23 results about "Shearlet" patented technology

The invention discloses an adaptive blocking compressed sensing image super-resolution reconstruction method and system. The method comprises the following steps: acquiring a low-resolution image and carrying out adaptive blocking on the low-resolution image; establishing a sparse representation model of the high-resolution image by using a discrete cosine transform basis; establishing an observation dimension reduction model by using the binary block diagonal matrix to obtain a relationship between a high-resolution image and a low-resolution image; performing compressed sensing super-resolution reconstruction solution on the low-resolution sub-block images by using a weighted iterative least square algorithm to generate high-resolution image blocks, and performing constraint by using Shearlet transformation and dual-scale total variation regularization in the reconstruction process; and splicing the generated high-resolution image blocks according to the position indexes to obtain a complete high-resolution image meeting the requirements. According to the method, the problems of unreasonable blocking caused by single blocking basis and limited reconstruction effect caused by insufficient consideration of prior information in the existing method are solved.

The invention discloses a precipitation forecasting method based on Shearlet and L-PWC, the precipitation forecasting method is decomposed into a global space, a local space and a time angle, the time feature extraction effect is improved through the consistency evaluation of a reverse optical flow graph and a forward optical flow graph, the decomposition of a picture in a frequency domain is guided by using an optical flow with higher precision, and the time feature extraction efficiency is improved. Feature extraction is carried out on different frequency domains to obtain information to guide directional learning of multi-head attention, and more comprehensive global features are generated through assistance of other frequency band features. Extraction of local space information is guided by time information, feature enhancement of key information is completed, future weather is predicted through gradient decomposition of optical flow and time dependence before and after, and a litsea rotundifolia optimization algorithm is optimized through an ant colony algorithm, so that the algorithm can search for an optimal solution in a wider space, and the optimal solution is obtained. And the possibility that the algorithm falls into local optimum is greatly reduced, so that the ability of the model to deal with complex weather is improved.

The invention belongs to the technical field of geophysical exploration, and relates to a land measured data Marchenko multiple suppression method based on compressed sensing, comprising a data preprocessing link: encrypting and regularizing original data; carrying out Shearlet de-noising and reconstruction; carrying out sparse constraint deconvolution; a step of suppressing multiple waves in iteration: initializing the first iteration of a wake wave; carrying out odd number and even number iterations to solve a tail wave; signal-noise separation based on the Bayesian principle is carried out in even iteration, and the sum of even term tail waves of suppression noise is obtained. According to the method, higher-quality input data is obtained through an optimized preprocessing process, a more anti-noise Marchenko iteration process is carried out, multiple signals in actually measured land data are effectively suppressed under the condition that any model information and prediction do not need to be subtracted, and a good foundation is laid for subsequent imaging and interpretation; the accuracy of oil and gas resource exploration is improved, and more cost consumed by manual false horizon judgment is saved.

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 invention discloses a sonar image denoising method of an adaptive threshold and an improved guide filter. According to the method, a noise-containing sonar image is decomposed into a high-frequency coefficient and a low-frequency coefficient through non-subsampled shearlet transform (NSST). Aiming at the noise characteristics in the high-frequency sub-band, adopting a self-adaptive threshold algorithm to complete de-noising; for a low-frequency component, a guide filter introducing peak perception weight and scale constraint is adopted, so that edge blur is avoided while background noise is smoothed. And finally, reconstructing high and low frequency coefficients through NSST inverse transformation to obtain a de-noised image. According to the method, the visual effect of the image is improved, and a good foundation is laid for detection and recognition of the image target in the next step.

The present invention discloses an image classification method based on a shear wave network and a directional attention mechanism, mainly solving the problem that existing methods ignore discriminative decomposition features, resulting in poor running speed and accuracy of image classification. The solution includes: 1) constructing a training sample set, preprocessing and padding it to obtain a set of images to be decomposed; 2) constructing a lightweight network model composed of a shear wave network, a directional attention module, and a lightweight convolutional neural network; wherein the shear wave network is used to extract features in different directions of the image, the directional attention module assigns adaptive weights according to the importance of features in different directions of the image, and the lightweight convolutional neural network performs abstract feature extraction; 3) training the constructed lightweight network model; 4) using the trained network model to predict the category of the image to be classified to complete the classification. The present invention can effectively reduce the computational cost while improving the running speed and accuracy of image classification.

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 watermark attack method based on mapping space conversion angle improvement, and relates to the technical field of digital watermarking, characterized by comprising the following steps: S1: first, carrying out non-subsampled shearlet transform on a watermark-containing image to obtain a low-frequency subband and a plurality of high-frequency subbands; S2: inputting the low-frequency subband and the high-frequency subbands into convolutional neural networks with similar structures respectively to obtain mean square errors; S3: taking the mean square errors as loss functions, and respectively calculating errors between low-frequency and high-frequency subbands of output of low-frequency restoration networks and high-frequency restoration networks and target restored images; and S4: updating and optimizing parameters of the two networks through minimization of the loss functions and back propagation. The application aims to provide a watermark attack method based on mapping space conversion angle improvement, and to design a new attack method which meets the requirements of improving imperceptibility and reducing robustness, and to design and implement a watermark attack model based on mapping space conversion angle improvement.

