19 results about "Spatial distortion" patented technology

The invention provides a cast-in-place pile quality online monitoring method and system based on an ultrasonic array, and the method comprises the steps: transmitting and receiving ultrasonic waves through the ultrasonic array arranged in a cast-in-place pile, and obtaining a multi-channel sound wave signal; performing generalized S transformation processing on the multichannel sound wave signals to obtain a time-frequency matrix, and calculating a cross correlation coefficient between each channel signal and the defect-free reference signal; an amplitude matrix and an instantaneous phase gradient matrix are calculated based on the time-frequency matrix, neighborhood amplitude energy and a phase consistency factor are fused in a time-frequency domain, and a defect energy indication diagram of the pile body section is generated; calculating the energy entropy of the defect energy indication diagram in a full frequency band; and extracting an actually measured energy arrival time sequence, comparing the actually measured energy arrival time sequence with a theoretical arrival time sequence to construct a space distortion vector, and setting a threshold value by combining energy entropy to judge defects.

This application provides an isolation structure and its manufacturing method. The isolation structure includes a substrate, an isolation trench, a flexible dielectric layer, and a filling layer located within the substrate. The flexible dielectric layer is made of hydroxyl-para-xylene. The filling layer covers the surface of the flexible dielectric layer and fills the isolation trench. This flexible dielectric layer can reduce cracks caused by excessive stress in subsequent thermal processes and can adapt to spatial distortion caused by the expansion of residual gas in the isolation trench through deformation under thermal conditions, reducing damage to the substrate, enhancing the electron coupling ability of the HiK material, improving the yield of devices on the substrate, and reducing dark current in devices and white spots in display images from the source. In addition, this flexible dielectric layer does not contain metal, so it will not cause metal ion contamination to the substrate. It eliminates the need for an additional isolation layer, improving the performance of devices on the substrate while simplifying device structure and processes and reducing manufacturing costs.

The present application belongs to the field of artificial intelligence and environmental monitoring technology, and particularly relates to an atmospheric pollutant concentration prediction method based on an ICLU-CWGAN model. By obtaining and preprocessing atmospheric pollutant concentration, meteorological and other data, the Inception multi-scale convolution idea is fused with the ConvLSTM network to construct a multi-scale ConvLSTM network; under the condition of the gradient-penalized Wassertein generative adversarial network framework, the multi-scale ConvLSTM is taken as a generator, and the improved U-Net is taken as a discriminator to construct an ICLU-CWGAN model; the model training is completed by using the pretreated training grid data to predict the atmospheric pollutant concentration. The present application can solve the problems of weak modeling capability for long-time sequence complex space-time correlation, spatial distortion and unstable training in the prior art, thereby improving the accuracy and stability of the atmospheric pollutant concentration space-time distribution prediction.

This invention relates to the field of mobile track geometry state detection technology, and discloses a real-time track state detection method based on multi-sensor fusion and dynamic compensation. It collects multi-source synchronous data from a global navigation satellite system receiver, inertial measurement unit, and laser profilometer mounted on the vehicle body, as well as accelerometers mounted on the bogie, and performs time synchronization and coordinate system unification. Through dynamic error correction and extended Kalman filtering fusion, it achieves high-precision estimation of vehicle attitude, velocity, and position. First-level point cloud motion compensation eliminates spatial distortion caused by the rigid body motion of the vehicle itself on the point cloud collected by the laser profilometer. Second-level point cloud motion compensation eliminates residual geometric errors caused by high-frequency vibration of the bogie. Finally, track geometric parameters are extracted and smoothness analysis is performed. This invention achieves high-precision reconstruction of track point clouds, providing technical support for real-time, high-precision track state monitoring on operating trains.

