14results about How to "Solve practicality" patented technology

This invention discloses a hierarchical supervised super-resolution reconstruction method, system, device, and medium for remote sensing images. The method includes acquiring a high-resolution original remote sensing image, preprocessing it to obtain multiple sets of sub-pixel remote sensing images; constructing a sub-pixel remote sensing image reconstruction network, and pre-training it using a low-resolution remote sensing image and a set of sub-pixel remote sensing images as input and ground truth, respectively; constructing an upsampling-free remote sensing image super-resolution network, and optimizing it using multiple sets of sub-pixel images; constructing a multi-level supervised upsampling-free super-resolution network, and training it using an intermediate-resolution remote sensing image and a high-resolution original remote sensing image as ground truth, respectively; and performing super-resolution reconstruction based on the remote sensing image super-resolution reconstruction model, inputting the remote sensing image whose resolution needs to be improved, to obtain a high-resolution remote sensing image. This invention, by employing a hierarchical supervised and upsampling-free super-resolution reconstruction deep network, can improve the quality and detail of super-resolution reconstruction of remote sensing images.

The utility model discloses a tool for overhauling a steam turbine bearing. The tool comprises a bottom plate, a mounting plate, a lifting mechanism and two sets of positioning mechanisms. One side of the bottom plate is arranged on the ground, the other side of the bottom plate is connected with one end of the lifting mechanism, the other end of the lifting mechanism is connected with the mounting plate, and the bottom plate and the mounting plate are arranged in parallel; each positioning mechanism comprises a side plate, a positioning plate and a moving assembly. The two side plates, the two positioning plates and the two moving assemblies are oppositely arranged. The two side plates are connected to the side, away from the bottom plate, of the mounting plate and located at the two ends of the mounting plate correspondingly. The two positioning plates are connected with the two side plates through moving assemblies correspondingly and are in sliding connection with the mounting plate. The two positioning plates are both configured to abut against the steam turbine bearing. The technical effect that the steam turbine bearing is more stable during overhauling is achieved, and the convenience of the steam turbine bearing during overhauling is improved.

The application provides a fusion data broadband coseismic velocity waveform real-time reconstruction method based on cascade filtering, which uses cascade filtering to fuse high-frequency GNSS original Doppler data, high-frequency GNSS carrier phase data and accelerometer data to realize broadband coseismic velocity waveform real-time reconstruction, and the realization process comprises the following steps: high-frequency GNSS / accelerometer co-located station real-time acquisition of high-frequency GNSS observation data, broadcast ephemeris and original acceleration data, and sending to a ground computing center; the ground computing center real-time calculation of high-frequency GNSS TDCP average velocity and high-frequency GNSS RD instantaneous velocity; the ground computing center zero offset correction of the real-time received original acceleration data to obtain zero offset correction acceleration data; and the ground computing center real-time reconstruction of the broadband coseismic velocity waveform of the high-frequency GNSS / accelerometer co-located station according to the high-frequency GNSS TDCP average velocity, the high-frequency GNSS RD instantaneous velocity and the zero offset correction acceleration data by using cascade filtering.

The application provides a dust falling device, which comprises a vertical dust falling mechanism, an adjusting dust falling mechanism and a triggering mechanism, wherein the adjusting dust falling mechanism is arranged on the vertical dust falling mechanism, the adjusting dust falling mechanism comprises a first dust falling assembly, the first dust falling assembly has an initial position and a dust falling position for dust falling on a target object, and the first dust falling assembly is movably arranged between the initial position and the dust falling position relative to the vertical dust falling mechanism; the triggering mechanism is connected with the first dust falling assembly, a control signal is sent to the first dust falling assembly through the triggering mechanism, and the first dust falling assembly is controlled to move between the initial position and the dust falling position. The vertical dust falling mechanism is arranged to dust fall on a target area, the adjusting dust falling mechanism is arranged to dust fall on a target object, and the triggering mechanism is arranged to control the starting of the adjusting dust falling mechanism, so that the problem that dust falling needs to be manually performed in the prior art, thereby resulting in poor dust falling effect and poor practicability, is solved.

