39 results about "Super resolution image reconstruction" patented technology

The invention discloses a super-resolution image reconstruction method, system and device based on dynamic frequency domain adaptive coding and contrast constraint optimization, and a medium. The method comprises the following steps: creating an original training data set; image data features and application scenes are considered, and feature extraction is performed on image data by adopting a modular design method; in combination with discrete cosine transform and inverse transform thereof, adaptive transform coding is carried out on different frequency components in the image features through a dynamic weight adjustment mechanism; the U-Net and Transform architectures are combined, isotropic design is optimized, a diffusion model and a feature fusion and reconstruction technology are applied, and diffusion process reconstruction is achieved; by introducing a contrast loss function, contrast learning is carried out between images with different resolutions, and the feature learning ability is enhanced. The image reconstruction method is more intelligent and efficient, and can effectively deal with frequency feature recovery and detail reconstruction problems in a complex image scene.

The invention relates to the technical field of forest fire recognition and early warning, in particular to a forest fire early warning method and system based on a super-resolution neural operator, and the method specifically comprises the following steps: extracting an initial feature map # imgabs1 # of a to-be-recognized low-resolution forest fire image # imgabs0 #; constructing a super-resolution feature capture network, three HAFM hierarchical attention fusion modules, an MSMO multi-scale mapping operator module, a super-resolution feature fusion module and a super-resolution image reconstruction module, inputting the initial feature map # imgabs2 # into the super-resolution feature capture network, and finally outputting a super-resolution image # imgabs3 #; and constructing a forest fire recognition module, inputting the super-resolution image # imgabs4 # into a ResNet-18 neural network model to obtain a recognition feature # imgabs5 #, finally performing full connection layer processing on the recognition feature # imgabs6 # to obtain a recognition result of the forest fire image, and judging whether to perform early warning or not according to the recognition result. According to the invention, the problem that a low-resolution fire image cannot be accurately identified and timely early warned in existing forest fire identification and detection can be solved.

The invention relates to a skin tissue layering evaluation method, device and equipment, a medium and a program product. The method comprises the following steps: acquiring an original gray-scale ultrasonic image of skin tissue layering, and preprocessing the original gray-scale ultrasonic image to obtain a preprocessed ultrasonic image; performing elastic image generation on the preprocessed ultrasonic image through an elastic imaging generation network to obtain an elastic modulus diagram; performing super-resolution image reconstruction on the preprocessed ultrasonic image through a super-resolution reconstruction network to obtain a high-resolution image; performing feature extraction on the preprocessed ultrasonic image, the elastic modulus diagram and the high-resolution diagram to obtain a multi-modal hierarchical feature map; performing cross-modal attention fusion on the multi-modal hierarchical features to obtain a fusion feature map; and according to the fusion feature map, performing layering evaluation on the skin tissue layering to obtain a multi-skin tissue probability map. By adopting the method, the integrated skin tissue layering evaluation of the whole body skin, fascia and muscular tissues can be realized under the limitation of insufficient resolution.

The invention discloses a super-resolution image reconstruction method based on a multi-scale large-kernel convolution double-residual neural network, which is suitable for the field of image processing, and comprises the following steps: cutting a data set, inputting a cut original low-resolution image into a preprocessing module, carrying out image normalization and data enhancement operation, and carrying out image reconstruction; generating a preprocessed low-resolution image; the preprocessed low-resolution images form a distorted image block data set, and a training set, a verification set and a test set are formed; according to an existing distorted image block data set, a super-resolution image reconstruction method based on a multi-scale large-kernel convolution double-residual neural network is constructed; and inputting the data set into the constructed multi-scale large-kernel convolution double-residual neural network to extract semantic features, and amplifying a feature map by using an up-sampling module of the model to generate a super-resolution image. According to the method, a multi-scale large-kernel convolution and double-residual structure is introduced, a visual attention mechanism is used in the neural network, the extracted features better conform to human visual perception features, and super-resolution image reconstruction is more accurate.

