WO2017150565A1 - ガス漏れ位置推定装置、ガス漏れ位置推定方法及びガス漏れ位置推定プログラム - Google Patents
ガス漏れ位置推定装置、ガス漏れ位置推定方法及びガス漏れ位置推定プログラム Download PDFInfo
- Publication number
- WO2017150565A1 WO2017150565A1 PCT/JP2017/007951 JP2017007951W WO2017150565A1 WO 2017150565 A1 WO2017150565 A1 WO 2017150565A1 JP 2017007951 W JP2017007951 W JP 2017007951W WO 2017150565 A1 WO2017150565 A1 WO 2017150565A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- pixel
- gas
- image
- indicating
- gas leak
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 41
- 230000001186 cumulative effect Effects 0.000 claims description 101
- 238000012544 monitoring process Methods 0.000 claims description 54
- 238000004364 calculation method Methods 0.000 claims description 46
- 230000008569 process Effects 0.000 claims description 26
- 230000005484 gravity Effects 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 16
- 239000000284 extract Substances 0.000 claims description 8
- 230000004048 modification Effects 0.000 description 56
- 238000012986 modification Methods 0.000 description 56
- 238000010586 diagram Methods 0.000 description 22
- 230000006870 function Effects 0.000 description 18
- 238000009825 accumulation Methods 0.000 description 12
- 230000008859 change Effects 0.000 description 12
- 238000001514 detection method Methods 0.000 description 8
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000012886 linear function Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- WPYVAWXEWQSOGY-UHFFFAOYSA-N indium antimonide Chemical compound [Sb]#[In] WPYVAWXEWQSOGY-UHFFFAOYSA-N 0.000 description 2
- 206010037660 Pyrexia Diseases 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 238000005401 electroluminescence Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/38—Investigating fluid-tightness of structures by using light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/002—Investigating fluid-tightness of structures by using thermal means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3504—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing gases, e.g. multi-gas analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/174—Segmentation; Edge detection involving the use of two or more images
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
- G01N2021/1795—Atmospheric mapping of gases
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Definitions
- the present invention relates to a technology for remotely detecting a gas leaked from a monitoring target.
- Patent Document 1 includes an infrared camera that captures an inspection target region and an image processing unit that processes an infrared image captured by the infrared camera. Discloses a gas leak detection apparatus having a fluctuation extracting unit that extracts dynamic fluctuation due to gas leak from a plurality of infrared images arranged in time series.
- gas detection using an infrared image an image including a gas region image indicating a region where leaked gas is drifting is displayed on the display unit.
- the worker searches for a gas leak position using the gas region image as a clue. Since the gas region image is a surface and the gas leak position is a point, it is not easy to specify the gas leak position from the gas region image, and it takes time. In particular, when the area of the gas region image is large, it is difficult to specify the gas leak position from the gas region image. Therefore, a technique capable of estimating the gas leak position from the gas region image is desired.
- the gas leak position estimating apparatus includes a specifying unit and a first determining unit.
- the specifying unit specifies a gas region image indicating a region where gas is drifting in an image obtained by photographing the monitoring region.
- the first determining unit determines a pixel indicating a gas leak estimated position, which is estimated to be a position where the gas is leaking, from a plurality of pixels constituting an outline of the gas region image.
- the modification 1 it is an image figure which shows the relationship between an accumulation gas area
- it is an image figure which shows the relationship of the circumscribed rectangle which has an accumulation gas area
- FIG. It is an image figure of the accumulation image containing the outline of the image comprised by the pixel extracted by the threshold value B.
- FIG. It is an image figure of the accumulation image containing the outline of the image comprised by the pixel extracted by the threshold value C.
- FIG. In modification 2 it is an image figure showing the relation of the pixel which shows an accumulation gas field image and a feature point.
- FIG. 19 is an image diagram showing a cumulative image generated using the first to 300th frames shown in FIG. 18. It is explanatory drawing explaining the positional relationship of the some pixel which shows a gas leak estimated position. 10 is a flowchart for explaining the operation of a modification 8. In modification 8, it is an image figure which shows the relationship between a binarized image and a cumulative image. FIG. 16 is an explanatory diagram for explaining a positional relationship of pixels indicating feature points in Modification Example 8.
- FIG. 1 is a block diagram of a gas leak position estimation system 1 to which a gas leak position estimation apparatus 3 according to the present embodiment is applied.
- the gas leak position estimation system 1 includes an infrared camera 2 and a gas leak position estimation device 3.
- the infrared camera 2 captures a moving image of a monitoring target W of gas leakage (for example, a location where gas transport pipes are connected) and an infrared image of the background, and generates moving image data D1 indicating the moving image.
- the moving image data D1 is an example of image data of an infrared image.
- the infrared camera 2 may be used to capture the gas leak monitoring object W and the background infrared image at a plurality of times.
- the gas leak monitoring target W can be restated as a gas leak monitoring region. Therefore, it can be said that the frames constituting the moving image and the infrared images taken at the plurality of times are images indicating the monitoring area.
- the infrared camera 2 includes an optical system 4, a filter 5, a two-dimensional image sensor 6, and a signal processing unit 7.
- the optical system 4 forms an infrared image of the subject (the monitoring target W and the background) on the two-dimensional image sensor 6.
- the filter 5 is disposed between the optical system 4 and the two-dimensional image sensor 6, and allows only infrared light having a specific wavelength to pass through the light that has passed through the optical system 4.
- the wavelength band that passes through the filter 5 depends on the type of gas to be detected. For example, in the case of methane, a filter 5 that passes a wavelength band of 3.2 to 3.4 ⁇ m is used.
- the two-dimensional image sensor 6 is a cooled indium antimony (InSb) image sensor, for example, and receives the infrared rays that have passed through the filter 5.
- InSb cooled indium antimony
- the signal processing unit 7 converts the analog signal output from the two-dimensional image sensor 6 into a digital signal and performs known image processing. This digital signal becomes the moving image data D1.
- the moving image data D1 generated by the infrared camera 2 is input to the gas leak position estimation device 3 via the interface circuit.
- the gas leak position estimation device 3 is a personal computer, a smartphone, a tablet terminal, or the like, and includes a calculation control unit 8, a display control unit 9, a display unit 10, and an input unit 11 as functional blocks.
- the arithmetic control unit 8 and the display control unit 9 are realized by a processor.
- the gas leak position estimation device 3 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and a HDD (Hard Disk Drive) as a processor, and a ROM and HDD.
- the arithmetic control unit 8 and the display control unit 9 are realized by the processor executing the program stored in the RAM using the RAM.
- the display unit 10 is realized by various displays such as a liquid crystal display and an organic electroluminescence display.
- the input unit 11 is realized by a keyboard, a touch panel, or the like.
- the calculation control unit 8 performs various calculations and controls related to the operation of the gas leak position estimation device 3.
- the calculation includes image processing for obtaining the estimated gas leak position and image processing for detecting gas leak as a premise of this processing.
- the display control unit 9 displays a predetermined image on the display unit 10.
- the predetermined image is, for example, an infrared image of the monitoring target W (in other words, the monitoring region) where the moving image indicated by the moving image data D1 or the estimated gas leak position is indicated.
- the input unit 11 receives various inputs necessary for the operation of the gas leak position estimation device 3.
- the operation of the gas leak position estimation apparatus 3 includes a process of extracting a gas region image.
- the gas region image is an image that is included in the infrared image of the monitoring target W and indicates a region where the gas leaked from the monitoring target W is drifting.
- the arithmetic control unit 8 determines that a gas leak has occurred when the gas region image has been extracted.
- the temperature threshold method can be applied when the temperature of the leaking gas is higher or lower than the temperature at the location of the monitoring target W.
- a predetermined calculation is performed using the temperature and temperature indicated by the pixel value of a pixel, and it is determined whether or not gas is present at a location corresponding to the pixel.
- determination is made for all pixels constituting a frame (infrared image), and a group of pixels corresponding to a location where gas is present is defined as a gas region image.
- an image indicating a moving object region included in a frame is detected, and this image is used as a gas region image. That is, in the moving object detection method, a pixel in which a difference in pixel values of pixels at the same position is larger than a predetermined threshold in a frame of interest and a reference frame is set as a pixel constituting an image showing a moving object region. A collection of these pixels (that is, an image showing a moving body region) is a gas region image.
- the reference frame is a frame immediately before the frame of interest, a frame a predetermined number of frames before the frame of interest, or an infrared image of the monitoring target W taken in the past in a state where no gas leaks.
- FIG. 2 is a flowchart for explaining the operation of the program executed by the processor of the gas leak position estimating apparatus 3. 1 and 2, when the operator operates the input unit 11 and inputs a command for starting gas detection, the gas leak position estimation apparatus 3 is a moving image sent from the infrared camera 2. Data D1 is received.
- the arithmetic control unit 8 selects the moving image data D1 as a plurality of continuous frames (step S1). Here, a description will be given by taking 300 frames as an example.
- FIG. 3 is an image diagram generated by image processing executed until the accumulated image Im3 is generated based on the moving image data D1 indicating the moving image captured by the infrared camera 2.
- the 300 (first to 300th frames) infrared images Im1 are the 300 frames selected in step S1.
- the 300 frames are 10-second moving images when the moving image frame rate indicated by the moving image data D1 is, for example, 30 fps.
- Each of the 300 infrared images Im1 includes an instantaneous gas region image P1.
- the instantaneous gas region image P1 is a gas region image showing a region where the gas leaked from the monitoring target W reflected in the frame is drifting at the time when the frame is captured.
- the instantaneous gas region image P1 of the first frame is a gas region image indicating a region where the gas leaked from the monitoring target W is drifting at the time when the first frame is captured, and the 150th frame.
- the instantaneous gas region image P1 is a gas region image showing a region where the gas leaked from the monitoring target W is drifting at the time when the 150th frame is taken, and the instantaneous gas region image P1 of the 300th frame. Is a gas region image showing a region where the gas leaked from the monitoring target W is drifting at the time when the 300th frame is captured.
