Gas leakage detection method and device based on image reconstruction, medium and terminal

Abstract

The invention discloses a gas leakage detection method and device based on image reconstruction, a medium and a terminal, relates to the technical field of detection, and mainly aims to solve the problems of poor detection accuracy and effectiveness of gas leakage in the prior art. Comprising the following steps: acquiring a first gray value of a gas absorption wave band and a second gray value of a gas non-absorption wave band of a target position point in a spectral image of a to-be-detected region; determining actually measured absorption band radiation data corresponding to the first gray value, and reconstructing theoretical absorption band radiation data based on the second gray value; and extracting a gas radiation difference value based on the actually measured absorption wave band radiation data and the theoretical absorption wave band radiation data, and performing leakage detection on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result.

Description

Technical Field

[0001] The present application relates to a field of detection technology, and in particular to a gas leakage detection method, device, medium and terminal based on image reconstruction. Background Art

[0002] With the gradual enhancement of industrial production safety awareness, industrial fields such as petrochemicals, power transportation, and transportation need to conduct leak detection of various gases, such as sulfur hexafluoride (SF 6 ), chemical plant methane (CH 4 ) and other gas leak detection to ensure the safety of the working environment and staff.

[0003] At present, existing gas leak detection usually uses optical detection technology to detect gas leaks, that is, active imaging based on the absorption of laser radiation energy analyzes the optical image to make leak judgments. However, the radiation source of active imaging is usually heavy, and gas detection is limited by the range of the laser light source spectral response, which greatly reduces the accuracy and effectiveness of gas leak detection. Summary of the invention

[0004] In view of this, the present application provides a gas leakage detection method, device, medium and terminal based on image reconstruction, the main purpose of which is to solve the problem of poor accuracy and effectiveness of existing gas leakage detection.

[0005] According to one aspect of the present application, a gas leakage detection method based on image reconstruction is provided, comprising: Acquire a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in the spectral image of the area to be detected; Determine the measured absorption band radiation data corresponding to the first gray value, and reconstruct the theoretical absorption band radiation data based on the second gray value; A gas radiation difference value is extracted based on the measured absorption band radiation data and the theoretical absorption band radiation data, and leakage detection is performed on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result.

[0006] Furthermore, reconstructing the theoretical absorption band radiation data based on the second gray value includes: Determine the non-absorption band background temperature corresponding to the second gray value based on the temperature calibration mapping relationship; Determine the absorption band background temperature of the gas absorption band using the non-absorption band background temperature, and reconstruct theoretical absorption band radiation data based on the absorption band background temperature; The temperature calibration mapping relationship is obtained by solving the linear relationship between the gray value variable and the background temperature variable of the non-absorption band based on the least squares method.

[0007] Furthermore, the reconstructing theoretical absorption band radiation data based on the absorption band background temperature includes: Determine the background radiation data corresponding to the background temperature of the absorption band based on Planck's law; The theoretical absorption band radiation data is determined based on the background radiation data, the atmospheric path radiation, and the corrected atmospheric transmittance.

[0008] Furthermore, the method further comprises: Obtaining the ambient humidity, ambient temperature, atmospheric pressure and vapor pressure of the area to be detected; The water vapor concentration is determined based on the ambient humidity, the ambient temperature, the atmospheric pressure and the vapor pressure, and the atmospheric transmittance is calculated based on the water vapor concentration and the absorption coefficient and optical path length of the water vapor to obtain a corrected atmospheric transmittance.

[0009] Further, the determining of the measured absorption band radiation data corresponding to the first gray value includes: Determine the measured absorption band radiation data corresponding to the first gray value based on the radiation calibration mapping relationship; The radiation calibration mapping relationship is obtained by solving the linear relationship between the gray value variable and the measured absorption band radiation variable based on the least squares method.

[0010] Furthermore, the extracting of gas radiation difference values ​​based on the measured absorption band radiation data and the theoretical absorption band radiation data, and performing leakage detection on the gas radiation difference values ​​based on threshold segmentation to obtain a gas leakage detection result includes: Using the non-absorption band background temperature and the theoretical absorption band radiation data to perform difference calculation to obtain a gas radiation difference value; Perform leakage comparison on the gas radiation difference value according to threshold segmentation to obtain the gas leakage detection result of the target location point; The method further comprises: The gas leakage detection results of all target positions in the spectral image are traversed to generate a gas difference image of the spectral image.

[0011] Furthermore, the step of obtaining a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in the spectral image of the area to be detected includes: Determine the gas absorption band and the gas non-absorption band of the gas to be detected; The spectral image of the area to be detected is collected by a time-synchronized dual-band infrared device, and the first grayscale value corresponding to the target position point and the second grayscale value corresponding to the gas non-absorption band are determined from the spectral image.