The invention discloses a super-resolution image reconstruction method based on regional degradation perception. The method comprises the following steps: respectively constructing a Dse training data set for a degradation region estimator and an SR training data set for a super-resolution model; constructing a degradation area estimator and a mask image encoder, and generating N random masks by using a random mask generator; training a degradation region estimator and a mask image encoder by using a random mask and Dse training data set; then, constructing an EDSR model combined with degraded region features as a super-division model, and generating N random masks' by using a random mask generator; and training the super-division model by using the random mask'and the SR training data set, and outputting a reconstructed image by the super-division model after the training is completed. According to the method, spatial domain difference degradation with diversified degradation shapes is designed to serve as data enhancement, perception and area adaptability optimization are carried out on the degradation area, the robustness and adaptability of the model are enhanced, and the super-resolution effect is improved.

The invention relates to the technical field of image super-resolution, and provides an image super-resolution reconstruction method, and the method comprises the steps: obtaining a to-be-reconstructed low-resolution image, inputting the to-be-reconstructed low-resolution image into a trained super-resolution image reconstruction model, and obtaining a super-resolution reconstruction image corresponding to the to-be-reconstructed low-resolution image. A shallow layer feature extraction module in the super-resolution image reconstruction model is composed of a depth separable convolution sub-module and a standard convolution sub-module, and a deep layer feature extraction module is composed of a plurality of dense parallel residual blocks constructed based on an adaptive attention mechanism and a standard convolution layer which are connected in sequence. The reconstruction module is composed of a dynamic convolution layer, a moving window attention layer, a pixel reconstruction layer and a standard convolution layer, and solves the problems that an existing shallow feature extraction module cannot fully extract shallow features, the local modeling capability of a residual Swin Transform block in a deep feature extraction module is insufficient, and the reconstruction module cannot obtain features of a target area. Therefore, a high-quality super-resolution reconstructed image is obtained.

The invention discloses a medical image processing method, and particularly relates to a medical image super-resolution method and device based on an edge enhancement diffusion model. According to the method, image edge extraction is carried out on a prediction image, a low-resolution image and an auxiliary image of a t-th time step to obtain target edge information, and then the images and edges are coded to generate enhanced unique features and shared features after deentanglement; effective auxiliary information of different modes is adaptively integrated, and complementarity of multi-mode data is fully exerted to improve feature expression ability; a decoder is used for generating a noise image in a diffusion model, and a high-resolution target image is reconstructed through a step-by-step de-noising reverse diffusion process, so that more detail information is recovered. In the embodiment of the invention, the importance of the edge information is considered, and the high-frequency edge information is injected into the corresponding image encoder, so that details are more effectively captured, and super-resolution image reconstruction with a better effect is obtained.

The invention discloses a semi-supervised laser microscopic imaging enhancement method, which comprises the following steps of: constructing a laser microscopic image data set, and carrying out normalization processing on an image; constructing a two-stage deep learning network structure, wherein the two-stage deep learning network structure comprises a first-stage unsupervised degradation representation learning network and a second-stage supervised super-resolution image reconstruction network; training the two-stage deep learning network; and network reasoning is carried out, a low-resolution laser microscopic image is input, a high-resolution image is output, and the super-resolution of laser microscopic imaging is realized. According to the method, an unsupervised comparative learning strategy and a supervised image reconstruction method are combined, feature extraction is performed by fully utilizing unlabeled data, the reconstruction quality is improved through supervised learning, and the generalization ability and the reconstruction precision of the model are effectively enhanced; according to the method, an encoder of a transform (a deep learning model) architecture is introduced to capture complex degradation information from a global perspective, and it is ensured that the model can adapt to various complex degradation.

The invention discloses a super-resolution image reconstruction method based on a multi-scale large separable kernel convolutional neural network, which is suitable for the field of image processing, and comprises the following steps: cutting a data set, inputting a cut original low-resolution image into a preprocessing module, carrying out image normalization and data enhancement operation, and carrying out image reconstruction; generating a preprocessed low-resolution image; the preprocessed low-resolution images form a distorted image block data set, and a training set, a verification set and a test set are formed; constructing a super-resolution image reconstruction method based on a multi-scale large separable kernel convolutional neural network according to an existing distorted image block data set; and inputting the data set into the constructed multi-scale large separable kernel convolutional neural network to extract semantic features, and amplifying a feature map by using an up-sampling module of the model to generate a super-resolution image. According to the method, a multi-scale large separable kernel convolution structure is introduced, a visual attention mechanism is used in the neural network, the extracted features better conform to human visual perception features, and super-resolution image reconstruction is more accurate.

