141 results about "Infrared remote sensing" patented technology

The invention discloses an intelligent monitoring and early warning method for gas concentration of an ultra-thin coal seam, and belongs to the technical field of gas monitoring. The method comprises the following steps: transmitting gas data to a ground platform in real time by using a 5G technology through monitoring devices and worker portable equipment which are arranged in each underground area; constructing an underground three-dimensional model by combining infrared remote sensing and a visualization technology, dividing a working area and generating a gas concentration stereogram; a width learning neural network optimized by an SCSO algorithm is adopted to predict concentration change, and a dynamic early warning system is established in combination with weighted optimization analysis of regional ventilation capacity; and finally, a regional standard exceeding alarm is sent to a monitoring device and personnel equipment through 5G communication, so that accurate positioning early warning is realized. According to the method, multi-dimensional data modeling and an intelligent algorithm are fused, and the real-time performance and accuracy of gas monitoring of the ultra-thin coal seam are improved.

The invention relates to the technical field of image processing, and discloses an infrared image enhancement method and system based on local phase correlation, and the method comprises the steps: obtaining a plurality of continuous frames of infrared images, carrying out the intelligent partitioning of a reference frame, and calculating the variance feature, the method comprises the following steps: selecting regions of interest with rich information, independently executing phase correlation operation in each region to extract a local translation vector, obtaining global displacement estimation through weighted fusion, adopting an abnormal value detection algorithm to improve robustness, and finally realizing sub-pixel-level image alignment and intelligent weighted fusion. The method is suitable for real-time enhancement processing of satellite-borne infrared remote sensing images, the resource constraint requirement of an embedded platform is met while the processing quality is guaranteed, and an efficient and reliable technical scheme is provided for space remote sensing image processing.

The invention discloses a target detection method based on an image semantic matching algorithm, and the method comprises the steps: carrying out the multi-source data collection through an image sensor, an SAR (Synthetic Aperture Radar) radar and infrared remote sensing equipment which are carried by an unmanned plane, and obtaining a visible light image, a high-resolution radar image and thermal imaging data in a low-light environment; carrying out target identification on different data sources by utilizing an integrated learning method; judging whether the target is a tank or not by adopting a soft voting fusion strategy; after the tank is detected, the crossing unmanned aerial vehicle is dispatched to adjust a flight path, and image data with higher resolution are obtained; a deep learning model is trained based on an image semantic matching technology, semantic analysis is performed on a high-precision image, and weak parts of a target are automatically identified and labeled by matching standard part features. According to the method, the multi-modal source data is fused, the reliability of tank recognition is improved, the weak part of the target is accurately positioned by combining the image semantic matching technology, the method can adapt to a complex battlefield environment, and the intelligent level of battlefield intelligence analysis is improved.

A method for spatial reconstruction and downscaling of all-sky surface temperature belongs to the field of remote sensing science and technology. It contains the following main steps: acquisition and preprocessing of multi-source remote sensing data and atmospheric driven data, spatial reconstruction of all-sky surface temperature data, and spatial downscaling of all-sky surface temperature data. The operability and universality of the present invention in practical applications will promote the popularization and application of surface temperature data in the fields of climate change, dynamic monitoring and assessment of hydrological and ecological environment, land surface radiation budget and energy balance, and further promote the development of thermal infrared remote sensing science.

The invention discloses a background spectrum accurate acquisition method for infrared remote measurement in a complex scene, and the method comprises the steps: carrying out the division of sky and ground object backgrounds for an input background image, and selecting different radiation spectrum generation modes based on a division result; if yes, sky radiation spectrum extraction is carried out based on an MODTRAN radiation transfer model; if the background is judged to be a single ground object background, performing background spectrum extraction by adopting ELM-EMD (Extreme Learning Mode-Empirical Mode Decomposition) which is extracted in real time based on a measurement spectrum and changes slowly at low frequency; and if the background is not single, fusion of the two spectrum extraction modes is adopted. The method has the advantages that the background classification method with the visible image as the reference is adopted, the difference of infrared radiation characteristics of the sky background and the ground feature background is analyzed, different spectrum extraction modes are selected according to the difference, and therefore accurate obtaining of the target smoke plume transmittance spectrum is achieved.

