Method and device for making multispectral infrared gas imaging data set

Abstract

The invention relates to the technical field of infrared gas imaging, and particularly provides a multispectral infrared gas imaging data set manufacturing method and device, and the method comprises the steps: constructing an infrared radiation transmission model of gas; a propagation and diffusion geometric model of the gas is constructed, and the propagation and diffusion geometric model comprises gas types, gas concentrations and gas contours; and a multispectral infrared gas imaging data set is manufactured based on the propagation and diffusion geometric model and the infrared radiation transmission model. Therefore, the multispectral infrared gas imaging data set is obtained according to the infrared radiation transmission model and the propagation and diffusion geometric model of the gas, the infrared gas imaging data set is manufactured on the premise that hazardous chemical gas is not discharged, safety is guaranteed, manufacturing is conducted on the basis of the gas type and concentration information, and the method is easy to implement. A rich and colorful multispectral infrared gas imaging data set can be made, and the requirement of deep learning training for the data set is met.

Description

Technical Field

[0001] The present invention relates to the technical field of infrared gas imaging, and particularly to a method for producing a multi-spectral infrared gas imaging data set and an apparatus for producing a multi-spectral infrared gas imaging data set. Background Art

[0002] Since most gases have no response in the visible band and have a relatively weak response in the infrared band, traditional algorithms have a high false detection rate when facing the detection task of such weak signals in a complex background, and deep learning methods need to be used. However, deep learning methods rely on a complete and rich infrared gas image database. Currently, there is no complete image database of hazardous chemicals gases. Due to the hazards and safety issues of hazardous chemicals gases themselves, it is impossible to obtain a hazardous chemicals gas image database by discharging hazardous chemicals gases multiple times and taking pictures.

[0003] Therefore, there is an urgent need for a new way to obtain an infrared gas imaging data set of hazardous chemicals gases applicable to the spectral system. Summary of the Invention

[0004] To solve one of the above technical problems, the present invention proposes the following technical solutions.

[0005] An embodiment of the first aspect of the present invention proposes a method for producing a multi-spectral infrared gas imaging data set, including the following steps: constructing an infrared radiation transmission model of a gas; constructing a propagation and diffusion geometric model of the gas, wherein the propagation and diffusion geometric model includes gas species, gas concentration, and gas contour; and producing a multi-spectral infrared gas imaging data set based on the propagation and diffusion geometric model and the infrared radiation transmission model.

[0006] In addition, the method for producing a multi-spectral infrared gas imaging data set according to the above embodiment of the present invention may further have the following additional technical features.

[0007] According to an embodiment of the present invention, the expression of the infrared radiation transmission model is:

[0008] DN = kτ srf τ opt (τ 1 τ 2 L B -τ 2 L bgas )(e -αCL -1)

[0009] wherein, DN represents the signal change value caused by gas absorption, k represents the radiation calibration coefficient, τ srf represents the response rate of the detector to different spectra, τ opt represents the transmittance of the optical system, τ 1 、τ2 respectively represent the atmospheric transmittance between the observation background and the gas, and between the gas and the detection system, L B represents the thermal radiation of the observation background, L bgas represents the radiance of the gas of equivalent blackbody radiation, α is the gas absorption coefficient, C is the gas concentration, and L is the optical path of the gas.

[0010] According to an embodiment of the present invention, the propagation and diffusion geometric model is constructed by CFD simulation software.

[0011] According to an embodiment of the present invention, based on the propagation and diffusion geometric model and the infrared radiation transmission model, a multi-spectral infrared gas imaging data set is produced, including: collecting an infrared background image of the observation background by an infrared camera; combining the propagation and diffusion geometric model and the infrared radiation transmission model to obtain a simulated gas image; and superimposing the simulated gas image on the infrared background image to obtain a multi-spectral infrared gas image data set.

[0012] According to an embodiment of the present invention, after collecting the infrared background image of the observation background by the infrared camera, it further includes: preprocessing the infrared background image.

[0013] An embodiment of the second aspect of the present invention proposes a device for producing a multi-spectral infrared gas imaging data set, including: a first construction module for constructing an infrared radiation transmission model of the gas; a second construction module for the propagation and diffusion geometric model of the gas, where the propagation and diffusion geometric model includes the gas type, gas concentration, and gas profile; and a production module for producing a multi-spectral infrared gas imaging data set based on the propagation and diffusion geometric model and the infrared radiation transmission model.