[0012] According to another aspect of the present application, a gas leakage detection device based on image reconstruction is provided, comprising: An acquisition module, used for acquiring a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in a spectral image of a region to be detected; A reconstruction module, used to determine the measured absorption band radiation data corresponding to the first gray value, and reconstruct the theoretical absorption band radiation data based on the second gray value; The detection module is used to extract the gas radiation difference value based on the measured absorption band radiation data and the theoretical absorption band radiation data, and perform leakage detection on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result.

[0013] Furthermore, the reconstruction module is specifically used to determine the non-absorption band background temperature corresponding to the second grayscale value based on the temperature calibration mapping relationship; determine the absorption band background temperature of the gas absorption band using the non-absorption band background temperature, and reconstruct the theoretical absorption band radiation data based on the absorption band background temperature; wherein the temperature calibration mapping relationship is obtained by solving the linear relationship between the grayscale value variable and the non-absorption band background temperature variable based on the least squares method.

[0014] Furthermore, the reconstruction module is specifically used to determine the background radiation data corresponding to the background temperature of the absorption band based on Planck's law; and determine the theoretical absorption band radiation data based on the background radiation data, atmospheric path radiation, and corrected atmospheric transmittance.

[0015] Furthermore, the device also includes: a calculation module.

[0016] The acquisition module is also used to acquire the ambient humidity, ambient temperature, atmospheric pressure and vapor pressure of the area to be detected; The calculation module is used to determine the water vapor concentration based on the ambient humidity, the ambient temperature, the atmospheric pressure and the vapor pressure, and calculate the atmospheric transmittance based on the water vapor concentration and the absorption coefficient and optical path length of the water vapor to obtain the corrected atmospheric transmittance.

[0017] Furthermore, the reconstruction module is also used to determine the measured absorption band radiation data corresponding to the first grayscale value based on the radiation calibration mapping relationship; wherein the radiation calibration mapping relationship is obtained by solving the linear relationship between the grayscale value variable and the measured absorption band radiation variable based on the least squares method.

[0018] Furthermore, the device also includes: a generating module.

[0019] The detection module is specifically used to perform difference calculation using the non-absorption band background temperature and the theoretical absorption band radiation data to obtain a gas radiation difference value; perform leakage comparison on the gas radiation difference value according to threshold segmentation to obtain a gas leakage detection result at the target location point; The generating module is used to traverse the gas leakage detection results of all target positions in the spectral image and generate a gas difference image of the spectral image.

[0020] Furthermore, the determination module is also used to determine the gas absorption band and the gas non-absorption band of the gas to be detected; collect the spectral image of the area to be detected through a time-synchronized dual-band infrared device, and determine the first grayscale value corresponding to the target position point and the second grayscale value corresponding to the gas non-absorption band from the spectral image.

[0021] According to another aspect of the present application, a storage medium is provided, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned gas leakage detection method based on image reconstruction.

[0022] According to another aspect of the present application, a terminal is provided, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned gas leakage detection method based on image reconstruction.

[0023] By means of the above technical solution, the technical solution provided by the embodiment of the present application has at least the following advantages: The present application provides a gas leakage detection method, device, medium and terminal based on image reconstruction. Compared with the prior art, the embodiments of the present application obtain a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in a spectral image of a region to be detected; determine the measured absorption band radiation data corresponding to the first grayscale value, and reconstruct the theoretical absorption band radiation data based on the second grayscale value; extract a gas radiation difference value based on the measured absorption band radiation data and the theoretical absorption band radiation data, and perform leakage detection on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result. Leakage detection is performed through the difference value, thereby improving the signal-to-noise ratio of the spectral image, greatly improving the applicable scope of gas detection, and realizing the inversion of theoretical background radiation using the same background temperature characteristics, thereby greatly improving the accuracy and effectiveness of gas leakage detection.

[0024] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A flow chart of a gas leakage detection method based on image reconstruction provided in an embodiment of the present application is shown; Figure 2 A schematic diagram of three-layer atmospheric radiation transmission provided by an embodiment of the present application is shown; Figure 3 It shows a SF provided by the embodiment of the present application 6 Schematic diagram of gas release test results; Figure 4 It shows a SF provided by the embodiment of the present application 6 and NH 3 Schematic diagram of the field test results of released gas; Figure 5 A block diagram of a gas leakage detection device based on image reconstruction provided in an embodiment of the present application is shown; Figure 6 A schematic diagram of the structure of a terminal provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0027] The present application embodiment provides a gas leakage detection method based on image reconstruction, such as Figure 1 As shown, the method includes: 101 obtains a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band of a target position point in a spectral image of a region to be detected.

[0028] In the embodiment of the present application, the spectral image of the area to be detected is an infrared detector that performs infrared imaging of the gas that may be leaking, such as an infrared video imaging system. At this time, the infrared detector can scan and obtain the infrared radiation of the background of the area to be detected and the expected leaking gas, and output it in the form of a spectral image. In order to be applicable to the detection of multiple gas leaks, dual-band radiation is used to collect spectral images. At this time, the center wavelengths of the gas absorption band and the gas non-absorption band are selected based on the gas that may be leaking for infrared detection scanning to obtain different center wavelengths. A corresponding spectral image is obtained, and then a target position point in the spectral image is selected, such as a pixel point in the spectral image, to obtain two grayscale values ​​corresponding to this target position point, namely, a first grayscale value in the gas absorption band at this target position point and a second grayscale value in the gas non-absorption band.