This invention relates to a video object removal method based on a text-based video model and learnable negative tokens, comprising: acquiring the original video to be processed and a specified target to be removed; segmenting the target to be removed using a video segmentation model to generate a corresponding video mask sequence; preprocessing the original video and the video mask sequence to obtain masked video latent features and mask latent features; constructing an object removal model based on a text-based video model, wherein the object removal model retains the cross-attention module of the pre-trained text-based video model; setting the text prompt input to empty and introducing learnable negative tokens; inputting the masked video latent features, mask latent features, and negative tokens into the object removal model; the object removal model processes the negative tokens through the cross-attention module, suppressing object generation features within the mask region, and generating filling content based on video background information; and outputting the video after removing the specified target.

This invention provides a method, system, and computer device for feature matching of heterogeneous images. The method includes acquiring two heterogeneous images, extracting image edges to obtain feature regions as targets for matching; calculating the gray-level centroid of each target region; determining the principal direction of each target region, using the principal direction as the starting direction and clockwise as the positive direction, drawing several rays clockwise from the origin of each region, calculating the Euclidean distance between the corresponding intersection points and the origin of each region, arranging them in the generation order, removing several maximum and minimum values, and normalizing the remaining ordered array to form a feature vector; calculating the Euclidean distance between the feature vectors of each target region, and considering a successful match when the Euclidean distance between the feature vectors of two target regions is less than a preset threshold. This invention effectively solves the region matching problem caused by image rotation and scale changes in heterogeneous images, significantly improving the region matching results.

The application discloses an electrical instrument convenient to install and maintain, which comprises a pressure gauge, a flange and a sealing device; the pressure gauge is connected to a pipeline through the flange; the sealing device comprises a driving connection assembly and two semicircular fixed clamping grooves, one end of the driving connection assembly is rotationally connected to one semicircular fixed clamping groove, and the other end is clamped to the other semicircular fixed clamping groove, so that the two semicircular fixed clamping grooves are spliced to form an annular clamping groove; the annular clamping groove is used for clamping the flange and the pipeline; the inner side of the semicircular fixed clamping groove is slidably provided with a movable sealing piece along the radial direction of the semicircular fixed clamping groove; the outer side of the driving connection assembly is provided with a limiting assembly; the limiting assembly penetrates through the driving connection assembly along the radial direction of the semicircular fixed clamping groove and is embedded into the outer side of the semicircular fixed clamping groove. The stability and practicability of the existing installation device of the electronic instrument are improved, the electrical instrument is more convenient to install and maintain, the loosening of the connecting plate is avoided, and the practicability and stability of the device are improved.

This utility model discloses an outdoor fitness sit-up board with massage function, relating to the field of fitness equipment. It includes a sit-up board with a front support rod fixedly installed at one end and a rear support rod fixedly installed at the other end via a diagonal brace. A massage groove is fixedly formed inside the sit-up board, and a lifting frame is slidably mounted inside the massage groove via a power assembly. The lifting frame includes two brackets, which movably fit against the inner walls of both sides of the massage groove. This utility model, through the installation of the power assembly, drives the lifting frame to move within the massage groove, thereby adjusting the protrusion height of the massage rollers on the sit-up board. This makes it suitable for users of different body types, solving the problem that existing outdoor fitness sit-up boards with massage function cannot freely adjust the protrusion height of the massage rollers according to the user's body shape, thus reducing the practicality of the outdoor fitness sit-up board.

The application provides a high-precision magnetic target classification system based on coarse-precision two-stage, relates to the technical field of magnetic target classification, and comprises a magnetic field data acquisition component, a magnetic field data acquisition component configured to acquire magnetic field data of a target to be detected; a magnetic field data processing component, a magnetic field data processing component configured to sequentially perform coarse processing and fine processing according to the magnetic field data to obtain a global context enhanced feature vector corresponding to the target to be detected; the coarse processing comprises using a grey wolf algorithm and a physical information neural network to perform rapid inversion of magnetic distance parameters; the fine processing comprises using a space-time convolution neural network and a multi-head self-attention mechanism to perform dynamic focusing on key magnetic field mutations; and a target classification component, a target classification component configured to determine a target classification probability according to the global context enhanced feature vector to obtain a target classification result of the target to be detected. The application solves the problems of low reliability and practicability of the existing magnetic induction triggering technology through the above system.