- the instantaneous gas region image P1 is extracted by the arithmetic control unit 8. That is, the arithmetic control unit 8 functions as a first extraction unit, and gas is drifting from each of the frames (a plurality of images arranged in time series) constituting the moving image data D1 when each frame is captured. Processing for extracting an instantaneous gas region image P1 indicating the region is performed.
- the arithmetic control unit 8 sets the pixels constituting the instantaneous gas region image P1 to “1” and the other pixels to “0” for each of 300 infrared images Im1 including the instantaneous gas region image P1. Binarization processing is performed to generate 300 binarized images Im2 (step S2). A collection of pixels indicated by “1” becomes an instantaneous gas region image P2 after binarization processing.
- the arithmetic control unit 8 performs processing for accumulating 300 binarized images Im2, and generates an accumulated image Im3 (step S3). More specifically, a process of adding pixel values of pixels at the same position in 300 binarized images Im2. Since the pixel value of the pixel constituting the binarized image Im2 is binary, that is, 1 or 0, the maximum value that can be the pixel value of the pixel constituting the accumulated image Im3 is 300.
- the cumulative image Im3 includes the cumulative gas region image P3.
- the cumulative gas region image P3 is a gas region image generated by generating the cumulative image Im3.
- a process of adding pixel values of pixels at the same position is performed, and 300 sheets are obtained. Is an image obtained by accumulating the instantaneous gas region image P2.
- the arithmetic control unit 8 functions as a generation unit that generates the cumulative gas region image P3. That is, the generation unit performs a process of adding the pixel values of the pixels at the same position in the plurality of instantaneous gas region images P2 extracted from each of the plurality of images (300 frames), and thereby generates a plurality of instantaneous gas regions.
- a cumulative gas region image P3 that is an image obtained by accumulating the image P2 is generated.
- the calculation control unit 8 may generate a cumulative image (not shown) by performing a process of accumulating 300 infrared images Im1 without generating 300 binarized images Im2. Since the pixel values of the pixels constituting the infrared image Im1 are not binary but multivalued, the maximum value that can be the pixel value of the pixels constituting the accumulated image is larger than 300.
- FIG. 4 is an image diagram showing the relationship between the accumulated gas region image P3 and pixels indicating feature points.
- the accumulated image Im3 illustrated in FIG. 4 is an image obtained by enlarging the accumulated gas region image P3 of the accumulated image Im3 illustrated in FIG.
- the arithmetic control unit 8 functions as a specifying unit. Referring to FIG. 4, arithmetic control unit 8 binarizes cumulative image Im3 to generate binarized cumulative image Im4 shown in FIG. 6, and binarization included in binarized cumulative image Im4
- the processed cumulative gas region image P4 is specified (step S4).
- the binarization threshold is, for example, 20% of the number of frames used for generating the cumulative image Im3. When the number of frames is 300, the threshold value is 60.
- the arithmetic control unit 8 compares the pixel values of all the pixels constituting the cumulative image Im3 with a threshold value, sets a pixel value larger than the threshold value to “1”, and sets a pixel value less than the threshold value to “0”. " Thereby, the binarized cumulative image Im4 is generated. A group of pixels indicating “1” is the accumulated gas region image P4 after the binarization process. As described above, the arithmetic control unit 8 (identification unit) identifies the accumulated gas region image P4 (gas region image) after the binarization process in the frame (image obtained by photographing the monitoring region).
- the accumulated image Im3 means the binarized accumulated image Im4, and the accumulated gas region image P3 means the accumulated gas region image P4 after the binarization process.
- the cumulative image Im3 means the binarized cumulative image Im4, and the cumulative gas region image P3 is binarized. This means the subsequent accumulated gas region image P4.
- the calculation control unit 8 specifies the cumulative gas region image P3 using the cumulative gas region image P3 included in the cumulative image Im3 as a gas region image. However, the arithmetic control unit 8 selects one infrared image Im1 from which the instantaneous gas region image P1 is extracted without generating the cumulative image Im3, and binarizes the infrared image Im1. The generated image obtained by binarizing the instantaneous gas region image P1 may be specified as the gas region image.
- the calculation control unit 8 determines a pixel indicating the feature point of the cumulative gas region image P3 (step S5). This will be described in detail with reference to FIG.
- the cumulative gas region image P3 is composed of a plurality of pixels.
- the arithmetic control unit 8 functions as a first calculation unit, and calculates a regression line L1 indicating the relationship between the positions of a plurality of pixels (all pixels) constituting the cumulative gas region image P3.
- a linear function having the calculated slope a and intercept b is a regression line L1 (an example of a regression line).
- a secondary or higher order regression curve (another example of the regression line) may be used.
- the arithmetic control unit 8 performs a process of superimposing the regression line L1 on the cumulative gas region image P3, and changes the pixel constituting the regression line L1 from the pixel constituting the cumulative gas region image P3 to the pixel not constituting the cumulative gas region image P3.
- Pixels to be switched that is, two points where the contour 30 of the cumulative gas region image P3 and the regression line L1 intersect
- a pixel indicating one of the two points is a first pixel 31, and a pixel indicating the other of the two points is a second pixel 32.
- Each of the first pixel 31 and the second pixel 32 is a pixel indicating a feature point. Note that one of the first pixel 31 and the second pixel 32 may be a feature point.
- the arithmetic control unit 8 functions as a first determination unit. That is, the arithmetic control unit 8 (first determination unit) selects a pixel indicating a feature point of the cumulative gas region image P3 (gas region image) from among a plurality of pixels constituting the contour 30 of the cumulative gas region image P3.
- the pixel indicating the gas leak estimated position is determined from the feature points.
- the pixel indicating the gas leak estimation position is determined from the pixels indicating the feature points, but is not limited to the pixels indicating the feature points. That is, the arithmetic control unit 8 (first determination unit) may determine a pixel indicating the gas leak estimation position from among a plurality of pixels constituting the contour 30 of the cumulative gas region image P3 (gas region image). Good.
- the calculation control unit 8 determines a pixel indicating a gas leak estimated position (step S6). More specifically, the arithmetic control unit 8 obtains the target pixel 33.
- the leaked gas is drifting in a region corresponding to the cumulative gas region image P3 (gas region image). In this region, there is a location where the gas concentration is high, and the pixel corresponding to this location is the target pixel 33.
- the target pixel 33 is, for example, a pixel having the largest pixel value among a plurality of pixels (all pixels) constituting the cumulative gas region image P3 or a pixel indicating the center of gravity of the cumulative gas region image P3.
- the gas concentration thickness product is a value obtained by integrating the gas concentration along the depth direction of the space where the gas is drifting. The largest pixel value means that the gas appears frequently.
- the center of gravity can be obtained by a known method.
- the arithmetic control unit 8 functions as a second determination unit, and determines one of the first pixel 31 or the second pixel 32 as a pixel indicating a gas leak estimation position.
- FIG. 5 is an image diagram showing the relationship between the cumulative gas region image P3, the pixels indicating the feature points (first pixel 31 and second pixel 32), and the pixel of interest 33.
- the arithmetic control unit 8 sets the gas leak estimated position as the first pixel 31.
- the second pixel 32 is set as the gas leak estimation position. The pixel to be shown is determined.
- the portion corresponding to the target pixel 33 has a high gas concentration, so that the arithmetic control unit 8 includes the first pixel 31 or the second pixel 32.
- the pixel closer to the target pixel 33 is set as a pixel indicating the estimated gas leak position.
- the second pixel 32 is set as the gas leak estimation position.
- the display control unit 9 visualizes the pixel indicating the gas leak estimated position determined in step S6 as the gas leak estimated position, and displays an infrared image (not shown) of the monitoring target W in which the gas leak estimated position is indicated. It is displayed on the display unit 10.
- the gas region image is an image showing a region where the gas leaked from the monitoring target W (FIG. 1) is drifting
- the gas leakage position is included in the gas region image.
- the present inventor has found that the gas leaking from the monitoring target W is fluctuated by wind or the like, and therefore the gas leak position is highly likely to be present at or near the contour of the gas region image. From this, the present inventor considered that it is appropriate to set any position on the contour of the gas region image as the gas leak estimation position.
- the gas leak position estimation device 3 uses the cumulative gas region image P3 as a gas region image, and uses the cumulative gas region image P3 to determine pixels indicating the gas leak estimated position. Pixels (first pixel 31 and second pixel 32) indicating the feature points are determined from among a plurality of pixels constituting the contour 30 of the cumulative gas region image P3. Therefore, according to the gas leak position estimation apparatus 3 according to the present embodiment, the gas leak position can be estimated using the accumulated gas region image P3 (gas region image).
- the regression line L1 linearly approximates the position of each of a plurality of pixels constituting the cumulative gas region image P3 (gas region image).
- the gas leak position estimation apparatus 3 accumulates pixels (first pixel 31 and second pixel 32) indicating two points where the regression line L1 and the contour 30 of the accumulated gas region image P3 intersect. By setting the pixels to indicate the feature points of the gas region image P3, the number of pixels serving as feature points is narrowed down from among a plurality of pixels constituting the contour 30 of the cumulative gas region image P3.
- Modification 1 is different from the present embodiment in the process of step S5 shown in FIG.
- the pixels (first pixel 31 and second pixel 32) indicating feature points are obtained using the regression line L1 shown in FIG. 4, but in the first modification, the cumulative gas region image P3 is obtained.
- a pixel that indicates a feature point is obtained using a rectangle that circumscribes (a circumscribed rectangle).
- FIG. 7 is an image diagram showing the relationship between the cumulative gas region image P3 and the circumscribed rectangle R in Modification 1, and corresponds to FIG.
- the circumscribed rectangle R has four sides that are in contact with the cumulative gas region image P3 (gas region image), and is a rectangle that surrounds the cumulative gas region image P3.
- the circumscribed rectangle R is a rectangle that has four sides in contact with the contour 30 of the cumulative gas region image P3 and surrounds the contour 30.