The invention discloses a fast response flood disaster monitoring method and system based on super-resolution reconstruction. The method comprises the following steps: continuously acquiring a plurality of geostationary orbit satellite remote sensing images of an affected area and preprocessing the images; inputting the preprocessed geostationary orbit satellite remote sensing image into the trained super-resolution image reconstruction deep learning model, and outputting a reconstructed disaster area remote sensing image; and inputting the reconstructed disaster area remote sensing image into the trained flood disaster monitoring neural network model, and outputting a disaster range extraction result and a disaster situation evaluation result. According to the method, the characteristic of high time resolution of the geostationary orbit satellite is utilized to provide emergency response when a disaster occurs, cloud removal processing, super-resolution reconstruction and flood disaster area extraction are completed based on pure vision and a deep learning model algorithm, application under various extreme weathers can be supported, and the method has a wide application prospect. And a quick-response basic data service is provided for timely rescue and disaster relief and economic loss estimation.

The invention provides a super-resolution image reconstruction method based on implicit neural representation. A high-frequency component and a low-frequency component are separated and reconstructed, a continuous up-sampling module is used for focusing on generation of high-frequency details, meanwhile, low-frequency basic information of an image is reserved through interpolation up-sampling, and finally fusion is achieved through component superposition. The design effectively overcomes the defect that in traditional implicit neural representation, a multi-layer perceptron deviates to learn low-frequency content and neglects high-frequency details, and it is ensured that a reconstructed image can keep a clear texture structure and edge integrity under any preset scale. Through an independent processing mechanism of high and low frequency components, the problem of structural distortion under a large scale factor is significantly suppressed, the visual quality of the image is improved, the advantage of self-adaption of a single model to any scale is maintained, and the storage and calculation cost of multi-model training is reduced.

The present invention belongs to the technical field of super-resolution image reconstruction, and discloses a method for identifying long-distance dial information based on PSO and ESRGAN, including Step 1: setting up an operation site; Step 2: establishing an ESRGAN model and calculating the feature similarity between the real high-resolution image and the image based on the generative adversarial network GAN and the perceptual loss function; Step 3: magnifying a new image through the best model obtained by training. The present invention solves the problem that when identifying the dial information on the surface of a measured instrument at a long distance, the image is unclear and the features are not obvious, resulting in a poor recognition rate. Through this method, it is possible to reconstruct a photo with a low resolution and overall blurriness taken at a long distance into a high-resolution state, ensuring that as many details in the image as possible can be obtained during subsequent image recognition and improving the recognition accuracy.

The present invention relates to the field of image processing technology, and in particular to an adaptive image super-resolution reconstruction method based on compressed sensing. The present invention designs a trainable compressed sensing sampling module for performing sparse observation compression on an input image. The module supports end-to-end joint training and has data-driven optimization capabilities. Subsequently, the content structure in the compressed image is modeled through an image prior analysis module, and the image complexity index is calculated as a reference for subsequent path selection. The present invention combines compressed sensing theory with an image structure complexity perception mechanism, and realizes a more efficient and quality-controlled super-resolution image reconstruction process through an adaptive path selection strategy.

The present invention discloses an image classification method based on super-resolution image reconstruction and class consistency constraint. The implementation steps are as follows: obtaining a training sample set and a test sample set; constructing an image classification network model based on super-resolution reconstruction and class consistency; performing iterative training on the image classification network model; and obtaining the classification result of the low-resolution image. The present invention uses the short-circuit connection between the super-resolution reconstruction network modules to improve the quality of the low-resolution image, enrich the detailed information of the image, and improve the classification accuracy of the network. By constraining the class probabilities between the networks to be consistent, the discriminability of the features extracted by the low-resolution feature extraction network is increased, and the image classification accuracy is further improved. It can be used for low-resolution image classification.