[0014] The technical solution of the embodiment of the present invention obtains a multi-spectral infrared gas imaging data set according to the infrared radiation transmission model and the propagation and diffusion geometric model of the gas, which not only completes the production of the multi-spectral infrared gas imaging data set without discharging hazardous chemicals, ensuring safety, but also produces a rich and colorful multi-spectral infrared gas imaging data set based on the gas type and concentration information, meeting the requirements of deep learning training for the data set. Description of the Drawings

[0015] Figure 1 is a flowchart of the method for producing a multi-spectral infrared gas imaging data set according to the embodiment of the present invention.

[0016] Figure 2 is a schematic diagram of the infrared radiation transmission process of the gas according to the embodiment of the present invention.

[0017] Figure 3 is a schematic diagram of the production of multi-spectral infrared gas imaging data according to an example of the present invention.

[0018] Figure 4 This is a structural block diagram of an apparatus for producing a multi-spectral infrared gas imaging data set according to an embodiment of the present invention. Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] Currently, the main technology is to convert visible RGB images into infrared images. For infrared gas leakage scenarios, gas leakage traces cannot be detected by visible light. Secondly, some other superposition methods lack theoretical analysis. They simply superpose grayscale gas contours, lack concentration labels, and are not applicable to multi-spectral systems.

[0021] In order to obtain a multi-spectral infrared gas imaging data set with gas contours and concentrations for deep learning training, the present invention uses algorithms such as a gas radiative transfer model to simulate the propagation paths and diffusion effects of hazardous chemicals in various scenarios, and establish a database of hazardous chemical gas images without discharging hazardous chemicals, laying a foundation for the training of subsequent hazardous chemical gas monitoring networks and algorithm research, and can be applied to multi-spectral systems at the same time.

[0022] Figure 1 This is a flowchart of a method for producing a multi-spectral infrared gas imaging data set according to an embodiment of the present invention.

[0023] As Figure 1 shown, the method for producing the multi-spectral infrared gas imaging data set includes the following steps S1 to S3.

[0024] S1. Construct an infrared radiative transfer model of the gas.

[0025] Specifically, when infrared radiation passes through the gas and interacts with molecules through vibration or rotation, energy will be transferred to the molecules, resulting in the absorption of infrared radiation at specific gas wavelengths. This absorption phenomenon can be visualized through absorption spectra, similar to the fingerprint of the gas.

[0026] During the entire gas detection process, the infrared radiative transfer process of the gas is as Figure 2 shown. The radiant energy reaching the detection system includes the thermal radiation L B of the observed background, the thermal radiation L gas of the gas itself, and the atmospheric path radiation L pThe incident pupil radiation undergoes attenuation through the optical system lens, the transmittance of the filter, and the response attenuation of the detector window, and is finally converted by the detector into a DN value (signal value, which refers to the value reflecting the amount of received radiation. The larger the value, the stronger the energy).

[0027] According to Figure 2 the infrared radiation transmission process shown, construct the expression of the infrared radiation transmission model of the gas, that is, the expression of the DN value.

[0028] S2. Construct the propagation and diffusion geometric model of the gas. Among them, the propagation and diffusion geometric model includes gas type, gas concentration, and gas profile.

[0029] Among them, the propagation and diffusion geometric model is constructed by CFD simulation software.

[0030] Specifically, geometric gas modeling uses CFD simulation software to simulate the propagation and diffusion of the leaked gas. Common CFD simulation software includes ANSYS Fluent, Open FOAM, and COMSOL Multiphysics, etc. Among them, OpenFOAM is an open-source CFD software with high customizability and flexibility, suitable for various fluid dynamics simulations. Users can write their own solvers and physical models according to their needs. OpenFOAM supports multiple grid types and is applicable to complex geometries and flow conditions, and is often used in academic research and industrial applications. Use OpenFOAM to simulate the diffusion of the leaked gas and generate a diffusion image to obtain a two-dimensional propagation and diffusion geometric model containing the gas type, concentration, and profile.

[0031] S3. Based on the propagation and diffusion geometric model and the infrared radiation transmission model, produce a multi-spectral infrared gas imaging dataset.

[0032] Specifically, combine the gas geometric profile and concentration information of the propagation and diffusion geometric model with the infrared radiation transmission model, and obtain a multi-spectral infrared gas imaging dataset applied to the multi-spectral system according to the combination result, including gas type and gas concentration labels.