- the accumulated gas region image P3 and the four sides of the circumscribed rectangle R are in contact with each other at the contact points 40, 41, 42, and 43.
- the calculation control unit 8 functions as a setting unit and sets a circumscribed rectangle R.
- the arithmetic control unit 8 functions as a first determination unit. That is, the arithmetic control unit 8 (first determination unit) includes the first pixel 31 and the second pixel located at two points (contact points 40 and 42) at which the two short sides of the circumscribed rectangle R are in contact with the accumulated gas region image P3.
- the second pixel 32 is determined as a pixel indicating a feature point. Note that one of the first pixel 31 and the second pixel 32 may be a feature point.
- the circumscribed rectangle R is a rectangle that approximates the cumulative gas region image P3 (gas region image).
- the gas leaked from the monitoring target W does not spread evenly in all directions while the wind direction is constant, but has a tendency to spread along one direction. For this reason, there is a high possibility that the gas leakage position exists on one short side of the two short sides of the circumscribed rectangle R.
- pixels (first pixel 31 and second pixel 32) indicating two points at which the two short sides of the circumscribed rectangle R are in contact with the cumulative gas region image P3 are feature points of the cumulative gas region image P3.
- circumscribed rectangle R there are multiple circumscribed rectangles R. Of the circumscribed rectangle R, it is considered that the circumscribed rectangle R that is closest to the accumulated gas region image P3 (gas region image) is preferably set as the circumscribed rectangle R.
- the circumscribed rectangle R having the smallest area is a circumscribed rectangle that is closest to the accumulated gas region image P3 (gas region image).
- the arithmetic control unit 8 sets the circumscribed rectangle R having the smallest area as the circumscribed rectangle R.
- FIG. 8 is an image diagram showing the relationship between the cumulative gas region image P3 and the circumscribed rectangle R having the smallest area in the first modification, and corresponds to FIG.
- the arithmetic control unit 8 sets a reference rectangle (not shown) surrounding the accumulated gas region P3.
- the arithmetic control unit 8 adjusts the lengths of the long side and the short side of the reference rectangle, obtains the circumscribed rectangle R, and calculates its area.
- the arithmetic control unit 8 rotates the reference rectangle little by little (for example, by 1 degree) around its center point (not shown), obtains the same process (the circumscribed rectangle R, and calculates its area) )do.
- the arithmetic control unit 8 repeats the process until the reference rectangle is rotated 180 degrees.
- the calculation control unit 8 sets the circumscribed rectangle R having the smallest area among the obtained circumscribed rectangles R as the circumscribed rectangle R.
- Modification 2 will be described. Modification 2 differs from the present embodiment in the process of step S5 shown in FIG. In the present embodiment, as shown in FIG. 4, a pixel (first pixel 31, The second pixel 32) is determined. On the other hand, in the second modified example, pixels (first pixel 31 and second pixel 32) indicating feature points using a regression line L2 (FIG. 12) indicating the relationship between the positions of two or more centroids. )
- the calculation control unit 8 functions as a second extraction unit.
- the arithmetic control unit 8 (second extraction unit) performs an extraction process of extracting pixels from a plurality of pixels (all pixels) constituting the cumulative image Im3 shown in FIG. 3 based on a predetermined threshold value. .
- the arithmetic control unit 8 performs an extraction process based on each of two or more threshold values having different values.
- the threshold A, threshold B, and threshold C are assumed (threshold A> threshold B> threshold C).
- the threshold value is, for example, 70%, 40%, or 10% of the number of frames used for generating the cumulative image Im3. When the number of frames is 300, threshold A is 210, threshold B is 120, and threshold C is 30.
- FIG. 9 is an image diagram of the cumulative image Im3 including the contour 50 of the image composed of the pixels extracted with the threshold value A.
- FIG. 10 is an image diagram of the cumulative image Im3 including the contour 52 of the image composed of the pixels extracted with the threshold value B.
- FIG. 11 is an image diagram of the cumulative image Im3 including the contour 54 of the image composed of the pixels extracted with the threshold value C.
- the calculation control unit 8 functions as a first calculation unit.
- the arithmetic control unit 8 (first calculation unit) performs a calculation process for calculating the center of gravity of an image composed of pixels extracted with a threshold value.
- the arithmetic control unit 8 (first calculation unit) calculates two or more centroids by performing calculation processing on images corresponding to two or more threshold values having different values. Specifically, with reference to FIG. 9, the arithmetic control unit 8 extracts a pixel larger than the threshold value A among a plurality of pixels (all pixels) constituting the cumulative image Im3.
- the arithmetic control unit 8 obtains the center of gravity 51 of the image composed of the extracted pixels.
- the arithmetic control unit 8 extracts pixels larger than the threshold value B among a plurality of pixels (all pixels) constituting the cumulative image Im3.
- the arithmetic control unit 8 obtains the center of gravity 53 of the image composed of the extracted pixels.
- the arithmetic control unit 8 extracts pixels larger than the threshold value C among a plurality of pixels (all pixels) constituting the cumulative image Im3.
- the arithmetic control unit 8 obtains the center of gravity 55 of the image composed of the extracted pixels.
- the calculation control unit 8 uses the centroids 51, 53, and 55 to determine pixels indicating feature points. More specifically, FIG. 12 is an image diagram showing the relationship between the accumulated gas region image P3 and the pixels indicating the feature points (first pixel 31 and second pixel 32) in Modification 2.
- the arithmetic control unit 8 functions as a second calculation unit and calculates a regression line L2 indicating the relationship between the positions of the three centroids 51, 53, and 55.
- a linear function having the calculated slope a and intercept b is the regression line L2.
- the calculation control unit 8 functions as a first determination unit.
- the arithmetic control unit 8 (first determination unit) performs a process of superimposing the regression line L2 on the cumulative gas region image P3, and obtains two points where the contour 30 of the cumulative gas region image P3 and the regression line L2 intersect.
- a pixel indicating one of the two points is a first pixel 31, and a pixel indicating the other of the two points is a second pixel 32.
- Each of the first pixel 31 and the second pixel 32 is a pixel indicating a feature point.
- the calculation control unit 8 determines a gas leak estimated position in the same manner as the calculation control unit 8 according to the present embodiment (step S6 in FIG. 2).
- a pixel indicating the centroid 51 may be used as the target pixel 33 (FIG. 5) used for this determination.
- the pixel having the largest pixel value is the pixel indicating the centroid 51. Since the target pixel 33 is a pixel corresponding to a location where the appearance frequency of gas is high, the pixel indicating the center of gravity 51 is the target pixel 33.
- pixels (first pixel 31 and second pixel 32) indicating two points where the regression line L2 and the contour 30 of the cumulative gas region image P3 (gas region image) intersect are represented by the cumulative gas region image.
- the pixels By setting the pixels to indicate the feature points of P3, the number of pixels that are the feature points of the cumulative gas region image P3 is narrowed down from among the plurality of pixels constituting the contour 30 of the cumulative gas region image P3.
- the regression line L1 calculated based on the cumulative gas region image P3 that is, the positional relationship between the plurality of pixels constituting the cumulative gas region image P3 (gas region image)
- the regression line L2 is calculated based on the accumulated image Im3.
- Modification 3 will be described. Modification 3 differs from the present embodiment in the process of step S6.
- the pixel closer to the target pixel 33 out of the first pixel 31 or the second pixel 32 is determined as a pixel indicating the gas leak estimation position.
- one of the first pixel 31 and the second pixel 32 is determined as a pixel indicating the estimated gas leak position based on the gas density.
- FIG. 13 is an image diagram showing the relationship between the accumulated gas region image P3 and the pixels (first pixel 31 and second pixel 32) indicating feature points in the third modification, and corresponds to FIG.
- the first pixel 31 or the second pixel 32 is a pixel indicating a gas leak estimated position.
- the calculation control unit 8 functions as a second determination unit.
- the arithmetic control unit 8 sets the lower pixel of the first pixel 31 or the second pixel 32 as the gas leak estimated position.
- the pixel having the higher position of the first pixel 31 and the second pixel 32 is determined as the pixel indicating the gas leak estimation position. .
- the position of the first pixel 31 is higher than the position of the second pixel 32.
- the arithmetic control unit 8 determines the second pixel 32 as a pixel indicating the gas leak estimation position, and when the gas density is higher than the air density, the first pixel is determined. 31 is determined as a pixel indicating a gas leak estimated position.
- Modification 4 to Modification 6 will be described. These modifications differ from the present embodiment in the process of step S6 shown in FIG. The leaked gas drifts to spread. Based on this, in Modifications 4 to 6, one of the first pixel 31 and the second pixel 32 is determined as a pixel indicating the estimated gas leak position.
- FIG. 14 is an image diagram showing the relationship between the accumulated gas region image P3 and the pixels indicating the feature points (first pixel 31 and second pixel 32) in Modification Example 4, and corresponds to FIG.
- the first line segment L3 is one of two line segments that intersect with a line (not shown) connecting the first pixel 31 and the second pixel 32 and have both ends located on the contour 30.
- the first line segment L3 is located between the first pixel 31 and the target pixel 33.
- the second line segment L4 is the other of the two line segments that intersect with the line (not shown) and have both ends located on the contour 30.
- the second line segment L4 is located between the second pixel 32 and the target pixel 33.
- the first line segment L3 and the second line segment L4 are parallel.
- the first line segment L3 and the second line segment L4 pass through the vicinity of the target pixel 33. For example, the first line segment L3 and the second line segment L4 pass through a position two pixels away from the target pixel 33.
- the accumulated gas region image P3 (gas region image) is shorter in the y direction than in the x direction.
- the direction of the first line segment L3 and the second line segment L4 is the y direction.
- the direction of the first line segment L3 and the second line segment L4 may be the direction of the short side of the circumscribed rectangle R (FIGS. 7 and 8).
- the arithmetic control unit 8 functions as a second determination unit.
- the arithmetic control unit 8 (second determining unit) causes the gas to flow from the first line segment L3 side toward the second line segment L4 side.
