11 results about "Shearlet" patented technology

The invention discloses a multi-scale infrared polarization image enhancement method based on MSD-PCNN, and relates to the technical field of infrared image processing, and the method comprises the steps: firstly, carrying out the multi-scale and multi-direction decomposition of an input intensity image I and a polarization feature map DoLP based on NSST, and obtaining a low-frequency sub-band and a high-frequency sub-band; secondly, according to the obtained low-frequency sub-band, designing a low-frequency sub-band fusion rule based on distance difference perception; and finally, according to the obtained high-frequency sub-band, designing a high-frequency sub-band fusion rule based on MSD-PCNN, and fully extracting texture and edge detail features. According to the MSD-PCNN-based multi-scale infrared polarization image enhancement method provided by the invention, redundant information interference is suppressed, the hierarchical definition of an image structure is improved, and meanwhile, the visual comfort and global naturalness of a fused image are also improved.

The application discloses a fine-grained representation remote sensing image interpretation method and system based on Shearlet prior knowledge, adopts Shearlet transformation to extract high-frequency sub-band information of preprocessed remote sensing image data; uses Laplace pyramid and shearlet filter to obtain high-frequency components and multi-direction high-frequency sub-bands after directional splitting; through a spatial attention mechanism, sub-bands of the same level are adaptively fused to generate a detail-enhanced feature map; high-frequency components extracted through Shearlet transformation are prior to multi-scale and multi-level weighted fusion of deep residual blocks obtained through a deep residual network; a trained detail-enhanced backbone and different detection heads of multiple tasks are used to output accurate remote sensing image analysis results; through combination of Shearlet transformation and an advanced deep learning architecture, the accuracy and efficiency of remote sensing image interpretation are significantly improved, meanwhile, good model generalization ability and practicability are maintained, and it is expected that the application will promote the development of remote sensing image processing in a more intelligent and automatic direction.

This invention discloses a method and apparatus for noise-resistant frequency compensation of seismic data, relating to the fields of compressed sensing and seismic exploration design. The method includes: performing spectral analysis on the original seismic data to determine the expected frequency broadening range; performing autocorrelation calculation on the original seismic data to obtain wavelet-like waveform data; using the wavelet-like waveform data as simulated wavelet data, inputting iterative solutions to the compressed sensing noise-resistant frequency extension basis function to obtain the full bandwidth reflection coefficient; concatenating the full bandwidth spectrum with the original seismic data spectrum to obtain the extended spectrum; and performing an inverse Fourier transform on the extended spectrum to obtain the noise-resistant frequency extension data. This invention is based on the compressed sensing framework, utilizes the Shearlet denoising basis function to constrain the frequency extension basis function, and constructs a noise-resistant frequency extension basis function based on compressed sensing, achieving good high- and low-frequency compensation effects for seismic data under low signal-to-noise ratio conditions.

The application discloses a SAR image filtering method based on non-subsampled shearlet transform, and belongs to the technical field of image processing. The application comprises the following steps: performing logarithmic transform on a SAR image, and then performing non-subsampled shearlet (NSST) transform; modifying NSST transform coefficients of each high-frequency subband image based on a set threshold function; performing median filtering on each NSST transform coefficient of a low-frequency subband image; performing exponential transform on the processed low-frequency subband image and high-frequency subband image after NSST inverse transform, and obtaining a filtered SAR image. The threshold function adopted by the application is based on a hard threshold and a soft threshold, and the threshold of different layers of high-frequency subband coefficients is calculated respectively, considering that different subbands contain different noise components. The application can effectively filter out coherent speckle noise in the SAR image, and ensure the reservation of the detail information of the SAR image.

The present application relates to a kind of image thick cloud removal pre-processing method for high-performance video coding application, it is related to image processing technical field, solve the technical problem that it is difficult to fully capture cross-scale complementary features, there is deficiency in the balance between global structure and local detail.The pre-processing method includes: based on the guided image estimation of non-subsampled shearlet transform and the cloud removal model of full connection tensor decomposition guided by non-subsampled shearlet transform to carry out multi-time remote sensing image thick cloud removal.The present application is an image thick cloud removal pre-processing method for high-performance video coding application, realizes the generation of high-quality reference image: to obtain the reference image containing more details, first, the multi-time remote sensing image is carried out gamma correction, to normalize radiation intensity;Subsequently, improved adaptive PCNN fusion algorithm is applied in NSST domain, thereby enhancing detail representation while maintaining image energy distribution, finally, high-quality reference image is obtained.