In some embodiments, there is provided a system configured to provide super resolution comprising a grating configured to include a plurality of openings, wherein each of the openings is subpixel in size, wherein the subpixel size is smaller than an image sensor pixel of a camera including a plurality of image sensor pixels; a slider to move the grating laterally along an image plane of the camera; an illumination source; and super resolution image reconstruction operations comprising receiving the plurality of low-resolution images; reconstructing a super resolution image using the plurality of low-resolution images, wherein the reconstructed super resolution image is noise filtered to remove noise due to in part upscaling of the plurality of low resolution images; and outputting the reconstructed super resolution image as a representation of the subject. Related systems, methods, and articles of manufacture are also disclosed.

The application relates to the technical field of image enhancement, in particular to a mine environment super-resolution image reconstruction method based on vibration induction for mine monitoring, which comprises collecting vibration data and image data and performing pretreatment; the processed vibration data sequence is input into a double-layer LSTM network, vibration data is analyzed by using the LSTM, vibration characteristics at the next moment are predicted, and dynamic compensation parameters are generated; the processed image is input into a convolutional neural network constructed by using a blueprint separable convolution, a residual attention module and a coordinate attention mechanism, and multi-scale feature extraction is performed; time alignment of the vibration data and the image data is performed, corresponding compensation parameters are generated, and meanwhile, spatial alignment and fusion of the two are performed to obtain fusion features; based on the fusion features, super-resolution reconstruction is performed on the image to generate a high-resolution image. Through technical fusion innovation, the recognition quality of image quality in a complex vibration scene is significantly enhanced.

The present application provides a super-resolution image reconstruction method and a device. Since the super-resolution image reconstruction method fully considers internal relationship between local pixels of an original image, detailed information of an image can be better maintained, while problems of aliasing, blurring, and graininess are significantly reduced, and display effect of the original image after stretching is improved.

The invention relates to the technical field of image processing, and discloses a medical image super-resolution reconstruction method and system, and the method comprises the steps: constructing a multi-modal medical image data set which comprises a high-resolution image and a corresponding low-resolution image pair; performing decoupling modeling on the organ structure and the noise features by adopting frequency domain analysis and a Gaussian mixture model, and establishing a multi-modal organ template library; organ recognition and frequency domain feature matching are carried out on the input image, and the optimal noise priori is retrieved from the multi-modal organ template library; and a noise priori guide item is injected in a reverse denoising process of the diffusion model to realize anatomical structure adaptive super-resolution image reconstruction. According to the method, through deep fusion of multi-modal data driving, frequency domain statistical modeling and a diffusion model, full-process optimization of the medical image from noise decoupling to structure self-adaption super-resolution image reconstruction is achieved, the precision, efficiency and robustness of medical image super-resolution reconstruction are improved, and the method is suitable for clinical real and complex scenes.

The invention discloses a single-frame composite structure illumination obvious micro-imaging method based on ensemble learning. Single-time transverse isotropic spectrum modulation is achieved through an efficient six-beam interference composite structure illumination strategy, an optical device of a structured light illumination microscope (SIM) does not need to be modified, and therefore the number of original images is reduced by 9 times in the physical sense. In addition, the problem that the super-resolution reconstruction is unsuitable for inversion is solved by integrating the sub-networks of different frequency component characteristics in different domains through integrated learning, and the super-resolution image reconstruction with higher quality is realized in a low signal-to-noise ratio environment at a 9-time imaging speed of a traditional illumination mode. Due to higher imaging speed, less light damage, higher reconstruction quality and better noise immunity, the device becomes an efficient and powerful imaging tool, and can be used for studying the dynamic state of a nanoscale fine structure in living cells.

The invention discloses a radiation transfer simulation-oriented super-resolution image reconstruction method and system. The method comprises the steps of constructing input features and labels through strict space-time pairing and multi-source data fusion; a residual error learning network based on Unet + + is adopted to learn a residual error from a coarse resolution baseline brightness temperature to a pixel-level resolution target brightness temperature, the network is subjected to multi-task learning transformation, and a SmoothL1 and SSIM combined loss function is adopted to train in an effective mask so as to constrain an amplitude error and a structural error at the same time; and finally, systematic deviation is eliminated through linear segmentation calibration driven by a verification set. According to the method, the problems of excessive smoothness, physical inconsistency and low calculation efficiency of a traditional interpolation method in radiation transfer simulation are solved, high-precision and high-efficiency super-resolution reconstruction is realized, and the requirement of near real-time quantitative inversion of massive spaceborne data is met.