- the first pixel 31 positioned on the first line segment L3 side is determined as a pixel indicating the gas leak estimation position and the second line segment L4 is shorter than the first line segment L3.
- the second pixel 32 positioned on the second line segment L4 side is assumed to indicate the gas leak estimation position, assuming that the gas spreads from the second line segment L4 side toward the first line segment L3 side. It is determined as a pixel.
- the second pixel 32 is a pixel indicating the estimated gas leak position.
- FIG. 15 is an image diagram showing the relationship between the accumulated gas region image P3 and the pixels indicating the feature points (first pixel 31 and second pixel 32) in Modification 5, and corresponds to FIG.
- the dividing line L5 crosses a line (not shown) connecting the first pixel 31 and the second pixel 32 and passes through the target pixel 33.
- the cumulative gas region image P3 (gas region image) is shorter in the y direction than in the x direction.
- the direction of the dividing line L5 is the y direction.
- the direction of the dividing line L5 may be the direction of the short side of the circumscribed rectangle R (FIGS. 7 and 8).
- the first divided image P ⁇ b> 5 is one of two divided images formed by dividing the cumulative gas region image P ⁇ b> 3 (gas region image) by the dividing line L ⁇ b> 5 and includes the first pixel 31.
- the second divided image P6 is the other of the two divided images formed by dividing the cumulative gas region image P3 (gas region image) into two by the dividing line L5, and includes the second pixel 32.
- the arithmetic control unit 8 functions as a second determination unit.
- the arithmetic control unit 8 moves from the first divided image P5 side to the second divided image P6 side.
- the first pixel 31 included in the first divided image P5 is determined as a pixel indicating the gas leak estimation position, and the area of the second divided image P6 is the first divided image.
- the second pixels 32 included in the second divided image P6 are The pixel indicating the estimated position of gas leakage is determined.
- the second pixel 32 is a pixel indicating the estimated gas leak position.
- FIG. 16 is an image diagram showing the relationship between the accumulated gas region image P3 and the pixels indicating the feature points (first pixel 31 and second pixel 32) in Modification Example 6, and corresponds to FIG. 16 is different from FIG. 15 in that the outline 30 of the cumulative gas region image P3 is not shown, and the outline 60 of the first divided image P5 and the outline 61 of the second divided image P6 are shown. That is. This is because the contour 30 (FIG. 15) of the cumulative gas region image P3 overlaps the contour 60 of the first divided image P5 and the contour 61 of the second divided image P6.
- the arithmetic control unit 8 functions as a second determination unit.
- the arithmetic control unit 8 starts from the first divided image P5 side to the second divided image P6.
- the first pixel 31 included in the contour 60 of the first divided image P5 is determined as a pixel indicating the gas leakage estimation position, and the contour of the second divided image P6 is considered as gas spreading toward the side.
- the second pixel 32 included in is determined as a pixel indicating the estimated gas leak position.
- the second pixel 32 is a pixel indicating the estimated gas leak position.
- the pixel indicating the estimated gas leak position is a plurality of pixels constituting the contour 30 of the cumulative gas region image P3 (gas region image).
- a pixel (first pixel 31 and second pixel 32) indicating a feature point is determined from among a plurality of pixels constituting the contour 30, and the first pixel 31 or the second pixel is determined.
- 32 is determined as a pixel indicating a gas leak estimated position.
- the accumulated gas region image P3 is included in the accumulated image Im3.
- the cumulative image Im3 is generated using a plurality of frames arranged in time series, that is, a frame group of a predetermined period. If the wind direction changes during the predetermined period, the pixel indicating the estimated gas leak position may not be included in the plurality of pixels constituting the contour 30 of the cumulative gas region image P3 (gas region image). As a result, the gas leak estimation position may be separated from the gas leak position.
- FIG. 17 is a flowchart for explaining the operation of the modification 7.
- FIG. 18 is an image diagram showing the relationship between the binarized image Im2 and the cumulative image Im3 in Modification 7.
- Step S1 is the same as step S1 shown in FIG.
- the calculation control unit 8 selects 300 frames in step S1.
- the calculation control unit 8 uses three 300 frames.
- the first to 100th frames are selected (step S1). This will be described in detail with reference to FIG.
- the predetermined period is 10 seconds, and the accumulated image Im3 is generated using a 10-second frame group.
- the predetermined period is divided into a plurality of divided periods, and in each of the plurality of divided periods, a cumulative image Im3 is generated using a frame group of the divided periods.
- a 10-second frame group is composed of 300 frames.
- the 300 frames are the first to 100th frames (100 frames), the 101st to 200th frames (100 frames), 201 Divided into the first to 300th frames (100 frames).
- the arithmetic control unit 8 executes steps S2 to S6 using the first to 100th frames selected in step S1, and determines the pixel 70 indicating the estimated gas leak position. Steps S2 to S6 are the same as steps S2 to S6 shown in FIG.
- the pixel 70 indicating the gas leak estimation position is selected from the first pixel 31 or the second pixel (not shown). Here, it is assumed that the first pixel 31 is selected.
- the calculation control unit 8 determines whether or not the plurality of frames selected in step S1 are the last (step S7).
- the last plurality of frames are the 201st to 300th frames.
- the first to 100th frames are selected.
- the arithmetic control unit 8 determines that the plurality of frames selected in step S1 are not the last (No in step S7), and the arithmetic control unit 8 returns to step S1 and selects the 101st to 200th frames.
- the arithmetic control unit 8 performs steps S2 to S6 using the 101st to 200th frames selected in step S1, and determines the pixel 71 indicating the estimated gas leak position.
- the pixel 71 indicating the gas leak estimation position is selected from the first pixel 31 or the second pixel (not shown). Here, it is assumed that the first pixel 31 is selected.
- the calculation control unit 8 determines whether or not the plurality of frames selected in step S1 are the last (step S7). In step S1, the 101st to 200th frames are selected. The arithmetic control unit 8 determines that the plurality of frames selected in step S1 are not the last (No in step S7), and the arithmetic control unit 8 returns to step S1 and selects the 201st to 300th frames.
- the arithmetic control unit 8 executes steps S2 to S6 using the 201st to 300th frames selected in step S1, and determines the pixel 72 indicating the gas leak estimated position.
- the pixel 72 indicating the gas leak estimation position is selected from the first pixel (not shown) or the second pixel 32. Here, it is assumed that the second pixel 32 is selected.
- the shape and position of the cumulative gas region image P3 are different from each other.
- FIG. 19 is an image diagram showing a cumulative image Im3 generated using the first to 300th frames shown in FIG.
- FIG. 19 shows a pixel 73 indicating the estimated gas leak position determined using this cumulative image Im3.
- FIG. 20 is an explanatory diagram for explaining the positional relationship between the pixels 70, 71, 72, and 73 that indicate the gas leak estimated positions. Pixels 70, 71, and 72 that indicate gas leak estimation positions are close to each other.
- the cumulative image Im3 used to determine these pixels is generated using a relatively small number (100) of frames, that is, generated using a group of frames having a relatively short period (about 3.3 seconds). This is because the influence of the change in the wind direction is small.
- the pixel 73 indicating the gas leak estimated position is separated from the pixels 70, 71, and 72 indicating the gas leak estimated position.
- the accumulated image Im3 used for determining the pixel is generated using a relatively large number (300) of frames, that is, generated using a group of frames having a relatively long period (10 seconds). This is because the influence of change is great.
- the pixel 74 indicating the gas leak estimated position in consideration of the change in the wind direction is determined based on the pixels 70, 71, and 72 indicating the gas leak estimated position (step S8).
- the calculation control unit 8 functions as a second determination unit.
- the arithmetic control unit 8 (second determination unit) performs pixel (pixel 70, pixel) indicating the gas leak estimation position for each of the three cumulative gas region images P3 (a plurality of gas region images arranged in time series) illustrated in FIG. Pixel 71 and pixel 72) are determined (step S6).
- the arithmetic control unit 8 sets the pixels (pixel 70, pixel 71, pixel 72) indicating the plurality of gas leak estimated positions determined in step S6 as pixels indicating the plurality of first gas leak estimated positions, Each coordinate value of the pixel indicating the first gas leak estimated position is set as a population, and the pixel indicating the coordinate value that is the average value or the median value of the population is a pixel indicating the second gas leak estimated position. decide.
- the pixel indicating the second gas leak estimated position becomes the pixel 74 indicating the gas leak estimated position in consideration of the change in the wind direction.
- the pixel 74 indicating the second gas leak estimated position is determined based on the pixels indicating the plurality of first gas leak estimated positions 70, 71, 72.
- Pixels 70, 71, and 72 that indicate a plurality of first gas leak estimated positions are pixels that indicate gas leak estimated positions obtained from each of a plurality of accumulated gas region images P3 (gas region images) arranged in time series.
- the second gas leak estimation position is a gas leak estimation position that is less affected by changes in the wind direction. That is, the second gas leak estimated position is a gas leak estimated position that is not separated from the gas leak position even if the wind direction changes. Therefore, according to the modification 7, even if a wind direction changes, it can prevent that the precision of a gas leak estimated position falls.
- the coordinate value that is the average value of the population and the coordinate value that is the median value of the population will be specifically described.
- the coordinate value of the pixel 70 indicating the first gas leak estimated position is set to (x1, y1)
- the coordinate value of the pixel 71 indicating the first gas leak estimated position is set to (x2, y2).
- the coordinate value of the pixel 72 indicating the position is (x3, y3), x2 ⁇ x3 ⁇ x1, and y1 ⁇ y2 ⁇ y3.
- the coordinate values serving as the average value of the population are ((x1 + x2 + x3) ⁇ 3, (y1 + y2 + y3) ⁇ 3).
- the coordinate value serving as the median value of the population is (x3, y2).
- Modification 8 will be described.
- the pixel indicating the gas leak estimated position in consideration of the change in the wind direction is determined based on the pixels indicating the plurality of gas leak estimated positions determined in step S6 (step S8).
