79 results about "Single band" patented technology

The invention provides a method for generating multi-dimensional landform vector data based on remote sensing image semantic segmentation, and belongs to the technical field of remote sensing image ground object recognition and artificial intelligence, and the method comprises the steps: training a landform recognition deep learning model based on a remote sensing image, adjusting a pre-training weight to optimize an image encoder, and generating a classification result; the landform recognition deep learning model comprises an encoder formed by a multi-layer convolutional network and a decoder of an up-sampling and feature fusion architecture; extracting a single-band label corresponding to each landform type from the classification result, and generating a binary raster image with the single-band labels; and converting the binary raster image with the single-band label into a vector diagram, and combining the vector diagram with the elevation information to generate multi-dimensional geographic data.

The invention provides a large-scale insect and bird migratory flight monitoring system based on a weather radar net, and the system employs a data collection module to obtain S, C and X wave band weather radar monitoring data of the national weather radar net, and a quality control module carries out the quality control of the radar-based data in the monitoring data, and further provides the radar-based data to an echo recognition module to construct recognition features. A classification recognition result is obtained by adopting a recognition model corresponding to the wave band; the inversion quantification module inverts the insect and bird density, the insect and bird speed and the vertical distribution of the movement direction based on the classified and identified insect and bird echoes to obtain an inversion quantification result; and the classification identification result and the inversion quantification result of the single wave band form a local monitoring result. And the visualization module displays a single-band local monitoring result or a multi-band fusion monitoring result. According to the invention, multi-band data can be collected, monitoring results are fused, real-time and efficient monitoring of migration of insects and birds is realized, and the monitoring range is expanded.

The invention relates to the technical field of electrocatalytic oxidation, and provides a fluorescence detection condition control system and method, and the system comprises a strategy library which uses XGBoost to train strategy algorithm models of different water sample water qualities and initial wave bands; the initialization module is used for calling the strategy library to load the water quality type according to a detection environment and setting initial state water sample condition matching; the pre-excitation module is used for lightening the single-band LEDs one by one to obtain an initial fluorescence response value; the self-adaptive detection module is used for calling a strategy algorithm model and generating a wave band combination and excitation intensity configuration according to the initial fluorescence response value; the temperature compensation module monitors the key temperature in real time through a temperature sensor and carries out compensation correction according to a fluorescence error caused by temperature drift; and the analysis report module outputs a Cu < 2 + > concentration detection result. According to the method, the water quality preset strategy library and the temperature compensation mechanism are combined, Cu < 2 + > fluorescence detection under the complex matrix background is achieved, and the accuracy and environmental adaptability of low-concentration heavy metal detection are remarkably improved.

The invention relates to the technical field of image data processing, in particular to a multiband hyperspectral image fusion method for predicting surface moisture of coal, which comprises the following steps: acquiring visible light and near-infrared images and calculating reflection difference frequency, constructing a grade layer and then executing region mapping and brightness superposition, extracting pixel features and sorting and dividing threshold regions, and identifying boundary change and generating a graph block, and finally reconstructing a moisture distribution graph surface according to a gray scale. According to the method, pixel-level distinguishing is carried out through reflection differences of visible light and near-infrared images, hierarchical layers are constructed based on multi-band reflection changes, layer stacking and classification are completed in combination with characteristics such as brightness, edge changes and space concentration ratio, moisture region boundaries are delimited, and moisture level maps are generated according to gray scale sorting. Fine grading and boundary positioning of the moisture content are realized, the prediction precision is improved, the problems of single-band processing limitation and fusion information loss are solved, and the identification capability of the moisture area in the complex coal surface environment is enhanced.

The invention provides a hyperspectral tailing pond dry beach line intelligent analysis method, and belongs to the technical field of image processing. Through multiband characteristics of a hyperspectral remote sensing image, principal component clustering analysis and characteristic wavelength selection are combined, so that the problems of insufficient spectral information of the image after dimension reduction and serious data redundancy caused by use of a full-band image are solved; single-band images corresponding to different characteristic bands emphasize different target information in the original image, and different combinations are beneficial to fully exerting the advantages of different target information of each band, so that a water area and a dry beach are distinguished more accurately; a double-branch network model is adopted, the difference between spectral dimensions and spatial dimensions is synchronously analyzed, spectral features and spatial information are fused, and the two branches have certain complementarity, so that rich spatial spectrum information of an input hyperspectral remote sensing image can be fully excavated, a dry beach line can be identified more accurately and effectively, the length of the dry beach is calculated, manual intervention is reduced, and the working efficiency is improved. The treatment efficiency is improved.

