Infrared broadband multispectral radiation temperature measuring device and method, medium and equipment

Abstract

The embodiment of the invention discloses an infrared broadband multispectral radiation temperature measuring device and method, a medium and equipment, the device comprises a front optical module, a micro lens array, an optical filter array and a detector array, the front optical module is used for separating medium-wave radiation and long-wave radiation of a target object, and the micro lens array is used for detecting the medium-wave radiation and the long-wave radiation of the target object; reducing the medium wave radiation and the long wave radiation and projecting the medium wave radiation and the long wave radiation to the micro-lens array; the micro-lens array is used for focusing and converging the medium-wave radiation and the long-wave radiation after the reduction projection to obtain medium-wave converged light and long-wave converged light; the optical filter array is used for receiving the corresponding medium-wave convergent light and the long-wave convergent light and filtering the medium-wave convergent light and the long-wave convergent light respectively; and the detector array is used for performing multi-spectrum acquisition on the filtered medium-wave convergent light and long-wave convergent light to obtain a target spectrum radiation image. The multispectral radiation temperature measuring device is simple in structure, and temperature field measurement of a target object can be easily realized by a high-speed infrared broadband multispectral imaging technology.

Description

Technical Field

[0001] The present invention relates to the field of radiation temperature measurement technology, and in particular to an infrared wide-band multi-spectral radiation temperature measurement device, method, medium and equipment. Background Art

[0002] Temperature measurement plays an important role in all walks of life, and temperature measurement technology is constantly developing to meet the needs of different scenarios. According to the use of temperature sensors, measurement methods can be roughly divided into contact and non-contact. Contact temperature measurement requires physical contact with the surface of the object to be measured to obtain the temperature, which is suitable for occasions with high requirements for measurement convenience. However, this method may disturb the temperature field distribution of the object to be measured, especially for materials with poor thermal conductivity. In addition, the dynamic measurement performance of contact temperature measurement is limited, and it is difficult to apply to high-temperature or potentially dangerous environments. In contrast, non-contact temperature measurement technology does not need to contact the object to be measured, and can perform long-distance temperature measurement, which is suitable for inaccessible or dangerous environments. Non-contact temperature measurement technology can complete temperature measurement in a short time, has high measurement efficiency, and is not limited by the temperature itself. It can be used for temperature detection in high-temperature environments such as furnaces. Non-contact temperature measurement has the advantages of long-distance, high temperature and safety, but its accuracy may be affected by environmental factors and target emissivity.

[0003] In the existing technology, multi-spectral camera combined with radiation temperature measurement technology is a non-contact method based on the multi-wavelength temperature measurement principle, but multi-spectral camera combined with radiation temperature measurement technology requires high-precision optical systems, sensors and data processing algorithm support, which increases the manufacturing cost and usage threshold of the equipment. Summary of the invention

[0004] Based on this, it is necessary to propose an infrared wide-band multi-spectral radiation temperature measurement device, method, medium and equipment to address the above problems.

[0005] An infrared wide-band multi-spectral radiation temperature measurement device, comprising: a front optical module, a microlens array, a filter array and a detector array,

[0006] The front optical module is used to separate the medium-wave radiation and the long-wave radiation of the spectral radiation of the target object.

[0007] The microlens array is used to focus and converge the medium-wave radiation and the long-wave radiation respectively to obtain medium-wave converged light and long-wave converged light.

[0008] The filter array is used to receive the corresponding medium-wave converged light and long-wave converged light, and filter the medium-wave converged light and long-wave converged light respectively.

[0009] The detector array is used to collect the filtered medium-wave converged light and long-wave converged light in multiple spectral bands to obtain a target spectral radiation image.

[0010] An infrared wide-band multi-spectral radiation temperature measurement method, the method comprising:

[0011] Separate the medium-wave radiation and long-wave radiation of the target object's spectral radiation.

[0012] The medium-wave radiation and the long-wave radiation are focused and converged respectively to obtain medium-wave converged light and long-wave converged light.

[0013] The corresponding medium-wave converged light and long-wave converged light are received, and the medium-wave converged light and long-wave converged light are filtered respectively.

[0014] The filtered medium-wave converged light and long-wave converged light are respectively collected in multiple spectral bands to obtain a target spectral radiation image.