- the modification 8 determines the pixel which shows the gas leak estimated position in which the change of the wind direction was considered based on the pixel which shows the some feature point determined by step S5 (step S8).
- FIG. 21 is a flowchart for explaining the operation of the modification 8.
- FIG. 22 is an image diagram showing the relationship between the binarized image Im2 and the cumulative image Im3 in Modification 8.
- Step S1 is the same as step S1 shown in FIG.
- the arithmetic control unit 8 selects the first to 100th frames as in the seventh modification (step S1).
- the arithmetic control unit 8 executes Steps S2 to S5 using the first to 100th frames selected in Step S1, and displays the feature points (first pixel 31a, second pixel 32a). To decide. Steps S2 to S5 are the same as steps S2 to S5 shown in FIG.
- the calculation control unit 8 determines whether or not the plurality of frames selected in step S1 are the last (step S7).
- the last plurality of frames are the 201st to 300th frames.
- the first to 100th frames are selected.
- the arithmetic control unit 8 determines that the plurality of frames selected in step S1 are not the last (No in step S7), and the arithmetic control unit 8 returns to step S1 and selects the 101st to 200th frames.
- the arithmetic control unit 8 performs steps S2 to S5 using the 101st to 200th frames selected in step S1, and displays the feature points (first pixel 31b, second pixel 32b). To decide.
- the calculation control unit 8 determines whether or not the plurality of frames selected in step S1 are the last (step S7). In step S1, the 101st to 200th frames are selected. The arithmetic control unit 8 determines that the plurality of frames selected in step S1 are not the last (No in step S7), and the arithmetic control unit 8 returns to step S1 and selects the 201st to 300th frames.
- the arithmetic control unit 8 executes Steps S2 to S5 using the 201st to 300th frames selected in Step S1, and displays the feature points (first pixel 31c, second pixel 32c). To decide.
- FIG. 23 is an explanatory diagram for explaining the positional relationship of pixels indicating feature points.
- the pixels indicating the six feature points first pixel 31a, second pixel 32a, first pixel 31b, second pixel 32b, first pixel 31c, second pixel 32c
- the first pixel 31a, the first pixel 31b, and the second pixel 32c are close to each other.
- the second pixel 32a, the second pixel 32b, and the first pixel 31c are in isolated positions.
- the first pixel 31a and the first pixel located closer to each other are determined based on the pixels indicating the six feature points, rather than determining the pixels indicating the gas leak estimation position in consideration of the change in the wind direction. It is considered that the accuracy of the gas leak estimated position is higher when the pixel indicating the gas leak estimated position in consideration of the change in the wind direction is determined based on the 31b and the second pixel 32c.
- the first pixel 31a, the first pixel 31b, and the second pixel 32c that are located close to each other are set as pixels within the range where the feature points are concentrated, and these pixels are used as the basis.
- the pixel 74 indicating the estimated gas leak position in consideration of the change in the wind direction is determined (step S8).
- the arithmetic control unit 8 functions as a second determination unit.
- the arithmetic control unit 8 (second determination unit) is a pixel (first pixel 31a, second pixel 32a, first pixel 31b, second pixel 32b) indicating a plurality of feature points determined in step S5.
- the pixel (the first pixel 31a, the first pixel 31b, and the second pixel 32c) within the predetermined range 75 is specified.
- the arithmetic control unit 8 sets each coordinate value of the identified pixels as a population, and determines a pixel indicating a coordinate value that is an average value or a median value of the population as a pixel indicating a gas leak estimation position.
- This pixel is a pixel 74 indicating the estimated gas leak position in consideration of changes in the wind direction. Therefore, according to the modification 8, even if a wind direction changes, it can prevent that the precision of a gas leak estimated position falls.
- the modified examples 7 and 8 the example in which 300 frames are divided into three has been described. However, it may be divided into two, or may be divided more finely than three divided up to 300 divided.
- the modified example 7 determines a pixel indicating a gas leak estimated position for each frame
- the modified example 8 determines a pixel indicating a feature point for each frame.
- the pixels (first pixel 31 and second pixel 32) indicating the feature points are determined by Modification 2 shown in FIG. 12, and the pixels indicating the gas leak estimated position are determined by Modification 3 shown in FIG. The combination to be determined.
- the specifying unit that specifies the gas area image indicating the area where the gas is drifting, and the gas is leaking
- a first determination unit that determines a pixel that indicates a gas leak estimated position that is estimated as a position from among a plurality of pixels that form an outline of the gas region image.
- the gas leakage position is included in the gas region image.
- the present inventor believes that the gas leaking from the monitoring region (which can also be referred to as a monitoring target) fluctuates due to wind or the like, and therefore there is a possibility that the gas leakage position exists at or near the contour of the gas region image. Found it expensive. From this, the present inventor considered that it is appropriate to set any position on the contour of the gas region image as the gas leak estimation position. Therefore, the gas leak position estimation device according to the first aspect of the embodiment determines a pixel indicating the gas leak estimation position from among a plurality of pixels constituting the contour of the gas region image. Therefore, according to the gas leak position estimation apparatus according to the first aspect of the embodiment, the gas leak position can be estimated using the gas region image.
- the first determination unit determines a pixel indicating a feature point of the gas region image from a plurality of pixels constituting an outline of the gas region image, and the gas leakage from the feature point. A pixel indicating the estimated position is determined.
- a pixel indicating a feature point of a gas region image is a pixel indicating an estimated position of gas leakage rather than a pixel indicating other than the feature point among a plurality of pixels constituting the contour of the gas region image. I think it is expensive. Therefore, in this configuration, a pixel indicating the estimated gas leak position is determined from the feature points.
- the image processing apparatus further includes a first calculation unit that calculates a regression line indicating a relationship between positions of the plurality of pixels constituting the gas region image, and the first determination unit includes the regression line and the contour. At least one of the first pixel and the second pixel located at two points where and intersect is determined as a pixel indicating the feature point.
- the regression line is a line that approximates the position of each of the plurality of pixels constituting the gas region image.
- at least one of the pixels (first pixel and second pixel) indicating two points where the regression line and the outline of the gas region image intersect is set as a pixel indicating the feature point of the gas region image.
- the above configuration further includes a setting unit that has four sides in contact with the gas region image and sets a circumscribed rectangle that is a rectangle that surrounds the gas region image, and the first determining unit includes two sides of the circumscribed rectangle. At least one of the first pixel and the second pixel located at two points where one short side and the gas region image are in contact is determined as a pixel indicating the feature point.
- the circumscribed rectangle is a rectangle that approximates the gas region image.
- Gas leaking from the monitoring region (monitoring target) does not spread evenly in all directions while the wind direction is constant, but tends to spread along one direction. For this reason, there is a high possibility that the gas leak position exists on one short side of the two short sides of the circumscribed rectangle.
- at least one of the pixels (first pixel and second pixel) indicating two points where the two short sides of the circumscribed rectangle are in contact with the gas region image is a pixel indicating the characteristic point of the gas region image.
- the setting unit sets the circumscribed rectangle having the smallest area among the circumscribed rectangles as the circumscribed rectangle.
- the circumscribed rectangle that most closely approximates the gas region image is preferably set as the circumscribed rectangle.
- the circumscribed rectangle having the smallest area is the circumscribed rectangle that most closely approximates the gas region image. In this configuration, the circumscribed rectangle having the smallest area is set as the circumscribed rectangle.
- a first extraction unit that extracts an instantaneous gas region image indicating a region where the gas drifts at the time when each image is captured from each of the plurality of images arranged in time series, and the plurality of the plurality of the images
- a process of adding pixel values of pixels at the same position is performed to generate a cumulative gas region image that is an image obtained by accumulating the plurality of instantaneous gas region images.
- a generating unit that specifies the accumulated gas region image after binarization processing as the gas region image.
- This configuration specifies an outline using a cumulative gas region image which is a kind of gas region image.
- the pixel value may be binary or multi-valued.
- a first extraction unit that extracts an instantaneous gas region image indicating a region where the gas drifts at the time when each image is captured from each of the plurality of images arranged in time series, and the plurality of the plurality of the images
- a cumulative gas region image which is an image obtained by accumulating the plurality of instantaneous gas region images, by adding pixel values of pixels at the same position is included.
- a generating unit that generates a cumulative image; a second extracting unit that performs extraction processing based on a predetermined threshold value from a plurality of pixels constituting the cumulative image; and the threshold value
- a first calculation unit that performs a calculation process for calculating the center of gravity of an image composed of the extracted pixels, and the second extraction unit sets each of the two or more threshold values having different values.
- the calculation unit of 1 performs the calculation process on the image corresponding to each of the two or more threshold values having different values, thereby calculating the two or more centroids, and the gas leak position estimation device Further includes a second calculation unit that calculates a regression line indicating a relationship between positions of two or more of the centroids, and the specifying unit uses the accumulated gas region image after binarization processing as the gas Specifying as a region image, the first determination unit indicates at least one of the first pixel and the second pixel located at two points where the regression line and the contour intersect with each other to indicate the feature point Determined as a pixel.
- At least one of the pixels (first pixel and second pixel) indicating two points where the regression line and the outline of the gas region image intersect is set as a pixel indicating the feature point of the gas region image.
- the number of pixels that are characteristic points of the gas region image is narrowed down from among a plurality of pixels constituting the contour of the gas region image.
- there is a regression line calculated based on the gas region image that is, a regression line indicating the relationship between the positions of a plurality of pixels constituting the gas region image). The regression line is calculated based on
- a pixel having the largest pixel value among a plurality of pixels constituting the gas region image or a pixel indicating the center of gravity of the gas region image is set as a target pixel, and the first pixel and When the distance to the target pixel is shorter than the distance between the second pixel and the target pixel, the first pixel is determined as a pixel indicating the gas leak estimation position, and the second pixel and the When the distance to the target pixel is shorter than the distance between the first pixel and the target pixel, the second determination unit further determines the second pixel as a pixel indicating the gas leak estimation position.