The embodiment of the invention provides a remote sensing image atmospheric correction method and system for an ocean near-shore scene, and relates to the technical field of ocean remote sensing image atmospheric correction. According to the method, after remote sensing data is obtained, solar flare correction is executed by extracting a target mask and using a secondary simulation model of a satellite signal in a solar spectrum. And then a multi-band darkness index is calculated, and an optimal aerosol optical thickness value is inverted through a radiation transmission model. And calculating the atmospheric correction coefficient of each wave band according to the optimal aerosol optical thickness value so as to generate correction result data. According to the method, on the basis of robust flare correction of the SWIR proxy, scene-adaptive flare proxy is constructed by utilizing water body reflection and path radiation physical characteristics of the SWIR under a deepwater condition, and flare deduction is realized. Inversion is carried out through multiband combined darkness indexes, and the spectral characteristics of the deep water body reflected in the visible spectrum are utilized, so that single-band random noise is smoothed, and the accuracy of an AOT estimation result is improved.

Single band and multiband wireless antennas are an important element of wireless systems. Competing tradeoffs of overall footprint, performance aspects such as impedance matching and cost require not only consideration but become significant when multiple antenna elements are employed within a single antenna such as to obtain circular polarization transmit and / or receive. Accordingly, it would be beneficial to provide designers of a wide range of electrical devices and systems with compact single or multiple frequency band antennas which, in addition to providing the controlled radiation pattern and circular polarization purity (where required) are impedance matched without substantially increasing the footprint of the antenna and / or the complexity of the microwave / RF circuit interfaced to them, whilst supporting multiple signals to / from multiple antenna elements in antennas employing them. Solutions present achieve this through provisioning one or more capacitive series reactances discretely or in combination with one or more shunt capacitive reactances.

The invention discloses a water quality inversion method based on multi-strategy improved sparrow search optimization machine learning. The method comprises the following steps: firstly, collecting the reflectivity of a water sample by using a spectrograph, and converting the collected reflectivity into an equivalent albedo of a corresponding wave band of a Sentinel-2 satellite through a spectral response function; collecting a water sample on site, and measuring the TSM concentration and Chla concentration; the obtained equivalent albedo is constructed into combined features in a single-band and multi-band mode, and the first four combined features of the correlation are selected as feature input; inputting the selected combined features into a plurality of machine learning models for contrastive analysis to invert the performance of TSM and Chla concentration, and determining an optimal machine learning model; then constructing a multi-strategy optimized sparrow search algorithm; and performing water quality inversion on the Sentinel-2 image by using the optimal machine learning model obtained by optimization of the obtained multi-strategy optimized sparrow search algorithm. According to the invention, the model inversion precision is improved.

The present application belongs to the technical field of image processing, and particularly relates to a multi-band image cascade fusion method. The present application adopts a brightness modulation method to normalize the gray scale or brightness component of one of the single-band images to be fused, and to multiply the brightness component of the other single-band image in the HSV color space format, so as to complete brightness fusion. Then, the brightness cascade fusion of the third image or more images is performed, so that the multi-band fusion image retains the brightness information of different band images, and reflects the significant features of different band images. Furthermore, the color information of the restored color visible light image or the colorization of the black-and-white visible light image / infrared thermal image makes the feature details of the fusion image more clear and easy to identify. The present application has low computational complexity and is suitable for real-time processing of embedded systems.