This invention relates to the field of mobile device camera testing technology, and discloses an Android dynamic adaptive screen camera testing system, including a light sensing module, an algorithm module, a parametric template system, a distortion compensation engine, and a differential rendering module. The light sensing module collects ambient absolute illuminance data; the algorithm module calculates the ambient illuminance gradient and controls the system state flow; the parametric template system reconstructs basic texture parameters based on the gradient to generate a two-dimensional texture of the test pattern; the distortion compensation engine constructs a non-uniform three-dimensional geometric mesh model based on the screen curvature radius and performs spatial distortion calculations on the vertices of the two-dimensional texture; the differential rendering module obtains a feature mask image, performs shading resource reallocation calculations, and sends a timing synchronization trigger command to the camera under test after rendering is completed. This invention can reduce the impact of sudden changes in external ambient light on the pattern display quality and compensate for the geometric deformation at the edges of curved screens.

The application belongs to the technical field of image fusion, and particularly relates to a remote sensing image fusion method and system based on local variance image mutual information. The method comprises the following steps: firstly, using a multivariate linear regression component replacement fusion method to perform fusion to obtain an initial fusion image; then, on the basis of the initial fusion image, similarity between an intensity component of a high-resolution multispectral image and an intensity component of the initial fusion image is calculated with the aim of obtaining an optimal Gaussian filter; finally, the original high-resolution panchromatic image is filtered by using the estimated optimal Gaussian filter to obtain a low-resolution panchromatic image, and image fusion is performed on the basis of the low-resolution panchromatic image. The application makes the fused image more conducive to the preservation of spectral characteristics and reduces spatial distortion in the spatial scale.

The invention provides a long-time viewport prediction method based on a space deformation attention network, and belongs to the technical field of 360-degree panoramic video viewport prediction. The method comprises the following steps: firstly, modeling a historical head movement track of a user by using a convolutional long-short-term memory network, and extracting basic spatio-temporal characteristics; then introducing a spatial deformation attention network, dynamically adjusting a convolution sampling position through a biased field prediction module, and adaptively compensating spatial distortion generated by isometric columnar projection through deformable sampling; meanwhile, in combination with a space and channel dual attention gating mechanism, performing multi-dimensional significance enhancement on the deformed feature map; and finally, generating a probability distribution diagram of a future viewport through feature fusion and edge enhancement output network. Experimental results show that the average prediction accuracy of the method exceeds 97% within the range of 1s to 5s, the limitation that a traditional fixed convolution kernel is difficult to adapt to the non-uniform distortion of the panoramic image is effectively broken through, and the perception ability of the model to the change of the space structure and the stability of long-term prediction are remarkably improved.

The tunnel floor heave state recognition method and device are disclosed, the over-limit section is determined in the target section, the high-low irregularity waveform, the track irregularity waveform, the horizontal irregularity waveform, the triangular pit irregularity waveform, the track slab separation thickness and / or the center ditch shape and the like track parameters of the over-limit section are obtained, the spatial distortion form of the track slab is determined according to the track parameters, the tunnel floor heave state of the over-limit section is determined according to the spatial distortion form, and thus, the deformation state of the track slab and the floor heave state of the tunnel can be determined by analyzing the track detection data, and technical support is provided for identifying the tunnel disease range, analyzing the tunnel disease causes and proposing the tunnel disease solution scheme.

The embodiment of the invention discloses a tunnel floor heave state identification method and device, and the method comprises the steps: determining an over-limit section, of which the uneven value exceeds an over-limit threshold value, in a target section; the method comprises the following steps: acquiring track parameters such as unevenness waveform, rail direction unevenness waveform, horizontal unevenness waveform, triangular pit unevenness waveform, track plate gap thickness and / or central ditch shape of an overrun section, determining a spatial distortion form of a track plate according to the track parameters, and determining a tunnel floor heave state of the overrun section according to the spatial distortion form. According to the embodiment of the invention, the deformation state of the track plate and the heaving floor state of the tunnel can be determined by analyzing the track detection data, so that technical support is provided for identifying the tunnel disease range, analyzing the tunnel disease cause and proposing a tunnel disease solution.

