JP7036112B2 - Gas leak position estimation device, gas leak position estimation method and gas leak position estimation program - Google Patents

Description

The present invention relates to a technique for estimating a gas leak position using an infrared image.

When a gas leak occurs, a slight temperature change occurs in the area where the leaked gas is floating. As a technique for detecting gas using this principle, gas detection using an infrared image is known.

As gas detection using an infrared image, for example, Patent Document 1 includes an infrared camera that captures an inspection target area and an image processing unit that processes an infrared image captured by the infrared camera, and performs image processing. The unit discloses a gas leak detection device having a fluctuation extraction unit that extracts dynamic fluctuations due to gas leakage from a plurality of infrared images arranged in time series.

When a gas leak is detected in a plant or the like, the worker needs to go to the gas leak position and repair the gas leak. In the gas detection using an infrared image, an image including a gas region image showing a region where the leaked gas is floating is displayed on the display unit. The worker searches for the gas leak position by using the gas area image as a clue.

However, at present, the estimation of the gas leak position based on the gas region image (hereinafter referred to as the gas region) cannot obtain sufficient accuracy. This is because, as described above, the gas region is a surface and the gas leak position is a point. In particular, when gas is leaking from one of a plurality of dense objects (for example, dense piping, dense structure), the estimation accuracy of the gas leak position is not good. This is because the dense objects are very close to each other or partially overlap on the image, so that the gas region and the image of the dense objects overlap.

Japanese Unexamined Patent Publication No. 2012-58093

An object of the present invention is to provide a gas leak position estimation device, a gas leak position estimation method, and a gas leak position estimation program that can improve the estimation accuracy of a gas leak position based on a gas region.

In order to realize the above-mentioned object, the gas leak position estimation device reflecting one aspect of the present invention includes a first processing unit and a determination unit. The first processing unit generates a plurality of first images by performing a process of extracting a gas region from each of the plurality of infrared images captured in time series. The determination unit is included in the first infrared image included in the plurality of infrared images and used for generating the first image having the gas region, and included in the plurality of infrared images and the gas region. The gas leak position is determined based on the second infrared image used for generating the first image having no effect.

The advantages and features provided by one or more embodiments of the invention are fully understood from the detailed description and accompanying drawings provided below. These detailed description and accompanying drawings are given by way of example only and are not intended as a limitation definition of the present invention.

It is a block diagram which shows the structure of the gas leak position estimation system which concerns on embodiment. FIG. 3 is a block diagram showing a hardware configuration of the gas leak position estimation device shown in FIG. 1A. It is explanatory drawing explaining the time series pixel data D1. It is an image diagram which shows the infrared image which took the outdoor test place in the time series in the state that the gas leak and the temperature change of the background occur in parallel. It is a graph which shows the temperature change of the point SP1 of a test place. It is a graph which shows the temperature change of the point SP2 of a test place. It is a flowchart explaining the generation process of a surveillance image. In the graph showing the time-series pixel data D1 of the pixels corresponding to the point SP1 (FIG. 3), the low-frequency component data D2 extracted from the time-series pixel data D1, and the high-frequency component data D3 extracted from the time-series pixel data D1. be. It is a graph which shows the difference data D4. It is a graph which shows the difference data D5. It is a graph which shows the standard deviation data D6 and the standard deviation data D7. It is a graph which shows the difference data D8. It is an image diagram which shows image I10, image I11 and image I12 generated based on the frame of time T1. FIG. 3 is an image diagram showing an image I13, an image I14, and an image I15 generated based on a frame at time T2. It is a flowchart of the process executed in 1st Embodiment of Embodiment. It is a schematic diagram which shows an example of the infrared image of the monitoring target of a gas leak. It is a schematic diagram which shows an example of the frame group which comprises the moving image of the surveillance image generated by using the moving image data which consists of a plurality of infrared images (frames) including the image of three pipes. It is a schematic diagram which shows the 1st infrared image used for generating a 1st image. It is a schematic diagram which shows the 2nd infrared image used for the generation of the 1st image. It is a schematic diagram of an example of a difference image. It is explanatory drawing explaining the example in which the group of the 1st image which has a gas region and the group of the 1st image which does not have a gas region are generated alternately. It is a flowchart of the process executed in the 2nd aspect of an embodiment. It is a schematic diagram which shows an example of two or more first images used for generating a second image having a cumulative gas region, and an example of a second image. It is a schematic diagram which shows an example of a 3rd image, and an example of a difference image and a 2nd image used for generating a 3rd image.

Hereinafter, one or more embodiments of the present invention will be described with reference to the drawings. However, the scope of the invention is not limited to the disclosed embodiments.

In each figure, the configurations with the same reference numerals indicate that they are the same configuration, and the description of the configurations already described will be omitted. In the present specification, when they are generically referred to, they are indicated by reference numerals without subscripts (for example, the first image Im1), and when they refer to individual configurations, they are indicated by reference numerals with subscripts (for example, first image). Image Im1-1).

FIG. 1A is a block diagram showing a configuration of a gas leak position estimation system 1 according to an embodiment. 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 an infrared image of a subject including a gas leak monitoring target (for example, a location where gas transport pipes are connected to each other), and generates a moving image data MD showing the moving image. It is not limited to moving images as long as it is a plurality of infrared images captured in time series. 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 on the two-dimensional image sensor 6. The filter 5 is arranged between the optical system 4 and the two-dimensional image sensor 6, and allows only infrared rays having a specific wavelength to pass through the light that has passed through the optical system 4. Of the infrared wavelength bands, the wavelength band through which the filter 5 is passed depends on the type of gas to be detected. For example, in the case of methane, a filter 5 that passes through a wavelength band of 3.2 to 3.4 μm is used. The two-dimensional image sensor 6 is, for example, a cooled indium antimonide (InSb) image sensor, and receives infrared rays that have passed through the filter 5. 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 MD.

The gas leak position estimation device 3 is a personal computer, a smartphone, a tablet terminal, or the like, and includes an image data input unit 8, an image processing unit 9, a display control unit 10, a display 11, and an input unit 12 as functional blocks.

The image data input unit 8 is a communication interface that communicates with a communication unit (not shown) of the infrared camera 2. The moving image data MD sent from the communication unit of the infrared camera 2 is input to the image data input unit 8. The image data input unit 8 sends the moving image data MD to the image processing unit 9.

The image processing unit 9 performs predetermined processing on the moving image data MD. The predetermined process is, for example, a process of generating time-series pixel data from the moving image data MD.

The time series pixel data will be specifically described. FIG. 2 is an explanatory diagram illustrating the time-series pixel data D1. The moving image represented by the moving image data MD has a structure in which a plurality of frames are arranged in chronological order. In a plurality of frames (a plurality of infrared images), the data in which the pixel data of the pixels at the same position are arranged in time series is referred to as time-series pixel data D1. Let K be the number of frames of the infrared image moving image. One frame is composed of M pixels, that is, the first pixel, the second pixel, ..., the M-1st pixel, and the Mth pixel. Physical quantities such as brightness and temperature are determined based on pixel data (pixel values).