The invention discloses a full-wave-band dynamic sunlight player with a three-stage coaxial soft light structure, and relates to the technical field of healthy lighting and high-precision simulation light sources. The core three-stage coaxial soft light structure is composed of a high-atomization concave soft light cavity, a convex high-reflection soft light structure and a full-coating high-transmittance soft light shell which are coaxial, and glare-free and high-uniformity full-wave-band light emitting is achieved. The equipment is provided with a full-wave band narrow-band combined lamp group covering weak ultraviolet rays to near infrared rays, so that a continuous sunlight spectrum is formed; single-band single-line independent driving is adopted, a pure hardware simulation gradual change control unit is matched, and non-stroboscopic smooth gradual change and accurate regulation and control are achieved. The equipment is provided with a local time service module and a storage medium, and a networking module can be selected to be matched with a factory spectrum calibration method to guarantee output consistency. The system can truly restore the natural sunlight spectrum, adapts to the biological rhythm, is suitable for medical treatment, laboratories, space stations and other scenes, and has the advantages of being high in reliability, continuous in spectrum, strong in soft light effect, high in biological friendliness and the like.

The invention provides a multiband intelligent radiation temperature control device, which realizes multiband intelligent radiation temperature control through innovative design, and is characterized in that a first micro-unit and a second micro-unit with different characteristic lengths are adopted in an optical functional layer, and according to an electromagnetic resonance theory, the first micro-unit with the long characteristic length is matched with a far infrared band wavelength, and the second micro-unit with the long characteristic length is matched with a far infrared band wavelength; the far infrared radiance can be modulated along with the change of the external temperature, and the second micro-unit with the short characteristic length is adaptive to a middle infrared band to realize corresponding radiance modulation; meanwhile, large-area temperature control uniformity is guaranteed through array arrangement of the modulation areas, and environment adaptability is enhanced through combination of the protection layer and the optical function layer. Compared with a traditional single-band temperature control device, the design breaks through band limitation, achieves mid-infrared and far-infrared dual-band cooperative regulation and control, can respond to environment temperature changes in real time, improves the temperature control precision and dynamic performance, and effectively solves the problems that in the prior art, temperature control is not accurate in a complex environment, and the application scene is single.

The application provides a method for searching exposure time and a quantum efficiency measuring system, comprising: a data processing module configured to configure fixed parameters of an image acquisition module and wavelengths of a wavelength configuration device; the image acquisition module is controlled to determine a candidate exposure time set according to a search step and an initial value of exposure time; after the wavelengths of the wavelength configuration device are configured, single-band light configured by the wavelength configuration device is received through an optical fiber bundle; a target exposure time is selected from the candidate exposure time set multiple times; images are captured multiple times under the environment of the wavelength of the wavelength configuration device; if the images do not occur light cutoff and satisfy a preset image saturation constraint condition and an image linearity constraint condition, the target exposure time is taken as a set of exposure times corresponding to the current wavelength; and a set of exposure times corresponding to the wavelength of each wavelength configuration device is searched until a set of exposure times corresponding to the wavelength of each wavelength configuration device is searched. The method is used to accurately search for exposure time meeting the linearity requirement.

This invention relates to the field of optical imaging technology, specifically providing an optical radar co-aperture off-axis imaging system, comprising: an off-axis mirror assembly, a frequency-splitting device, a radar transceiver system, and an optical imaging system. The frequency-splitting device is disposed in the rear optical path of the secondary mirror and is used to reflect light waves and transmit microwaves. The frequency-splitting device includes a frequency-selective surface, which comprises an FSS pattern layer and a bias line layer. The FSS pattern layer includes periodically arranged FSS units. Nonlinear capacitors are electrically connected to the FSS units. The bias line layer applies a voltage to the nonlinear capacitors according to the received microwave band. By changing the voltage applied to the nonlinear capacitors, the resonant frequency of the FSS units is tuned, thereby changing the microwave passband frequency of the frequency-splitting device. This invention not only achieves a reflective wave-transmitting microwave design but also solves the problem that transmitting only a single band of microwaves in microwave-transmitting and light-reflecting methods is difficult to adapt to different task requirements.

A computer-implemented method and system includes accessing neurophysiological and neurovascular data recorded during sleep. A device worn on the subject's head during sleep can collect the neurovascular data by measuring transcranial impedance. The device can be in the form of a single band, multiple bands, or a head cap worn on the subject's head. Electrodes positioned along the inner surface of the wearable device contact the subject's head and measure the transcranial impedance. Transcranial impedance measurements are collected from multiple locations on the subject's head and across multiple frequencies to obtain a more complete assessment of glymphatic flow.