[0015] The step of collecting the filtered medium-wave converged light and the long-wave converged light in multiple spectral bands to obtain a target spectral radiation image specifically includes:

[0016] The target spectral radiation image is wavelength calibrated to determine the calibration relationship between the wavelength and the grayscale value.

[0017] The target spectral radiation image is calibrated to determine the calibration relationship between temperature and grayscale value.

[0018] Based on the calibration relationship between the wavelength and the grayscale value and the calibration relationship between the temperature and the grayscale value, the grayscale value of each wavelength of the target object at different temperatures is obtained according to the spectral emissivity model, and the grayscale value of each wavelength at the different temperatures is used as temperature measurement data.

[0019] A multi-spectral temperature measurement model is constructed based on the state space model and multi-layer perceptron.

[0020] The multi-spectral temperature measurement model is trained according to the temperature measurement data.

[0021] The trained multi-spectral temperature measurement model is used to invert the real temperature of the target spectral radiation image and obtain the temperature field distribution of the target object.

[0022] The step of performing wavelength calibration on the target spectral radiation image to determine the calibration relationship between wavelength and grayscale value specifically includes:

[0023] In a dark environment, the monochromatic radiation energy of the target spectral radiation image at different wavelengths is obtained.

[0024] The grayscale value of each pixel area in the target spectral radiation image is determined according to the monochromatic radiation energy of the target spectral radiation image at different wavelengths.

[0025] The effective wavelength value corresponding to the maximum grayscale value in the current pixel area is determined according to the grayscale value of each pixel area, and the grayscale value and wavelength of the pixel area are calibrated.

[0026] The step of performing radiation calibration on the target spectral radiation image to determine the calibration relationship between temperature and grayscale value specifically includes:

[0027] At fixed temperature intervals, the temperature of the blackbody furnace is raised and after the current temperature is stabilized for a preset time, the radiation data of the target spectral radiation image is collected until the temperature reaches a preset temperature threshold.

[0028] The radiation data of the target spectral radiation image is fitted according to the least square method to determine the calibration relationship between temperature and grayscale value.

[0029] The step of fitting the radiation data of the target spectral radiation image according to the least square method to determine the calibration relationship between temperature and grayscale value specifically includes:

[0030] according to Determine the calibration relationship between temperature and grayscale value, where V i is the pixel grayscale value of the ith wavelength, A is a constant independent of temperature, B is a coefficient inversely proportional to the temperature, and C is a coefficient inversely proportional to the square of the temperature.

[0031] The step of training the multi-spectral temperature measurement model according to the temperature measurement data specifically includes:

[0032] Feature extraction is performed on the temperature measurement data, and data updating is performed on the temperature measurement data after feature extraction according to a state space model.

[0033] The updated temperature measurement data is predicted to obtain a temperature prediction value.

[0034] The gap between the predicted temperature value and the true temperature value is determined by the semi-mean square error loss until the gap between the predicted temperature value and the true temperature value reaches a preset threshold, thereby completing the training of the multi-spectral temperature measurement model.

[0035] The step of extracting features from the temperature measurement data and updating the temperature measurement data after feature extraction according to the state space model specifically includes:

[0036] The state matrix data of the updated temperature measurement data is determined according to hk(t)=Ahk-1(t)+BX(t), wherein hk(t) is the updated state matrix data, hk-1(t) is the state matrix data of the temperature measurement data, A is the state transfer matrix, and B is the input matrix.

[0037] The updated temperature measurement data is determined according to Y(t)=Chk(t), wherein Y(t) is the updated temperature measurement data and C is the output matrix.

[0038] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the method described above.

[0039] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0040] The embodiments of the present invention have the following beneficial effects:

[0041] The present invention effectively separates the medium-wave radiation and long-wave radiation in the spectral radiation of the target object through the front optical module, and the microlens array focuses the medium-wave radiation and the long-wave radiation respectively and converges them into medium-wave converged light and long-wave converged light. The collection efficiency of the radiation energy is significantly improved by focusing and converging, so that the detector array can receive a stronger signal. At the same time, the advantages of the microlens array, such as small size, light weight, easy integration and arraying, are utilized to make the structure of the entire temperature measurement device more compact, convenient for use in various scenarios, and improve the stability and reliability of the device. Furthermore, the corresponding medium-wave converged light and long-wave converged light are received by the filter array, and filtering is performed respectively to further remove stray light and interference light, so that the spectral information received by the detector array is more accurate. Finally, the detector array respectively collects the filtered medium-wave converged light and long-wave converged light in multiple spectral bands to obtain the target spectral radiation image, so that the device can simultaneously obtain radiation information of multiple bands, realize high-resolution imaging of the target object, and then more accurately judge its temperature distribution. In summary, the multi-spectral temperature measurement device proposed in the present invention has a simple structure, detects a wide infrared band, and is easy to implement high-speed infrared wide-band multi-spectral imaging technology to measure the temperature field of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] in:

[0044] Figure 1 A schematic structural diagram of an infrared wide-band multi-spectral radiation temperature measurement device according to an embodiment of the present invention;

[0045] Figure 2 A schematic flow chart of an embodiment of an infrared wide-band multi-spectral radiation temperature measurement method provided by the present invention;

[0046] Figure 3 A schematic structural diagram of another embodiment of an infrared wide-band multi-spectral radiation temperature measurement device provided by the present invention;

[0047] Figure 4 A schematic diagram of a flow chart of another embodiment of an infrared wide-band multi-spectral radiation temperature measurement method provided by the present invention;

[0048] Figure 5 A schematic diagram of the structure of an embodiment of a multi-spectral temperature measurement model provided by the present invention;

[0049] Figure 6 A schematic structural diagram of an embodiment of the device provided by the present invention;

[0050] Figure 7 A schematic structural diagram of an embodiment of the medium provided by the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] like Figure 1 As shown, Figure 1 The present invention provides a schematic diagram of the structure of an infrared broadband multi-spectral radiation temperature measurement device according to an embodiment of the present invention. An infrared broadband multi-spectral radiation temperature measurement device 10 includes: a front optical module 11, a microlens array 12, a filter array 13 and a detector array 14.

[0053] The front optical module 11 is used to separate the medium-wave radiation and the long-wave radiation of the spectral radiation of the target object, and to reduce and project the medium-wave radiation and the long-wave radiation onto the microlens array.

[0054] Exemplarily, the front optical module 11 adopts a band coaxial design, and separates the medium-wave radiation and the long-wave radiation of the spectral radiation of the target object through the front optical module 11, and reduces and projects the target object onto the microlens array.

[0055] The microlens array 12 is used to focus the medium-wave radiation and the long-wave radiation respectively and converge them to the corresponding filter array to obtain the medium-wave converged light and the long-wave converged light.

[0056] Exemplarily, the microlens array 12 includes a plurality of microlenses, which are arranged in a specific matrix. When the medium-wave radiation and long-wave radiation of the target object pass through the front optical module and are projected onto the microlens array, each microlens of the microlens array will focus the medium-wave radiation and the long-wave radiation respectively and converge them onto the filter array 13 to obtain medium-wave converged light and long-wave converged light.

[0057] Since there is an accurate optical correspondence between the microlens array 12 and the filter array 13, that is, the light spot focused and converged by each microlens can accurately correspond to one or more filter positions in the filter array. This accurate correspondence ensures that radiation of different wavelength bands can be effectively separated and transmitted to the corresponding detectors, thereby realizing multi-spectral temperature measurement.

[0058] The filter array 13 is used to receive the corresponding medium-wave converged light and long-wave converged light, and filter the medium-wave converged light and the long-wave converged light respectively.

[0059] Exemplarily, the filter array 13 includes a plurality of narrow bandpass filters with different central wavelengths, each of which is designed to transmit light of a specific wavelength band and block light of other wavelength bands. The plurality of narrow bandpass filters with different central wavelengths are arranged in a matrix, and are optically arranged corresponding to the microlens array, and receive corresponding medium-wave converged light and long-wave converged light, and filter the medium-wave converged light and the long-wave converged light respectively.

[0060] The detector array 14 is used to collect the filtered medium-wave converged light and the long-wave converged light in multiple spectral bands to obtain a target spectral radiation image.

[0061] Exemplarily, the high-speed detector pixel array 14 corresponds to the filter array 13 one by one, ensuring that the optical signal filtered by each filter can be received by the corresponding detector. After the filter array 13 filters the medium-wave convergent light and the long-wave convergent light, the light of the corresponding wavelength will be focused on the detector array 14. The detector array 14 converts the received optical signal into an electrical signal, and converts the electrical signal into a digital image through a further signal processing circuit. This image contains the spectral radiation information of the target object, that is, the distribution of radiation intensity at different wavelengths, realizes multi-spectral synchronous acquisition, and obtains an image containing spectral information.