Pixels at the same position in a plurality of (K) frames mean pixels in the same order. For example, when the first pixel is described, the pixel data of the first pixel included in the first frame, the pixel data of the first pixel included in the second frame, ..., K-1st frame. The data in which the pixel data of the first pixel included in the first pixel and the pixel data of the first pixel included in the Kth frame are arranged in time series is the time-series pixel data D1 of the first pixel. Further, when the M-th pixel is described, the pixel data of the M-th pixel included in the first frame, the pixel data of the M-th pixel included in the second frame, ..., K-1st frame. The data in which the pixel data of the M-th pixel included in the above and the pixel data of the M-th pixel included in the K-th frame are arranged in time series is the time-series pixel data D1 of the M-th pixel. The number of time-series pixel data D1 is the same as the number of pixels constituting one frame.

With reference to FIG. 1A, the image processing unit 9 includes a processing unit 91 and a determination unit 92. These will be described later.

The display control unit 10 causes the display 11 to display the moving image shown by the moving image data MD and the moving image that has been subjected to the predetermined processing by the image processing unit 9.

The input unit 12 receives various inputs related to gas detection. The gas leak position estimation device 3 according to the embodiment includes a display control unit 10, a display 11, and an input unit 12, but may be a gas leak position estimation device 3 that does not include these.

FIG. 1B is a block diagram showing a hardware configuration of the gas leak position estimation device 3 shown in FIG. 1A. The gas leak position estimation device 3 includes a CPU (Central Processing Unit) 3a, a RAM (Random Access Memory) 3b, a ROM (Read Only Memory) 3c, an HDD (Hard Disk Drive) 3d, a liquid crystal display 3e, a communication interface 3f, a keyboard, and the like. It is provided with 3 g and a bus 3h connecting them. The liquid crystal display 3e is hardware that realizes the display 11. Instead of the liquid crystal display 3e, an organic EL display (Organic Light Emitting Diode display), a plasma display, or the like may be used. The communication interface 3f is hardware that realizes the image data input unit 8. The keyboard and the like 3g are hardware that realizes the input unit 12. A touch panel may be used instead of the keyboard.

The HDD 3d stores, for the image processing unit 9 and the display control unit 10, a program for realizing each of these functional blocks and various data (for example, moving image data MD). The program that realizes the image processing unit 9 is a processing program that acquires the moving image data MD and performs the above-mentioned predetermined processing on the moving image data MD. The program that realizes the display control unit 10 is, for example, a display control that displays a moving image shown by the moving image data MD on the display 11 or displays a moving image that has been subjected to the predetermined processing by the image processing unit 9 on the display 11. It is a program. These programs are stored in HDD3d in advance, but are not limited thereto. For example, a recording medium (for example, an external recording medium such as a magnetic disk or an optical disk) for recording these programs may be prepared, and the program stored in the recording medium may be stored in the HDD 3d. .. Further, these programs are stored in a server connected to the gas leak position estimation device 3 via a network, and these programs may be sent to the HDD 3d and stored in the HDD 3d via the network. These programs may be stored in the ROM 3c instead of the HDD 3d. The gas leak position estimation device 3 includes a flash memory instead of the HDD 3d, and these programs may be stored in the flash memory.

The CPU 3a is an example of a hardware processor, and the image processing unit 9 and the display control unit 10 are realized by reading these programs from the HDD 3d, expanding them into the RAM 3b, and executing the expanded programs. However, with respect to the functions of the image processing unit 9 and the functions of the display control unit 10, some or all of the functions are realized by the processing by the DSP (Digital Signal Processor) instead of the processing by the CPU 3a or together with the processing by the CPU 3a. May be good. Similarly, a part or all of each function may be realized by processing by a dedicated hardware circuit in place of or in combination with processing by software.

The gas leak position estimation device 3 has a first aspect and a second aspect as described below. Each of these aspects is composed of a plurality of elements. Therefore, the HDD 3d stores a program for realizing these elements. For example, the first aspect of the gas leak position estimation device 3 includes a processing unit 91 (first processing unit) and a determination unit 92 as elements. The HDD 3d stores programs for realizing each of the processing unit 91 (first processing unit) and the determination unit 92. These programs are referred to as a first processing program and a determination program.

These programs are represented using element definitions. The first processing unit and the first processing program will be described as an example. The first processing unit generates a plurality of first images by performing a process of extracting a gas region from each of the plurality of infrared images captured in time series. The first processing program is a program that generates a plurality of first images by performing a process of extracting a gas region for each of a plurality of infrared images captured in time series.

A flowchart of these programs (first processing program, determination program, etc.) executed by the CPU 3a is shown in FIG. 12 to be described later.

In gas detection using an infrared image, the present inventor presents a background temperature when a gas leak and a background temperature change occur in parallel and the background temperature change is larger than the temperature change due to the leaked gas. We found that it was not possible to display an image of gas leaks without considering the changes. This will be explained in detail.

FIG. 3 is an image diagram showing an infrared image taken of an outdoor test site in chronological order in a state where a gas leak and a temperature change in the background occur in parallel. These are infrared images obtained by shooting a moving image with an infrared camera. At the test site, there is a point SP1 where gas can be ejected. For comparison with the point SP1, the point SP2 where the gas does not eject is shown.

Image I1 is an infrared image of the test site taken at time T1 just before the sunlight is blocked by clouds. Image I2 is an infrared image of the test location taken at time T2, 5 seconds after time T1. At time T2, the temperature of the background is lower than that at time T1 because the sunlight is blocked by clouds.

Image I3 is an infrared image of the test location taken at time T3, 10 seconds after time T1. Since the state in which the sunlight is blocked by the clouds continues from the time T2 to the time T3, the background temperature of the time T3 is lower than that of the time T2.

Image I4 is an infrared image of the test site taken at time T4, 15 seconds after time T1. Since the state in which the sunlight is blocked by the clouds continues from the time T3 to the time T4, the background temperature of the time T4 is lower than that of the time T3.

In 15 seconds from time T1 to time T4, the background temperature has dropped by about 4 ° C. Therefore, it can be seen that the image I4 is darker than the image I1 as a whole, and the temperature of the background is lowered.

At the time point SP1 after the time T1 and before the time T2, the gas ejection is started. The temperature change due to the ejected gas is slight (about 0.5 ° C.). Therefore, at time T2, time T3, and time T4, gas is ejected at the point SP1, but the temperature change in the background is much larger than the temperature change due to the ejected gas. Even if I look at I3 and image I4, I can't see how gas is coming out from point SP1.