Systems and methods for reducing loading in antenna switch module multiplexing are disclosed. In one aspect, a radio frequency front end includes a plurality of filters configured to filter radio frequency signals, the filters including a first filter configured for single band wireless communication and two second filters configured for multiplexing wireless communication. The radio frequency front end further includes an antenna switch module including a first switch configured to connect an antenna to the first filter for the single band wireless communication, and two second switches configured to connect the antenna to the second filters for the multiplexing wireless communication, the second switches having a lower on-state resistance than the first switch.

Multi-band remotely configurable tuning probes for slide screw impedance tuners allow instantaneous larger frequency coverage beyond the capacity of existing tuning probes using the single horizontal and vertical axis mechanism of a prior art single probe, single band tuner. This is done by carving multiple slugs of different length and frequency coverage as segments of a disc-shaped revolving slab, which rotates inside the legs of a captive unit and locks at distinct angles. The captive unit is attached to the vertical control mechanism of the tuner and rotation is ensured using multiple traverse lateral studs on the disc unit and a set of vertical studs on the slabline close to the idle port of the tuner. An automated procedure ensures remote switching between tuning slugs. Calibration and tuning is as in prior art single probe tuners.

This invention relates to the field of electrocatalytic oxidation technology, and provides a fluorescence detection condition control system and method, comprising: a strategy library, which uses XGBoost to train strategy algorithm models for different water sample qualities and initial wavelength bands; an initialization module, which loads water quality types from the strategy library according to the detection environment and sets initial state water sample conditions; a pre-excitation module, which illuminates single-band LEDs one by one to obtain initial fluorescence response values; an adaptive detection module, which calls the strategy algorithm model and generates wavelength combinations and excitation intensity configurations based on the initial fluorescence response values; a temperature compensation module, which monitors key temperatures in real time using a temperature sensor and compensates for fluorescence errors caused by temperature drift; and an analysis report module, which outputs Cu... 2+ Concentration detection results. This invention combines a water quality preset strategy library and a temperature compensation mechanism to achieve Cu concentration detection in complex matrix environments. 2+ Fluorescence detection significantly improves the accuracy and environmental adaptability of detecting low-concentration heavy metals.

Triple band remotely configurable tuning probes for slide screw impedance tuners allow instantaneous larger frequency coverage beyond the capacity of existing tuning probes using the single horizontal and vertical axis mechanism of a prior art single probe, single band tuner. This is done by combining two types of tuning slug, a core slug and a saddle slug into a configurable tuning probe assembly mounted in the same mobile tuner carriage and controlled using the same single vertical axis mechanism with the help of two ridges on the core slug and a permanently mounted slug control fork. To avoid spurious resonance phenomena the tuning slugs are controlled, driven, and locked vertically sliding on each other, and guided appropriately allowing smooth, uninhibited vertical movement of the metallic bodies.

The invention relates to a water body remote sensing image solar flare identification method based on multispectral features and XGBoost, and the method comprises the steps: extracting a water body from a remote sensing image, screening out a region affected by solar flare and a normal water body region, marking the regions, and constructing a corresponding label data set; constructing an input feature data set by taking the atmospheric top reflection data of all wavebands of samples in the label data set and the spectral index data of the multi-waveband combination as input features; constructing a training set in combination with the input feature data set and the label data set, performing model training based on an XGBoost model, and constructing a solar flare recognition model; and carrying out solar flare identification on the to-be-identified water body remote sensing image based on the solar flare identification model. By adopting the method disclosed by the invention, the limitation of solar flare identification in a complex environment by a traditional single-band threshold method can be overcome, the identification precision and efficiency are improved, and a reliable technical means is provided for solar flare identification of large-area long-time-sequence remote sensing data.

This invention discloses a testing device and method for testing crystal uniformity using photoelectric properties. The method includes: pre-setting multiple different target detection bands; scanning the target detection area of ​​the crystal under test using excitation light in each preset target detection band to obtain a fluorescence signal matrix; preprocessing the fluorescence signal matrix in each target detection band to obtain a fluorescence intensity distribution matrix; extracting single-band uniformity parameters from the fluorescence intensity distribution matrix; and fusing the single-band uniformity parameters from all target detection bands to obtain crystal uniformity parameters as the test result. This invention achieves quantitative output of both global and local uniformity results for crystal uniformity.