The invention relates to the technical field of absolute radiometric calibration of satellite infrared remote sensing sensors, and provides a method for analyzing sensitivity of infrared remote sensing calibration black body emissivity to equivalent radiation, which comprises the following steps of: 1, selecting a specific satellite data file as an experimental sample; step 2, extracting key temperature data from the selected data file; 3, performing data calculation according to the data extracted in the step 2; and 4, calculating the equivalent emergent radiation of the black body by using a Planck function and the emissivity of the black body. According to the method, the equivalent emergent radiation of the satellite infrared remote sensing calibration black body is accurately calculated, so that the absolute radiation calibration precision of the satellite infrared remote sensor on the on-satellite black body is effectively improved, and the defects of large workload and low frequency of site calibration, high implementation threshold of cross calibration and the like can be effectively overcome; therefore, high-frequency and automatic radiometric calibration of the on-orbit infrared channel of the remote sensing satellite is realized.

A detection method for determining the communication availability of a satellite-to-ground laser link based on sky infrared remote sensing images comprises the following steps: 1) obtaining meteorological information and sky infrared remote sensing images above a satellite-to-ground laser communication ground station; 2) calculating the corresponding elevation angle and position relationship between the satellite and the ground station at each moment, and calculating the cloud base height and cloud optical depth of the spatial region through which the satellite-to-ground link passes based on the meteorological information and the sky infrared remote sensing images; 3) using a Monte Carlo laser vector transmission model to model the cloud laser channel based on the corresponding elevation angle and position relationship, cloud base height, and cloud optical depth results between the satellite and the ground station at each moment, and normalizing the residual to serve as a reference value for the link communication availability; 4) judging the communication availability of the laser link between the satellite and the ground station based on the atmospheric turbulence obtained in step 1; and 5) predicting future sky infrared remote sensing image change information of a specified satellite-to-ground laser ground station using machine learning technology.

The invention provides a control system and method for a Fourier interference infrared spectral imaging remote sensing instrument, and relates to the technical field of infrared remote sensing, and the system comprises a main control module, a sub-control module, a control interface, an execution element and a spectral imaging display system. And the main control module is used for controlling the sub-control module to control the execution element through the control interface according to a logic process set by a program so as to obtain Fourier interference infrared spectral imaging remote sensing data of an observation target, and completing display and control functions of a human-computer interaction interface through the spectral imaging display system. According to the invention, centralized control management of an optical-mechanical-electrical-thermal whole system of an instrument is realized, automatic work and operation of a remote sensing instrument system are realized, and rapid acquisition and analysis of Fourier interference infrared spectrum imaging are realized by using an area array detector.

The invention discloses a deep learning-based satellite remote sensing collapsible loess foundation evaluation method, which comprises the following steps of: acquiring an optical remote sensing image, a radar remote sensing image and an infrared remote sensing image of a target area, and preprocessing; collapsibility feature weighted data are screened, and feature weights are distributed; feature extraction is carried out through a local space exhibition structure and a multi-layer Transform structure of the collapsibility foundation evaluation network; collapsibility area self-supervised collaborative learning is carried out, and self-supervised training is carried out based on spatial correlation, pseudo labels and spatial consistency regular terms; and carrying out risk grade division on the target area, and outputting a collapsibility risk result of each spatial position. According to the method, multi-mode remote sensing and deep learning are fused, high-precision intelligent partitioning of the collapsible loess foundation is achieved, and the method has the advantages of being self-adaptive, low in manpower and high in spatial resolution.

The invention provides a soybean growth monitoring method based on satellite remote sensing, and relates to the technical field of crop growth monitoring, and the method specifically comprises the steps: setting two monitoring nodes according to a soybean growth period, and collecting multispectral and thermal infrared remote sensing images and normal growth leaf area density and stem diameter sample data; a soybean area and a non-soybean area are distinguished by using a vegetation index threshold, cloud / shadow pixels are eliminated by using a multiband combination-threshold method, effective pixels are screened, and two types of remote sensing data are matched. Extracting leaf area density, canopy temperature and collaborative inversion stem diameter from the effective data; calculating the relative growth rate of the two types of indexes based on samples, and constructing a collaborative growth reference equation and a residual standard deviation; and substituting the growth rate of the planting area into an equation to obtain a theoretical value, calculating a deviation value, and judging the soybean growth state by combining the comparison between the deviation and a normal fluctuation interval and the positive and negative characteristics of the growth rate.