[0062] From the above description, it can be known that the present invention effectively separates the medium-wave radiation and long-wave radiation of the target object through the front optical module, and performs reduced projection of the medium-wave radiation and the long-wave radiation, which helps to improve the convergence effect of subsequent light. Furthermore, the medium-wave radiation and the long-wave radiation after reduced projection are focused and converged by a microlens array to form medium-wave converged light and long-wave converged light, thereby improving the energy density of the light. The detector array can respectively collect the filtered medium-wave converged light and the long-wave converged light in multiple spectral bands to obtain the target spectral radiation image, and can simultaneously obtain the radiation information of the target object in different bands, thereby realizing high-sensitivity and high-precision spectral radiation measurement, which helps to more accurately reflect the actual temperature state of the target object and improve the accuracy and reliability of the entire temperature measurement system.

[0063] like Figure 2 As shown, Figure 2 A schematic diagram of a flow chart of an embodiment of an infrared broadband multi-spectral radiation temperature measurement method provided by the present invention. An infrared broadband multi-spectral radiation temperature measurement method, the method comprising:

[0064] S101: separating the medium-wave radiation and the long-wave radiation of the spectral radiation of the target object, and reducing the projection of the medium-wave radiation and the long-wave radiation.

[0065] For example, referring to Figure 3 , Figure 3 A schematic diagram of the structure of another embodiment of an infrared wide-band multi-spectral radiation temperature measurement device provided by the present invention. The medium-wave radiation and the long-wave radiation are separated by the front module 11, and the target object is reduced and projected onto the microlens array. Specifically, the front optical module 11 includes a front lens 111 and a beam splitter 112, wherein the beam splitter 112 is used to effectively separate the medium-wave radiation and the long-wave radiation in the spectral radiation of the target object collected by the lens.

[0066] S102: focusing and converging the medium-wave radiation and the long-wave radiation respectively to obtain medium-wave converged light and long-wave converged light.

[0067] Exemplarily, the microlens array 12 includes a plurality of microlenses, which are arranged in a specific matrix. When the medium-wave radiation and long-wave radiation of the target object pass through the front optical module and are projected onto the microlens array, each microlens of the microlens array will focus the medium-wave radiation and the long-wave radiation respectively and converge them onto the filter array 13 to obtain medium-wave converged light and long-wave converged light.

[0068] S103: receiving the corresponding medium-wave converged light and long-wave converged light, and filtering the medium-wave converged light and the long-wave converged light respectively.

[0069] Exemplarily, the filter array 13 includes a plurality of narrow bandpass filters with different central wavelengths, each of which is designed to transmit light of a specific wavelength band and block light of other wavelength bands. The plurality of narrow bandpass filters with different central wavelengths are arranged in a matrix, and are optically arranged corresponding to the microlens array, and receive corresponding medium-wave converged light and long-wave converged light, and filter the medium-wave converged light and the long-wave converged light respectively.

[0070] S104: performing multi-spectral acquisition on the filtered medium-wave converged light and the long-wave converged light respectively to obtain a target spectral radiation image.

[0071] Exemplarily, the high-speed detector pixel array 14 corresponds to the filter array 13 one by one, ensuring that the optical signal filtered by each filter can be received by the corresponding detector. After the filter array 13 filters the medium-wave convergent light and the long-wave convergent light, the light of the corresponding wavelength will be focused on the detector array 14. The detector array 14 converts the received optical signal into an electrical signal, and converts the electrical signal into a digital image through a further signal processing circuit. This image contains the spectral radiation information of the target object, that is, the distribution of radiation intensity at different wavelengths, realizes multi-spectral synchronous acquisition, and obtains an image containing spectral information.

[0072] Furthermore, the wavelength of the target spectral radiation image is calibrated to determine the calibration relationship between the wavelength and the grayscale value; the radiation calibration of the target spectral radiation image is performed to determine the calibration relationship between the temperature and the grayscale value; based on the calibration relationship between the wavelength and the grayscale value and the calibration relationship between the temperature and the grayscale value, according to the spectral emissivity model, the grayscale value of each wavelength of the target object at different temperatures is obtained, and the grayscale value of each wavelength at different temperatures is used as the temperature measurement data; a multi-spectral temperature measurement model is constructed according to the state-space model and the multi-layer perceptron; the multi-spectral temperature measurement model is trained according to the temperature measurement data; the real temperature of the target spectral radiation image is inverted using the trained multi-spectral temperature measurement model to obtain the temperature field distribution of the target object.