- the pixel of interest is a pixel having the largest pixel value among a plurality of pixels constituting the gas region image, or a pixel indicating the center of gravity of the gas region image. Therefore, in the region where the gas leaked from the monitoring object is drifting, the gas concentration is high in the portion corresponding to the target pixel.
- a pixel closer to the target pixel is set as a pixel indicating a gas leak estimation position.
- the lower pixel of the first pixel or the second pixel is determined as a pixel indicating the gas leak estimation position
- a second determination that determines a pixel having a higher position among the first pixel and the second pixel as a pixel indicating the estimated gas leak position.
- the gas leaked from the monitoring object goes from the bottom to the top.
- the density of the gas is higher than the density of the air (for example, Freon gas)
- the gas leaked from the monitoring target goes from top to bottom.
- a pixel having the largest pixel value among a plurality of pixels constituting the gas region image or a pixel indicating the center of gravity of the gas region image is set as a target pixel
- the first pixel and A first line segment that intersects a line connecting the second pixel and has both ends located on the contour and is located between the first pixel and the target pixel is the first line segment.
- Crossing a line connecting the pixel and the second pixel, having both ends located on the contour, shorter than the second line segment located between the second pixel and the target pixel When the first pixel is determined as a pixel indicating the gas leak estimated position and the second line segment is shorter than the first line segment, the second pixel is determined as the gas leak estimated position.
- a second determining unit that determines the pixel to indicate.
- a pixel having the largest pixel value among a plurality of pixels constituting the gas region image or a pixel indicating the center of gravity of the gas region image is set as a target pixel, and the first pixel and The gas region image is divided into a first divided image including the first pixel and a second pixel including the second pixel by a dividing line passing through the pixel of interest intersecting with a line connecting the second pixel.
- the first pixel is determined as a pixel indicating the gas leak estimation position
- the 2nd determination part which determines the 2nd pixel as a pixel which shows the gas leak presumed position.
- a pixel having the largest pixel value among a plurality of pixels constituting the gas region image or a pixel indicating the center of gravity of the gas region image is set as a target pixel, and the first pixel and The gas region image is divided into a first divided image including the first pixel and a second pixel including the second pixel by a dividing line passing through the target pixel and intersecting a line connecting the second pixel.
- the first pixel is determined as a pixel indicating the estimated gas leak position
- the 2nd determination part which determines a said 2nd pixel as a pixel which shows the said gas leak estimated position is further provided.
- the second determination unit determines a pixel indicating the gas leak estimated position for each of the plurality of gas region images arranged in time series, and indicates the determined plurality of gas leak estimated positions.
- a pixel indicating the gas leak estimated position for each of the plurality of gas region images arranged in time series, and indicates the determined plurality of gas leak estimated positions.
- coordinate values of pixels indicating the plurality of first gas leak estimated positions are set as a population, and an average value of the population or The pixel indicating the coordinate value serving as the median value is determined as the pixel indicating the second gas leak estimated position.
- the pixel indicating the second gas leak estimated position is determined based on a plurality of pixels indicating the first gas leak estimated position.
- the pixels indicating the plurality of first gas leak estimated positions are pixels indicating the gas leak estimated positions obtained from each of the plurality of gas region images arranged in time series.
- the second gas leak estimation position is a gas leak estimation position that is less affected by changes in the wind direction. That is, the second gas leak estimated position is a gas leak estimated position that is not separated from the gas leak position even if the wind direction changes. Therefore, according to this structure, even if a wind direction changes, it can prevent that the precision of a gas leak estimated position falls.
- the first determination unit determines the first pixel and the second pixel for each of the plurality of gas region images arranged in time series, and the second determination unit Among the plurality of first pixels and the plurality of second pixels determined by the first determination unit, the coordinate values of the pixels within the range where the feature points are concentrated are used as a population.
- the pixel indicating the coordinate value which is set and indicates the average value or median value of the population is determined as the pixel indicating the gas leak estimation position.
- a pixel indicating a gas leak estimated position is determined based on pixels (first pixel and second pixel) indicating feature points obtained from each of a plurality of gas region images arranged in time series. For this reason, the gas leak estimated position is a gas leak estimated position that is not separated from the gas leak position even if the wind direction changes. Therefore, according to this structure, even if a wind direction changes, it can prevent that the precision of a gas leak estimated position falls.
- a display control unit for displaying the image of the monitoring area on which the gas leak estimation position is displayed on a display unit
- the positional relationship between the estimated gas leak position and the monitoring area can be known.
- the gas leak position estimation method includes a first step of identifying a gas region image indicating a region where gas is drifting in an image obtained by photographing a monitoring region, and the gas leaks.
- the gas leak position estimation method according to the second aspect of the embodiment has the same effects as the gas leak position estimation apparatus according to the first aspect of the embodiment.
- a gas leakage position estimation program includes a first step of identifying a gas region image indicating a region where gas is drifting in an image obtained by photographing a monitoring region, and the gas leakage. And causing the computer to execute a second step of determining, from among a plurality of pixels constituting the outline of the gas region image, a pixel indicating the estimated gas leak position.
- the gas leak position estimation program according to the third aspect of the embodiment has the same effects as the gas leak position estimation apparatus according to the first aspect of the embodiment.