FIG. 4A is a graph showing the temperature change at the point SP1 at the test site, and FIG. 4B is a graph showing the temperature change at the point SP2 at the test site. The vertical axis of these graphs shows the temperature. The horizontal axis of these graphs shows the order of the frames. For example, 45 means the 45th frame. The frame rate is 30 fps. Therefore, the time from the first frame to the 450th frame is 15 seconds.

The graph showing the temperature change at the point SP1 and the graph showing the temperature change at the point SP2 are different. Since no gas is ejected at the point SP2, the temperature change at the point SP2 indicates the temperature change in the background. On the other hand, since the gas is ejected at the point SP1, the gas is floating at the point SP1. Therefore, the temperature change at the point SP1 indicates the temperature change obtained by adding the temperature change in the background and the temperature change due to the leaked gas.

From the graph shown in FIG. 4A, it can be seen that the gas is ejected at the point SP1 (that is, it can be seen that the gas leak occurs at the point SP1). However, as described above, from the images I2, I3, and image I4 shown in FIG. 3, it cannot be seen that the gas is ejected at the point SP1 (that is, a gas leak occurs at the point SP1). do not know).

In this way, when the temperature change in the background is much larger than the temperature change due to the ejected gas (leaked gas), the image I2, the image I3, and the image I4 shown in FIG. 3 can be seen from the point SP1. I don't know how the gas is coming out.

The reason for this is that in the moving image data MD (FIG. 1A), in addition to the frequency component data indicating the temperature change due to the leaked gas, the frequency is lower than this frequency component data, and the low frequency component data D2 indicating the change in the background temperature. Is included. The image shown by the low frequency component data D2 (change in brightness of the background) makes the image shown by the frequency component data invisible. With reference to FIGS. 4A and 4B, the small changes contained in the graph showing the temperature change at point SP1 correspond to the frequency component data. The graph showing the temperature change at the point SP2 corresponds to the low frequency component data D2.

Therefore, the image processing unit 9 (FIG. 1A) generates a plurality of time-series pixel data D1 (that is, a plurality of time-series pixel data D1 constituting the moving image data MD) having different pixel positions from the moving image data MD. , Each of the plurality of time-series pixel data D1 is processed to remove the low frequency component data D2. With reference to FIG. 2, the plurality of time-series pixel data in which the pixel positions are different are the time-series pixel data D1 of the first pixel, the time-series pixel data D1 of the second pixel, ..., M-1st. It means the time-series pixel data D1 of the pixel and the time-series pixel data D1 of the Mth pixel.

The frequency component data having a higher frequency than the frequency of the frequency component data indicating the temperature change due to the leaked gas and indicating high frequency noise is referred to as high frequency component data D3. The image processing unit 9 performs processing for removing the high-frequency component data D3 in addition to processing for removing the low-frequency component data D2 for each of the plurality of time-series pixel data D1 constituting the moving image data MD.

As described above, the image processing unit 9 does not perform processing excluding the low frequency component data D2 and the high frequency component data D3 in the frame unit, but the low frequency component data D2 and the high frequency component data in the time series pixel data D1 unit. Process excluding D3.

The gas leak position estimation device 3 uses an infrared image to generate a surveillance image. If a gas leak has occurred, the surveillance image will include an image showing the area where the gas is appearing due to the gas leak. The gas leak position estimation device 3 detects a gas leak based on the monitoring image. There are various methods for generating a surveillance image, but here, an example of a method for generating a surveillance image will be described. The surveillance image is generated using an infrared image of the surveillance target and the background. FIG. 5 is a flowchart illustrating a process of generating a surveillance image.

With reference to FIGS. 1A, 2 and 5, the image processing unit 9 generates M time-series pixel data D1 from the moving image data MD (step S1).

The image processing unit 9 calculates data extracted from the time-series pixel data D1 by calculating a simple moving average in units of a first predetermined number of frames, which is less than K frames, with respect to the time-series pixel data D1. Is the low frequency component data D2, and M low frequency component data D2 corresponding to each of the M time series pixel data D1 are extracted (step S2).

The first predetermined number of frames is, for example, 21 frames. The breakdown is the target frame, 10 consecutive frames before this, and 10 consecutive frames after this. The first predetermined number may be any number as long as the low frequency component data D2 can be extracted from the time-series pixel data D1, and is not limited to 21, and may be more than 21 or less than 21.

The image processing unit 9 calculates a simple moving average for the time-series pixel data D1 in units of a third predetermined number (for example, 3) of frames, which is less than the first predetermined number (for example, 21). The data extracted from the time-series pixel data D1 is used as the high-frequency component data D3, and the M high-frequency component data D3 corresponding to each of the M time-series pixel data D1 is extracted (step S3).

FIG. 6 shows the time-series pixel data D1 of the pixels corresponding to the point SP1 (FIG. 4A), the low-frequency component data D2 extracted from the time-series pixel data D1, and the high-frequency component data D3 extracted from the time-series pixel data D1. It is a graph which shows. The vertical and horizontal axes of the graph are the same as the vertical and horizontal axes of the graph of FIG. 4A. The temperature indicated by the time-series pixel data D1 changes relatively rapidly (the cycle of change is relatively short), and the temperature indicated by the low-frequency component data D2 changes relatively slowly (cycle of change). Is relatively long). The high frequency component data D3 appears to substantially overlap with the time series pixel data D1.

The third predetermined number of frames is, for example, three frames. The breakdown is the target frame, the one frame immediately before this, and the one frame immediately after this. The third predetermined number may be any number as long as it can extract the third frequency component from the time-series pixel data, and may be more than three.

With reference to FIGS. 1A, 2 and 5, the image processing unit 9 calculates the difference between the time-series pixel data D1 and the low-frequency component data D2 extracted from the time-series pixel data D1. Is the difference data D4, and M difference data D4 corresponding to each of the M time series pixel data D1 is calculated (step S4).

The image processing unit 9 uses the data obtained by calculating the difference between the time-series pixel data D1 and the high-frequency component data D3 extracted from the time-series pixel data D1 as the difference data D5, and M time-series pixel data. M pieces of difference data D5 corresponding to each of D1 are calculated (step S5).

FIG. 7A is a graph showing the difference data D4, and FIG. 7B is a graph showing the difference data D5. The vertical and horizontal axes of these graphs are the same as the vertical and horizontal axes of the graph of FIG. 4A. The difference data D4 is data obtained by calculating the difference between the time-series pixel data D1 and the low-frequency component data D2 shown in FIG. Before the gas ejection is started at the point SP1 shown in FIG. 4A (frames up to the 90th frame), the repetition of the minute amplitude shown by the difference data D4 mainly indicates the sensor noise of the two-dimensional image sensor 6. ing. After the gas ejection is started at the point SP1 (the 90th and subsequent frames), the variation of the amplitude and the waveform of the difference data D4 becomes large.

