performs image pre-processing for reducing the captured image to a predetermined image size;
The measurement apparatus according to claim 1, wherein the filtered image generation unit performs a filtering process on the reduced captured image. A measurement method for measuring the particle size and temperature of agglomerates discharged from a reduction furnace,
An imaging step of imaging the agglomerated material discharged using an imaging device and generating a captured image;
A filtered image generation step of generating a plurality of filtered images by causing a plurality of normalized Laplacian Gaussian filters having different standard deviation values to act on the generated captured image;
A threshold value determining step for determining a binarization threshold value when binarizing the filtered image using at least a part of the plurality of filtered images;
A binarized image generating step of binarizing each of the plurality of filter processed images using the determined binarization threshold and generating a plurality of binarized images;
A composite image generation step of generating a composite image by combining the plurality of generated binary images;
A particle size calculating step for calculating a particle size of the agglomerated product using the generated composite image;
A temperature calculating step of calculating a temperature of the agglomerated material using the generated composite image;
Including a measuring method. A computer that can communicate with an imaging device that images the agglomerate discharged from the reduction furnace and generates a captured image functions as a measurement device that measures the particle size and temperature of the agglomerate discharged from the reduction furnace A program for
On the computer,
A filtered image generation function for generating a plurality of filtered images by causing a plurality of normalized Laplacian Gaussian filters having different standard deviation values to act on the captured image, respectively,
A threshold value determining function for determining a binarization threshold value when binarizing the filtered image using at least a part of the plurality of filtered images;
A binarized image generation function for binarizing each of the plurality of filtered images using the determined binarization threshold, and generating a plurality of binarized images;
A composite image generation function for generating a composite image by combining the plurality of generated binary images;
Using the generated composite image, a particle size calculation function for calculating the particle size of the agglomerated material,
A temperature calculation function for calculating the temperature of the agglomerated product using the generated composite image;
A program to realize