- the gas leak position estimation apparatus specifies a gas region image indicating a region where gas is drifting in an image obtained by photographing a monitoring region, and estimates that the gas is leaking.
- the control area for determining a pixel indicating the estimated gas leak position from among a plurality of pixels constituting the outline of the gas area image, and the image of the monitoring area showing the estimated gas leak position And a display unit for displaying.
- the gas leak position estimation apparatus has the same operational effects as the gas leak position estimation apparatus according to the first aspect of the embodiment.
- the positional relationship between the gas leak estimate position and the monitoring region can be understood.
- a gas leak position estimation device a gas leak position estimation method, and a gas leak position estimation program can be provided.
Abstract
Description
実施形態の第1の局面に係るガス漏れ位置推定装置は、監視領域を撮影した画像の中において、ガスが漂っている領域を示すガス領域像を特定する特定部と、前記ガスが漏れている位置と推定されるガス漏れ推定位置を示す画素を、前記ガス領域像の輪郭を構成する複数の画素の中から決定する第1の決定部と、を備える。
Claims (18)
- 監視領域を撮影した画像の中において、ガスが漂っている領域を示すガス領域像を特定する特定部と、
前記ガスが漏れている位置と推定されるガス漏れ推定位置を示す画素を、前記ガス領域像の輪郭を構成する複数の画素の中から決定する第1の決定部と、を備えるガス漏れ位置推定装置。 - 前記第1の決定部は、前記ガス領域像の特徴点を示す画素を前記ガス領域像の輪郭を構成する複数の画素の中から決定し、前記特徴点の中から前記ガス漏れ推定位置を示す画素を決定する請求項1に記載のガス漏れ位置推定装置。
- 前記ガス領域像を構成する複数の画素のそれぞれの位置の関係を示す回帰線を算出する第1の算出部をさらに備え、
前記第1の決定部は、前記回帰線と前記輪郭とが交差する二点に位置する第1の画素及び第2の画素の少なくとも一方の画素を、前記特徴点を示す画素として決定する請求項2に記載のガス漏れ位置推定装置。 - 前記ガス領域像と接する四辺を有しており、前記ガス領域像を囲む長方形である外接長方形を設定する設定部をさらに備え、
前記第1の決定部は、前記外接長方形の二つの短辺と前記ガス領域像とが接する二点に位置する第1の画素及び第2の画素の少なくとも一方の画素を、前記特徴点を示す画素として決定する請求項2に記載のガス漏れ位置推定装置。 - 前記設定部は、前記外接長方形のうち、最小の面積を有する前記外接長方形を、前記外接長方形として設定する請求項4に記載のガス漏れ位置推定装置。
- 時系列に並ぶ複数の前記画像のそれぞれから、各画像が撮影された時点で前記ガスが漂っている領域を示す瞬時ガス領域像を抽出する第1の抽出部と、
複数の前記画像のそれぞれから抽出された複数の前記瞬時ガス領域像において、同じ位置の画素の画素値を加算する処理をして、複数の前記瞬時ガス領域像を累積した像である累積ガス領域像を生成する生成部と、をさらに備え、
前記特定部は、二値化処理後の前記累積ガス領域像を、前記ガス領域像として特定する請求項3~5のいずれか一項に記載のガス漏れ位置推定装置。 - 時系列に並ぶ複数の前記画像のそれぞれから、各画像が撮影された時点で前記ガスが漂っている領域を示す瞬時ガス領域像を抽出する第1の抽出部と、
複数の前記画像のそれぞれから抽出された複数の前記瞬時ガス領域像において、同じ位置の画素の画素値を加算する処理をして、複数の前記瞬時ガス領域像を累積した像である累積ガス領域像を含む累積画像を生成する生成部と、
前記累積画像を構成する複数の画素から、所定のしきい値を基にして、画素を抽出する抽出処理をする第2の抽出部と、
前記しきい値で抽出された画素で構成される像の重心を算出する算出処理をする第1の算出部と、をさらに備え、
前記第2の抽出部は、異なる値の二以上の前記しきい値のそれぞれを基にして、前記抽出処理をし、
前記第1の算出部は、異なる値の二以上の前記しきい値のそれぞれに対応する前記像に対して、前記算出処理をすることにより、二以上の前記重心を算出し、
前記ガス漏れ位置推定装置は、二以上の前記重心のそれぞれの位置の関係を示す回帰線を算出する第2の算出部を、さらに備え、
前記特定部は、二値化処理後の前記累積ガス領域像を、前記ガス領域像として特定し、
前記第1の決定部は、前記回帰線と前記輪郭とが交差する二点に位置する第1の画素及び第2の画素の少なくとも一方の画素を、前記特徴点を示す画素として決定する請求項2に記載のガス漏れ位置推定装置。 - 前記ガス領域像を構成する複数の画素の中で、画素値が一番大きい画素、又は、前記ガス領域像の重心を示す画素を注目画素として設定し、前記第1の画素と前記注目画素との距離が、前記第2の画素と前記注目画素との距離より短いとき、前記第1の画素を、前記ガス漏れ推定位置を示す画素と決定し、前記第2の画素と前記注目画素との距離が、前記第1の画素と前記注目画素との距離より短いとき、前記第2の画素を、前記ガス漏れ推定位置を示す画素と決定する第2の決定部をさらに備える請求項3~7のいずれか一項に記載のガス漏れ位置推定装置。
- 前記ガスの密度が空気の密度より低いとき、前記第1の画素又は前記第2の画素のうち、位置が低い方の画素を、前記ガス漏れ推定位置を示す画素と決定し、前記ガスの密度が前記空気の密度より高いとき、前記第1の画素又は前記第2の画素のうち、位置が高い方の画素を、前記ガス漏れ推定位置を示す画素と決定する第2の決定部をさらに備える請求項3~7のいずれか一項に記載のガス漏れ位置推定装置。
- 前記ガス領域像を構成する複数の画素の中で、画素値が一番大きい画素、又は、前記ガス領域像の重心を示す画素を注目画素として設定し、
前記第1の画素と前記第2の画素とを結ぶ線と交差して、前記輪郭上に位置する両端を有し、前記第1の画素と前記注目画素との間に位置する第1の線分が、前記第1の画素と前記第2の画素とを結ぶ線と交差して、前記輪郭上に位置する両端を有し、前記第2の画素と前記注目画素との間に位置する第2の線分より短いとき、前記第1の画素を、前記ガス漏れ推定位置を示す画素と決定し、前記第2の線分が前記第1の線分より短いとき、前記第2の画素を、前記ガス漏れ推定位置を示す画素と決定する第2の決定部をさらに備える請求項3~7のいずれか一項に記載のガス漏れ位置推定装置。 - 前記ガス領域像を構成する複数の画素の中で、画素値が一番大きい画素、又は、前記ガス領域像の重心を示す画素を注目画素として設定し、
前記第1の画素と前記第2の画素とを結ぶ線と交差して、前記注目画素を通る分割線によって、前記ガス領域像を前記第1の画素を含む第1の分割像と前記第2の画素を含む第2の分割像とに二分割し、
前記第1の分割像の面積が前記第2の分割像の面積より小さいとき、前記第1の画素を、前記ガス漏れ推定位置を示す画素と決定し、前記第2の分割像の面積が前記第1の分割像の面積より小さいとき、前記第2の画素を、前記ガス漏れ推定位置を示す画素と決定する第2の決定部をさらに備える請求項3~7のいずれか一項に記載のガス漏れ位置推定装置。 - 前記ガス領域像を構成する複数の画素の中で、画素値が一番大きい画素、又は、前記ガス領域像の重心を示す画素を注目画素として設定し、
前記第1の画素と前記第2の画素とを結ぶ線と交差して、前記注目画素を通る分割線によって、前記ガス領域像を前記第1の画素を含む第1の分割像と前記第2の画素を含む第2の分割像とに二分割し、
前記第1の分割像の輪郭が前記第2の分割像の輪郭より小さいとき、前記第1の画素を、前記ガス漏れ推定位置を示す画素と決定し、前記第2の分割像の輪郭が前記第1の分割像の輪郭より小さいとき、前記第2の画素を、前記ガス漏れ推定位置を示す画素と決定する第2の決定部をさらに備える請求項3~7のいずれか一項に記載のガス漏れ位置推定装置。 - 前記第2の決定部は、時系列に並ぶ複数の前記ガス領域像のそれぞれについて、前記ガス漏れ推定位置を示す画素を決定し、決定した複数の前記ガス漏れ推定位置を示す画素を、複数の第1のガス漏れ推定位置を示す画素として設定し、
複数の前記第1のガス漏れ推定位置を示す画素のそれぞれの座標値を母集団として設定し、
前記母集団の平均値又は中央値となる座標値を示す画素を、第2のガス漏れ推定位置を示す画素と決定する請求項8~12のいずれか一項に記載のガス漏れ位置推定装置。 - 前記第1の決定部は、時系列に並ぶ複数の前記ガス領域像のそれぞれについて、前記第1の画素及び前記第2の画素を決定し、
前記第2の決定部は、前記第1の決定部によって決定された複数の前記第1の画素及び複数の前記第2の画素の中から、前記特徴点が集中している範囲内にある画素のそれぞれの座標値を母集団として設定し、前記母集団の平均値又は中央値となる座標値を示す画素を、前記ガス漏れ推定位置を示す画素と決定する請求項8~12のいずれか一項に記載のガス漏れ位置推定装置。 - 前記ガス漏れ推定位置が示されている、前記監視領域の前記画像を表示部に表示させる表示制御部をさらに備える請求項1~14のいずれか一項に記載のガス漏れ位置推定装置。
- 監視領域を撮影した画像の中において、ガスが漂っている領域を示すガス領域像を特定する第1のステップと、
前記ガスが漏れている位置と推定されるガス漏れ推定位置を示す画素を、前記ガス領域像の輪郭を構成する複数の画素の中から決定する第2のステップと、を備えるガス漏れ位置推定方法。 - 監視領域を撮影した画像の中において、ガスが漂っている領域を示すガス領域像を特定する第1のステップと、
前記ガスが漏れている位置と推定されるガス漏れ推定位置を示す画素を、前記ガス領域像の輪郭を構成する複数の画素の中から決定する第2のステップと、をコンピューターに実行させるガス漏れ位置推定プログラム。 - 監視領域を撮影した画像の中において、ガスが漂っている領域を示すガス領域像を特定し、前記ガスが漏れている位置と推定されるガス漏れ推定位置を示す画素を、前記ガス領域像の輪郭を構成する複数の画素の中から決定する演算制御部と、
前記ガス漏れ推定位置を示されている、前記監視領域の前記画像を表示する表示部と、を備えるガス漏れ位置推定装置。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/080,388 US10739226B2 (en) | 2016-03-03 | 2017-02-28 | Gas leak position estimation device, gas leak position estimation method and gas leak position estimation program |
EP17760029.3A EP3425364B1 (en) | 2016-03-03 | 2017-02-28 | Gas leak position estimation device, gas leak position estimation method, and gas leak position estimation program |
JP2018503348A JP6620878B2 (ja) | 2016-03-03 | 2017-02-28 | ガス漏れ位置推定装置、ガス漏れ位置推定方法及びガス漏れ位置推定プログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016041171 | 2016-03-03 | ||
JP2016-041171 | 2016-03-03 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017150565A1 true WO2017150565A1 (ja) | 2017-09-08 |
Family
ID=59742929
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2017/007951 WO2017150565A1 (ja) | 2016-03-03 | 2017-02-28 | ガス漏れ位置推定装置、ガス漏れ位置推定方法及びガス漏れ位置推定プログラム |
Country Status (4)
Country | Link |
---|---|
US (1) | US10739226B2 (ja) |
EP (1) | EP3425364B1 (ja) |
JP (1) | JP6620878B2 (ja) |
WO (1) | WO2017150565A1 (ja) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019058863A1 (ja) * | 2017-09-21 | 2019-03-28 | コニカミノルタ株式会社 | ガス検知用画像処理装置、ガス検知用画像処理方法、及び、ガス検知用画像処理プログラム |
WO2019058864A1 (ja) * | 2017-09-21 | 2019-03-28 | コニカミノルタ株式会社 | ガス検査レポート作成支援装置、ガス検査レポート作成支援方法、及び、ガス検査レポート作成支援プログラム |
JPWO2020039606A1 (ja) * | 2018-08-20 | 2021-08-26 | コニカミノルタ株式会社 | ガス検出装置、情報処理装置およびプログラム |
KR102517477B1 (ko) * | 2022-07-20 | 2023-04-05 | (주)하이브시스템 | 인공지능 기반 유해 가스 누출 원점을 식별하는 방법 및 장치 |
KR102517478B1 (ko) * | 2022-07-20 | 2023-04-05 | (주)하이브시스템 | 인공지능 기반 유해 가스 누출 여부를 결정하는 방법 및 장치 |
WO2024019342A1 (ko) * | 2022-07-20 | 2024-01-25 | (주)하이브시스템 | 인공지능 기반 유해 가스 누출 탐지 시스템 및 이의 동작 방법 |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020021785A1 (ja) * | 2018-07-25 | 2020-01-30 | コニカミノルタ株式会社 | ガス検出装置、ガス検出方法、表示制御方法、およびプログラム |
US10697947B1 (en) * | 2019-01-23 | 2020-06-30 | Project Canary, Inc. | Apparatus and methods for reducing fugitive gas emissions at oil facilities |
US10970852B2 (en) * | 2019-04-01 | 2021-04-06 | Alloy Surfaces Company, Inc. | Systems and methods for multi-signature countermeasure testing |
DE102021100405A1 (de) * | 2021-01-12 | 2022-07-14 | Inficon Gmbh | Verfahren zur Detektion von aus einem Prüfling austretendem Prüfgas mit einem optischen Sensor |