The invention discloses an unconventional horizontal well perforation segmentation and clustering method, which relates to the field of geological engineering, and comprises the following steps of: performing competitive evaluation on an optimization result through a double optimization model, performing multi-scheme curve comparison, performing modular design on an algorithm, and performing component interface and modularization; comparing various segmentation and clustering results on a logging curve, and comparing and displaying the results on a graphical interface; calculating scores of yield, cost, safety and the like of a perforation division scheme through super-resolution image reconstruction based on a convolutional network, and performing adjustment according to the scores; and the evaluation module analyzes each scheme, gives evaluation in combination with engineering dessert and geological dessert calculation results, optimizes perforation cluster positions through an algorithm, and generates a final optimization scheme. According to the method, segmentation and clustering schemes can be continuously compared and evaluated, the design scheme is continuously optimized, finally, the adaptability of the method is wider, the calculation result is more accurate, field personnel can use the method more conveniently, and the timeliness and energy efficiency of field operation are improved.

The invention relates to the technical field of image enhancement, in particular to a mine monitoring-oriented mine environment super-resolution image reconstruction method based on vibration induction, and the method comprises the steps: collecting vibration data and image data, and carrying out the preprocessing; inputting the processed vibration data sequence into a double-layer LSTM network, analyzing the vibration data by using the LSTM, predicting the vibration characteristics of the next moment and generating a dynamic compensation parameter; inputting the processed image into a convolutional neural network constructed by adopting blueprint separable convolution, a residual attention module and a coordinate attention mechanism, and performing multi-scale feature extraction; performing time alignment of the vibration data and the image data to generate corresponding compensation parameters, and performing space alignment and fusion of the vibration data and the image data to obtain fusion features; and performing super-resolution reconstruction on the image based on the fusion features to generate a high-resolution image. According to the invention, through technology fusion innovation, the identification quality of the image quality in a complex vibration scene is significantly enhanced.

The application provides a face super-resolution reconstruction method based on progressive training and face semantic segmentation, which mainly comprises the following steps: a light and efficient face super-resolution network is proposed, the network mainly comprises a residual aggregation module and three up-sampling modules; a progressive training method is used to make the model develop in three stages in one iteration training, and the trained model can perform two-fold, four-fold and eight-fold super-resolution image reconstruction on a low-resolution face image; a face semantic segmentation network is used to obtain face prior information, and a face segmentation loss is added in the model training to assist the network in generating a more realistic face structure. The application is improved based on the RFDN network, is suitable for super-low resolution face image input, can output three kinds of high-resolution reconstruction images with different magnification, and solves some defects of traditional models.

The invention relates to a super-resolution image reconstruction technology, and discloses a mobile terminal image super-resolution method based on prompt calibration and multi-scale cascading, and the method comprises the steps: obtaining a low-resolution image, carrying out the shallow feature extraction of the low-resolution image through blueprint separation convolution, and obtaining an initial feature map; performing down-sampling on the initial feature map, and inputting the down-sampled feature map into a feature extraction network formed by cascading a plurality of RMVP modules for deep feature extraction; performing up-sampling on the deep features output by the feature extraction network; performing feature fusion on the up-sampled features and the initial feature map through jump connection; and carrying out image reconstruction on the fused features, and outputting a high-resolution image. According to the mobile terminal image super-resolution method based on prompt calibration and multi-scale cascade, the high image super-resolution performance is achieved, and meanwhile the light-weight structure is kept to meet the real-time reasoning requirement of the mobile terminal.

This invention provides an image super-resolution reconstruction method based on multi-scale residual feature fusion, comprising: preprocessing the image to obtain high- and low-resolution image pairs; constructing a multi-scale feature extraction module based on depthwise separable convolution to extract features from the preprocessed high- and low-resolution image pairs and output a feature map; constructing a residual feature fusion module to perform residual feature fusion processing on the output feature map; constructing an enhanced attention module to process the feature map after residual feature fusion processing; S5. Upsampling the feature map using an adaptive upsampling module to generate a super-resolution image; constructing a loss function module and processing the super-resolution image; S7. Constructing a super-resolution image reconstruction model based on multi-scale residual feature fusion and inputting the super-resolution image into the super-resolution reconstruction model for training; S8. Inputting the image to be processed into the super-resolution image reconstruction model based on multi-scale residual feature fusion for processing.