This application belongs to the field of primary-multiple separation of marine controlled-source seismic data. Specifically, it provides a method for primary-multiple separation of marine controlled-source seismic data with Doppler distortion, comprising: acquiring predicted primary waves and predicted multiple waves; inverting the predicted primary waves and predicted multiple waves using a moving Bayesian primary-multiple separation method to obtain the primary wave shearlet coefficients and multiple wave shearlet coefficients. The predicted primary wave is a moving marine controlled-source primary wave predicted using SRME technology, and the predicted multiple waves are moving marine controlled-source multiple waves predicted using SRME technology. The primary wave shearlet coefficients are those of a stationary marine controlled-source primary wave, and the multiple wave shearlet coefficients are those of a stationary marine controlled-source multiple wave. This method reduces computational costs and solves the interference problems of Doppler effect and free surface multiple waves in the observation records acquired during marine controlled-source seismic data acquisition.

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 invention belongs to the technical field of geophysical exploration, and relates to a Marchenko multiple suppression method for onshore measured data based on compressive sensing, including a data preprocessing link: original data encryption and regularization; Shearlet denoising and reconstruction; sparse constraint deconvolution; an iterative link for suppressing multiples: initializing the coda for the first iteration; obtaining the coda for odd and even iterations; and performing signal-to-noise separation based on Bayes' principle in even iterations to obtain the sum of the coda terms for even iterations that suppress noise. By means of an optimized preprocessing process, the present invention obtains higher-quality input data and performs a more noise-resistant Marchenko iterative process, effectively suppressing the multiple wave signals in onshore measured data without the need for any model information and predictive subtraction, laying a good foundation for subsequent imaging and interpretation, improving the accuracy of oil and gas resource exploration, and saving the costs consumed by more manual judgment of false horizons.

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 invention relates to the technical field of seismic data processing, in particular to a Marchenko imaging-oriented dual-norm constraint near-offset missing seismic data reconstruction method and device. The method comprises the following steps: obtaining original data, and carrying out Radon reconstruction on the original data to obtain data after Radon reconstruction; calculating a residual error between the Radon domain reconstruction data and the original data to obtain empty channel data; constructing a sparse reconstruction framework based on an lq1-lq2 norm to obtain a final objective function; and by utilizing a block coordinate descent method, substituting the data reconstructed based on the Radon and the empty channel data into the final objective function for solving so as to obtain a final reconstruction result. According to the method, a conventional single-norm sparse reconstruction method based on an l1 norm is improved into a double-norm constraint framework based on an lq1-lq2 norm, Radon reconstruction and Shearlet domain reconstruction are combined, compared with a traditional reconstruction method, the improved method has the advantages that the reconstruction effect of near large offset missing is obviously improved, and the reconstruction efficiency is greatly improved. And meanwhile, the requirement on the sampling rate of the input data is also reduced.

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 present invention discloses a VideoSAR deception jamming method and system based on Shearlet domain scattering control. The method comprises the following steps: first, intercepted enemy VideoSAR radar signals are reconnaissance analyzed to obtain enemy VideoSAR signal parameters and platform motion parameters; then, the own VideoSAR is used to perform frame imaging processing on the dynamic region of interest to obtain a highly realistic benchmark deception template, and frame-by-frame non-subsampled Shearlet domain transform and scattering control are performed to obtain a deception jamming template video containing low-frequency and high-frequency components. The false point coefficients are solved by combining the highly realistic benchmark deception template video sequence to obtain a VideoSAR deception jamming modulation coefficient video library; then, the intercepted enemy VideoSAR signal is subjected to delay, amplitude, and phase modulation using an adaptive jamming strategy to obtain a deception jamming signal of a VideoSAR false scene; finally, the deception jamming signal of the VideoSAR false scene is forwarded to achieve a VideoSAR deception jamming imaging effect. The present invention achieves the purpose of deception jamming of the VideoSAR system and has the advantages of low sample requirement and high jamming efficiency.

The invention provides a small sample double-photo-thermal fault recognition algorithm based on improved meta learning, and the algorithm achieves the training and testing of a detection target under the condition that the number of samples is limited through the optimization of a meta learning frame and the combination of a YOLOv7 deep learning algorithm, and solves a problem of target recognition under the condition of small samples. The fusion of the visible light image and the infrared image is realized by adopting an improved non-subsampled shearlet transform algorithm, and the detection precision and accuracy are improved. The target identification result area temperature value is automatically extracted and compared with the corresponding temperature fault threshold value, whether a fault exists or not is judged, the detection efficiency is improved, manual misjudgment is avoided, and the detection operation difficulty is reduced.

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.

The invention discloses an improved watermark attack method based on a mapping space conversion angle, which relates to the technical field of digital watermarking and is characterized by comprising the following steps: S1, firstly, performing non-subsampled shearlet transform on a watermark-containing image to obtain a low-frequency sub-band and a plurality of high-frequency sub-bands; s2, respectively inputting the low-frequency sub-band and the high-frequency sub-band into convolutional neural networks with similar structures to obtain mean square errors; s3, taking the mean square error as a loss function, and respectively calculating errors between the output of the low-frequency restoration network and the high-frequency restoration network and the low-frequency and high-frequency sub-bands of the target restoration image; and S4, updating and optimizing the two network parameters by minimizing the loss function and back propagation. The technical problem to be solved by the invention is to provide an improved watermark attack method based on a mapping space conversion angle, and a watermark attack model for realizing the improvement of the mapping space conversion angle is designed by aiming at designing a novel attack method which simultaneously meets two requirements of improving imperceptibility and reducing robustness.