The difference data D5 is data obtained by calculating the difference between the time-series pixel data D1 and the high-frequency component data D3 shown in FIG.

The difference data D4 includes frequency component data indicating a temperature change due to the leaked gas and high frequency component data D3 (data indicating high frequency noise). The difference data D5 does not include the frequency component data indicating the temperature change due to the leaked gas, but includes the high frequency component data D3.

Since the difference data D4 includes frequency component data indicating a temperature change due to the leaked gas, the amplitude and waveform variation of the difference data D4 is large after the gas ejection is started at the point SP1 (the 90th and subsequent frames). It has become. On the other hand, the difference data D5 does not include the frequency component data indicating the temperature change due to the leaked gas, so that is not the case. The difference data D5 repeats a minute amplitude. This is high frequency noise.

The difference data D4 and the difference data D5 are correlated, but not completely correlated. That is, in a certain frame, the value of the difference data D4 may be positive, the value of the difference data D5 may be negative, or vice versa. Therefore, even if the difference between the difference data D4 and the difference data D5 is calculated, the high frequency component data D3 cannot be removed. In order to remove the high frequency component data D3, it is necessary to convert the difference data D4 and the difference data D5 into a value such as an absolute value that can be subtracted.

Therefore, the image processing unit 9 uses the data obtained by calculating the moving standard deviation in units of a second predetermined number of frames, which is less than K frames, as the standard deviation data D6 with respect to the difference data D4. The M standard deviation data D6 corresponding to each of the M time-series pixel data D1 is calculated (step S6). Instead of the movement standard deviation, the movement variance may be calculated.

Further, the image processing unit 9 uses data obtained by calculating a moving standard deviation in units of a fourth predetermined number (for example, 21) of frames, which is less than K frames, with respect to the difference data D5. The deviation data D7 is used, and M standard deviation data D7 corresponding to each of the M time-series pixel data D1 are calculated (step S7). Instead of the moving standard deviation, the moving variance may be used.

FIG. 8 is a graph showing the standard deviation data D6 and the standard deviation data D7. The horizontal axis of the graph is the same as the horizontal axis of the graph of FIG. 4A. The vertical axis of the graph shows the standard deviation. The standard deviation data D6 is data showing the moving standard deviation of the difference data D4 shown in FIG. 7A. The standard deviation data D7 is data showing the moving standard deviation of the difference data D5 shown in FIG. 7B. The number of frames used to calculate the moving standard deviation is 21 in both the standard deviation data D6 and the standard deviation data D7, but it may be any number as long as a statistically significant standard deviation can be obtained. Not limited.

Since the standard deviation data D6 and the standard deviation data D7 are standard deviations, they do not include negative values. Therefore, the standard deviation data D6 and the standard deviation data D7 can be regarded as data converted so that the difference data D4 and the difference data D5 can be subtracted.

The image processing unit 9 uses the data obtained by calculating the difference between the standard deviation data D6 and the standard deviation data D7 obtained from the same time-series pixel data D1 as the difference data D8, and sets M time-series pixel data D1. The M difference data D8 corresponding to each of the above is calculated (step S8).

FIG. 9 is a graph showing the difference data D8. The horizontal axis of the graph is the same as the horizontal axis of the graph of FIG. 4A. The vertical axis of the graph is the difference in standard deviation. The difference data D8 is data showing the difference between the standard deviation data D6 and the standard deviation data D7 shown in FIG. The difference data D8 is data that has been processed except for the low frequency component data D2 and the high frequency component data D3.

The image processing unit 9 generates a surveillance image (step S9). That is, the image processing unit 9 generates a moving image composed of the M difference data D8 obtained in step S8. Each frame constituting this moving image is a surveillance image. The surveillance image is an image that visualizes the difference in standard deviation. The image processing unit 9 outputs the moving image obtained in step S9 to the display control unit 10. The display control unit 10 displays this moving image on the display 11. As the monitoring images included in this moving image, for example, there are an image I12 shown in FIG. 10 and an image I15 shown in FIG.

FIG. 10 is an image diagram showing an image I10, an image I11, and an image I12 generated based on a frame at time T1. The image I10 is an image of a frame at time T1 in the moving image shown by the M standard deviation data D6 obtained in step S6 of FIG. Image I11 is an image of a frame at time T1 in the moving image shown by the M standard deviation data D7 obtained in step S7 of FIG. The difference between the image I10 and the image I11 becomes the image I12 (monitoring image).

FIG. 11 is an image diagram showing the image I13, the image I14, and the image I15 generated based on the frame at the time T2. The image I13 is an image of a frame at time T2 in the moving image shown by the M standard deviation data D6 obtained in step S6. The image I14 is an image of a frame at time T2 in the moving image shown by the M standard deviation data D7 obtained in step S7. The difference between the image I13 and the image I14 becomes the image I15 (monitoring image). Both images I10 to I15 shown in FIGS. 10 and 11 are images in which the standard deviation is multiplied by 5000.

Since the image I12 shown in FIG. 10 is an image taken before the gas is ejected from the point SP1 shown in FIG. 4A, the image I12 does not show the appearance of the gas being emitted from the point SP1. On the other hand, since the image I15 shown in FIG. 11 is an image taken at the time when the gas is ejected from the point SP1, the image I15 shows that the gas is emitted from the point SP1.

As described above, according to the embodiment, the image processing unit 9 (FIG. 1A) performs processing excluding the low frequency component data D2 included in the moving image data MD of the infrared image to generate moving image data. The display control unit 10 causes the display 11 to display the moving image (moving image of the surveillance image) indicated by the moving image data. Therefore, according to the embodiment, a monitoring image shows that the gas leaks and the background temperature change occurs in parallel, and the gas leaks even when the background temperature change is larger than the temperature change due to the leaked gas. It can be displayed in the video of.

The sensor noise decreases as the temperature rises, so it varies depending on the temperature. In the two-dimensional image sensor 6 (FIG. 1A), noise corresponding to the temperature perceived by the pixels is generated in each pixel. That is, the noise of all pixels is not the same. According to the embodiment, since the high frequency noise can be removed from the moving image, even a slight gas leak can be displayed on the display 11.

In the embodiment, the gas leak position is estimated based on the gas region. The embodiment includes a first aspect and a second aspect. The first aspect will be described. FIG. 12 is a flowchart of the process executed in the first aspect of the embodiment. FIG. 13 is a schematic diagram showing an example of an infrared image Im0 to be monitored for gas leakage. In FIG. 13, not the entire infrared image Im0, but only the rectangular portion of the infrared image Im0 including the image 101 of the pipe is shown. Infrared image Im0 shows images 101-1, 101-2, and 101-3 of three pipes extending in parallel.