[0029] It should be noted that the current execution end, as the executor of gas leakage detection, can be a computer device such as a server, wherein the server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms, etc., and the embodiments of this application do not make specific limitations.

[0030] 102. Determine measured absorption band radiation data corresponding to the first gray value, and reconstruct theoretical absorption band radiation data based on the second gray value.

[0031] In the embodiment of the present application, since the background temperature of the gas absorption band is the same as the background temperature of the gas non-absorption band, the measured absorption band radiation data can be determined based on the first grayscale value obtained by detecting the gas absorption band. At the same time, inversion and reconstruction are performed based on the second grayscale value obtained by detecting the gas non-absorption band to obtain the theoretical absorption band radiation data with the gas absorption band as the theoretical background.

[0032] It should be noted that, since the radiation data in the embodiment of the present application is affected by factors such as the atmosphere and the environment when the detector is detecting, the transmission process of the gas in the environment is usually described using the infrared layer radiation transmission model (Layer Model), that is, the transmission path of the infrared radiation is divided into a series of parallel layers, and the input radiation of each layer is the output radiation of the previous layer, and the output radiation of the current layer is used as the input radiation of the next layer. The infrared layer radiation transmission model assumes that the infrared radiation of the background and the leaked gas is transmitted between a series of spatial parallel layers. In order to simplify the infrared layer radiation transmission model, in the embodiment of the present application, the gas distribution of each atmospheric transmission layer and the gas distribution of the leaked gas layer are set to be uniform. Therefore, the infrared radiation transmission model can be simplified into three layers, that is, the leaked gas cloud is used as the dividing line, and the transmission path from the background to the infrared detector is divided into three parts: background, target gas to be measured, and infrared detection instrument. Therefore, when determining the theoretical absorption band radiation data, it is reconstructed using the second gray value under the premise of setting the background temperature the same.

[0033] 103. Extract gas radiation difference values ​​based on the measured absorption band radiation data and the theoretical absorption band radiation data, and perform leakage detection on the gas radiation difference values ​​based on threshold segmentation to obtain a gas leakage detection result.

[0034] In the embodiment of the present application, the gas radiation difference value can be extracted by taking the difference between the measured absorption band radiation data and the theoretical absorption band radiation data, so as to perform leakage detection on the gas radiation difference value using the threshold segmentation method to obtain the gas leakage detection result. Among them, the radiation threshold corresponding to the threshold segmentation method can be configured based on the leakage radiation interval of different target gases, so that when it is greater than this radiation threshold, it is determined that there is leakage of the target gas.

[0035] In another embodiment of the present application, for further definition and explanation, the step of reconstructing the theoretical absorption band radiation data based on the second gray value includes: Determine the non-absorption band background temperature corresponding to the second gray value based on the temperature calibration mapping relationship; The absorption band background temperature of the gas absorption band is determined by using the non-absorption band background temperature, and theoretical absorption band radiation data is reconstructed based on the absorption band background temperature.

[0036] In order to achieve the purpose of reconstructing the absorption band radiation of the target gas under theoretical conditions by using the grayscale value of the gas non-absorption band in the spectral image, thereby improving the accuracy of gas leakage detection, the current execution end first determines the non-absorption band background temperature corresponding to the second grayscale value based on the temperature calibration mapping relationship when reconstructing the theoretical absorption band radiation data. At this time, the temperature calibration mapping relationship is obtained by solving the linear relationship between the grayscale value variable and the non-absorption band background temperature variable based on the least squares method. In the embodiment of the present application, for the case where the target gas to be detected is relatively uniform on the gas surface, the thermal properties of the gas surface material are stable, and the wavelength range collected by the infrared video imaging system is relatively narrow, the grayscale value of the infrared image and the radiation data of the target gas surface can be determined as a linear relationship. Therefore, in the embodiment of the present application, the infrared system is calibrated using a radiation source with a preset temperature.

[0037] In some embodiments, for the temperature calibration mapping relationship, the spectral images of radiation sources of different temperatures are first collected. For example, the radiation source temperatures are set to 30°C to 60°C, with a temperature point every 5°C. Since the signal detected by the infrared video imaging system may be unstable and the radiation source temperature may have errors, in order to ensure the accuracy of the radiation calibration results, the radiation source data of continuous frames at each temperature point is selected by taking the average value multiple times, for a total of 100 frames. Furthermore, a grayscale-temperature curve is drawn based on the collected grayscale value and the radiation data of the radiation source. The grayscale here is the digital value output by the detector, that is, the DN value. The conversion relationship between the DN value and the temperature data is obtained by the linear fitting method, that is, the temperature calibration mapping relationship is expressed as a linear relationship between the background temperature of the absorption band and the digital value DN value of the collected data: ,in, It is expressed as the central wavelength λ and the radiation source temperature T at the position (m, n) on the spectrum image. k The non-absorption band background temperature under the condition of , k is the Boltzmann constant, are the responsiveness and response bias of the infrared video imaging system respectively. The temperature calibration coefficient in the above formula can be solved using the least squares algorithm, thereby obtaining a temperature calibration mapping relationship for solving the background temperature of the non-absorption band corresponding to the second gray value.