The present invention belongs to the technical field of super-resolution image reconstruction, and particularly relates to a method and system for image super-resolution reconstruction based on parameter reconstruction, by constructing a super-resolution reconstruction network for extracting features from a low-resolution image in input image data and reconstructing the image based on the extracted features, wherein in the super-resolution reconstruction network, firstly, standard convolution is used to extract shallow features of the input image data, and then deep separable convolution with parameter reconstruction is used to extract deep features from the shallow features, and the image is reconstructed using the deep features; the network is trained using the collected sample data; and for the image data to be reconstructed, the trained super-resolution reconstruction network is used to extract features and reconstruct the image. The present invention extracts features through parameter reconstruction, which can achieve deeper feature extraction while reducing the amount of network parameters and the amount of calculation, improve the quality of the reconstructed image, and facilitate application in actual scenarios.

The present invention discloses a medical image processing method, specifically, a medical image super-resolution method and device based on an edge-enhanced diffusion model. The present invention first extracts image edges from the predicted image, low-resolution image, and auxiliary image at the t-th time step to obtain target edge information, and then encodes the image and edge respectively to generate enhanced disentangled unique features and shared features; adaptively integrates effective auxiliary information of different modalities, and gives full play to the complementarity of multimodal data to enhance feature expression capabilities; uses a decoder to generate a noise image in a diffusion model, and reconstructs a high-resolution target image through a step-by-step denoising reverse diffusion process, thereby restoring more detail information. In the embodiment of the present invention, the importance of edge information is taken into account, and high-frequency edge information is injected into the corresponding image encoder to help capture details more effectively and obtain better super-resolution image reconstruction.

The present disclosure discloses a method and a system for wavelet domain-based normalizing flow super-resolution image reconstruction. The method includes constructing a training set and a normalizing flow model, wherein the normalizing flow model includes a plurality of levels, each of the plurality of levels including a squeeze layer, two types of conditional mapping layers, a split layer, an activation standard layer, and a quick response (QR) layer; determining a stable normalizing flow model through a wavelet transform, a reconstructed QR layer, and a T-distribution based on the normalizing flow model; determining a wavelet domain-based normalizing flow super-resolution model by adding a refinement layer based on the stable normalizing flow model; training the wavelet domain-based normalizing flow super-resolution model based on the training set; and reconstructing a super-resolution image based on a trained normalizing flow super-resolution model.

According to implementations of the subject matter described herein, a solution is proposed for super-resolution image reconstructing. According to the solution, an input image with first resolution is obtained. An invertible neural network is trained using the input image, wherein the invertible neural network is configured to generate an intermediate image with second resolution and first high-frequency information based on the input image, the second resolution being lower than the first resolution. Subsequently, an output image with third resolution is generated based on the input image and second high-frequency information by using an inverse network of the trained invertible neural network, the second high-frequency information conforming to a predetermined distribution, and the third resolution being higher than the first resolution. The solution can effectively process a low-resolution image obtained by an unknown downsampling method, thereby obtaining a high-quality and high-resolution image.

A deep learning-based method for synthesizing multimodal super-resolution magnetic resonance (MRI) images across datasets is presented, relating to the field of MRI. Utilizing unsupervised methods in deep learning and employing a generative adversarial network (GAN) architecture, multimodal super-resolution MRI images are synthesized. The images undergo data preprocessing, including registration, slicing, and normalization. A high-frequency template is then constructed, and the data is subjected to an FFT transform to obtain its K-space representation. The K-space image is multiplied by the high-frequency template to obtain its K-space high-frequency information, followed by an IFFT transform to obtain the high-frequency information in the image domain. The prepared images and their high-frequency information are then fed into the network. Through network training, multimodal data synthesis is achieved. An image degradation algorithm for the super-resolution reconstruction network is constructed. The super-resolution image reconstruction network architecture is constructed, and the degraded image and the original ground truth image are input into the network for training to obtain high-resolution multimodal MRI images.