The invention discloses an infrared target detection method based on a bidirectional receptive field attention feature network, which is realized by constructing a model comprising a feature coding network, a feature fusion network and a detection head, and improves the detection precision and model generalization ability of an infrared remote sensing image, especially a small target. A receiving field attention convolution module is introduced into the feature coding network, different spatial positions in a receptive field are independently weighted, fine-grained feature extraction is enhanced, and the problem that multi-scale target feature extraction is insufficient is solved; further, the feature coding network optimizes feature extraction and fusion operations by alternately stacking RFAConv modules and standard convolution modules, so that key features of a target are reserved and enhanced to the greatest extent, and the problem of poor adaptability of a complex background is solved; the feature fusion network adopts a bidirectional feature pyramid network, high-level semantics and low-level detail information are bidirectionally and efficiently fused, and the problem of information loss in the fusion process is solved.

The invention discloses a lightweight unmanned aerial vehicle infrared remote sensing target detection method and device based on knowledge distillation, and belongs to the technical field of infrared weak and small target image recognition and deep learning model compression. In order to solve the problems of low detection precision, high omission ratio, high calculation complexity and difficulty in deployment at edge equipment of an existing unmanned aerial vehicle infrared remote sensing image weak and small target detection algorithm, an infrared remote sensing image data set is constructed, and a basic network model containing an intra-scale feature efficient interaction and fusion module is constructed; a teacher model and a student model are designed, a lightweight student network is trained by using a channel dimension knowledge distillation mechanism, and optimization is performed by using a WIoU loss function based on a distance attention mechanism and a soft-NMS, so that multi-scale feature fusion and model compression are realized. According to the method, the accuracy and robustness of weak and small target detection are improved, the model parameter quantity and the calculation quantity are reduced, and the method is suitable for real-time application in the fields of environmental monitoring, military reconnaissance and the like.

The invention provides a transformer substation noise traceability and diffusion simulation method fusing multi-source remote sensing data. Belongs to the technical field of power environment protection and remote sensing science. The method comprises the following steps: acquiring thermal infrared remote sensing image data of a transformer substation, after preprocessing, finding out a temperature anomaly region of main noise source equipment by using a temperature anomaly recognition algorithm, determining the position of the main noise source equipment in combination with equipment layout information, and generating position data of the noise source equipment; a laser radar is used for scanning a transformer substation and surrounding areas to obtain high-precision point cloud data, the high-precision point cloud data are processed to generate high-precision digital elevation model data, and a transformer substation three-dimensional scene model containing detailed topographic features and noise source positions is constructed in combination with noise source equipment position data. Temperature abnormity of main noise source equipment is identified by means of thermal infrared images, noise sources of specific equipment such as a main transformer and an electric reactor can be accurately positioned, equipment-level traceability is realized, the situation that traceability is difficult in a traditional method is changed, and a clear direction is provided for targeted noise treatment.

The invention discloses a cross radiation calibration method and device for artificial intelligence correction, and belongs to the technical field of electronic information, and the method comprises the steps: S1, obtaining a sample pair through a space-time matching method, and carrying out the fitting of sample data, and obtaining a fitting curve; s2, a series of time points are selected, and temperature measurement values of the light path component of the infrared remote sensing instrument at the time points are obtained; inputting the output values of the remote sensing instrument to be calibrated corresponding to the selected series of time points into the fitting curve to obtain corresponding cross calibration result values; s3, taking the output value of the remote sensing instrument to be calibrated and the temperature measurement value of the optical path component of the infrared remote sensing instrument as the input of a neural network, taking the cross calibration result value as the output of the neural network, and training the neural network; and S4, obtaining a calibration result of the remote sensing instrument at any moment through network output. According to the invention, any short-time single-time radiometric calibration result can be provided.

The invention relates to an unmanned aerial vehicle infrared remote sensing image weak and small target detection method and device. The method comprises the steps of obtaining a to-be-detected infrared remote sensing image; the to-be-detected infrared remote sensing image is input into a preset target detection model, a weak and small target detection result is output, the target detection model is obtained by inputting a training set and adopting a WIoU loss function based on a distance attention mechanism for training, the training set comprises the infrared remote sensing image and a corresponding target label, and the target label is a target label corresponding to the infrared remote sensing image. The target detection model is constructed by introducing an intra-scale feature efficient interaction mechanism and a non-maximum suppression mechanism into a yolk-based target detector. According to the method, the feature information in the infrared remote sensing image can be effectively utilized, and the detection accuracy and robustness of the weak and small target are improved.