The processing unit 91 shown in FIG. 1A generates a moving image of a surveillance image by using a moving image data MD composed of a plurality of infrared images Im0 (frames) including an image 101 (FIG. 13) of three pipes (FIG. 1A). Step S100 of 12). More specifically, the processing unit 91 processes the moving image data MD in steps S1 to S9 shown in FIG. As a result, each frame constituting the moving image becomes a monitoring image from the infrared image Im0, and a moving image of the monitoring image is generated. The monitoring image is, for example, the image I12 shown in FIG. 10 and the image I15 shown in FIG. If a gas leak has occurred, the gas region is included in the surveillance image. Image I15 is an image 2 seconds after the start of gas ejection. The white region located near the center of the image I15 is the gas region.

FIG. 14 is an example of a frame group constituting a moving image of a surveillance image generated by using a moving image data MD composed of a plurality of infrared images Im0 (frames) including an image 101 (FIG. 13) of three pipes. It is a schematic diagram which shows. Each frame (surveillance image) becomes the first image Im1. In FIG. 14, not the entire first image Im1, but the portion of the first image Im1 corresponding to the infrared image Im0 shown in FIG. 13 is shown. The first image Im1-3 is an image immediately after a gas leak occurs from one of the three pipes, and has a gas region 121-1. The first image Im1-1 is an image 10 seconds before the occurrence of a gas leak and does not have a gas region 121. The first image Im1-2 is an image one second before the occurrence of a gas leak, and does not have a gas region 121.

The first image Im1-4 is an image one second after the occurrence of a gas leak, and has a gas region 121-2. The first image Im1-5 is an image 2 seconds after the occurrence of a gas leak and has a gas region 121-3. The first image Im1-6 is an image 3 seconds after the occurrence of a gas leak, and has gas regions 121-4 and 121-5.

The leaked gas fluctuates due to wind and the like. Therefore, the shape, size, and position of the gas region 121 are changing every moment.

In the first aspect of the embodiment and the second aspect described later, the gas region is extracted by the processing of steps S1 to S9 shown in FIG. 5, but the infrared image Im0 is image-processed. A known technique for extracting a gas region (for example, image processing disclosed in Patent Document 1) may be used.

As described above, the processing unit 91 (first processing unit) performs a process of extracting the gas region 121 for each of the plurality of infrared images Im0 captured in time series, thereby performing a plurality of first processes. 1 Image Im1 is generated.

The processing unit 91 determines whether or not the first image Im1 has the gas region 121 by, for example, labeling the generated plurality of first images Im1 in the order of generation. When the processing unit 91 determines that there is a first image Im1 having the gas region 121, the determination unit 92 determines that the first red image Im0 is among the plurality of infrared images Im0 used to generate the plurality of first images Im1. An outside image and a second infrared image are determined (step S101).

The first infrared image is the infrared image Im0 used to generate the first image Im1 having the gas region 121. The second infrared image is the infrared image Im0 used to generate the first image Im1 having no gas region 121. Here, the determination unit 92 determines the infrared image Im0 used for generating the first image Im1-4 as the first infrared image, and the infrared image Im0 used for generating the first image Im1-2. Is determined as the second infrared image. FIG. 15 is a schematic diagram showing an infrared image Im0-4 (first infrared image) used for generating the first image Im1-4. FIG. 16 is a schematic diagram showing an infrared image Im0-2 (second infrared image) used for generating the first image Im1-2. In FIGS. 15 and 16, not the entire infrared image Im0 but the portion of the infrared image Im0 corresponding to the infrared image Im0 shown in FIG. 13 is shown.

The infrared images Im0-4 shown in FIG. 15 have the same order as the first images Im1-4 shown in FIG. The infrared image Im0-2 shown in FIG. 16 has the same order as the first image Im1-2 shown in FIG. The same order will be described. As shown in FIG. 5, the moving image data of the first image Im1 (surveillance image) is generated by using the moving image data MD (FIG. 1A) of the infrared image Im0. The first image Im1 and the infrared image Im0 in the same order mean that the order of the frames of the moving image data is the same. More specifically, when the order of the first images Im1-4 (the order of the frames shown in FIG. 9) is, for example, 200, the order of the infrared images Im0-4 (the order of the frames shown in FIG. 4A) is 200. Is.

With reference to FIGS. 15 and 16, the infrared image Im0 is an image showing the difference in temperature in shades. Here, for the sake of simplicity, four different temperatures are taken as examples. The temperature is higher in the order of the first temperature, the second temperature, the third temperature, and the fourth temperature. The temperature of the leaked gas is assumed to be higher than the air temperature. In the infrared image Im0, the first temperature region is shown in the first temperature region 103, the second temperature region is shown in the second temperature region 105, and the third temperature region is shown in the third temperature region 107. , The fourth temperature region is indicated by the fourth temperature region 109.

The first temperature region 103-1 corresponds to the image 101-1 of the pipe, the first temperature region 103-2 corresponds to the image 101-2 of the pipe, and the first temperature region 103-3 corresponds to the image 101-2 of the pipe. , Corresponds to the image 101-3 of the pipe. The causes of the generation of the second temperature region 105, the third temperature region 107, and the fourth temperature region 109 can be divided into the leaked gas and the others. Other than the leaked gas, there are, for example, deterioration of the heat insulating material covering the pipe and corrosion of the pipe.

At the time when the infrared image Im0-2 was imaged, no gas leak occurred, but a part of the image 101-2 of the pipe was shown in the second temperature region 105-1, the third temperature region 107-1, and the third temperature region 107-1. 4 is shown in the temperature range 109-1. This can be considered as a cause other than the leaked gas.

In the infrared image Im0-4, as in the infrared image Im0-2, a part of the image 101-2 of the pipe is a second temperature region 105-1, a third temperature region 107-1, and a fourth temperature region 109. It is indicated by -1. In addition, in the infrared image Im0-4, a part of the image 101-2 of the pipe is shown in the second temperature region 105-2, the third temperature region 107-2, and the fourth temperature region 109-2. , A part of the image 101-1 of the pipe is shown in the second temperature region 105-3 and the third temperature region 107-3. This can be attributed to the leaked gas.

In the first aspect, the combination of the first infrared image and the second infrared image is used to generate the first image Im1-4 (FIG. 14) 1 second after the gas leak occurrence time. -4 is combined with the infrared image Im0-2 used to generate the first image Im1-2 (FIG. 14) 1 second before the gas leak occurrence time. This is just one example, and is not limited to this. For example, the infrared image Im0 used to generate the first image Im1-3 (FIG. 14) immediately after the gas leak may be used as the first infrared image. For example, the infrared image Im0 used to generate the first image Im1-1 (FIG. 14) 10 seconds before the gas leak occurrence time may be used as the second infrared image.

The second infrared image is the infrared image Im0 used to generate the first image Im1 having no gas region 121. Therefore, the second infrared image may be predetermined. For example, the determination unit 92 determines the infrared image Im0 captured at a predetermined time as the second infrared image.