This invention provides a magnesium-lithium-based composite material and its preparation method, belonging to the technical field of magnesium-based composite materials. The magnesium-lithium-based composite material provided by this invention comprises alternating layers of a first magnesium-lithium alloy layer, a second magnesium-lithium alloy layer, and a third magnesium-lithium alloy layer. The first magnesium-lithium alloy layer comprises, by mass percentage, 2-5.7% Li and the balance Mg; the second magnesium-lithium alloy layer comprises, by mass percentage, 10.3-16% Li and the balance Mg. In this invention, the matrix structure of the first magnesium-lithium alloy layer is an α-Mg single phase, and the matrix structure of the second magnesium-lithium alloy layer is a β-Li single phase, arranged in a sandwich structure of α-Mg / β-Li / α-Mg. This integrates the high-strength α-Mg phase with the high-plasticity β-Li phase, utilizing the impedance mismatch effect of the two different matrix phases to improve the electromagnetic shielding performance of the magnesium-lithium-based composite material.

The present disclosure relates to a power system source side carbon emission prediction method and system, the method comprising: collecting multi-source data; data preprocessing of the collected multi-source data, the data preprocessing comprising data alignment, outlier processing and normalization processing; based on wavelet decomposition method and compressed sensing reconstruction algorithm, time-frequency expansion is performed on the multi-source data after data preprocessing to obtain a high-resolution wavelet coefficient matrix; the high-resolution wavelet coefficient matrix is high-resolution time-frequency data; based on the multi-scale physical properties of carbon emission and the high-resolution wavelet coefficient matrix, enhanced data are generated which conform to the physical law and cover various scenarios; based on the resolution branch design, precise feature screening is performed on the enhanced data to obtain a plurality of high-resolution branch prediction sequence matrices and output; all branch prediction sequence matrices are respectively reconstructed into corresponding time-frequency features through inverse wavelet transform, and each time-frequency feature is fused based on a preset attention mechanism to obtain a carbon emission prediction value.

This invention provides a method, device, and storage medium for unifying the absolute radiometric reference of a remote sensing mega-satellite cluster. The method includes establishing a ground-based absolute radiometric reference, which involves acquiring the surface reflectance and atmospheric parameters of the ground radiometric calibration field using automated observation equipment; constructing an on-board absolute radiometric reference, which involves selecting several satellites in the cluster as calibration satellites based on satellite radiometric stability, orbital distribution, and redundancy requirements. These calibration satellites carry on-board calibration devices to obtain a traceable on-board reference; unifying the satellite-ground reference, which involves performing both site calibration and on-board calibration on the calibration satellites, and weighted fusion of the two calibration results based on calibration uncertainty to obtain the optimal absolute radiometric coefficient; and transferring the reference between satellites, which involves transferring the optimal absolute radiometric coefficient to other satellites in the cluster through a one-to-many cross-calibration process, achieving unification of the radiometric reference across the entire cluster. This invention achieves high-precision, high-stability, and automated absolute radiometric calibration for remote sensing mega-satellite clusters.

The application provides a power transmission pole tower type identification method based on point cloud, which comprises the following steps: making a pole tower type data set, converting a standard pole tower model into a consistent height-width image file, and establishing a standard pole tower character library; extracting power transmission pole tower point cloud, eliminating miscellaneous points and power line point cloud in unmanned aerial vehicle measured point cloud, and extracting power transmission pole tower point cloud; calculating a pole tower symmetry axis plane, calculating the symmetry axis plane of the measured pole tower point cloud by counting points in each angle direction; re-projecting the pole tower point cloud by using a coordinate transformation method; and identifying the pole tower type by using a template matching method. The application improves the automation level of power transmission line point cloud data processing, solves the problem of visual identification consuming a large amount of manpower and material resources, and provides a data basis for subsequent pole tower automatic modeling and pole tower deformation detection.