[0038] It should be noted that after obtaining the background temperature of the non-absorption band, since the gas distribution of each atmospheric transmission layer and the gas distribution of the leakage gas layer are uniform, the infrared radiation transmission can be simplified into three layers, namely, the background, the gas to be measured and the data collected by the infrared video imaging system. At this time, for the background temperature of the target gas that may have a leak, the temperature values ​​in the gas absorption band and the gas non-absorption band are the same. Therefore, the non-absorption band background temperature is determined as the absorption band background temperature of the gas absorption band, and then the theoretical absorption band radiation data can be reconstructed based on the absorption band background temperature.

[0039] In another embodiment of the present application, for further definition and explanation, the step of reconstructing theoretical absorption band radiation data based on the absorption band background temperature includes: Determine the background radiation data corresponding to the background temperature of the absorption band based on Planck's law; The theoretical absorption band radiation data is determined based on the background radiation data, the atmospheric path radiation, and the corrected atmospheric transmittance.

[0040] In order to achieve the purpose of leaking gas detection based on the reconstructed theoretical absorption band radiation and improve the effectiveness of gas leak detection, the current execution end reconstructs the theoretical absorption band radiation data based on the absorption band background temperature. Specifically, the background radiation data corresponding to the absorption band background temperature is first determined based on Planck's law, that is, , is the central wavelength of the gas absorption band, T is the background temperature of the absorption band, and then, the theoretical absorption band radiation data is determined based on the background radiation data, atmospheric path radiation, and corrected atmospheric transmittance. As the theoretical measured background radiation received after atmospheric attenuation and atmospheric path radiation, the calculation method is expressed as , The central wavelength The corrected atmospheric transmittance is The central wavelength Radiation in the lower atmosphere.

[0041] In some measured embodiments, in the infrared video imaging system, the radiation transmission path is set to be in a uniform atmosphere. At this time, the atmospheric transmittance is . When there is no target gas for expected leakage in the scene, the detector entrance pupil radiation data consists of two parts, including: 1. The radiance from the observed background thermal radiation and the thermal radiation from the surrounding objects reflected by the observed background after atmospheric attenuation; 2. Atmospheric path radiation. It should be noted that the background infrared radiation also includes the reflected radiation from other objects, but other objects usually have a weak ability to reflect radiation. Therefore, the infrared radiation detected by the detector is set to be the infrared radiation emitted by the background. At this time, the radiation formula for the entrance pupil radiation data when there is no target gas in the path is expressed as: ; in, The central wavelength And the background temperature The background radiation data detected below, is the atmospheric radiation. Among them, the background radiation data can be equivalent to an emissivity of The radiation data emitted by the radiation source, at this time, at the central wavelength , Background temperature Radiation data of equivalent radiation source under It can be calculated according to Planck's law, and the embodiments of this application do not make specific limitations. When there is a target gas in the scene, the radiation data detected by the detector includes three parts: 1. The energy from the observed background thermal radiation and the thermal radiation of the surrounding objects reflected by the observed background after being absorbed by the gas; 2. The thermal radiation of the gas itself; 3. The atmospheric radiation, such as Figure 2 As shown. At this time, the detector's entrance pupil radiation data The radiation formula is expressed as: ;in, Expressed as the central wavelength , Background temperature The background radiation data obtained by detection is is the gas permeability, is the self-radiation data of the target gas, is the atmospheric radiation, that is, the detector's entrance pupil radiation data Mainly thermal radiation from the background Transmittance The radiation data after gas absorption and atmospheric attenuation, thermal radiation from the gas itself Radiation data after atmospheric attenuation, and atmospheric path radiation According to Kirchhoff's law, under thermodynamic equilibrium conditions, the absorptivity of a gas is equal to the emissivity. At this time, the sum of the emissivity and transmittance of the gas is set to 1. Therefore, the gas emissivity can be expressed as 1 minus the transmittance, that is, Furthermore, subtracting the pupil radiation data with and without the target gas can eliminate the above parameters and obtain the amplitude data corresponding to the gas absorption. , which is expressed as: ; At this time, the target gas infrared radiation data and atmospheric transmittance , Target gas permeability , gas temperature and background radiation data, Background temperature The radiation data of the equivalent radiation source under is the radiation source temperature The radiation data of the equivalent radiation source under can be calculated based on Planck's law, and the embodiments of the present application do not make specific limitations.

[0042] In the above-mentioned measured embodiment, in the dual-band radiation transmission path when there is no target gas, the change of the dual-band radiation data is mainly caused by the band, and different central wavelengths are used. , After detection, we get: ; .