The determination unit 92 generates a difference image Imd between the infrared image Im0-4 (first infrared image) shown in FIG. 15 and the infrared image Im0-2 (second infrared image) shown in FIG. 16 ( Step S102 in FIG. 12). FIG. 17 is a schematic diagram of an example of the difference image Imd. The difference image Imd is an image showing the amount of temperature change between the first infrared image and the second infrared image. The determination unit 92 subtracts the pixel values of the pixels in the same order (position) in the infrared image Im0-4 (first infrared image) and the infrared image Im0-2 (second infrared image), and the determination unit 92 subtracts the pixel values. The difference image Imd is generated by performing a process of converting the absolute value of the result into the pixel value of the pixels in the order (position). The region 111 has different temperatures at the same position in the infrared image Im0-4 (first infrared image) shown in FIG. 15 and the infrared image Im0-2 (second infrared image) shown in FIG. , Shows the temperature difference. For example, region 111-1 shows the temperature difference between the second temperature region 105-2 shown in FIG. 15 and the first temperature region 103-2 shown in FIG. The temperature difference indicated by the regions 111-3 is the largest, followed by the temperature difference indicated by the regions 111-2 and 111-5, and then the temperature difference indicated by the regions 111-1 and 111-4.

Among the pixels constituting the difference image Imd, the pixel having the maximum pixel value is in the area 111-3. The determination unit 92 determines the position of the pixel as the gas leak position (step S103 in FIG. 12). This position is presumed to be the position where the gas leak occurred.

The main effects of the first aspect of the embodiment will be described. With reference to FIGS. 14 and 15, the infrared image Im0-4 (first infrared image) is the infrared image Im0 used to generate the first image Im1-4 having the gas region 121-2. .. With reference to FIGS. 14 and 16, the infrared image Im0-2 (second infrared image) is the infrared image Im0 used to generate the first image Im1-2 without the gas region 121. .. Therefore, among the pixels constituting the difference image Imd (FIG. 17) showing the difference between the infrared image Im0-4 (first infrared image) and the infrared image Im0-2 (second infrared image), the pixel. The position of the pixel with a relatively large value can be considered as the gas leak position. In the first aspect of the embodiment, the position of the pixel having the maximum pixel value is determined as the gas leak position. As described above, according to the first aspect of the embodiment, since the gas leak position is determined based on the first infrared image and the second infrared image, the gas leak based on the gas region 121 is determined. The accuracy of position estimation can be improved.

The first group G1 which is a group of the first image Im1 having the gas region 121 and the second group G2 which is the group of the first image Im1 having no gas region 121 may be generated alternately. In other words, the period in which the first image Im1 has the gas region 121 and the period in which the first image Im1 does not have the gas region 121 may occur alternately. .. In FIG. 18, the group of the first image Im1 having the gas region 121 (first group G1) and the group of the first image Im1 having no gas region 121 (second group G2) are alternately generated. It is explanatory drawing explaining an example.

Such alternating events occur, for example, when the gas leaking from one of the densely packed pipes fluctuates due to wind or the like. When viewed from the infrared camera 2 (FIG. 1A), there is a period during which the leaking gas enters the area in the shadow of the pipe located in front. The group of the first image Im1 corresponding to this period (second group G2) does not have the gas region 121. On the other hand, there is a period in which a part of the leaking gas enters or the leaking gas does not enter. The group of the first image Im2 (first group G1) corresponding to this period has a gas region 121.

If the first infrared image is the infrared image Im0 used to generate the first image Im1 (one first image Im1) belonging to any one of the first group G1 among the plurality of first group G1s. good. The second infrared image is an infrared image Im0 used for generating the first image Im1 (one first image Im1) belonging to any of the second group G2 among the plurality of second group G2s. good.

The first group G1 to which the first image Im1 generated based on the first infrared image belongs and the second group G2 to which the first image Im1 generated based on the second infrared image belongs are continuous. It may be (for example, first group G1-2 and second group G2-2), or it may not be continuous (for example, first group G1-2 and second group G2-1).

In the first group G1 to which the first image Im1 generated based on the first infrared image belongs and the second group G2 to which the first image Im1 generated based on the second infrared image belongs. The 1st group G1 may come first (1st group G1-1 and 2nd group G2-2), or may be later (2nd group G2-1 and 1st group G1-1).

However, if the air temperature changes between the time when the first infrared image is taken and the time when the second infrared image is taken, the estimation accuracy of the gas leak position is lowered. If the time when the first infrared image is captured and the time when the second infrared image is captured are different, the temperature is likely to change, so the time when the first infrared image was captured and the first 2 It is preferable that the time is close to the time when the infrared image was captured. Therefore, the determination unit 92 uses the infrared image Im0 used to generate the first image Im1 (one first image Im1) belonging to each of the continuous first group G1 and the second group G2 as the first infrared image Im0. The image is determined to be the second infrared image. For example, the determination unit 92 determines the infrared image Im0 used to generate one first image Im1 belonging to the first group G1-2 as the first infrared image, and one belonging to the second group G2-2. The infrared image Im0 used to generate the first image Im1 is determined to be the second infrared image.

The above description applies to the first aspect of the embodiment and the second aspect described below.

The second aspect of the embodiment will be described. In the second aspect, the gas leak position is estimated using the second image Im2 (FIG. 20) having the cumulative gas region 123 in addition to the difference image Imd (FIG. 17). FIG. 19 is a flowchart of the process executed in the second aspect of the embodiment. Steps S100 to S102 are the same as steps S100 to S102 shown in FIG.

The processing unit 91 (second processing unit) generates a second image Im2 having a cumulative gas region 123 (step S104). More specifically, FIG. 20 is a schematic diagram showing an example of two or more first images Im1 used for generating a second image Im2 having a cumulative gas region 123 and an example of a second image Im2. In FIG. 20, not the whole of the first image Im1 and the second image Im2, but the portion of these images corresponding to the infrared image Im0 shown in FIG. 13 is shown.

As described in the first aspect, when the processing unit 91 determines that there is a first image Im1 having the gas region 121, the determination unit 92 uses a plurality of reds used to generate the plurality of first images Im1. A first infrared image and a second infrared image are determined from the outside image Im0 (step S101). The processing unit 91 selects the first image Im1 (that is, the first image Im1-3 immediately after the gas leak) and the subsequent first image Im1 for which the determination has been made. For example, the processing unit 91 selects the first image Im1 from immediately after the gas leak to 10 seconds later. In this case, for example, when the frame rate is 30 fps, the number of first images Im1 selected is 300. Hereinafter, this will be described as an example.