This invention relates to the technical field of ecological product value accounting, and in particular to an ecological product value accounting mapping system and method based on grid conservation allocation. The system includes a data source access module, a basic data management subsystem, a value accounting management subsystem, a spatialization and consistency engine, and a result output module. The system solves the problem of mismatch between multi-source heterogeneous data through online verification and consistency preprocessing. Utilizing the spatialization and consistency engine, it introduces vegetation net primary productivity weighting in material product allocation and suitability weighting in cultural service allocation, and employs a normalized conservation allocation algorithm. This invention can reveal spatial heterogeneity within a county and strictly ensures the conservation constraint between grid summary values ​​and statistical totals, realizing a closed-loop operation from raw data management to result mapping, improving the authenticity and consistency of accounting results, and solving the problems of spatial distortion, inconsistent definitions, and cumbersome operation in existing technologies.

This invention relates to the field of online detection technology for surface defects of counterweights, specifically disclosing a machine vision-based online detection method and system for surface defects of counterweights. This invention constructs a phase synchronization triggering mechanism based on physical displacement to ensure sub-pixel synchronization between camera line scanning and conveyor belt displacement, eliminating motion blur. It utilizes a high-speed linear scan camera to acquire multiple rows of one-dimensional image data, generating a continuous row pixel sequence carrying absolute spatial position. By extracting physical contour features and calculating instantaneous spatial attitude parameters, spatial distortion correction is performed on the image. Furthermore, by integrating the corrected row pixel data, a virtual global static image with eliminated motion distortion is reconstructed, and a defect recognition algorithm is applied to detect microscopic defects on the counterweight surface, outputting a quality judgment result. This invention effectively solves the problem of microscopic defect detection in high-speed non-uniform motion scenarios, improving the reliability and repeatability of detection.

This invention belongs to the technical field of image data processing and relates to an image processing method and system for adaptive optimization detection of a float position. The method includes the following steps: generating a spatial kinematic tensor based on basic geometric center data; generating a hydrodynamic spatial distortion phase array by modifying the preset standard point matrix distribution coordinates using addressing scaling factors; superimposing and merging the hydrodynamic spatial distortion phase array with the default center reference base address to generate a deformation address offset read / write pointer; merging the distortion spatial feature data to generate a target adaptive filtering pixel matrix; calculating the anti-interference centroid target position based on the entity's vertical contour boundary; generating a defect pointer and triggering a hardware abnormal interrupt level to reset the visual acquisition parameters. This invention solves the problem of limited target detection accuracy and insufficient tracking stability caused by using a fixed image sampling and processing model under dynamic fluid disturbance environments.

The application discloses a wheel image acquisition device based on a heterogeneous composite structure light and a wheel multi-parameter calculation method, relates to the technical field of wheelset parameter measurement, and comprises multiple light measurement units, a photoelectric triggering component and a controller. The multiple light measurement units are installed within the safety limit outside the same steel rail and are arranged in a straight line at equal intervals along the longitudinal direction of the steel rail. The light measurement unit is used for simultaneously generating a spatial laser plane of three common projection optical centers and a single-line laser plane in an excited state, and forming a three-line+single-line heterogeneous composite structure light on a wheel. The light measurement unit is also used for acquiring a local structure light image of the wheel. When the wheel travels, the wheel blocks the photoelectric triggering component, and a switching value signal is generated. The controller is used for generating a triggering pulse according to the switching value signal and controlling the light measurement unit to be in the excited state. The application shortens the wheelset measurement baseline, reduces the dynamic spatial distortion of the image, and improves the image quality of the structure light image.

The application discloses a sandstorm identification method based on stationary satellite remote sensing data and ground-based cloud images, and relates to the technical field of meteorological monitoring. The method comprises the following steps: step S10, spatial distortion correction is performed on a stationary satellite cloud image, multi-channel remote sensing data of a specified area is acquired, and standardization processing is performed; step S20, the cloud coverage area and the sandstorm area are identified by using the processed multi-channel satellite remote sensing data; and step S30, according to the identification results of the cloud coverage area and the sandstorm area, the satellite cloud image row and column numbers of the cloud coverage area are acquired, and the sandstorm area under the cloud condition is identified by using the all-sky ground-based cloud image. The application identifies the sandstorm weather of the sandstorm and the sandstorm under the cloud based on the deep learning method, and by fusing the channel data features and the time sequence features, the correlation between the fused features and the sandstorm weather is mined, so that the sandstorm identification precision of the cloud layer and the sand-dust layer boundary area based on the multi-channel satellite remote sensing data is improved.