The invention discloses an infrared and visible light remote sensing image deep learning fusion method based on a visual state space model. The method comprises the following steps: acquiring an infrared remote sensing image and a visible light remote sensing image to be fused; the infrared remote sensing image and the visible light remote sensing image are spliced and then input into a pre-constructed and trained image fusion network model, a fusion image output by the image fusion network model is obtained, and the image fusion network model comprises a first convolution module, a double-attention residual module, a multidirectional scanning module and a second convolution module which are connected in sequence. The first convolution module is used for extracting image shallow layer features, the double-attention residual module is used for extracting and fusing important features of an infrared remote sensing image and a visible light remote sensing image, the multi-direction scanning module is used for obtaining global features of the images in multiple directions, and the second convolution module is used for recovering image dimensions and obtaining a fused image; and outputting the fused image. According to the invention, infrared remote sensing image information and visible light remote sensing image information can be fully fused.

This invention provides a method, apparatus, and device for generating high-fidelity infrared remote sensing images. The method includes: acquiring a visible light remote sensing image to be processed; cropping the visible light remote sensing image to obtain a cropped visible light remote sensing image; and inputting the cropped visible light remote sensing image into a pre-trained infrared image generation network to generate a corresponding high-fidelity infrared remote sensing image. Specifically, during the training process of the pre-trained infrared image generation network, visible light remote sensing image samples are used as input data, while radiation spectral characteristic mapping data is embedded as prior information into the design of the pre-trained infrared image generation network. A specific loss function is designed to guide the learning direction of the pre-trained infrared image generation network. This allows the interpretability of the physical model to enhance the generalization ability and reliability of the deep learning model, thereby improving the fidelity and reliability of the high-fidelity infrared remote sensing image ultimately generated by the pre-trained infrared image generation network.

The invention discloses a multi-mode remote sensing image weak and small target detection method based on super-resolution. The method comprises the following steps that firstly, feature fusion is carried out on input RGB and infrared remote sensing images through BFM to generate comprehensive features, and the BFM can effectively make up for the defect that weak and small target information is insufficient in a single mode; the features are then sent to a backbone network to generate multi-level features. Secondly, a backbone network in the SA-YOLO is responsible for further fusing the multi-level features in a feature pyramid network, and then classification and regression are carried out in a detection head; a branch network in SA-YOLO selects low-level and high-level features output by a backbone network, and local texture and semantic information are fused to carry out super-resolution reconstruction. According to the method provided by the invention, the detection precision of the weak and small target in the multi-mode remote sensing image is effectively improved, and the method has a wide application prospect in the aspects of military reconnaissance, civil monitoring, disaster early warning and the like.

The invention relates to a multi-source remote sensing image-based visual large model construction method, device and equipment and a medium, and the method comprises the steps: researching a multi-source remote sensing image-based visual large model for solving the problems that the image feature difference of an optical remote sensing image, an SAR remote sensing image and an infrared remote sensing image is large, and the cross-source generalization of the model is weak; by fusing multi-modal data complementary features and establishing a cross-source target unified representation space, the bottleneck that a single model is insufficient in adaptability to different image source features is solved, the relevance of target texture, geometry and radiation characteristics in a multi-source image is emphatically mined, a multi-level feature interaction and adaptive fusion mechanism is designed, and the multi-source image feature fusion is realized. The semantic consistency understanding of the model on the cross-source target is enhanced, a visual large model with strong generalization ability is finally constructed, a high-precision supervision signal is provided for an on-satellite lightweight small model, and the stability of the cross-source remote sensing image target detection performance is ensured. According to the method, the dependence on the target domain annotation data can be reduced, so that the model keeps good generalization ability.

The invention belongs to the technical field of computer vision and mode recognition, and particularly relates to an end-to-end weak alignment multispectral remote sensing image target detection method and device. The method specifically comprises the following steps of: constructing training data: labeling preset weak alignment visible light and infrared remote sensing images to obtain a weak alignment multispectral remote sensing image target detection data set; target detection network construction: constructing an end-to-end weak alignment multispectral remote sensing image target detection network, wherein the end-to-end weak alignment multispectral remote sensing image target detection network comprises a feature coding network, a query selection network and a decoding network; training a target detection network: training the target detection network by using the target detection data set; and remote sensing image target detection: performing remote sensing image target detection by using the trained target detection network, wherein a detection result comprises a target category, a visible light target position and an infrared target position.