[0043] In the actual measurement process, it was found that the main absorbers of infrared radiation in a uniform atmosphere are nitrogen (78.084%), oxygen (20.946%), water, and carbon dioxide (390 ppm). The effects of nitrogen and oxygen in the wavelength range of 7 μm-14 μm are negligible. At this time, water vapor is the dominant absorption component, especially at both ends of the band, while carbon dioxide has only a weak effect near 14 μm. Therefore, under the condition of setting a uniform atmosphere, only water vapor has an effect on the atmospheric transmittance, that is, the radiation formula of the entrance pupil radiation data when there is no target gas is simplified to the radiation data of water vapor at the atmospheric temperature T (i.e., ambient temperature). The radiation formula is expressed as: ,in, The central wavelength The equivalent radiation source temperature Finally, we can use It is deduced that , is the measured absorption band radiation data obtained through correction, is the theoretical measured background radiation after reconstruction.

[0044] In another embodiment of the present application, for further definition and explanation, the steps further include: Obtaining the ambient humidity, ambient temperature, atmospheric pressure and vapor pressure of the area to be detected; The water vapor concentration is determined based on the ambient humidity, the ambient temperature, the atmospheric pressure and the vapor pressure, and the atmospheric transmittance is calculated based on the water vapor concentration and the absorption coefficient and optical path length of the water vapor to obtain a corrected atmospheric transmittance.

[0045] In order to reduce the impact of ambient temperature and humidity on gas radiation absorption, thereby improving the accuracy of gas leakage detection, the current execution end first obtains the ambient humidity, ambient temperature, atmospheric pressure and vapor pressure of the area to be detected before determining the theoretical absorption band radiation data based on background radiation data, atmospheric path radiation and corrected atmospheric transmittance. At this time, the measured ambient humidity can be converted into water vapor concentration, and the conversion formula is: ; where RH is the ambient humidity, Ambient temperature The saturated vapor pressure under the atmospheric pressure, P is the atmospheric pressure, and further, the central wavelength The atmospheric transmittance can be calculated according to the Lambert-Beer law, which is expressed as: ; in, is the absorption coefficient of water vapor, d is the optical path length of water vapor, and the atmospheric transmittance is calculated based on the measured relative humidity and the optical path length of water vapor. .

[0046] In some actual measurement embodiments, the atmospheric parameters of the detection area, such as temperature, humidity, and air pressure, are collected, and the HITRAN database is called to calculate the atmospheric transmittance, that is, the gas absorption bands are calculated separately. and gas non-absorption band Atmospheric transmittance , , and atmospheric radiation , Since only the influence of water vapor is considered when calculating the atmospheric transmittance, the water vapor volume fraction is calculated using the relative humidity of water vapor, and the saturated water vapor pressure is calculated based on the temperature and air pressure (using the Magnus formula) and expressed as: ; Furthermore, the atmospheric transmittance can be calculated by Lambert-Beer law , considering the gas as a uniform atmosphere, the average atmospheric transmittance in the absorption band and the non-absorption band can be obtained.

[0047] In another embodiment of the present application, for further definition and explanation, the step of determining the measured absorption band radiation data corresponding to the first gray value includes: The measured absorption band radiation data corresponding to the first grayscale value is determined based on the radiation calibration mapping relationship.

[0048] In order to realize the linear relationship between grayscale value and radiation data as the basis for determining the measured absorption band radiation data, thereby improving the accuracy of gas leakage detection, the current execution end determines the measured absorption band radiation data corresponding to the first grayscale value based on the radiation calibration mapping relationship, wherein the radiation calibration mapping relationship is obtained by solving the linear relationship between the grayscale value variable and the measured absorption band radiation variable based on the least squares method. In the embodiment of the present application, when the target gas surface is relatively uniform, the thermal properties of the target gas surface material are stable, and the wavelength range collected by the system is relatively narrow, the grayscale value of the spectral image and the radiation data of the target gas surface can be set to a linear relationship. Therefore, in order to obtain reliable radiation data, a radiation source with a preset temperature is used to calibrate the infrared video imaging system, that is, through the radiation calibration mapping relationship, the conversion relationship between the grayscale value and the radiation data in the infrared video imaging system can be calculated. Specifically, the radiation calibration process enables the spectral gas image to more accurately reflect the radiation distribution of the target surface. At this time, the response of the system spectral channel is set to be uniform. Therefore, each channel corresponds to a radiation calibration curve, according to the center wavelength In the detected spectral image, the pixel with coordinates (m, n) has a radiation source temperature of When the detector detects the radiation data and the digital values ​​of the collected data are , , the linear calibration formula is expressed as: ,in, It is expressed as the central wavelength at the point (m, n) on the spectrum image. , radiation source temperature T k The gas absorption band radiation data under the condition, k is the Boltzmann constant, are the responsivity and response bias of the infrared video imaging system respectively. The radiation calibration coefficient in the above formula can be solved using the least squares algorithm, thereby obtaining a radiation calibration mapping relationship for solving the radiation data of the gas absorption band corresponding to the second gray value.