[0073] From the above description, it can be seen that the present invention performs wavelength calibration and radiation calibration on the target spectral radiation image, and establishes the corresponding relationship between the pixel grayscale value and the incident radiation illumination through calibration. Based on the calibration relationship between wavelength and grayscale value and the calibration relationship between temperature and grayscale value, the multi-spectral temperature measurement model is used to invert the target real temperature, thereby calculating the actual target object temperature field distribution and more accurately measuring the temperature of the target object.

[0074] like Figure 4 As shown, Figure 4 A schematic flow chart of another embodiment of an infrared broadband multi-spectral radiation temperature measurement method provided by the present invention. An infrared broadband multi-spectral radiation temperature measurement method, the method comprising:

[0075] S201: performing wavelength calibration on the target spectral radiation image to determine the calibration relationship between wavelength and grayscale value.

[0076] Exemplarily, in a lightless environment, the monochromatic radiation energy of the target spectral radiation image at different wavelengths is obtained; the grayscale value of each pixel area in the target spectral radiation image is determined according to the monochromatic radiation energy of the target spectral radiation image at different wavelengths; the effective wavelength value corresponding to the maximum grayscale value in the current pixel area is determined according to the grayscale value of each pixel area, and the grayscale value and wavelength of the pixel area are calibrated.

[0077] S202: Perform radiation calibration on the target spectral radiation image to determine the calibration relationship between temperature and grayscale value.

[0078] For example, at each fixed temperature interval, the temperature of the black body furnace is raised and the current temperature is stabilized for a preset time, and then the radiation data of the target spectral radiation image is collected until the temperature reaches a preset temperature threshold; the radiation data of the target spectral radiation image is fitted according to the least squares method to determine the calibration relationship between temperature and grayscale value. The calibration relationship between temperature and grayscale value is shown in the following formula:

[0079]

[0080] Among them, V i is the pixel grayscale value of the i-th wavelength, A1 is a constant independent of temperature, B1 is a coefficient inversely proportional to the temperature, and C1 is a coefficient inversely proportional to the square of the temperature.

[0081] S203: Based on the calibration relationship between wavelength and grayscale value and the calibration relationship between temperature and grayscale value, according to the spectral emissivity model, the grayscale value of each wavelength of the target object at different temperatures is obtained, and the grayscale value of each wavelength at different temperatures is used as temperature measurement data.

[0082] Exemplarily, based on the calibration relationship between wavelength and grayscale value and the calibration relationship between temperature and grayscale value, the grayscale value of each wavelength of the target object at different temperatures is obtained according to the actual measured data of the sensor combined with the spectral emissivity model, the grayscale values ​​of different wavelengths are selected as temperature measurement data, and the temperature measurement data are used as training samples for the network.

[0083] S204: Construct a multi-spectral temperature measurement model based on the state space model and the multi-layer perceptron.

[0084] Exemplarily, a multi-spectral temperature measurement model is constructed based on the state space model and the multi-layer perceptron. Figure 5 , Figure 5 A schematic diagram of the structure of an embodiment of the multi-spectral temperature measurement model provided by the present invention. The network model of the linear sequence module Mamba is used to train the multi-spectral temperature measurement data, wherein Mamba black filters irrelevant information through the state space model (The State Space Model, SSM) and remembers relevant information indefinitely, thereby improving the performance of the model when processing discrete and information-intensive data (such as text). Using the strong generalization ability of Mamba black, different types of sequence data can be processed to improve the efficiency and performance of processing long sequence data. Through Mamba's hardware-aware parallel algorithm, the training stability can be improved.

[0085] S205: Training a multi-spectral temperature measurement model according to the temperature measurement data.

[0086] For example, referring to Figure 5 The temperature measurement data of multi-spectral radiation is a one-dimensional six-channel vector. First, the input layer input is modified to 6×1 to use the temperature measurement data. At the same time, in order to improve the calculation efficiency and avoid overfitting, the number of network layers is appropriately simplified, and the convolution layer is changed from 3×3 to 2×1. The temperature measurement data is feature extracted, and the temperature measurement data after feature extraction is updated according to the state space model. Specifically, the state matrix data of the updated temperature measurement data is determined according to the following formula:

[0087] hk(t)=A2hk-1(t)+B2X(t);

[0088] Among them, hk(t) is the updated state matrix data, hk-1(t) is the state matrix data of the temperature measurement data, A2 is the state transfer matrix, and B2 is the input matrix.