[0033] The current infrared gas imaging dataset lacks a theoretical calculation basis, only contains contour information, and does not have the concentration and type information of each point. The embodiment of the present invention not only simulates the gas diffusion trend, but also simulates the gas concentration based on the gas radiation transmission model, and gives the contour, concentration, and type information of the gas under the multi-spectral image.

[0034] Thus, based on the infrared radiation transmission model and the propagation and diffusion geometric model of the gas, a multi-spectral infrared gas imaging dataset is obtained. This not only ensures safety by completing the production of the multi-spectral infrared gas imaging dataset without emitting hazardous gases, but also can produce a rich and colorful multi-spectral infrared gas imaging dataset based on gas type and concentration information, meeting the requirements of the deep learning training for the dataset.

[0035] In one embodiment, the expression of the infrared radiation transmission model is:

[0036] DN = kτ srf τ opt (τ 1 τ 2 L B -τ 2 L bgas )(e -αCL -1)

[0037] where DN represents the signal change value caused by gas absorption (the difference between the detector signal value without gas and the detector signal value with gas), k represents the radiation calibration coefficient, τ srf represents the detector's response rate to different spectra, τ opt represents the transmittance of the optical system, τ 1 、τ 2 respectively represent the atmospheric transmittance between the observation background and the gas, and between the gas and the detection system, L B represents the thermal radiation of the observation background, L bgas represents the radiance of the gas equivalent to a blackbody radiation, α is the gas absorption coefficient, C is the gas concentration, and L is the optical path length of the gas.

[0038] Specifically, referring to Figure 2 , when there is gas in the observation background, the radiance L I after passing through the detector is expressed as:

[0039] L I =τ srf τ opt (τ 1 τ 2 τ gas L B +τ 2 L gas +L p )

[0040] where τ srf represents the detector's response rate to different spectra, τ opt represents the transmittance of the optical system, mainly including the transmittance of the optical lens and the transmittance of the filter. τ 1 、τ 2They represent the atmospheric transmittance between the observation background and the gas, and between the gas and the detection system respectively. The thermal radiation L of the gas itself gas can be regarded as blackbody radiation and can be expressed as (1 - τ gas )L bgas . Similarly, when there is no gas in the observation background, the radiance L I2 after passing through the detector can be expressed as:

[0041] L I2 = τ srf τ opt (τ 1 τ 2 L B + L p )

[0042] Therefore, the change in radiance ΔL caused by the absorption of gas in the observation background can be expressed as:

[0043] ΔL = L I - L I2 = τ srf τ opt (τ 1 τ 2 L B - τ 2 L bgas )(τ gas - 1)

[0044] Secondly, according to the Beer-Lambert law, a relationship is established between the change in gas radiance ΔL and the gas concentration. τ gas can be expressed as:

[0045] τ gas = e -αCL

[0046] where α is the gas absorption coefficient, C is the gas concentration, and L is the optical path of the gas. When the background radiation temperature T B , the gas temperature T gas and the optical path of the gas L are determined, the DN value caused by gas absorption can be expressed as:

[0047] DN = kτ srf τ opt (τ 1 τ 2 L B - τ 2 L bgas )(e -αCL - 1).

[0048] In one embodiment, step S3 may include: collecting an infrared background image of the observation background through an infrared camera; combining a propagation and diffusion geometric model and an infrared radiation transmission model to obtain a simulated gas image; and superimposing the simulated gas image on the infrared background image to obtain a multi-spectral infrared gas image dataset.

[0049] Further, after collecting the infrared background image of the observation background through the infrared camera, it may further include: preprocessing the infrared background image.

[0050] Specifically, as Figure 3 shown, first, the infrared background image is obtained by actually shooting the actual application scenario through the infrared camera, and then the image geometric contour and the corresponding concentration information C generated by the software simulation in step S2 are combined with the infrared radiation transmission model obtained in step S1, and the concentration information C is substituted into the expression of the transmission model to calculate and obtain a simulated gas image including the gray information of the image. Finally, it is superimposed on the preprocessed infrared background image to obtain a multi-spectral infrared image dataset, including gas contours, gas types, and gas concentration labels.

[0051] Among them, the preprocessing of the multi-spectral image is generally non-uniformity correction, denoising, dynamic range adjustment, etc., and can be specifically determined according to actual requirements. The purpose of preprocessing is to improve the image quality and serve as a high-quality background map.