[0049] In another embodiment of the present application, for further definition and explanation, the step of extracting the gas radiation difference value based on the measured absorption band radiation data and the theoretical absorption band radiation data, and performing leakage detection on the gas radiation difference value based on threshold segmentation to obtain the gas leakage detection result includes: Using the non-absorption band background temperature and the theoretical absorption band radiation data to perform difference calculation to obtain a gas radiation difference value; The gas radiation difference value is subjected to leakage comparison according to the threshold segmentation to obtain the gas leakage detection result of the target location point.

[0050] In order to extract the target gas that may have leaked gas and thus improve the accuracy of gas leakage detection, the current execution end first uses the non-absorption band background temperature and the theoretical absorption band radiation data to perform difference calculation to obtain the gas radiation difference value, which is expressed as Then, the gas radiation difference value is segmented according to the threshold value. Leakage judgment is performed to obtain the gas leakage detection result at the target location. Different thresholds can be set for different target gases that may have leakage, so as to For comparison, such as when the gas radiation difference value When it is greater than the threshold, it is determined that there is leakage of the target gas. The embodiment of the present application does not specifically limit the specific setting of the threshold.

[0051] Correspondingly, in order to draw the gas leakage conditions of all positions in the spectral image, the step further includes: traversing the gas leakage detection results of all target positions in the spectral image to generate a gas differential image of the spectral image.

[0052] In some embodiments, the current execution end can perform leakage identification on a position point (m, n) in the spectral image, and then traverse and identify all position points in the spectral image, and render the position points of the gas leakage detection results where leakage exists to generate a gas differential image containing the gas leakage distribution for viewing.

[0053] In another embodiment of the present application, for further definition and explanation, the step of obtaining a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in a spectral image of a region to be detected includes: Determine the gas absorption band and the gas non-absorption band of the gas to be detected; The spectral image of the area to be detected is collected by a time-synchronized dual-band infrared device, and the first grayscale value corresponding to the target position point and the second grayscale value corresponding to the gas non-absorption band are determined from the spectral image.

[0054] In order to accurately improve the accuracy of gas leakage detection, the current execution end first determines the gas absorption band and gas non-absorption band of the target gas to be detected that may have a leak when obtaining the first grayscale value and the second grayscale value. At this time, the gas absorption band is used to characterize the central wavelength that can be absorbed by the gas after the radiation source is emitted, and the gas non-absorption band is used to characterize the central wavelength that cannot be absorbed by the gas after the radiation source is emitted, so as to use the above two bands for infrared detection to obtain a spectral image. At this time, the selection of the gas absorption band must meet the gas absorption coefficient Greater than the gas absorption coefficient in the non-absorption band of the gas .

[0055] In addition, when performing infrared detection, in order to ensure the stability of radiation absorption, data is collected through a time-synchronized dual-band infrared device, that is, a spectral image of the area to be detected is collected through a time-synchronized dual-band infrared video imaging system, and then a target position point is selected, such as (m, n) as the extraction position of the first grayscale value and the corresponding second grayscale value, which is not specifically limited in the embodiments of the present application.

[0056] In a specific implementation scenario, the target gas that may leak is set to SF 6 , the corresponding gas absorption band (SF 6 At a strong absorption peak), gas non-absorption band The atmospheric parameters of the area to be tested include temperature 25℃, humidity 40%, and air pressure 1013pa. The saturated water vapor pressure and water vapor concentration are calculated according to the Magnus formula, and the water vapor absorption coefficient under this atmospheric parameter condition is obtained using HITRAN data. Then, the atmospheric transmittance and atmospheric path radiation under two bands can be calculated according to the Lambert-Beer law. Specifically, the atmospheric transmittance in the band with a central wavelength of 10.55 microns and a wavelength width of 0.7 microns is , the atmospheric emissivity is The atmospheric radiation at an ambient temperature of 25°C is multiplied by the atmospheric emissivity under the radiation source condition. Therefore, the radiation data of the equivalent radiation source under the condition of absolute temperature T=25+273.15°C can be calculated by Planck's law, which is expressed as: ; in, is the first radiation constant, is the second radiation constant, represents Planck's constant, which is 6.6×10 -34 W.s 2 , c is the speed of light in vacuum, which is 3.0×10 10 cm / s -1 , k is the Boltzmann constant, which is 1.4×10 -23 J.K. -1 , calculated , by collecting the spectral data of radiation sources at different temperatures for many times, the corresponding atmospheric radiation value can be calculated. At this time, the radiation source temperature is set to 30℃~60℃, with a temperature point every 5℃. After the radiation source temperature is stable and the infrared video imaging system is in a stable operating state, the infrared multi-video imaging system may measure unstable signals and there may be errors in the radiation source temperature. In order to ensure the accuracy of the radiation calibration results, the infrared video imaging system is used to image the radiation source multiple times and calculate the average value. During the actual measurement, the radiation source data at each temperature point is collected continuously for 100 frames, and the spectral data of the radiation source at different temperatures are collected multiple times to calculate Radiation correction, and At this time, for the point (m, n) on the spectrum image, the DN values ​​measured in the two bands are and , the temperature correction and radiation correction results can be obtained and , under the same background temperature conditions for the gas absorption band and the gas non-absorption band, and when the emissivity is set to 1, the gas absorption band is reconstructed After the background is attenuated by the atmosphere and radiated by the atmosphere, the radiation that should be received in theory is Finally, the gas radiation difference is calculated Based on this difference value, it is determined whether there is a gas leak at the position (m, n) on the image, such as Figure 3 As shown, finally, the gas differential image can be obtained by traversing the entire image and performing calculations, as shown in Figure 4 shown.