CN113781568B (zh) * | 2021-11-11 | 2022-02-08 | 南京智谱科技有限公司 | 一种图像的流体泄漏点的确定方法及装置 |
US11686675B2 (en) * | 2021-11-19 | 2023-06-27 | Rebellion Photonics, Inc. | Systems, methods, and computer program products for infrared imaging operations |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5215385A (en) * | 1975-07-25 | 1977-02-04 | Hitachi Ltd | Image recognizer |
JPS63246638A (ja) * | 1987-04-01 | 1988-10-13 | Tokyo Gas Co Ltd | 流体の漏洩の広域監視方法 |
JPH08122197A (ja) * | 1994-10-21 | 1996-05-17 | Osaka Gas Co Ltd | 画像による漏出検知方法及び装置 |
JP2000310577A (ja) * | 1999-04-27 | 2000-11-07 | Toshiba Corp | 漏洩量測定装置および漏洩量測定方法 |
JP2012058093A (ja) | 2010-09-09 | 2012-03-22 | Mitsubishi Electric Building Techno Service Co Ltd | ガス漏れ検出装置 |
JP2013190229A (ja) * | 2012-03-12 | 2013-09-26 | Chugoku Electric Power Co Inc:The | チューブリーク検査装置、及びチューブリーク検査方法 |
JP2014055898A (ja) * | 2012-09-13 | 2014-03-27 | Mitsubishi Heavy Ind Ltd | 表示システム、表示方法及び制御プログラム |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SE526421C2 (sv) * | 2003-09-02 | 2005-09-13 | Gasoptics Sweden Ab | Lokalisering av en visualiserad gasläckas punktkälla |
US7375814B2 (en) * | 2005-03-11 | 2008-05-20 | Sandia Corporation | Natural gas leak mapper |
US7358860B2 (en) | 2005-03-31 | 2008-04-15 | American Air Liquide, Inc. | Method and apparatus to monitor and detect cryogenic liquefied gas leaks |
US8941734B2 (en) * | 2009-07-23 | 2015-01-27 | International Electronic Machines Corp. | Area monitoring for detection of leaks and/or flames |
US9879976B2 (en) * | 2010-01-20 | 2018-01-30 | Faro Technologies, Inc. | Articulated arm coordinate measurement machine that uses a 2D camera to determine 3D coordinates of smoothly continuous edge features |
KR101131095B1 (ko) * | 2011-06-10 | 2012-04-02 | 주식회사 창성에이스산업 | 가스누설감지 시스템 및 방법 |
JP5481498B2 (ja) * | 2012-01-12 | 2014-04-23 | 住友化学株式会社 | グリーンハニカム成形体の欠陥を検査する方法、グリーンハニカム構造体の製造方法及びグリーンハニカム成形体の欠陥の検査装置 |
US9225915B2 (en) * | 2012-07-06 | 2015-12-29 | Providence Photonics, Llc | Calibration and quantification method for gas imaging camera |
CN104007240B (zh) * | 2014-06-13 | 2015-08-26 | 重庆大学 | 一种基于双目识别与电子鼻网络气体检测的融合定位技术 |
US9726543B2 (en) * | 2015-02-18 | 2017-08-08 | Providence Photonics, Llc | Apparatus and method for validating leak survey results |
WO2016138991A1 (en) * | 2015-03-02 | 2016-09-09 | Flir Systems Ab | Quantifying gas in passive optical gas imaging |
JP2016206139A (ja) * | 2015-04-28 | 2016-12-08 | コニカミノルタ株式会社 | ガス検出装置 |
US9995647B2 (en) * | 2015-09-30 | 2018-06-12 | General Monitors, Inc. | Ultrasonic gas leak location system and method |
JP6773043B2 (ja) * | 2015-10-29 | 2020-10-21 | コニカミノルタ株式会社 | 漏洩ガス検出装置および漏洩ガス検出方法 |
US10732014B2 (en) * | 2016-12-20 | 2020-08-04 | Picarro, Inc. | Emission quantification using a line scan of gas concentration data |
US10386260B2 (en) * | 2017-03-07 | 2019-08-20 | Accenture Global Solutions Limited | Leak detection for fluid distribution networks using hyperspectral imaging |
EP3596308B1 (en) * | 2017-03-16 | 2022-11-16 | Multisensor Scientific, Inc. | Scanning ir sensor for gas safety and emissions monitoring |
-
2017
- 2017-02-28 JP JP2018503348A patent/JP6620878B2/ja active Active
- 2017-02-28 WO PCT/JP2017/007951 patent/WO2017150565A1/ja active Application Filing
- 2017-02-28 EP EP17760029.3A patent/EP3425364B1/en active Active
- 2017-02-28 US US16/080,388 patent/US10739226B2/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5215385A (en) * | 1975-07-25 | 1977-02-04 | Hitachi Ltd | Image recognizer |
JPS63246638A (ja) * | 1987-04-01 | 1988-10-13 | Tokyo Gas Co Ltd | 流体の漏洩の広域監視方法 |
JPH08122197A (ja) * | 1994-10-21 | 1996-05-17 | Osaka Gas Co Ltd | 画像による漏出検知方法及び装置 |
JP2000310577A (ja) * | 1999-04-27 | 2000-11-07 | Toshiba Corp | 漏洩量測定装置および漏洩量測定方法 |
JP2012058093A (ja) | 2010-09-09 | 2012-03-22 | Mitsubishi Electric Building Techno Service Co Ltd | ガス漏れ検出装置 |
JP2013190229A (ja) * | 2012-03-12 | 2013-09-26 | Chugoku Electric Power Co Inc:The | チューブリーク検査装置、及びチューブリーク検査方法 |
JP2014055898A (ja) * | 2012-09-13 | 2014-03-27 | Mitsubishi Heavy Ind Ltd | 表示システム、表示方法及び制御プログラム |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019058863A1 (ja) * | 2017-09-21 | 2019-03-28 | コニカミノルタ株式会社 | ガス検知用画像処理装置、ガス検知用画像処理方法、及び、ガス検知用画像処理プログラム |
WO2019058864A1 (ja) * | 2017-09-21 | 2019-03-28 | コニカミノルタ株式会社 | ガス検査レポート作成支援装置、ガス検査レポート作成支援方法、及び、ガス検査レポート作成支援プログラム |
JPWO2019058863A1 (ja) * | 2017-09-21 | 2020-09-10 | コニカミノルタ株式会社 | ガス検知用画像処理装置、ガス検知用画像処理方法、及び、ガス検知用画像処理プログラム |
JPWO2019058864A1 (ja) * | 2017-09-21 | 2020-09-10 | コニカミノルタ株式会社 | ガス検査レポート作成支援装置、ガス検査レポート作成支援方法、及び、ガス検査レポート作成支援プログラム |
JP7156291B2 (ja) | 2017-09-21 | 2022-10-19 | コニカミノルタ株式会社 | ガス検査レポート作成支援装置、ガス検査レポート作成支援方法、及び、ガス検査レポート作成支援プログラム |
JP7230813B2 (ja) | 2017-09-21 | 2023-03-01 | コニカミノルタ株式会社 | ガス検知用画像処理装置、ガス検知用画像処理方法、及び、ガス検知用画像処理プログラム |
JPWO2020039606A1 (ja) * | 2018-08-20 | 2021-08-26 | コニカミノルタ株式会社 | ガス検出装置、情報処理装置およびプログラム |
JP7294343B2 (ja) | 2018-08-20 | 2023-06-20 | コニカミノルタ株式会社 | ガス検出装置、情報処理装置およびプログラム |
KR102517477B1 (ko) * | 2022-07-20 | 2023-04-05 | (주)하이브시스템 | 인공지능 기반 유해 가스 누출 원점을 식별하는 방법 및 장치 |
KR102517478B1 (ko) * | 2022-07-20 | 2023-04-05 | (주)하이브시스템 | 인공지능 기반 유해 가스 누출 여부를 결정하는 방법 및 장치 |
WO2024019342A1 (ko) * | 2022-07-20 | 2024-01-25 | (주)하이브시스템 | 인공지능 기반 유해 가스 누출 탐지 시스템 및 이의 동작 방법 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2017150565A1 (ja) | 2018-12-27 |
EP3425364B1 (en) | 2020-09-23 |
EP3425364A1 (en) | 2019-01-09 |
EP3425364A4 (en) | 2019-02-27 |
US10739226B2 (en) | 2020-08-11 |
US20190078966A1 (en) | 2019-03-14 |
JP6620878B2 (ja) | 2019-12-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6620878B2 (ja) | ガス漏れ位置推定装置、ガス漏れ位置推定方法及びガス漏れ位置推定プログラム | |
JP6319527B2 (ja) | ガス検知用画像処理装置、ガス検知用画像処理方法、ガス検知用画像処理プログラム、ガス検知用画像処理プログラムを記録したコンピュータ読み取り可能な記録媒体、及び、ガス検知システム | |
EP3957969A1 (en) | Image processing device for gas detection, image processing method for gas detection and image processing program for gas detection | |
JPWO2017104607A1 (ja) | ガス濃度厚み積測定装置、ガス濃度厚み積測定方法、ガス濃度厚み積測定プログラム、及び、ガス濃度厚み積測定プログラムを記録したコンピュータ読み取り可能な記録媒体 | |
JP2014059875A5 (ja) | ||
JP6493624B2 (ja) | ガス検知用画像処理装置、ガス検知用画像処理方法及びガス検知用画像処理プログラム | |
KR20170056860A (ko) | 이미지 생성 방법 및 장치 | |
US10997734B2 (en) | Gas detection-use image processing device, gas detection-use image processing method, and gas detection-use image processing program | |
JP6579291B2 (ja) | ガス検知用画像処理装置、ガス検知用画像処理方法、及び、ガス検知用画像処理プログラム | |
US9305233B2 (en) | Isotropic feature matching | |
JP6693609B1 (ja) | ガス流量推定装置、ガス流量推定方法、及び、ガス流量推定プログラム | |
CN102131078B (zh) | 一种视频图像校正方法和系统 | |
WO2020110411A1 (ja) | ガス流量推定装置、ガス流量推定方法、及び、ガス流量推定プログラム | |
JP2011154634A (ja) | 画像処理装置、画像処理方法及び画像処理用プログラム | |
JP7302605B2 (ja) | 漏洩源特定支援装置、漏洩源特定支援方法、及び、漏洩源特定支援プログラム | |
JP2019184485A (ja) | ガス検知用画像処理装置、ガス検知用画像処理方法、及び、ガス検知用画像処理プログラム | |
US10991090B2 (en) | Gas detection-use image processing device, gas detection-use image processing method, and gas detection-use image processing program | |
JP6838605B2 (ja) | 画像処理装置、画像処理方法、画像処理プログラム、及び、ガス検知システム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2018503348 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2017760029 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2017760029 Country of ref document: EP Effective date: 20181004 |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17760029 Country of ref document: EP Kind code of ref document: A1 |