[0089] The updated temperature measurement data is determined according to the following formula:

[0090] Y(t) = C2hk(t);

[0091] Among them, Y(t) is the updated temperature measurement data, C2 is the output matrix, and hk(t) is the updated state matrix data.

[0092] Furthermore, the updated temperature measurement data (input data) is passed through the MLP (Multi-Layer Perceptron) block, and nonlinearity is introduced in the hidden layer using an activation function. By training the input-output data, complex nonlinear function mapping can be learned, and the mapping relationship from input to output can be learned. Through the generalization ability of MLP, new inputs can be predicted or classified to obtain temperature prediction values; and the good parallelization of the forward propagation and back-propagation processes of MLP can be used to improve the network computing efficiency.

[0093] At the same time, the gap between the predicted temperature value and the true temperature value is determined by the semi-mean square error loss until the gap between the predicted temperature value and the true temperature value reaches the preset threshold, completing the training of the multi-spectral temperature measurement model.

[0094] S206: Using the trained multi-spectral temperature measurement model to invert the real temperature of the target spectral radiation image, and obtain the temperature field distribution of the target object.

[0095] Exemplarily, the infrared wide-band multi-spectral radiation temperature measurement device measures the radiation intensity of the target object (E=σT^4, where E represents the thermal radiation intensity, σ is the Stefan-Boltzmann constant, and T is the absolute temperature of the object), establishes the correspondence between the pixel grayscale value and the incident radiation illuminance through calibration, and uses the trained multi-spectral temperature measurement model to invert the true temperature of the target spectral radiation image, thereby obtaining the temperature field distribution of the actual target object.

[0096] like Figure 6 As shown, Figure 6 The device 20 includes a memory 21 and a processor 22. The memory 21 stores a computer program, and the processor 22 executes the computer program when working to implement the following. Figure 2 and Figure 4 The method shown.

[0097] The specific technical details of an infrared wide-band multi-spectral radiation temperature measurement method implemented when the above-mentioned device 20 executes a computer program have been discussed in detail in the aforementioned method steps, so they will not be repeated here.

[0098] like Figure 7 As shown, Figure 7 The structure diagram of an embodiment of the medium provided by the present invention is shown in FIG. The medium 30 stores at least one computer program 31, and the computer program 31 is executed by the processor 22 to implement the following Figure 2 and Figure 4In one embodiment, the medium 30 may be a storage chip, a hard disk, a mobile hard disk, a USB flash drive, an optical disk, or other readable and writable storage tools, or a server, etc.

[0099] Additionally, the processes depicted in the figures do not necessarily have to be performed in the particular order shown or in sequential order to achieve desired results. In certain implementations, multitasking and parallel processing are also possible or may be advantageous.

[0100] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0101] The apparatus, device, non-volatile computer-readable storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding apparatus, device, and non-volatile computer storage medium will not be repeated here.

[0102] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0103] For the convenience of description, the above device is described by being divided into various units according to their functions and described separately. Of course, when implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware. It should be understood by those skilled in the art that this specification embodiment can be provided as a method, system, or computer program product. Therefore, this specification embodiment can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification embodiment can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] This specification is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0108] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0109] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0110] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0111] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0112] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0113] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. An infrared wide-band multi-spectral radiation temperature measurement device, characterized in that: The device comprises: a front optical module, a microlens array, a filter array and a detector array. The front optical module is used to separate the medium-wave radiation and the long-wave radiation of the target object, and to reduce and project the medium-wave radiation and the long-wave radiation onto the microlens array; The microlens array is used to focus and converge the medium-wave radiation and the long-wave radiation after the reduced projection to obtain medium-wave converged light and long-wave converged light; The filter array is used to receive the corresponding medium-wave converged light and long-wave converged light, and filter the medium-wave converged light and long-wave converged light respectively; The detector array is used to collect the filtered medium-wave converged light and long-wave converged light in multiple spectral bands to obtain a target spectral radiation image.