The above 10 seconds and 300 are specific examples, and are not limited thereto, and may be longer or shorter than 10 seconds. It may be more or less than 300. Further, the selected first image Im1 includes, but is not limited to, the first image Im1-3 immediately after the gas leak. For example, the first image Im1-4 after 1 second to the first image Im1 after 10 seconds may be selected. Further, among the selected first image Im1, there may be a first image Im1 that does not have the gas region 121. This is because, as described with reference to FIG. 18, the first group G1 and the second group G2 may appear alternately.

The processing unit 91 performs binarization processing for each of the selected 300 first images Im1 so that the pixels constituting the gas region 121 are "1" and the other pixels are "0". The 300 first images Im1 are binarized. The group of pixels represented by "1" becomes the gas region 121 after the binarization process.

The processing unit 91 (second processing unit) performs a process of accumulating the binarized 300 first images Im1 to generate the second image Im2. More specifically, the processing unit 91 accumulates the gas regions 121 by performing a process of adding the pixel values of the pixels in the same order (position) in the binarized 300 first images Im1. A second image Im2 with a gas region 123 is generated. Since the pixel value of the pixel constituting the binarized image is binary, that is, 1 or 0, the maximum value that can be the pixel value of the pixel constituting the second image Im2 is 300.

Of the pixels constituting the second image Im2, the region composed of the pixels having a pixel value exceeding zero is the cumulative gas region 123. In FIG. 20, for simplification of illustration, the region 125-3, the region 125-2 located around the region 125-3, and the region 125-1 located around the region 125-2 are configured. The cumulative gas region 123 to be generated is shown. The pixel value of the pixel constituting the area 125-3 is larger than the pixel value of the pixel constituting the area 125-2, and the pixel value of the pixel constituting the area 125-2 is the pixel value of the pixel constituting the area 125-1. It is larger than the pixel value.

Even if the processing unit 91 performs a process of accumulating 300 first images Im1 without binarizing the 300 first images Im1, the second image Im2 (not shown) is generated. good. Since the pixel values of the pixels constituting the first image Im1 are not binary but multi-valued, the maximum value that can be the pixel values of the pixels constituting the second image Im2 is larger than 300.

The determination unit 92 generates a third image Im3 (intensity image) based on the difference image Imd shown in FIG. 17 and the second image Im2 shown in FIG. 20 (step S105 in FIG. 19). FIG. 21 is a schematic diagram showing an example of the third image Im3 and an example of the difference image Imd and the second image Im2 used for generating the third image Im3. In FIG. 21, not the whole of these images, but the portion of these images corresponding to the infrared image Im0 shown in FIG. 13 is shown.

The determination unit 92 generates the third image Im3 by multiplying the second image Im2 and the difference image Imd by the pixel values of the pixels in the same order (position) and making the obtained value an absolute value. do. The third image Im3 includes an overlapping region 127. The overlapping region 127 indicates a region where the cumulative gas region 123 and the region 111 included in the difference image Imd overlap. In this example, the cumulative gas region 123 and the regions 111-1 and 111-2 partially overlap, and this is the overlapping region 127. FIG. 21 shows an overlapping region 127 composed of a region 129-2 and a region 129-1 located around the region 129-2 for the sake of simplicity. The pixel value of the pixels constituting the region 129-2 (absolute value of the value obtained by multiplication) is larger than the pixel value of the pixels constituting the region 129-1 (absolute value of the value obtained by multiplication). Among the absolute values of the values obtained by the above multiplication, the pixel having the maximum value is included in the area 129-2. The determination unit 92 determines the position of the pixel as the gas leak position (step S103).

The main effects of the second aspect of the embodiment will be described. With reference to FIG. 21, since the cumulative gas region 123 included in the second image Im2 is a region where the gas region 121 is accumulated, a gas leak position exists in the cumulative gas region 123. The determination unit 92 determines the gas leak position based on the second image Im2 and the difference image Imd. According to the second aspect, since the second image Im2 having the cumulative gas region 123 is used in addition to the difference image Imd to determine the gas leak position, the estimation accuracy of the gas leak position can be further improved.

(Summary of embodiments)
The gas leak position estimation device according to the first aspect of the embodiment generates a plurality of first images by performing a process of extracting a gas region from each of the plurality of infrared images captured in time series. The first infrared image included in the plurality of infrared images and used to generate the first image having the gas region, and the first infrared image included in the plurality of infrared images. It includes a second infrared image used for generating the first image having no gas region, and a determination unit for determining a gas leak position based on the second infrared image.

The determination unit includes a first infrared image used to generate a first image having a gas region (one first image having a gas region) and a first image having no gas region (not having a gas region). The gas leak position is determined based on the second infrared image used to generate one first image). Specifically, the determination unit generates a difference image between the first infrared image and the second infrared image, and determines the gas leak position based on the size of the pixel value of each pixel constituting the difference image. decide.

The first infrared image is an infrared image used to generate the first image having a gas region. The second infrared image is an infrared image used to generate the first image having no gas region. Therefore, among the pixels constituting the difference image showing the difference between the first infrared image and the second infrared image, the position of the pixel having a relatively large pixel value can be considered as the gas leak position. For example, the determination unit determines the position of the pixel having the maximum pixel value as the gas leak position. Since the position of the pixel having the maximum pixel value may not match the gas leak position, the determination unit may determine the position of the pixel having the predetermined pixel value as the gas leak position. As described above, according to the gas leak position estimation device according to the first aspect of the embodiment, the gas leak position is determined based on the first infrared image and the second infrared image, so that the gas region It is possible to improve the estimation accuracy of the gas leak position based on.

In the above configuration, the gas regions are accumulated by performing a process of adding pixel values of pixels in the same order in two or more first images included in the plurality of first images and including the gas region. A second processing unit that generates a second image having a cumulative gas region is further provided, and the determination unit determines the gas leak position based on the second image and the difference image.

Since the cumulative gas region included in the second image is a region in which the gas region is accumulated, a gas leak position exists in the cumulative gas region. According to this configuration, the determination unit determines the gas leak position based on the second image and the difference image (for example, the determination unit determines the gas leak position in the second image and the difference image in the same order (position). Of the absolute values of the values obtained by multiplying the pixel values of the pixels, the position of the pixel having the maximum value is determined as the gas leak position). According to this configuration, since the second image having the cumulative gas region is used in addition to the difference image for determining the gas leak position, the estimation accuracy of the gas leak position can be further improved.

In the above configuration, the determination unit is a group of the first image having the gas region and a group of the first image having no gas region in the plurality of first images. When the two groups appear alternately, the infrared image used to generate the first image belonging to any one of the first groups among the plurality of first groups is referred to as the first infrared image. The infrared image used for generating the first image belonging to any one of the second groups is determined to be the second infrared image.