The application discloses an aerial filter array multi-spectral image strip preprocessing method and belongs to the technical field of aerial image processing. The aerial filter array multi-spectral image strip preprocessing algorithm is proposed to solve the problem that the strip cutting is not accurate due to the low strip overlap rate and spectral aliasing interference of the filter array multi-spectral image. The strip image gray extreme points are calculated through the multi-spectral image row pixel gray mean value. The intersection position of the minimum value of the middle region gray of the strip image and the gray curve is taken as the strip cutoff point. The strip spectral aliasing range is obtained by subtracting the strip cutoff point from the gray extreme point. The effective region coordinates of each strip are calculated according to the maximum spectral aliasing width and the gray extreme point, and the single-band strip image is obtained. Theoretical analysis and experimental results show that the method can accurately extract the effective region of each strip and can maximize the retention of the overlapping region pixels.

The invention discloses a soil salinity inversion method and device based on a hybrid generative adversarial network, and the method comprises the steps: constructing a dual-band and a triple-band of each soil sample, and calculating a second spectral index of each dual-band and a third spectral index of each triple-band; screening dual wavebands according to the first Pearson's correlation coefficient and a preset threshold value, and screening three wavebands according to the second Pearson's correlation coefficient and the preset threshold value; and training the feature hybrid generative adversarial network by using the single wave band, the first coordinate and the first spectral index, and generating a plurality of first synthetic spectral samples and second coordinates according to the screened double wave bands, the second spectral index, the first coordinate, the screened three wave bands and the third spectral index. According to the method, the quality, diversity and number of the second synthetic spectrum samples are improved, the problem that the generalization ability of the soil salinity prediction performance optimal model is weak is solved, and the soil salinity prediction precision of the soil salinity prediction performance optimal model is improved.

The invention discloses a device and a method for testing crystal uniformity by using photoelectric characteristics. Comprising the following steps: presetting a plurality of different target detection wavebands, and scanning a target detection area of a to-be-detected crystal by using exciting light under each preset target detection waveband to obtain a fluorescence signal matrix; preprocessing the fluorescence signal matrix under each target detection waveband to obtain a fluorescence intensity distribution matrix, and extracting single-waveband uniformity parameters from the fluorescence intensity distribution matrix; and carrying out fusion processing on the single-band uniformity parameters under all the target detection bands to obtain a crystal uniformity parameter as a test result. According to the method disclosed by the invention, quantitative result output of global and local uniformity of the crystal uniformity is realized.

This invention relates to the field of laser signal processing technology, and discloses a method, system, terminal, and storage medium for shallow water depth estimation based on asynchronous observation and scanning angle correction. The method includes: performing multiple asynchronous observations of a land target area for error optimization processing, then performing asynchronous observations of an underwater target area and extracting multiple key point pairs to construct a sparse correspondence; using the sparse correspondence to construct multiple distance values, and further selecting multiple initial key point pairs with consistent distances; performing structural consistency screening on the initial key point pairs and constructing difference values ​​to optimize the estimated water depth value. This invention is based on the spatial detection principle and point cloud solution method of an airborne single-band depth sounding system, avoiding the error influence between multi-source heterogeneous data detection results from multi-system integration, and effectively improving the ground detection accuracy and integrated land-water detection capability of the airborne blue-green lidar depth sounding system.

The application discloses a multispectral point cloud generation method based on multispectral image reconstruction, a storage medium and equipment, and belongs to the technical field of multispectral image three-dimensional reconstruction. In order to solve the problems of insufficient utilization of spectral information, low reconstruction accuracy and low efficiency in the prior art, the application first performs radiation correction and band alignment on a multispectral image, and superimposes a plurality of single-band images to synthesize a band-aligned multispectral image; a combination of image enhancement and a SIFT feature operator is adopted to obtain wave-band-by-wave-band features and fuse multispectral features; then, NDVI masks based on the multispectral image are used to match the fused multispectral features, a matching relationship of the multispectral image in an image set is established based on the feature matching pairs, a motion structure recovery method is used to calculate image relative pose information, a multi-view geometric matching technology is used to calculate image depth values, multispectral values are projected, and multispectral point clouds are generated.