2. An infrared wide-band multi-spectral radiation temperature measurement method, characterized in that: The method comprises: Separating the medium-wave radiation and the long-wave radiation of the spectral radiation of the target object, and reducing the projection of the medium-wave radiation and the long-wave radiation; Focusing and converging the reduced-projected medium-wave radiation and the long-wave radiation to obtain medium-wave converged light and long-wave converged light; receiving the corresponding medium-wave converged light and long-wave converged light, and filtering the medium-wave converged light and long-wave converged light respectively; The filtered medium-wave converged light and long-wave converged light are respectively collected in multiple spectral bands to obtain a target spectral radiation image.

3. The infrared wide-band multi-spectral radiation temperature measurement method according to claim 2, characterized in that: After respectively performing multi-spectral acquisition on the filtered medium-wave converged light and the long-wave converged light to obtain the target spectral radiation image, the method specifically includes: Performing wavelength calibration on the target spectral radiation image to determine the calibration relationship between wavelength and grayscale value; Performing radiation calibration on the target spectral radiation image to determine the calibration relationship between temperature and grayscale value; Based on the calibration relationship between the wavelength and the grayscale value and the calibration relationship between the temperature and the grayscale value, according to the spectral emissivity model, the grayscale value of each wavelength of the target object at different temperatures is obtained, and the grayscale value of each wavelength at the different temperatures is used as temperature measurement data; Construct a multi-spectral temperature measurement model based on the state space model and multi-layer perceptron; Training the multi-spectral temperature measurement model according to the temperature measurement data; The trained multi-spectral temperature measurement model is used to invert the real temperature of the target spectral radiation image and obtain the temperature field distribution of the target object.

4. The infrared wide-band multi-spectral radiation temperature measurement method according to claim 3 is characterized in that: The wavelength calibration of the target spectral radiation image to determine the calibration relationship between the wavelength and the grayscale value specifically includes: In a lightless environment, obtaining the monochromatic radiation energy of the target spectral radiation image at different wavelengths; Determine the grayscale value of each pixel area in the target spectral radiation image according to the monochromatic radiation energy of the target spectral radiation image at different wavelengths; The effective wavelength value corresponding to the maximum grayscale value in the current pixel area is determined according to the grayscale value of each pixel area, and the grayscale value and wavelength of the pixel area are calibrated.

5. The infrared wide-band multi-spectral radiation temperature measurement method according to claim 3, characterized in that: The step of performing radiation calibration on the target spectral radiation image to determine the calibration relationship between temperature and grayscale value specifically includes: At fixed temperature intervals, the temperature of the black body furnace is raised and after the current temperature is stabilized for a preset period of time, the radiation data of the target spectrum radiation image is collected until the temperature is raised to a preset temperature threshold; The radiation data of the target spectral radiation image is fitted according to the least square method to determine the calibration relationship between temperature and grayscale value.

6. The infrared wide-band multi-spectral radiation temperature measurement method according to claim 5, characterized in that: The step of fitting the radiation data of the target spectral radiation image according to the least square method to determine the calibration relationship between temperature and grayscale value specifically includes: according to Determine the calibration relationship between temperature and grayscale value, where V i is the pixel grayscale value of the i-th wavelength, A1 is a constant independent of temperature, B1 is a coefficient inversely proportional to the temperature, and C1 is a coefficient inversely proportional to the square of the temperature.

7. The infrared wide-band multi-spectral radiation temperature measurement method according to claim 3, characterized in that: The training of the multi-spectral temperature measurement model according to the temperature measurement data specifically includes: Extracting features from the temperature measurement data, and updating the temperature measurement data after feature extraction according to a state space model; Predicting the updated temperature measurement data to obtain a temperature prediction value; The gap between the predicted temperature value and the true temperature value is determined by the semi-mean square error loss until the gap between the predicted temperature value and the true temperature value reaches a preset threshold, thereby completing the training of the multi-spectral temperature measurement model.

8. The infrared wide-band multi-spectral radiation temperature measurement method according to claim 7, characterized in that: The extracting features from the temperature measurement data and updating the temperature measurement data after feature extraction according to the state space model specifically includes: Determine the state matrix data of the updated temperature measurement data according to hk(t)=A2hk-1(t)+B2X(t), wherein hk(t) is the updated state matrix data, hk-1(t) is the state matrix data of the temperature measurement data, A2 is the state transfer matrix, and B2 is the input matrix; The updated temperature measurement data is determined according to Y(t)=C2hk(t), wherein Y(t) is the updated temperature measurement data, C2 is the output matrix, and hk(t) is the updated state matrix data.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 2 to 8.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 2 to 8.

Images