[0057] A gas leakage detection method based on image reconstruction is provided in an embodiment of the present application. Compared with the prior art, the embodiment of the present application obtains a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in a spectral image of a region to be detected; determines the measured absorption band radiation data corresponding to the first grayscale value, and reconstructs the theoretical absorption band radiation data based on the second grayscale value; extracts a gas radiation difference value based on the measured absorption band radiation data and the theoretical absorption band radiation data, and performs leakage detection on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result. Leakage detection is performed through the difference value, thereby improving the signal-to-noise ratio of the spectral image, greatly improving the applicable scope of gas detection, and realizing the inversion of the theoretical background radiation using the same background temperature characteristics, thereby greatly improving the accuracy and effectiveness of gas leakage detection.

[0058] Furthermore, as a response to the above Figure 1 The implementation of the method shown in the figure, the embodiment of the present application provides a gas leakage detection device based on image reconstruction, such as Figure 5 As shown, the device comprises: An acquisition module 21 is used to acquire a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in a spectral image of a region to be detected; A reconstruction module 22, used to determine the measured absorption band radiation data corresponding to the first gray value, and reconstruct the theoretical absorption band radiation data based on the second gray value; The detection module 23 is used to extract the gas radiation difference value based on the measured absorption band radiation data and the theoretical absorption band radiation data, and perform leakage detection on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result.

[0059] Furthermore, the reconstruction module is specifically used to determine the non-absorption band background temperature corresponding to the second grayscale value based on the temperature calibration mapping relationship; determine the absorption band background temperature of the gas absorption band using the non-absorption band background temperature, and reconstruct the theoretical absorption band radiation data based on the absorption band background temperature; wherein the temperature calibration mapping relationship is obtained by solving the linear relationship between the grayscale value variable and the non-absorption band background temperature variable based on the least squares method.

[0060] Furthermore, the reconstruction module is specifically used to determine the background radiation data corresponding to the background temperature of the absorption band based on Planck's law; and determine the theoretical absorption band radiation data based on the background radiation data, atmospheric path radiation, and corrected atmospheric transmittance.

[0061] Furthermore, the device also includes: a calculation module.

[0062] The acquisition module is also used to acquire the ambient humidity, ambient temperature, atmospheric pressure and vapor pressure of the area to be detected; The calculation module is used to determine the water vapor concentration based on the ambient humidity, the ambient temperature, the atmospheric pressure and the vapor pressure, and calculate the atmospheric transmittance based on the water vapor concentration and the absorption coefficient and optical path length of the water vapor to obtain the corrected atmospheric transmittance.

[0063] Furthermore, the reconstruction module is also used to determine the measured absorption band radiation data corresponding to the first grayscale value based on the radiation calibration mapping relationship; wherein the radiation calibration mapping relationship is obtained by solving the linear relationship between the grayscale value variable and the measured absorption band radiation variable based on the least squares method.

[0064] Furthermore, the device also includes: a generating module.

[0065] The detection module is specifically used to perform difference calculation using the non-absorption band background temperature and the theoretical absorption band radiation data to obtain a gas radiation difference value; perform leakage comparison on the gas radiation difference value according to threshold segmentation to obtain a gas leakage detection result at the target location point; The generating module is used to traverse the gas leakage detection results of all target positions in the spectral image and generate a gas difference image of the spectral image.

[0066] Furthermore, the determination module is also used to determine the gas absorption band and the gas non-absorption band of the gas to be detected; collect the spectral image of the area to be detected through a time-synchronized dual-band infrared device, and determine the first grayscale value corresponding to the target position point and the second grayscale value corresponding to the gas non-absorption band from the spectral image.

[0067] The embodiment of the present application provides a gas leakage detection device based on image reconstruction. Compared with the prior art, the embodiment of the present application obtains a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in a spectral image of a region to be detected; determines the measured absorption band radiation data corresponding to the first grayscale value, and reconstructs the theoretical absorption band radiation data based on the second grayscale value; extracts a gas radiation difference value based on the measured absorption band radiation data and the theoretical absorption band radiation data, and performs leakage detection on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result. Leakage detection is performed through the difference value, thereby improving the signal-to-noise ratio of the spectral image, greatly improving the applicable scope of gas detection, and realizing the inversion of theoretical background radiation using the same background temperature characteristics, thereby greatly improving the accuracy and effectiveness of gas leakage detection.