The invention discloses a remote sensing image automatic classification system and method based on deep learning, which relates to the field of image processing technology, and comprises an infrared remote sensing module, an image classification module, and a landform determination module. The infrared remote sensing module is used to scan the ground of a grazing area by using infrared remote sensing technology. The image classification module is used to distinguish the types of infrared scanning images and to establish a far-infrared scanning map of the grazing area. The landform determination module is used to name the landform according to the analysis result of heat distribution and to predict the changing rules of various landforms with the seasons. The infrared remote sensing module comprises a near-infrared band sensor, a mid-infrared band sensor, a far-infrared band sensor, a data acquisition module, a sensor control module, a GPS positioning module, a scanning area definition module, and a drone. The invention has the characteristic of automatically determining the infrared image signal corresponding to the landform.

This invention provides a method for creating an infrared small target detection dataset, including S1, segmenting a satellite infrared remote sensing image to obtain at least two background images with different environments; S2, creating simulated target points; S3, adding simulated target points to the background images and fusing them with the background images; and S4, expanding the dataset of simulated target points. This invention uses space-based remote sensing satellite images as a background, providing a large data foundation for remote sensing infrared small target detection; it achieves diversity in complex backgrounds, motion characteristics of small targets, morphological diversity of small targets, and type diversity of small targets, making the simulated data closer to the required real data and greatly enriching the content of the dataset.

The embodiment of the invention discloses a method and device for generating a cloud picture by using multi-spectral long-wave infrared remote sensing data and electronic equipment. A specific embodiment of the method comprises the following steps: acquiring long-wave infrared remote sensing data of a plurality of spectral segments, determining brightness temperature information corresponding to the long-wave infrared remote sensing data of each spectral segment, and determining pseudo-emissivity corresponding to the long-wave infrared remote sensing data of each spectral segment based on the brightness temperature information corresponding to the long-wave infrared remote sensing data of each spectral segment; performing normalization processing on the pseudo-emissivity to obtain normalized pseudo-emissivity information corresponding to the long-wave infrared remote sensing data of each spectrum segment; and thus, a color cloud picture for indicating weather information is generated. In this way, the generated color cloud picture can be utilized to effectively distinguish the ground surface, the high cloud, the low cloud and other areas. Therefore, high-frequency effective information can be provided, and weather forecast personnel can master the actual weather condition conveniently.

The application relates to the technical field of image processing, and discloses an infrared image enhancement method and system based on local phase correlation, wherein the infrared image enhancement method based on local phase correlation is used for acquiring continuous multiple infrared images, performing intelligent block division on a reference frame, calculating variance features, selecting an information-rich region of interest, independently performing phase correlation operation in each region to extract a local translation vector, obtaining global displacement estimation through weighted fusion, improving robustness by using an outlier detection algorithm, and finally realizing sub-pixel level image alignment and intelligent weighted fusion. The application is suitable for real-time enhancement processing of spaceborne infrared remote sensing images, can guarantee processing quality while meeting the resource constraint requirements of an embedded platform, and provides an efficient and reliable technical scheme for space remote sensing image processing.

The invention is suitable for the technical field of infrared telemetering gas detection and data processing optimization, and provides a multi-source infrared telemetering gas identification optimization method and system, and the method comprises the steps: sorting samples from small to large according to the average value of the actual conveying speed corresponding to a speed increase event in each sample, and analyzing the change trend of the compensation residual optimization degree along with the actual conveying speed based on the sample feature information so as to judge whether a turning interval which firstly ascends and then descends exists or not, and if yes, adjusting the set conveying speed of the belt type conveying device based on the actual conveying speed of the speed increasing event of each sample in the turning interval. According to the method, a technical thought of reversely optimizing the infrared telemetering methane recognition performance by utilizing micro speed fluctuation caused by the maintenance period is provided for the first time by systematically analyzing a slight speed increase event naturally generated by the belt type conveying device in the maintenance period.

The application discloses a kind of multi-wavelength pumped mid-infrared upconversion spectral detection methods, its characteristics are that the method uses multi-wavelength narrowband laser as the pump source of nonlinear conversion, simultaneously adopt multi-period quasi-phase matching crystal as nonlinear upconversion medium, realize mid-infrared signal broadband and efficient conversion, and combine high-performance near-infrared spectral measurement and control element, finally obtain wide band, high resolution, ultra-sensitive mid-infrared spectral detection.The application has the characteristics of large bandwidth and high efficiency compared with existing upconversion spectral technology, simultaneously can high fidelity resolution mid-infrared spectral information, for realizing wide band, high resolution, ultra-sensitive mid-infrared spectral measurement provides effective means, is expected to be applied to molecular spectroscopy, trace substance detection, infrared remote sensing and atmospheric monitoring and other important fields.