A first group, which is a group of first images having a gas region, and a second group, which is a group of first images having no gas region, may occur alternately. This event occurs, for example, when the gas leaking from one of the dense pipes fluctuates due to wind or the like. When viewed from the infrared camera, there is a period during which leaking gas enters the area in the shadow of the pipe located in front. The group of the first image (second group) corresponding to this period does not have a gas region. On the other hand, there is a period in which a part of the leaking gas enters or the leaking gas does not enter. The group of first images corresponding to this period (first group) has a gas region.

The first infrared image may be an infrared image used for generating a first image (one first image) belonging to any one of the first groups among the plurality of first groups. The second infrared image may be an infrared image used for generating a first image (one first image) belonging to any of the second groups among the plurality of second groups. However, if the air temperature changes between the time when the first infrared image is taken and the time when the second infrared image is taken, the estimation accuracy of the gas leak position is lowered. If the time when the first infrared image is captured and the time when the second infrared image is captured are different, the temperature is likely to change, so the time when the first infrared image was captured and the first 2 It is preferable that the time is close to the time when the infrared image was captured. Therefore, the determination unit uses the infrared images used to generate the first image (one first image) belonging to each of the continuous first group and the second group as the first infrared image and the second infrared image. Determined as an image. The first group may be first and the second group may be later, or the second group may be first and the first group may be later. For example, if the first group A appears, then the second group B appears, then the first group C appears, then the second group D appears, then the consecutive first and second groups Is the first group A and the second group B, the second group B and the first group C, and the first group C and the second group D.

The gas leak position estimation method according to the second aspect of the embodiment generates a plurality of first images by performing a process of extracting a gas region from each of the plurality of infrared images captured in time series. The first processing step to be performed, the first infrared image included in the plurality of infrared images and used to generate the first image having the gas region, and the first infrared image included in the plurality of infrared images. A determination step for determining a gas leak position based on the second infrared image used for generating the first image having no gas region is provided.

The gas leak position estimation method according to the second aspect of the embodiment defines the gas leak position estimation device according to the first aspect of the embodiment from the viewpoint of the method, and the gas leak position estimation according to the first aspect of the embodiment. It has the same effect as the device.

The gas leak position estimation program according to the third aspect of the embodiment generates a plurality of first images by performing a process of extracting a gas region from each of the plurality of infrared images captured in time series. The first processing step to be performed, the first infrared image included in the plurality of infrared images and used to generate the first image having the gas region, and the first infrared image included in the plurality of infrared images. A computer is made to perform a determination step of determining a gas leak position based on the second infrared image used for generating the first image having no gas region.

The gas leak position estimation program according to the third aspect of the embodiment defines the gas leak position estimation device according to the first aspect of the embodiment from the viewpoint of the program, and the gas leak position estimation according to the first aspect of the embodiment. It has the same effect as the device.

Although embodiments of the present invention have been illustrated and described in detail, they are merely illustrations and examples, and are not limited thereto. The scope of the invention should be construed by the wording of the attached claims.

Japanese Patent Application No. 2017-098673 filed May 18, 2017, the entire disclosure of which is incorporated herein by reference in its entirety.

According to the present invention, it is possible to provide a gas leak position estimation device, a gas leak position estimation method, and a gas leak position estimation program.

Claims (9)

By performing a process of extracting a gas region for each of a plurality of infrared images captured in a time series, a plurality of first images are generated in the order of the time series, and each of the plurality of first images is , A first processing unit that determines whether or not it has a gas region ,
The infrared image included in the plurality of infrared images and used for generating the first image determined to have the gas region in the first processing unit, and the gas in the first processing unit. The infrared images in the same order as the time series of the first images determined to have a region are defined as first infrared images, which are included in the plurality of infrared images and are included in the plurality of infrared images . The infrared image used to generate the first image determined not to have a gas region, and the time series of the first image determined not to have the gas region by the first processing unit. The infrared image in the same order as the order is defined as a second infrared image, and the gas leak includes a determination unit for determining a gas leak position based on the first infrared image and the second infrared image . Position estimation device. The gas leak position estimation device according to claim 1, wherein the determination unit generates a difference image between the first infrared image and the second infrared image. The gas leak position estimation device according to claim 2, wherein the determination unit determines the position of the pixel having the maximum pixel value among the pixels constituting the difference image as the gas leak position. In two or more of the first images included in the plurality of first images and including the gas region, the cumulative gas region in which the gas regions are accumulated is obtained by performing a process of adding the pixel values of the pixels in the same order. Further provided with a second processing unit for generating a second image having a second image,
The gas leak position estimation device according to claim 2 or 3, wherein the determination unit determines the gas leak position based on the second image and the difference image. The determination unit determines the position of the pixel having the maximum value among the absolute values of the values obtained by multiplying the pixel values of the pixels in the same order in the second image and the difference image as the gas leak position. The gas leak position estimation device according to claim 4. In the plurality of first images, the determination unit includes a first group, which is a group of the first images having the gas region, and a second group, which is a group of the first images having no gas region. When the above-mentioned images appear alternately, the infrared image used for generating the first image belonging to any one of the first groups is determined to be the first infrared image, and a plurality of images are used. Any of claims 1 to 5, wherein the infrared image used for generating the first image belonging to any one of the second groups is determined to be the second infrared image. The gas leak position estimation device according to item 1. The determination unit uses the infrared image used to generate the first image belonging to each of the continuous first group and the second group as the first infrared image and the second infrared image. The gas leak position estimation device according to claim 6, which is determined. By performing a process of extracting a gas region for each of a plurality of infrared images captured in a time series, a plurality of first images are generated in the order of the time series, and each of the plurality of first images is , The first processing step to determine whether or not it has a gas region ,
The infrared image included in the plurality of infrared images and used for generating the first image determined to have the gas region in the first processing step, and the gas in the first processing step. The infrared images having the same order as the time series of the first images determined to have a region are defined as the first infrared images, are included in the plurality of infrared images, and are included in the plurality of infrared images. The infrared image used to generate the first image determined not to have a gas region, and the time series of the first image determined not to have the gas region in the first processing step. The infrared image in the same order as the order is defined as a second infrared image, and the gas leak includes a determination step of determining a gas leak position based on the first infrared image and the second infrared image . Position estimation method. By performing a process of extracting a gas region for each of a plurality of infrared images captured in a time series, a plurality of first images are generated in the order of the time series, and each of the plurality of first images is , The first processing step to determine whether or not it has a gas region ,
The infrared image included in the plurality of infrared images and used for generating the first image determined to have the gas region in the first processing step, and the gas in the first processing step. The infrared images having the same order as the time series of the first images determined to have a region are defined as the first infrared images, are included in the plurality of infrared images, and are included in the plurality of infrared images. The infrared image used to generate the first image determined not to have a gas region, and the time series of the first image determined not to have the gas region in the first processing step. The infrared image in the same order as the order is used as the second infrared image, and the computer executes a determination step of determining the gas leakage position based on the first infrared image and the second infrared image . Let the gas leak position estimation program.

Images