The invention relates to the technical field of offshore direct-current wind power, in particular to a multi-band torsional oscillation suppression method and system for an offshore direct-current wind turbine generator shaft system, and the method comprises the steps: building a control model of an oscillation suppression device comprising a plurality of parallel channels which comprise a band-pass filter, a wave trap, a proportional amplification link and an amplitude limiting link; a shafting rotating speed signal is obtained and input into the control model, and a control output signal value is calculated; and superposing the control output signal value and the original electromagnetic torque instruction value of the offshore direct-current wind turbine generator to participate in the torque control of the whole offshore direct-current wind turbine generator. Compared with a single band-pass filter or a PI controller adopted in a traditional method, the torsional vibration of different frequency bands can be more effectively restrained, and the mutual influence between torsional vibration signals of similar frequency bands is reduced. In addition, the method overcomes the problem that the existing method only aims at the single oscillation frequency of the shaft system of the wind turbine generator, does not need to add extra hardware equipment, and has good technical economy.

The invention relates to an acousto-optic tunable filter (Acoustical-optical tunable filter-AOTF), which is an electrically controlled tunable spectrum light splitting device, and is characterized in that the acousto-optic tunable filter (Acoustical-optical tunable filter-AOTF) is an electrically controlled tunable spectrum light splitting device. In a complex task, single-band information is often insufficient to support a decision, so that the invention provides a design method of a single transducer-dual-band acousto-optic tunable filter, a numerical calculation model is established through a dual-band wave vector geometry principle, and a dual-band tuning relationship under different cutting types is obtained. And furthermore, the design of the dual-band AOTF device with high diffraction efficiency and low power consumption is realized through the size optimization design of the transducer. Compared with an existing AOTF device design method, the single-transducer-dual-waveband AOTF device design method can utilize a single simple single-transducer AOTF device to obtain dual-waveband spectral data at the same time, the spectral range is expanded, the spectral detection efficiency is improved, and the detection capacity for a dynamic target is improved. Meanwhile, the dual-band detection can reduce the frequency of electrical power loading of the transducer, the thermal load of the device is reduced, and the working stability of the device is improved.

Tri-state triple band remotely configurable tuning probes for slide screw impedance tuners allow instantaneous larger frequency coverage beyond the capacity of existing tuning probes using the single horizontal and vertical axis mechanism of a prior art single probe, single band tuner. This is done by combining two tuning slugs, a master slug and a slave slug into a configurable tuning probe assembly mounted in the same mobile tuner carriage and controlled using a single vertical axis mechanism. To avoid spurious resonance phenomena the tuning slugs are controlled, driven, and locked vertically sliding on each other, and guided appropriately allowing smooth, uninhibited vertical movement of the metallic bodies.

Various solutions for supported band reporting in mobile communications are described. The user equipment (UE) may receive a capability enquiry message indicating a supported band filter information from a network node. Also, the UE may include at least one of a plurality of supported bands into a supported band list of single band based on the supported band filter information. Further, the UE may include the supported band list into a capability information message, and transmit the capability information message to the network node. As the supported bands are filtered based on the network indication, the size of the capability information message can be reduced.

The invention belongs to the technical field of hyperspectral remote sensing, and relates to a method for rapidly extracting chlorite minerals by using 02D data of resource I. The method comprises the following steps: step 1, carrying out atmospheric correction and ortho-rectification on the 02D data of the resource I; 2, calculating a single-band mean value image of a first spectral absorption valley of the chlorite altered mineral; 3, calculating a single-band mean value image of a second spectral absorption valley of the chlorite altered mineral; 4, calculating a single-band mean value image of a first spectral reflection peak of the chlorite altered mineral; 5, calculating a single-band mean value image of a second spectral reflection peak of the chlorite altered mineral; 6, calculating chlorite altered mineral single-band images for multiple times by adjusting floating parameters, and storing the chlorite altered mineral single-band images with relatively good extraction effects; and 7, determining a chlorite mineral distribution range by using a density segmentation method, and outputting vector elements. According to the method, the chlorite mineral extraction speed and the chlorite mineral extraction accuracy are improved.