[0068] According to an embodiment of the present application, a storage medium is provided, wherein the storage medium stores at least one executable instruction, and the computer executable instruction can execute the gas leakage detection method based on image reconstruction in any of the above method embodiments.

[0069] Figure 6 A schematic diagram of the structure of a terminal provided according to an embodiment of the present application is shown, and the specific embodiment of the present application does not limit the specific implementation of the terminal.

[0070] like Figure 6 As shown, the terminal may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .

[0071] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .

[0072] The communication interface 304 is used to communicate with other devices such as clients or other servers.

[0073] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above-mentioned gas leakage detection method embodiment based on image reconstruction.

[0074] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0075] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the terminal may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0076] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0077] The program 310 may be specifically configured to enable the processor 302 to perform the following operations: Acquire a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in the spectral image of the area to be detected; Determine the measured absorption band radiation data corresponding to the first gray value, and reconstruct the theoretical absorption band radiation data based on the second gray value; A gas radiation difference value is extracted based on the measured absorption band radiation data and the theoretical absorption band radiation data, and leakage detection is performed on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result.

[0078] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0079] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A gas leakage detection method based on image reconstruction, characterized in that: include: Acquire a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in the spectral image of the area to be detected; Determine the measured absorption band radiation data corresponding to the first gray value, and reconstruct the theoretical absorption band radiation data based on the second gray value; A gas radiation difference value is extracted based on the measured absorption band radiation data and the theoretical absorption band radiation data, and leakage detection is performed on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result.

2. The method according to claim 1, characterized in that The reconstructing the theoretical absorption band radiation data based on the second gray value comprises: Determine the non-absorption band background temperature corresponding to the second gray value based on the temperature calibration mapping relationship; Determine the absorption band background temperature of the gas absorption band using the non-absorption band background temperature, and reconstruct theoretical absorption band radiation data based on the absorption band background temperature; The temperature calibration mapping relationship is obtained by solving the linear relationship between the gray value variable and the background temperature variable of the non-absorption band based on the least squares method.

3. The method according to claim 2, characterized in that The reconstructing theoretical absorption band radiation data based on the absorption band background temperature comprises: Determine the background radiation data corresponding to the background temperature of the absorption band based on Planck's law; The theoretical absorption band radiation data is determined based on the background radiation data, the atmospheric path radiation, and the corrected atmospheric transmittance.

4. The method according to claim 3, characterized in that The method further comprises: Obtaining the ambient humidity, ambient temperature, atmospheric pressure and vapor pressure of the area to be detected; The water vapor concentration is determined based on the ambient humidity, the ambient temperature, the atmospheric pressure and the vapor pressure, and the atmospheric transmittance is calculated based on the water vapor concentration and the absorption coefficient and optical path length of the water vapor to obtain a corrected atmospheric transmittance.

5. The method according to claim 1, characterized in that The determining of the measured absorption band radiation data corresponding to the first gray value comprises: Determine the measured absorption band radiation data corresponding to the first gray value based on the radiation calibration mapping relationship; The radiation calibration mapping relationship is obtained by solving the linear relationship between the gray value variable and the measured absorption band radiation variable based on the least squares method.

6. The method according to claim 2, characterized in that The extracting of the gas radiation difference value based on the measured absorption band radiation data and the theoretical absorption band radiation data, and performing leakage detection on the gas radiation difference value based on threshold segmentation to obtain the gas leakage detection result includes: Using the non-absorption band background temperature and the theoretical absorption band radiation data to perform difference calculation to obtain a gas radiation difference value; Perform leakage comparison on the gas radiation difference value according to threshold segmentation to obtain the gas leakage detection result of the target location point; The method further comprises: The gas leakage detection results of all target positions in the spectral image are traversed to generate a gas difference image of the spectral image.

7. The method according to claim 1, characterized in that The step of obtaining a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position in a spectral image of the area to be detected comprises: Determine the gas absorption band and the gas non-absorption band of the gas to be detected; The spectral image of the area to be detected is collected by a time-synchronized dual-band infrared device, and the first grayscale value corresponding to the target position point and the second grayscale value corresponding to the gas non-absorption band are determined from the spectral image.

8. A gas leakage detection device based on image reconstruction, characterized in that: include: An acquisition module, used for acquiring a first grayscale value of a gas absorption band and a second grayscale value of a gas non-absorption band at a target position point in a spectral image of a region to be detected; A reconstruction module, used to determine the measured absorption band radiation data corresponding to the first gray value, and reconstruct the theoretical absorption band radiation data based on the second gray value; The detection module is used to extract the gas radiation difference value based on the measured absorption band radiation data and the theoretical absorption band radiation data, and perform leakage detection on the gas radiation difference value based on threshold segmentation to obtain a gas leakage detection result.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to claim 1 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method of claim 1.

Images