The invention discloses a multispectral guided atmospheric turbulence correction system and method. Relates to the technical field of photoelectric imaging, in particular to a multispectral guided atmospheric turbulence correction system and method. According to the method, reliable structure prior is provided for the RGB image correction process by using stable structure information contained in the multispectral image, effective cooperation of the multispectral structure information and RGB image features is realized through a cross-modal feature alignment and fusion mechanism, and the multi-spectral structure information and the RGB image features are combined with a spatio-temporal joint modeling method. Meanwhile, the problems of space distortion and time instability caused by turbulence are relieved, and the engineering deployability and application adaptability of the system are improved on the premise that complex optical hardware is not introduced. The system comprises a data acquisition module, a data preprocessing module, a multispectral structure feature extraction module, an RGB image feature extraction module, a cross-modal feature alignment and fusion module, a spatial-temporal feature modeling module and an image decoding and correction module.

The invention relates to a heart motion estimation method and device based on motion smoothness retention loss and a medium. The method comprises the following steps: inputting a moving image and a fixed image into a key point detection network to extract key point pairs; constructing a sparse basic motion vector according to the relative motion between each pair of key points to obtain a sparse motion vector expressed by heart motion, carrying out three-dimensional repeated broadcasting to generate a dense basic motion field, carrying out spatial distortion transformation on a moving image, generating a coarse registration image set, and carrying out coarse registration; inputting into a dense motion estimation network to predict to obtain a weight mask corresponding to each dense basic motion field, and weighting and combining to obtain a dense motion field; wherein the motion smoothness retention loss based on a key point sparse motion mask is introduced to carry out network training, and the smoothness of the dense motion field is adaptively adjusted according to a weight mask representing the motion intensity difference of different regions. Compared with the prior art, the method has the advantages of being high in structure retentivity, high in individual generalization and high in heart motion detail modeling capacity.

This invention discloses a multi-scene 3D target detection method for autonomous driving based on uncertainty-aware geometric modeling, comprising: extracting features from multi-view original images; inputting multi-dimensional contextual features in parallel into a height branch network and a depth branch network to obtain global geometric representations and deep geometric representations, and fusing them to obtain BEV features; using a temporal pyramid fusion module to aggregate multi-scale spatiotemporal features of BEV features from k consecutive frames; using a hierarchical refinement decoder to fuse the spatiotemporally enhanced BEV feature map and multi-dimensional contextual features, and obtaining 3D target detection results based on the fused features. This invention can compensate for camera extrinsic parameter perturbations and explicitly model the uncertainty of height prediction, effectively alleviate the geometric discontinuity caused by pixel-level prediction, effectively capture multi-scale spatiotemporal dynamic features, reduce the uncertainty of single-frame estimation, compensate for spatial distortion caused by forward projection, and effectively improve generalization ability and robustness.

A method and system for correcting PCR tube sidewall fluorescence images based on self-calibration inversion, relating to the field of fluorescence image processing, solves the problems of apparent compression, positional shift, and interlayer inconsistency spatial distortion of microdroplets in PCR tube light slide fluorescence microscopy due to the refractive index differences between the outer medium, tube wall, and inner medium, resulting in double refraction of light. The method includes: obtaining the original fluorescence image, determining the tube axis position, the tilt angle of the tube axis relative to the image perpendicular line, and the transition position from the cylindrical to the conical segment from the image, constructing the geometric parameter vector to be inverted, obtaining specific image-related parameters through a staged search based on image consistency indices, and establishing a monotone reversible mapping relationship between the cylindrical and conical segments by combining a strictly non-paraxial refraction model considering the double refraction from the outer medium to the polypropylene tube wall and from the polypropylene tube wall to the water phase inside the tube, and generating a remapping table using self-calibration parameters to complete the zonal geometric correction.