The invention discloses a diffusion model image denoising method based on non-subsampled shear wave transformation, and relates to the technical field of image denoising. The invention aims to solve the problems of low de-noising efficiency and image distortion after de-noising in the existing image de-noising method. The method comprises the following steps: performing non-subsampled shearlet transform on a noise image to obtain a high-frequency sub-band feature and a low-frequency sub-band feature, and combining the high-frequency sub-band feature and the low-frequency sub-band feature to obtain a fusion feature; performing iterative noise addition on the fusion features to obtain fusion features after each time of iterative noise addition; generating a de-noised feature sample according to the fusion feature after iterative noise addition, obtaining an image similarity classification value by using the de-noised feature sample, and obtaining a de-noised fusion feature based on the image similarity classification value; and performing NSST inverse transformation on the denoised fusion features to obtain a denoised image. The method is used for image denoising processing.

The application provides a kind of based on Shearlet domain continuous data prestack consistency processing method, to the data of each block in continuous exploration area respectively carry out surface consistency amplitude compensation and surface consistency deconvolution and other consistency pretreatment, select a processing target model, the application selects a certain amount of good quality data as target model in the block of relatively good quality data in continuous exploration area, the other data in continuous exploration area is corrected as the standard of the target data, estimate the consistency correction factor of Shearlet domain, eliminate the statistical difference between target model data and data to be processed, realize the consistency processing of continuous exploration area. Process prestack data, can eliminate the difference of continuous data in amplitude, frequency and space, has good stability under noise environment.

The application discloses a multi-scale infrared polarization image enhancement method based on MSD-PCNN and relates to the technical field of infrared image processing. First, based on non-subsampled shearlet transform (NSST), an input intensity image I and a polarization feature map DoLP are decomposed in a multi-scale and multi-directional manner to obtain low-frequency subbands and high-frequency subbands. Second, a low-frequency subband fusion rule based on distance difference perception is designed according to the obtained low-frequency subbands. Finally, a high-frequency subband fusion rule based on MSD-PCNN is designed according to the obtained high-frequency subbands to fully extract texture and edge detail features. The multi-scale infrared polarization image enhancement method based on MSD-PCNN provided by the application suppresses redundant information interference, improves the distinctness of image structure levels, and also improves the visual comfort and global naturalness of a fused image.

The application provides an artificial intelligence seismic data processing method based on NSST and deep learning, and comprises the following steps: step 1, synthesizing simulated pure seismic data, simulating noise in actual seismic data, and simulating actual exploration obtained seismic data; step 2, performing NSST transformation on the noise-containing data and the constructed noise data, slidingly intercepting the transformed Shearlet coefficient matrix by using a window with fixed size and sliding step length, and thereby constructing a training set and a test set; step 3, building a multi-level wavelet convolutional neural network, iteratively training the network by using the training set, updating parameters by using the forward and backward propagation of the network, calculating a loss function after each training, and gradually converging the loss function by continuously correcting hyperparameters; and step 4, using the method to denoise actual seismic data. The scheme solves the problems of great difficulty in suppressing various types of noise in seismic exploration data and poor generalization of traditional denoising methods.

Addressing the advantages and disadvantages of Shearlet threshold shrinkage and TGV (Transient Transformer-TGV) seismic data, this invention proposes a Shearlet-TGV seismic data random noise suppression method. This invention uses the result of Shearlet threshold shrinkage as input to the TGV method, and then iteratively extracts effective signals from the TGV differential profile, superimposing them to obtain the optimal denoising result. The TGV method is used to suppress the boundary effects caused by Shearlet threshold shrinkage, while using the Shearlet threshold shrinkage result as input mitigates the "painting" effect of the TGV method. During the iteration process, the weight coefficients of the TGV regularization term are adaptively changed, continuously extracting effective information from the TGV differential profile, superimposing the effective signals, and thus estimating the optimal random noise removal result.

The invention relates to the technical field of active source surface wave exploration, and particularly discloses a multi-modal surface wave frequency dispersion curve extraction method and system, and the method comprises the steps: obtaining a surface wave seismic record, carrying out the self-adaptive signal separation of the surface wave seismic record through Shearlet transformation, and obtaining a first signal with a primary base-order signal and a second signal containing a high-order signal; a high-precision linear Radon transformation inversion model based on multi-term regularization constraint is constructed; solving the inversion model by using an alternating direction multiplier method to obtain a base-order signal and a high-order signal in the Radon domain; converting the base-order signal and the high-order signal in the Radon domain into a frequency-speed domain, and generating a base-order frequency dispersion energy diagram and a high-order frequency dispersion energy diagram; according to the method, the anti-noise performance of high-precision Radon transformation can be improved while high-order modal frequency dispersion energy is highlighted, and a complex inverse problem under the constraint of multiple regularization terms is decomposed into a plurality of sub-problems easy to solve by adopting an ADMM algorithm, so that an optimal solution is efficiently obtained.