[0052] In summary, the method for producing a multi-spectral infrared gas imaging dataset according to the embodiments of the present invention is based on a full-link simulation model of gas radiation transmission, simulates multi-spectral gas leakage images in a specific environment, and solves the problem that it is difficult to obtain real image data of hazardous chemicals by traditional methods. At the same time, by actually shooting the complex background environment through a multi-spectral camera and combining real environmental illumination and weather data, the authenticity of the hazardous chemical gas data is enhanced. Finally, the simulated gas image is superimposed on the actually shot background image to create a rich multi-spectral image database, which not only ensures safety but also effectively meets the data requirements of the deep learning model.

[0053] Corresponding to the method for producing a multi-spectral infrared gas imaging dataset in the above embodiment, the present invention also proposes a device for producing a multi-spectral infrared gas imaging dataset.

[0054] Figure 4 It is a structural block diagram of the device for producing an infrared gas imaging dataset according to the embodiments of the present invention.

[0055] As Figure 4 shown, the device for producing a multi-spectral infrared gas imaging dataset includes: a first construction module 10, a second construction module 20, and a production module 30.

[0056] Among them, the first construction module 10 is used to construct an infrared radiation transmission model of the gas; the second construction module 20 is used for the propagation and diffusion geometry model of the gas, where the propagation and diffusion geometry model includes the gas type, gas concentration, and gas profile; the production module 30 is used to produce a multi-spectral infrared gas imaging data set based on the propagation and diffusion geometry model and the infrared radiation transmission model.

[0057] It should be noted that for the specific implementation of the device for producing the multi-spectral infrared gas imaging data set, reference can be made to the specific implementation of the above-mentioned method for producing the multi-spectral infrared gas imaging data set. To avoid redundancy, it will not be elaborated here in detail.

[0058] The device for producing the multi-spectral infrared gas imaging data set according to the embodiments of the present invention obtains the multi-spectral infrared gas imaging data set based on the infrared radiation transmission model and the propagation and diffusion geometry model of the gas. It not only completes the production of the multi-spectral infrared gas imaging data set without discharging hazardous chemicals, ensuring safety, but also produces a rich and colorful multi-spectral infrared gas imaging data set based on the gas type and concentration information, meeting the requirements of the data set for deep learning training.

[0059] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for preparing a multispectral infrared gas imaging data set, characterized in that: The following steps are involved: Construct infrared radiation transmission model of gas; Constructing a gas propagation and diffusion geometric model, wherein the propagation and diffusion geometric model includes gas type, gas concentration and gas profile; A multi-spectral infrared gas imaging data set is produced based on the propagation and diffusion geometric model and the infrared radiation transmission model.

2. The method for preparing a multi-spectral infrared gas imaging data set according to claim 1, characterized in that: The expression of the infrared radiation transmission model is: DN=kτ srf t opt (τ1τ2L B -τ2L bgas (e) -αCL -1) Where DN represents the signal change value caused by gas absorption, k represents the radiation calibration coefficient, τ srf represents the detector's response rate to different spectra, τ opt represents the transmittance of the optical system, τ1 and τ2 represent the atmospheric transmittance between the observation background and the gas, and between the gas and the detection system, respectively. B represents the thermal radiation of the observed background, L bgas It represents the radiance of the gas equivalent to blackbody radiation, α is the gas absorption coefficient, C is the gas concentration, and L is the optical path length of the gas.

3. The method for preparing a multi-spectral infrared gas imaging data set according to claim 1, characterized in that: The propagation and diffusion geometric model is constructed by CFD simulation software.

4. The method for preparing a multi-spectral infrared gas imaging data set according to claim 1, characterized in that: A multi-spectral infrared gas imaging data set is produced based on the propagation and diffusion geometric model and the infrared radiation transmission model, including: Collecting an infrared background image of the observation background by using an infrared camera; Combining the propagation and diffusion geometric model with the infrared radiation transmission model to obtain a simulated gas image; The simulated gas image and the infrared background image are superimposed to obtain an infrared gas image data set.

5. The method for preparing a multi-spectral infrared gas imaging data set according to claim 1, characterized in that: After collecting the infrared background image of the observation background by the infrared camera, it also includes: The infrared background image is preprocessed.

6. A device for producing a multi-spectral infrared gas imaging data set, characterized in that: include: The first building module is used to build an infrared radiation transmission model of gas; A second building block is used for a gas propagation and diffusion geometric model, wherein the propagation and diffusion geometric model includes gas type, gas concentration and gas profile; A production module is used to produce a multi-spectral infrared gas imaging data set based on the propagation and diffusion geometric model and the infrared radiation transmission model.

Images