The embodiments of the present invention provide a method, device, and computer equipment for identifying target types in infrared remote sensing images. The method extracts the radiation and motion characteristics of targets in infrared remote sensing images, plots characteristic curves as experimental data sets for this technology, feeds the data into a feature extraction network, and adds an attention module to the network structure to obtain the discriminative key features of the characteristic curves for each category. The loss function is designed to improve the imbalance problem in the data. Currently, relatively good experimental results can be obtained for high-speed targets such as rockets, ballistic missiles, and hypersonic aircraft. Using characteristic curves with large amounts of data to classify targets solves the difficulty of identifying target types, which only professionals can do, and is also superior to the latest existing technologies in terms of recognition accuracy.

The utility model is suitable for the technical field of electric power engineering, and provides an electric power engineering construction investigation device which comprises an unmanned aerial vehicle body, a camera, a spectrograph, an infrared remote sensing analyzer and a glass protective cover are installed on the bottom face of the unmanned aerial vehicle body, and a cleaning mechanism is further arranged on the bottom face of the unmanned aerial vehicle body. The cleaning mechanism comprises a mounting shaft rotationally mounted on the glass protective cover, sweeping rods fixedly mounted on the mounting shaft and a driving assembly for driving the multiple sweeping rods to synchronously rotate, the sweeping rods are in clearance fit with the outer side face of the glass protective cover, and wiping strips are arranged on the inner walls of the sweeping rods; the glass protective cover provides protection for the camera, the spectrograph and the infrared remote sensing analyzer, and equipment is prevented from being impacted by foreign objects and polluted by dust, water vapor, rain, snow and the like. And the cleaning mechanism can clean the glass protective cover to ensure that the surface of the glass protective cover is clean, so that internal equipment can obtain clear and accurate data, and the problem of equipment performance reduction caused by lack of protection and cleaning of an existing device is solved.

The invention provides a broadband bidirectional reflectance distribution function (BRDF) measurement method and system of source-to-direction hemispherical reflectance (DHR), belongs to the technical field of bidirectional reflectance distribution function measurement, and is used for reflection spectrum distribution measurement of materials at different wavebands and detection angles. Existing researches on the aspects of BRDF measurement, modeling, application and the like mainly aim at visible light and near-infrared bands, spectrum BRDF measurement is directly achieved through a broadband light source, the method has the advantages of being rapid, simple and convenient, however, when an incident signal is decomposed to a wavelength point, energy is weak, and the measurement signal-to-noise ratio is affected. According to the invention, the BRDF measurement absolute value is traced to the direction hemisphere reflectivity by using the relation between the BRDF and the reflectivity and adopting a BRDF relative measurement method, so that the measurement of incident light and a detection solid angle is avoided. In the aspect of detection, a band-pass spectrum is selected by using an optical filter, and broadband BRDF measurement is carried out. According to the method and the system, complete measurement of the BRDF is realized, and the method and the system have important significance in the fields of infrared remote sensing and radiation temperature measurement.

A diaphragm device for simulating an infrared target and a control circuit thereof relate to the technical field of infrared remote sensing external field radiometric calibration, and comprise a driving assembly, a base, a diaphragm disc, a vertical rod and photoelectric switches, a step-shaped cylinder is arranged at the center of the base, and a plurality of photoelectric switches are uniformly distributed along the circumferential direction of the edge of the base. A vertical rod is arranged between any two optoelectronic switches, the diaphragm disc is rotationally connected to the step face of the cylinder, a plurality of diaphragm pieces are arranged in the circumferential direction of the diaphragm disc, the diameters of diaphragm holes in the centers of the diaphragm pieces are different, a shielding rod is fixed to the position, between any two diaphragm pieces, of the diaphragm disc, and the shielding rod is fixed to the position, between any two diaphragm pieces, of the diaphragm disc. The lower part of the shielding rod penetrates through the diaphragm disc and is in contact with the vertical rod; the diaphragm disc is driven by the driving assembly to rotate, and elastic sheet assemblies are correspondingly arranged on the two sides of the upper face of the diaphragm disc. According to the invention, the automatic switching of different diaphragm apertures is realized, the precise control of the diaphragm aperture position is realized through the cooperative work of the driving circuit, the decoding precision is high, and the operation is convenient.